Internet DRAFT - draft-paillisse-nmrg-performance-digital-twin
draft-paillisse-nmrg-performance-digital-twin
Network Management Research Group J. Paillisse
Internet-Draft P. Almasan
Intended status: Informational M. Ferriol
Expires: 27 April 2023 P. Barlet
A. Cabellos
UPC-BarcelonaTech
S. Xiao
X. Shi
X. Cheng
C. Janz
Huawei
A. Guo
Futurewei
D. Perino
D. Lopez
A. Pastor
Telefonica I+D
24 October 2022
Performance-Oriented Digital Twins for Packet and Optical Networks
draft-paillisse-nmrg-performance-digital-twin-01
Abstract
This draft introduces the concept of a Network Digital Twin (NDT) for
performance evaluation, a so-called Performance-Oriented Digital Twin
(PODT). Two types of PODTs are described. The first, referred to as
a Network Performance Digital Twin (NPDT), produces performance
estimates (delay, jitter, loss) for a packet network with a specified
topology, traffic demand, and routing and scheduling configuration.
The second, referred to as an Optical Performance Digital Twin
(OPDT), produces transmission performance estimates of an optical
network with specified optical service topologies and network
equipment types, topology and status. This draft also discusses
interfaces to these digital twins, how these digital twins relate to
existing control plane elements, and describes use cases for these
digital twins, as well as possible implementation options.
Status of This Memo
This Internet-Draft is submitted in full conformance with the
provisions of BCP 78 and BCP 79.
Internet-Drafts are working documents of the Internet Engineering
Task Force (IETF). Note that other groups may also distribute
working documents as Internet-Drafts. The list of current Internet-
Drafts is at https://datatracker.ietf.org/drafts/current/.
Paillisse, et al. Expires 27 April 2023 [Page 1]
Internet-Draft Network Performance Digital Twin October 2022
Internet-Drafts are draft documents valid for a maximum of six months
and may be updated, replaced, or obsoleted by other documents at any
time. It is inappropriate to use Internet-Drafts as reference
material or to cite them other than as "work in progress."
This Internet-Draft will expire on 27 April 2023.
Copyright Notice
Copyright (c) 2022 IETF Trust and the persons identified as the
document authors. All rights reserved.
This document is subject to BCP 78 and the IETF Trust's Legal
Provisions Relating to IETF Documents (https://trustee.ietf.org/
license-info) in effect on the date of publication of this document.
Please review these documents carefully, as they describe your rights
and restrictions with respect to this document. Code Components
extracted from this document must include Revised BSD License text as
described in Section 4.e of the Trust Legal Provisions and are
provided without warranty as described in the Revised BSD License.
Table of Contents
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3
2. Terminology . . . . . . . . . . . . . . . . . . . . . . . . . 5
3. Generic Architecture of a Performance-Oriented Digital
Twin . . . . . . . . . . . . . . . . . . . . . . . . . . 6
3.1. Architecture of the Network Performance Digital Twin . . 7
3.2. Architecture of the Optical Performance Digital Twin . . 9
4. Interfaces . . . . . . . . . . . . . . . . . . . . . . . . . 12
4.1. Network Performance Digital Twin . . . . . . . . . . . . 12
4.1.1. Administrator . . . . . . . . . . . . . . . . . . . . 12
4.1.2. Configuration Interface . . . . . . . . . . . . . . . 12
4.1.3. Digital Twin Interface (DTI) . . . . . . . . . . . . 13
4.2. Optical Performance Digital Twin . . . . . . . . . . . . 14
5. Mapping to the Network Digital Twin Architecture . . . . . . 15
6. Use Cases . . . . . . . . . . . . . . . . . . . . . . . . . . 16
6.1. Network planning . . . . . . . . . . . . . . . . . . . . 16
6.1.1. Packet Network Planning . . . . . . . . . . . . . . . 16
6.1.2. Optical Network Planning . . . . . . . . . . . . . . 17
6.2. Network Optimization . . . . . . . . . . . . . . . . . . 18
6.2.1. Packet Network Optimization . . . . . . . . . . . . . 18
6.2.2. Optical Services and Network Optimization . . . . . . 19
6.3. Optical Service (Re-)Provisioning . . . . . . . . . . . . 20
6.4. Optical Service Planning . . . . . . . . . . . . . . . . 20
6.5. Optical Network Risk Mapping . . . . . . . . . . . . . . 21
6.5.1. Optical Network Dynamic Restoration Planning . . . . 21
6.6. Troubleshooting . . . . . . . . . . . . . . . . . . . . . 22
Paillisse, et al. Expires 27 April 2023 [Page 2]
Internet-Draft Network Performance Digital Twin October 2022
6.7. Anomaly detection . . . . . . . . . . . . . . . . . . . . 22
6.8. What-if scenarios . . . . . . . . . . . . . . . . . . . . 22
6.9. Training . . . . . . . . . . . . . . . . . . . . . . . . 23
7. Implementation Challenges . . . . . . . . . . . . . . . . . . 23
7.1. Network Performance Digital Twin Implementation
Challenges . . . . . . . . . . . . . . . . . . . . . . . 24
7.1.1. Simulation . . . . . . . . . . . . . . . . . . . . . 24
7.1.2. Emulation . . . . . . . . . . . . . . . . . . . . . . 25
7.1.3. Analytical Modelling . . . . . . . . . . . . . . . . 25
7.1.4. Neural Networks . . . . . . . . . . . . . . . . . . . 25
7.2. Optical Performance Digital Twin Implementation
Challenges . . . . . . . . . . . . . . . . . . . . . . . 28
8. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 29
9. Security Considerations . . . . . . . . . . . . . . . . . . . 29
10. References . . . . . . . . . . . . . . . . . . . . . . . . . 29
10.1. Normative References . . . . . . . . . . . . . . . . . . 29
10.2. Informative References . . . . . . . . . . . . . . . . . 29
Acknowledgements . . . . . . . . . . . . . . . . . . . . . . . . 35
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 35
1. Introduction
A Digital Twin for computer networks is a virtual replica of an
existing network with a behavior equivalent to that of the real one.
The key advantage of a Network Digital Twin (NDT) is the ability to
recreate the complexities and particularities of the network
infrastructure without the deployment cost of a real network. Hence,
network administrators can test, deploy and modify network
configurations safely, without worrying about the impact on the real
network. Once the administrator has found a configuration that
fulfills the expected objectives, it can be deployed to the real
network. The information provided by the NDT can also be used as
part of a closed loop-based automated process. In addition, using a
NDT is faster, safer and more cost-effective than interacting with
the physical network. All these characteristics make NDT useful for
different network management tasks ranging from network planning or
troubleshooting to optimization.
The concept of a NDT has been proposed for different approaches:
network management
[I-D.draft-zhou-nmrg-digitaltwin-network-concepts], 5G networks
[digital-twin-5G], Vehicular networks [digital-twin-vanets],
artificial intelligence [digital-twin-AI], or Industry 4.0
[digital-twin-industry], among others.
This draft proposes Digital Twins with a focus on performance
evaluation, for use in network management, network operations
optimization, network operations automation and other contexts.
Paillisse, et al. Expires 27 April 2023 [Page 3]
Internet-Draft Network Performance Digital Twin October 2022
Performance evaluation is examined in two contexts: with respect to a
packet network, and with respect to an optical transmission network.
In the packet network case, given several input parameters (topology,
traffic matrix, etc.), a Network Performance Digital Twin (NPDT)
predicts network performance metrics such as delay (per path or per
link), jitter, or loss. In the optical transmission network case,
given specified optical service topologies and network equipment
types, topology and status, an Optical Performance Digital Twin
(OPDT) estimates transmission performance metrics, such as optical
channel terminal powers and margins, in the face of channel
transmission noise and impairments [OPDT].
This draft defines the inputs and outputs of both types of
Performance-Oriented Digital Twins, their associated interfaces to
other modules in the network management or control plane or to
network equipment and components, and also discusses use cases.
This draft further discusses possible implementation options for the
NPDT, with a special emphasis on those based on Machine Learning.
The aim of Section 7 (Implementation Challenges) is, in part, to
describe the advantages and limitations of these techniques. For
example, most Machine Learning technologies rely heavily on large
amounts of data to achieve acceptable accuracy. Other considerations
include adjusting the architecture of the Neural Network to
successfully understand the structure of the input data. Challenges
particular to OPDT implementation are also discussed.
In order to use a Performance-Oriented Digital Twin (PODT) in
practical scenarios (c.f. Section 6), such as network optimization,
it should meet certain requirements:
Fast: low delay when making predictions (in the order of
milliseconds) to use it in optimization scenarios that need to
test a large number of configuration variables (c.f.
Section 6.2).
Accurate: the error of the prediction (vs the ground truth) has to
be below a certain threshold to be deployable in real-world
networks.
Scalable: support networks of arbitrarily large topologies
Variety of Inputs: accept a wide range of combinations of input
variables, depending on network type, packet or optical:
* Routing configurations
Paillisse, et al. Expires 27 April 2023 [Page 4]
Internet-Draft Network Performance Digital Twin October 2022
* Scheduling configurations (FIFO, Weighted Fair Queueing, Deficit
Round Robin, etc)
* Topologies
* Traffic matrices
* Traffic models (constant bitrate, Poisson, ON/OFF, etc)
* Optical network and/or service topologies and parameters
Accessible: despite the internal architecture of the PODT, it needs
to be easy to use for network engineers and administrators. This
includes, but is not limited to: interfaces to communicate with
PODT that ideally are well-known in the networking community,
metrics that are readily understood by network engineers, or
confidence values of the estimations.
Note that the inputs and outputs described here are an example, but
other inputs and outputs are possible depending on the specificities
of each scenario.
2. Terminology
Digital Twin (DT):
A virtual replica of a physical system that supports accurate
prediction of selected behaviours of the physical system.
Network Digital Twin (NDT):
A virtual replica a physical network that supports accurate
prediction of selected behaviours of the physical network.
Network Performance Digital Twin (NPDT):
A NDT that can predict with accuracy several performance metrics
of a physical packet network.
Optical Performance Digital Twin (OPDT):
A NDT that can predict with accuracy several transmission-related
performance metrics of a physical optical transmission network.
Performance-Oriented Digital Twin (PODT):
A generic term for a NDT whose function is to accurately predict
particular performance-oriented behaviours of a physical network.
Two flavours of PODTs are considered in this draft: NPDTs and
OPDTs.
Paillisse, et al. Expires 27 April 2023 [Page 5]
Internet-Draft Network Performance Digital Twin October 2022
Network Optimizer:
An algorithm capable of finding the optimal configuration
parameters of a network, e.g. OSPF weights (packet network) or
route, spectrum, modulation and coding assignments for optical
transmission channels (optical network), given an optimization
objective, e.g. latency below a certain threshold (packet network)
or lowest aggregate spectral use (optical network).
Control Plane:
Any system, hardware or software, centralized or decentralized, in
charge of controlling and managing a physical network. Examples
are routing protocols, SDN controllers, etc. Some or all of these
functions may also be encompassed by what is referred to as a
Management Plane.
3. Generic Architecture of a Performance-Oriented Digital Twin
Figure 1 presents an overview of the generic architecture of a
Performance-Oriented Digital Twin (PODT).
|Administrator Interfaces,
|Service Demand Interfaces,
|Intent-Based Interfaces,
|Associated Application Interfaces, etc.
|
+-------------------------------------------+
| |
| |
| | +-------------+
| | DT | |
| |Interface| Performance |
| Management Plane |<------->| Oriented |
| | | Digital |
| + Embedded Applications |-------->| Twin |
| | Network | |
| | Inform. +-------------+
| |Interface
| |
+-------------------------------------------+
| |
Measurement | | Configuration
Interface | | Interface
| |
+--------------------------------------+
| |
| Physical Network |
| |
+--------------------------------------+
Paillisse, et al. Expires 27 April 2023 [Page 6]
Internet-Draft Network Performance Digital Twin October 2022
Figure 1: Generic global architecture of a Performance-Oriented
Digital Twin (PODT).
Individual elements are discussed further in following sections of
this draft. But overall, the PODT represented in Figure 1 is an
information-oriented "utility". It works in concert with a
Management Plane and the latter's "embedded" applications or
components (i.e. applications or components comprising a part of the
Management Plane implementation), as well as any "associated"
applications (i.e. applications working in interaction with the
Management Plane implementation).
The essential function of the PODT is to estimate - and then to
present at the Digital Twin (DT) interface - particular, targeted
performance-oriented behaviours of the physical network, assessed in
scenarios that are defined by information presented at the DT
Interface. Optionally, complementary information used by the
behavioural models may be provided by the Network Information
Interface. The DT Interface is a sort of "run-time" interface while
the Network Information Interface, if present, serves as a conduit
for e.g. measurement data streamed from the physical network to the
management plane, or network or service topology information
generated within the management plane itself. As a rule, the Network
Information Interface, if present, provides to the NDT the broad set
of changing information necessary to construct an accurate and up-to-
date replica of the physical network for behavioural modeling
purposes.
The Management Plane may have interfaces to administrator, service
demand and/or intent generating systems, etc. It also has
configuration or control interfaces to the physical network.
Configuration or control inputs do not flow directly from the PODT to
the network: rather, the PODT provides information to the Management
Plane and the latter's embedded and associated applications,
components and processes - potentially including closed loop-based
automated processes - may generate network-facing configuration or
control outputs. The information provided by the PODT may thus be
used in evaluation, decision, etc. procedures that serve to optimize
operational outcomes, whether or not such procedures form part of
closed loop-based automated processes. The particular nature of such
operations, decisions etc. of PODT outputs is what defines and
distinguishes various use cases. Examples of use cases are
considered in Section 6.
3.1. Architecture of the Network Performance Digital Twin
Figure 2 presents an overview of the architecture of a Network
Performance Digital Twin (NPDT).
Paillisse, et al. Expires 27 April 2023 [Page 7]
Internet-Draft Network Performance Digital Twin October 2022
Administrator Intent
|
|
|Intent-Based Interface
|
|
+-------------+-----------------------------+
| | | |
| | Intent-Based Optimizer |
| | Renderer | +-------------+
| | | DTI | Network |
| Management | |Interface| Performance |
| Plane | |<------->| Digital |
| | | | Twin |
| | | | |
| | Measure Configure | +-------------+
| | | | |
+-------------+-----------------------------+
| |
| |
Measurement | | Configuration
Interface | | Interface
| |
+--------------------------------------+
| |
| Physical Packet Network |
| |
+--------------------------------------+
Figure 2: Global architecture of the Network Performance DT
Each element is defined as:
Network Performance Digital Twin (NPDT): a system capable of
generating performance estimates of a specific instance of a
packet network.
Physical Network: a real-world network that can be configured via
standard interfaces.
Management Plane: The set of hardware and software elements in
charge of controlling the Physical Network. This ranges from
routing processes, optimization algorithms, network controllers,
visibility platforms, etc. The definition, organization and
implementation of the elements within the management plane is
outside of the scope of this document. In what follows, some
elements of the management plane that are relevant to this
document are described.
Paillisse, et al. Expires 27 April 2023 [Page 8]
Internet-Draft Network Performance Digital Twin October 2022
* Optimizer: a network optimizer that can tune the configuration
parameters of a network given one or more optimization objectives,
e.g. do not exceed a latency threshold in all paths, minimize the
load of the most used link, and avoid more than 10 Gbps of traffic
at router R4 [DEFO].
* Intent-Based Renderer: a system capable of understanding network
intent, according to the definitions in
[irtf-nmrg-ibn-concepts-definitions-09].
* Measure: any system to measure the status and performance of a
network, e.g. Netflow [RFC3954], streaming telemetry
[streaming-telemetry], etc.
* Configure: any system to apply configuration settings to the
network devices, e.g. a NETCONF Manager or an end-to-end system to
manage device configuration files [facebook-config].
And the functions of each interface are:
DT Interface (DTI): an interface to communicate with the Network
Performance Digital Twin (NPDT). Inputs to the NPDT are a
description of the network (topology, routing configuration, etc),
and the outputs are performance metrics (delay, jitter, loss, c.f.
Section 4).
Configuration Interface (CI): a standard interface to configure the
physical network, such as NETCONF [RFC6241], YANG, OpenFlow
[OFspec], LISP [RFC6830], etc.
Measurement Interface (MI): a standard interface to collect network
status information, such as Netflow [RFC3954], SNMP, streaming
telemetry [openconfig-rtgwg-gnmi-spec-01], etc.
Intent-Based Interface (IBI): an interface for the network
administrator to define optimization objectives or run the NPDT to
obtain performance estimates, among others.
3.2. Architecture of the Optical Performance Digital Twin
Figure 3 presents an overview of the Optical Performance Digital Twin
(OPDT).
Paillisse, et al. Expires 27 April 2023 [Page 9]
Internet-Draft Network Performance Digital Twin October 2022
|Service Demand Interfaces,
|Intent-Based Interface,
|Associated Application Interfaces, etc.
|
+-------------------------------------------+
| |
|
| | DT +-------------+
| Management Plane |Interface| |
| |<------->| Optical |
| + Embedded Applications | | Performance |
| | | Digital |
| |-------->| Twin |
| | Network | |
| | Inform. +-------------+
| |Interface
+-------------------------------------------+
| |
| |
Measurement | | Configuration
Interface | | Interface
| |
+--------------------------------------+
| |
| Physical Optcial Network |
| |
+--------------------------------------+
Figure 3: Global architecture of an Optical Performance Digital Twin
The elements shown are defined as follows:
Optical Performance Digital Twin (OPDT): A NDT that can predict with
accuracy several transmission-related performance metrics of a
physical optical transmission network.
Physical Network: a real-world optical transmission network that can
be configured - and on which optical services may be configured
and subsequently provisioned - via standard or non-standard
interfaces.
Management Plane: The set of hardware and software elements and
processes in charge of managing and controlling the optical
physical network. This ranges from core processes such as optical
service route, spectrum and other parametric computation and
allocation, to embedded supporting applications and components
such as optimization algorithms, network controllers, visibility
platforms, etc. The definition, organization and implementation
Paillisse, et al. Expires 27 April 2023 [Page 10]
Internet-Draft Network Performance Digital Twin October 2022
of the elements within the optical network management plane is
outside of the scope of this document; however, associated
applications are referred to in Section 6 dealing with use cases.
The functions of the respective interfaces are:
DT Interface (DTI): an interface to communicate with the Optical
Performance Digital Twin (OPDT). This is a "run-time" interface
whose inputs to the OPDT specify the scenario under which optical
service transmission performance is to be evaluated, and whose
outputs from the OPDT comprise key transmission performance
metrics for the set of optical services present in that scenario,
such as service terminal powers and noise margins. The particular
scenario-defining inputs reflected in a given OPDT instance may be
a function of particular use case requirements. Further, the
information provided by these inputs may or may not replace or
complement information presented to the Network Information
Interface, which reflects in detail the actual configuration and
status of network, services, equipment, performance, etc.
Network Information Interface (NII): an interface to communicate
with the Optical Performance Digital Twin (OPDT). This is a
unidirectional interface whose inputs to the OPDT reflect current
attributes of the optical network and services configured and
operating on it, such as network topology, equipment types and
status, optical service topology, performance and other
attributes, instrumentation-generated measurement data, etc. The
source of this information may be the physical network itself, in
which case the information flows first to the Management Plane
over the so-called Measurement Interface; or, the source of the
information may be the Management Plane itself. Information
related to models used in performance analysis may also be
transferred over this interface.
The combination of the NII and a flexibly-defined DTI, enables
optical transmission performance to be assessed in respect of any
scenario, ranging from: wholly defined by the actual (or, some
historical) state and status of the physical network and services;
to, an entirely hypothetical network and service state and status;
or, to any scenario between these extremes. This enables the PODT to
be used in a wide variety of use cases, which are discussed in detail
in Section 6.
Configuration Interface (CI): an interface to configure the physical
optical network and the optical services deployed on it. This
interface may or may not be standards-based.
Measurement Interface (MI): an interface or set of interfaces to
Paillisse, et al. Expires 27 April 2023 [Page 11]
Internet-Draft Network Performance Digital Twin October 2022
collect network and service status and other information,
including device status, service performance, instrumentation
data, etc. Information related to models used in performance
analysis may also be transferred over this interface. This
(these) interface(s) may or may not be either partly or wholly
standards-based.
Service Demand Interface: a standards-based interface used to
provide optical service requirements to the Management Plane.
Intent-Based Interface: an (ideally) standards-based interface used
to specify, to the Management Plane, optical service requirements
and/or other attributes or constraints related to service delivery
or network operation.
Associated Application Interfaces: interfaces connecting the
Management Plane to externally-implemented applications, such as
network planning tools or other. These interfaces may or may not
be standards-based.
4. Interfaces
4.1. Network Performance Digital Twin
4.1.1. Administrator
This interface can be a simple CLI or a state-of-the-art GUI,
depending on the final product. In summary, it has to offer the
network administrator the following options/features:
* Predict the performance of one or more network scenarios, defined
by the administrator. Several use-cases related to this option
are detailed in Section 6.
* Define network optimization objectives and run the network
optimizer.
* Apply the optimized configuration to the physical network.
4.1.2. Configuration Interface
This interface is used to configure the Physical Network with the
configuration parameters obtained from the optimizer. It can be
composed of one or more IETF protocols for network configuration, a
non-exhaustive list is: NETCONF [RFC6241], RESTCONF/YANG [RFC8040],
PCE [RFC4655], OVSDB [RFC7047], or LISP [RFC6830]. It is also
possible to use other standards defined outside the IETF that allow
the configuration of elements in the forwarding plane, e.g. OpenFlow
Paillisse, et al. Expires 27 April 2023 [Page 12]
Internet-Draft Network Performance Digital Twin October 2022
[OFspec] or P4 Runtime [P4Rspec].
4.1.3. Digital Twin Interface (DTI)
This interface can be defined with any widespread data format, such
as CSV files or JSON objects. There are two groups of data. We are
assuming a network with N nodes.
Inputs: data sent to the NPDT to calculate the performance
estimates:
* Topology: description of the network topology in graph format, eg.
NetworkX [NetworkXlib].
* Routing configuration: a matrix of size N*N. Each cell contains
the path from source N(i) to destination N(j) as a series of nodes
of the topology. Note that not all source-destination pairs may
have a path. Since the NPDT only needs a sequence of nodes to
define a route, it supports different routing protocols, from
OSPF, IS-IS or BGP, to SRv6, LISP, etc.
* Traffic Demands: a definition of the traffic that is injected into
the network. It can be specified with different granularities,
ranging from a list of 5-tuple flows and their associated traffic
intensity, to a N*N matrix defining the traffic intensity for each
source-destination pair. Some source-destination pairs may have
zero traffic intensity. The traffic intensity defines parameters
of the traffic: bits per second, number of packets, average packet
size, etc.
* Traffic Model: the statistical properties of the input traffic,
e.g. Video on Demand, backup, VoIP traffic, etc. It can be
defined globally for the whole network or individually for each
flow in the Traffic Demands.
* Scheduling configuration: attributes associated to the nodes of
the topology graph describing the scheduling configuration of the
network, that is (1) scheduling policy (e.g. FIFO, WFQ, DRR,
etc), and (2) number of queues per output port.
Outputs: performance estimates of the NPDT: three matrices of size
N*N containing the delay, jitter and loss for all the paths in the
input topology.
Note that this is an example of the inputs/outputs of a performance
NPDT, but other inputs and outputs are possible depending on the
specificities of each scenario.
Paillisse, et al. Expires 27 April 2023 [Page 13]
Internet-Draft Network Performance Digital Twin October 2022
4.2. Optical Performance Digital Twin
Per Figure 3 in Section 3.2, an Optical Performance Digital Twin
(OPDT) interfaces with a Management Plane to obtain the information
related to the physical network and the scenario for which optical
service performance information is sought. Again, such information
is either sent to the OPDT at scenario assessment run-time through
the DT Interface (DTI), or is made available to the OPDT through the
Network Information Interface (NII) as stable (if evolving)
configuration, state, instrumentation and other data. As discussed
in Section 6, the best partitioning of information presentation
between DTI and NII is to some degree use case-specific. Categories
of such information include:
* Traffic-engineered (TE) topology and physical network topology
configuration, which includes customized TE topologies, TE
policies, profiles, and administrative routing constraints, etc.
* Operational state of the TE topology and network topology, which
contains critical information such as spectrum allocation status
and optical impairment characteristics of the optical components,
such as the modulation, error correction capabilities, launching
power and receiving power margins of the optical transponders.
* Wavelength-based optical service configuration, which includes
descriptions about the source, destination, path, protection and
restoration configurations, and other possible routing and
administrative configurations associated with the optical
services.
* Optical status of all the optical services within the network.
* Device configurations to various components such as fibers,
amplifiers, wavelength add-drop switches, transceivers, etc.
* Network and device level telemetry including alarm and performance
monitoring (PM) and instrumentation data.
* Historical configuration, state, telemetry and other data per the
preceding. This allows the OPDT to accommodate scenarios that
reflect network and service circumstances and status at prior
times. This is useful or necessary in some use cases.
A good part of the interface specifications needed to support these
information categories are available today in the IETF. For example,
the ACTN framework defines a hierarchical control framework, which
coupled with the various models defined in the TEAS, CCAMP, OPSAWG
and other working groups, can provide the configuration and state
Paillisse, et al. Expires 27 April 2023 [Page 14]
Internet-Draft Network Performance Digital Twin October 2022
data related to TE topology and services. The following is at least
a partial list of available models applicable to the DTI and NII
interfaces:
* [RFC8345]:A YANG data model for network topologies
* [RFC8795]: YANG data model for traffic-engineering topologies
* [RFC9094]: A YANG data model for wavelength switched optical
networks
* [I-D.ietf-ccamp-flexigrid-yang]: YANG data model for flexi-grid
optical networks
* [I-D.ietf-ccamp-optical-impairment-topology-yang]: YANG data model
for optical impairment-aware topology
* [I-D.ietf-teas-yang-te]: YANG model for TE tunnels
* [I-D.ietf-ccamp-wson-tunnel-model]: A Yang data model for WSON
tunnel
* [I-D.ietf-ccamp-flexigrid-tunnel-yang]: A YANG data model for
Flexi-Grid tunnels
Data models for management configuration and optical device
configurations, on the other hand, are mostly not available and need
to be developed in the IETF. As a starting point, the following
draft could potentially be extended to support OPDT functional
requirements:
* [I-D.yg3bp-ccamp-network-inventory-yang]: A YANG data model for
Network Hardware Inventory
Management models developed in other standard organizations such as
TM Forum and OpenConfig, might also be used by the OPDT. Applicable
instrumentation and measurement telemetry models are for further
study.
5. Mapping to the Network Digital Twin Architecture
Since the PODT is a type of Network Digital Twin, its elements can be
mapped to the reference architecture of a NDT described in
[I-D.draft-zhou-nmrg-digitaltwin-network-concepts]. Table 1 maps the
elements of the NDT reference architecture to those of the PODT.
Note that the Physical Network is the same for both architectures.
Paillisse, et al. Expires 27 April 2023 [Page 15]
Internet-Draft Network Performance Digital Twin October 2022
+====================================+==============================+
| NDT Reference Architecture | This draft |
+===================+================+==============================+
| Application Layer | | e.g. Intent-Based |
| | | Interface |
| | +------------------------------+
| | | e.g. Optimizer |
+-------------------+----------------+------------------------------+
| Digital Twin | Management | Management Plane |
| Layer +----------------+------------------------------+
| | Service | Performance-Oriented |
| | Mapping Models | Digital Twin |
| +----------------+------------------------------+
| | Data | Optional in production |
| | Repository | deployments |
+-------------------+----------------+------------------------------+
| Physical Network | Data | Measurement Interface |
| | Collection | |
| +----------------+------------------------------+
| | Control | Configuration |
| | | Interface |
+-------------------+----------------+------------------------------+
Table 1: Mapping of NDT reference architecture elements to the
architecture of the Performance-Oriented DT.
6. Use Cases
6.1. Network planning
6.1.1. Packet Network Planning
The size and traffic of networks has doubled every year
[network-capacity]. To accommodate this growth in users and network
applications, networks need periodical upgrades. For example, ISPs
might be willing to increase certain link capacities or add new
connections to alleviate the burden on the existing infrastructure.
This is typically a cumbersome process that relies on expert
knowledge. Furthermore, modern networks are becoming larger and more
complex, thus exacerbating the difficulty of existing solutions to
scale to larger networks [planning-scalability].
Since the NPDT models large infrastructures and can produce accurate
and fast performance estimates, it can help in different tasks
related to network capacity and planning:
* Estimating when an existing network will run out of resources,
assuming a given growth in users.
Paillisse, et al. Expires 27 April 2023 [Page 16]
Internet-Draft Network Performance Digital Twin October 2022
* Use performance estimates to plan the optimal upgrade that can
cope with user growth. Network operators can leverage the NPDT to
make better planning decisions and anticipate network upgrades.
* Find unconventional topologies: in some networking scenarios,
especially datacenter networks, some topologies are well-known to
offer high performance [Google-Clos]. However, it is also
possible to search for new topologies that optimize performance
with the help of algorithms. On one hand, the algorithm explores
different topologies and, on the other hand, the NPDT provides
fast performance estimations to the algorithm. Hence, the NPDT
guides the optimization algorithm towards the topologies with
better performance [auto-dc-topology].
6.1.2. Optical Network Planning
In an optical service planning exercise, the optical network topology
and equipment map are presumed fixed while the set of provisioned
optical services may be altered. In an optical network planning
exercise, not only the optical service map (or some component of it)
but also the network topology and deployed equipment map may be
augmented or changed. Optical network planning may thus be viewed as
a superset of the steps and processes associated with optical service
planning. The goal of optical network planning is usually to
accommodate some particular set of services or, more fundamentally,
some particular transmitted traffic requirements, using the least
amount or least (total or incremental) cost of equipment.
Optimization is thus generally a process component of optical network
planning; again, this is discussed in Section 6.2.2.
In general, the role of an OPDT in support of optical network
planning is the same as the one described in section Section 6.4
supporting optical services planning: to verify that all postulated
optical services would operate within acceptable performance bounds,
when deployed on a postulated new network topology and detailed
equipment and fibre map. As in the optical services planning case,
beyond identifying scenarios in which one or more optical services
would fail to operate, the identification of undesirably low or
unnecessarily high optical service margins could serve as a trigger
to explore alternative conjoint optical network and service plans.
Paillisse, et al. Expires 27 April 2023 [Page 17]
Internet-Draft Network Performance Digital Twin October 2022
For this use case, the appropriate input DT Interface specifies the
topology and other characteristics of postulated optical services,
and also the postulated new or modified network topology and map of
deployed equipment. Specific such postulated scenarios are conceived
by the Management Plane-embedded or -associated applications and
processes that are responsible for optical network planning. These
same applications and processes make use of the performance
information provided by the OPDT.
In the case of brown field optical network planning, the physical
network "twinned" is partly real and partly hypothetical. In the
case of green field planning the physical network is entirely
hypothetical. In practice, this means that in optical network
planning, the Network Information Interface can supply to the OPDT's
behavioural models only part - at best - of the information it would
supply in other cases. Such information "gaps" must be filled by
other means, e.g. using generic rather than specific equipment- and
fibre-characterizing information.
6.2. Network Optimization
6.2.1. Packet Network Optimization
Since the DT can provide performance estimates in short timescales,
it is possible to pair it with a network optimizer (Figure 4). The
network administrator defines one or more optimization objectives
e.g. maximum average delay for all paths in the network. The
optimizer can be implemented with a classical optimization algorithm,
like Constraint Programming [DEFO], or Local Search [LS], or a
Machine-Learning one, such as Deep Neural Networks [DNN-TM], or
Multi-Agent Reinforcement Learning [MARL-TE]. Regardless of the
implementation, the optimizer tests various configurations to find
the network configuration parameters that satisfy the optimization
objectives. In order to know the performance of a specific network
configuration, the optimizer sends such configuration to the NPDT,
that predicts the performance metrics of such configuration.
+------------+ Candidate +-------------+
| | Network Config. | Network |
Optimization----> | Network |------------------->| Performance |
objectives | Optimizer | | Digital |
| |<-------------------| Twin |
+------------+ Estimated +-------------+
| Performance
|
|
v
Optimized Network Configuration
Paillisse, et al. Expires 27 April 2023 [Page 18]
Internet-Draft Network Performance Digital Twin October 2022
Figure 4: Using a NPDT as a network model for an optimizer.
An example of optimization use case would be multi-objective
optimization scenarios: commonly, the network administrator defines a
set of optimization goals that must be concurrently met [DEFO], for
example:
* Bound the latency of all links to a maximum.
* Do not exceed a link utilization of 80%, but for only a sub-set of
all the links.
* Route all flows of type B through node 10.
* Avoid more than 35 Gbps of traffic to router R5.
* Minimize the routing cost, that is, the number of flow to re-route
[ReRoute-Cost].
6.2.2. Optical Services and Network Optimization
As suggested in Section 6.4 and Section 6.1.2, optimization - finding
the "best" solution as determined by some quantitative criterion that
is assessed for each candidate solution - is generally an intrinsic
component of optical network planning. This is because such planning
usually involves trying to find e.g. a lowest total or incremental
cost-of-equipment network plan. Where optical services planning
considers new service demands in batches or permits re-configuration
of some or all existing services, optimization of new and/or modified
batches of optical services may be sought as part of the planning
solution. Such optimization could involve, e.g. seeking to maximize
the overall spectral efficiency of the total optical services. Such
an optimization maximizes, in effect, the unused optical network
capacity that remains available for further service deployment.
The functions of the OPDT in these cases are essentially those
described in Section 6.4 and Section 6.1.2. First, the OPDT is used
to verify that all postulated optical services would operate within
acceptable performance bounds, when deployed on the existing or on a
postulated new network topology and detailed equipment map. Second,
the optical service margin information generated by the OPDT may flag
candidate solutions that feature a large number of unnecessarily high
optical service margins. Such findings reflect a general
inefficiency of the candidate solutions and may be used to indicate
that e.g. more spectrally efficient solutions are available and
should be sought.
Paillisse, et al. Expires 27 April 2023 [Page 19]
Internet-Draft Network Performance Digital Twin October 2022
The use of the OPDT with and within optimization process
architectures may be represented in ways qualitatively similar to
what Figure 4 depicts in respect of NPDTs in packet network
optimization use cases.
6.3. Optical Service (Re-)Provisioning
Optical service (re-)provisioning presents operational challenges and
risks. Optical service power levels and - by extension - their
optical noise and other impairment characteristics, are coupled by
optical amplifiers, which act collectively on transiting optical
services. Optical service add, drop and change operations can thus
have deleterious and non-obvious impacts across optical services,
particularly in ring and mesh optical network topologies and
potentially resulting in failure of added, changed or unchanged
optical services.
An OPDT can be used to assess the optical service performances that
would result from prospective optical service (re-)provisioning
operations. Such information could then be used by Management Plane-
embedded or -associated applications seeking to e.g. optimize
add/drop/change batching and sequencing operations, or to determine
optimized optical service launch powers.
For this use case, the appropriate input DT Interface specifies the
topology of optical services postulated for the post-(re)provisioning
scenario, as well as the launch powers and other characteristics
(modulation, coding, spectral characteristics, etc.) defining those
services. Specific scenarios thus postulated for performance
assessment are conceived and determined by the applications referred
to above.
6.4. Optical Service Planning
Before optical service provisioning is attempted, proposed routes
(topology) and other characteristics - launch powers, spectral
allocations, modulation, coding, baud rates, etc. - must be planned
for new optical services to accommodate new traffic, as must any
changes to or deletions of existing optical services that may be
suggested by shifting transmission traffic loads.
An OPDT, per the description in Section 6.3, can be used directly in
support of an optical service planning application, which is presumed
to operate as part of, or in conjunction with the Management Plane.
For example, prospective new optical service plans can be validated
as functional - i.e. that all services would operate within
acceptable performance bounds - by the OPDT. Beyond identifying
scenarios in which one or more optical services would fail to
Paillisse, et al. Expires 27 April 2023 [Page 20]
Internet-Draft Network Performance Digital Twin October 2022
operate, the identification of undesirably low or unnecessarily high
optical service margins could serve as a trigger to explore
alternative plans. This suggests a linkage to optimization
processes, which are discussed in Section 6.2.2
6.5. Optical Network Risk Mapping
The OPDT can be used to assess in advance the impacts on optical
services that can be expected should various "risk" scenarios
materialize [OPDT]. For example, the OPDT may be used to predict the
impacts on transmission performances of optical services that would
be indirectly affected by particular fibre cuts. This is important,
as while services that transit a cut fibre link will be interrupted,
other optical services - those that co-transited uncut links along
with the services that interrupted by the cut(s) - may experience
changes in terminal powers and margins due to amplifier-based
coupling. Where unacceptable event-driven risks to optical service
performances are identified by OPDT-based analysis, solutions may be
proactively sought. For example, optical service planning may be
undertaken to find more resilient optical service solutions for the
at-risk service instances identified.
6.5.1. Optical Network Dynamic Restoration Planning
An important specific use of risk mapping is in the assessment of
optical service dynamic restoration solutions [OPDT]. Dynamic
restoration involves pre-computing a set of failure scenario-based
restoration responses. Resources are not reserved a priori for each
active service; rather, restoration services are delivered as needed
from a "pool" of resources. This is a more efficient restoration
modality than dedicated protection, as the size of the resource pool
is limited by an assumption that only a limited number of failures
may happen at once. However, dynamic restoration requires ongoing
re-planning of restoration solutions, as optical service maps and
equipment and fibre conditions may both evolve over time, affecting
restoration service performance. Risk mapping as described in
Section 6.5 may be used on an ongoing basis to identify service risks
corresponding to planned failure-restoration scenarios. When such
performance risks are found, a search for new dynamic restoration
plans may be triggered, with new candidate restoration solutions
checked for predicted performance integrity using the OPDT.
Paillisse, et al. Expires 27 April 2023 [Page 21]
Internet-Draft Network Performance Digital Twin October 2022
6.6. Troubleshooting
There are many factors that cause network failures (e.g., invalid
network configurations, unexpected protocol interactions). Debugging
modern networks is complex and time consuming. Currently,
troubleshooting is typically done by human experts with years of
experience using networking tools.
Network operators can leverage a PODT to reproduce previous network
failures, in order to find the source of service disruptions.
Specifically, network operators can replicate past network failure
scenarios and analyze their impact on network performance, making it
easier to find specific configuration errors. In addition, the PODT
helps in finding more robust network configurations that prevent
service disruptions in the future.
6.7. Anomaly detection
Since the PODT models the behaviour of a real-world network, network
operators have access to an estimation of the expected network
behaviour. When the real-world network behaviour deviates from the
PODT's behaviour, it can act as an indicator of an anomaly in the
real-world network. Such anomalies can appear at different places in
a network (e.g. core, edge, IoT), and different data sources can be
used to detect such anomalies. Further, trial-and-error
modifications to the scenario assessed by the PODT - e.g. to network
or component configuration or status - can assist with anomaly
troubleshooting if convergence between predicted and observed
performance can be thus obtained. The detailed differences between
the scenario found to produce such convergence, and the actual
physical network scenario, may help to indicate the source of the
anomaly.
6.8. What-if scenarios
The PODT is a unique tool for performing what-if analysis; that is,
for analyzing the impact of potential scenarios and configurations
safely without any impact on the real network. In this context, the
PODT acts as a safe sandbox wherein, different configurations and
scenarios may be presented to the PODT in order to understand their
prospective impacts on physicalnetwork behaviours. It might be said
that the role of the PODT is always to perform a what-if behavioural
analysis, as its intrinsic function is to assess aspects of network
or service performance in scenarios that may be partly or entirely
hypothetical. Nevertheless, a variety of uses of PODTs beyond the
specific use cases already covered, and which fit the what-if
scenario analysis description, may be imagined. Some examples of
such cases include:
Paillisse, et al. Expires 27 April 2023 [Page 22]
Internet-Draft Network Performance Digital Twin October 2022
* What is the impact on my network performance if we acquire company
ACME and we incorporate all its employees?
* When will the network run out of capacity if we have an organic
growth of users?
* What is the optimal network hardware upgrade given a budget?
* We need to update this path. What is the impact on the
performance of the other flows?
* A particular day has a spike of 10% in traffic intensity. How
much loss will it introduce? Can we reduce this loss if we rate-
limit another flow?
* How many links can fail until the SLA is degraded?
* What happens if link B fails? Is the network able to process the
current traffic load? Or, on an optical transmission network,
what will be the performance of surviving optical services? (Per
the risk map use case described in Section 6.5).
6.9. Training
As discussed before, the PODT can be understood as a safe playground
where misconfigurations do not affect the real-world system
performance. In this context, the PODT can play an important role in
improving the education and certification process of network
professionals, both in basic networking training and advanced
scenarios. For example:
* In basic network training, understand how routing modifications
impact delay.
* In more advanced studies, showcase the impact of scheduling
configuration on flow performance, and how to use them to optimize
SLAs.
* In cybersecurity scenarios, evaluate the effects of network
attacks and possible counter-measures.
7. Implementation Challenges
Paillisse, et al. Expires 27 April 2023 [Page 23]
Internet-Draft Network Performance Digital Twin October 2022
7.1. Network Performance Digital Twin Implementation Challenges
This section presents different technologies that can be used to
build a NPDT, and details the advantages and disadvantages of using
them to implement a NPDT. It takes into account how they perform
with respect to the requirements of accuracy, speed, and scale of the
NPDT predictions.
7.1.1. Simulation
Packet-level simulators, such as OMNET++ [OMNET] and NS-3 [ns-3]
simulate network events. In a nutshell, they simulate the operation
of a network by processing a series of events, such as the
transmission of a packet, enqueuing and dequeuing packets in the
router, etc. Hence, they offer excellent accuracy when predicting
network performance metrics (delay, jitter and loss), but they take a
significant amount of time to run the simulation. They scale
linearly with number of packets to simulate.
In fact, the simulation time depends on the number of events to
process [limitations-net-sim]. This limits the scalability of
simulators, even if the topology does not change: increasing traffic
intensities will take longer to simulate because more packets enter
the network per unit of time. Conversely, simulating the same
traffic intensity in larger topologies will also increase the
simulation time. For example, consider a simulator that takes 11
hours to process 4 billion events (these values are obtained from an
actual simulation). Although 4 billion events may appear a large
figure, consider:
* A 1 Gbps ethernet link, transmitting regular frames with the
maximum of 1518 bytes.
* This translates to approx. 82k packets crossing the link per
second.
* Assuming a network with 50 links, and that the transmission of a
packet over a link equals to a single event a in the simulator,
such network translates to 82k packets/s/link * 50 links * 1
event/packet ~ 4 million events to simulate one second of network
activity.
* Then, with a budget of 4 billion events, it takes 11 hours to
simulate only 16 minutes of network activity.
These figures show that, despite the high accuracy of network
simulators, they take too much time to calculate performance
estimations.
Paillisse, et al. Expires 27 April 2023 [Page 24]
Internet-Draft Network Performance Digital Twin October 2022
7.1.2. Emulation
Network emulators run the original network software in a virtualized
environment. This makes them easy to deploy, and depending on the
emulation hardware, they can produce reasonably fast estimations.
However, for large scale networks their speed will eventually
decrease because they are not using specific hardware built for
networking. For fully-virtualized networks, emulating a network
requires as many resources as the real one, which is not cost-
effective.
In addition, some studies have reported variable accuracy depending
on the emulation conditions, both the parameters and underlying
hardware and OS configurations [emulation-perf]. Hence, emulators
show some limitations if we want to build a fast and scalable NPDT.
However, emulators are useful in other use cases, for example in
training, debugging, or testing new features.
7.1.3. Analytical Modelling
Queueing Theory (QT) is an analytical tool that models computer
networks as a series of queues. The key advantage of QT is its
speed, because the calculations rely on mathematical equations. QT
is arguably the most popular modeling technique, where networks are
represented as interconnected queues that are evaluated analytically.
This represents a well-established framework that can model complex
and large networks.
However, the main limitation of QT is the traffic model: although it
offers high accuracy for Poisson traffic models, it presents poor
accuracy under realistic traffic models [qt-precision]. Internet
traffic has been extensively analyzed in the past two decades, and
despite the community has not agreed on a universal model, there is
consensus that in general aggregated traffic shows strong
autocorrelation and a heavy-tail [inet-traffic].
7.1.4. Neural Networks
Finally, Neural Networks (NN) and other Machine Learning (ML) tools
are as fast as QT (in the order of milliseconds), and can provide
similar accuracy to that of packet-level simulators. They represent
an interesting alternative, but have two key limitations. First,
they require training the NN with a large amount of data from a wide
range of network scenarios: different routings, topologies,
scheduling configurations, as well as link failures and network
congestion. This dataset may not be always accessible, or easy to
produce in a production network (see Section 7.1.4.6). Second, in
order to scale to larger topologies and keep the accuracy, not all NN
Paillisse, et al. Expires 27 April 2023 [Page 25]
Internet-Draft Network Performance Digital Twin October 2022
provide sufficient accuracy, therefore, some use cases need custom NN
architectures.
7.1.4.1. MultiLayer Perceptron
A MultiLayer Perceptron [MLP] is a basic kind of NN from the family
of feedforward NN. In short, input data is propagated
unidirectionally from the input layer of neurons through the output.
There may be an arbitrary number of hidden layers between the input
and output layer. They are widely used for basic ML applications,
such as regression.
7.1.4.2. Recurrent Neural Networks
Recurrent Neural Networks [RNN] are a more advanced type of NN
because they connect some layers to the previous ones, which gives
them the ability to store state. They are mostly used to process
sequential data, such as handwriting, text, or audio. They have been
used extensively in speech processing [RNN-speech], and in general,
Natural Language Processing applications [NLP].
7.1.4.3. Convolutional Neural Networks
Convolutional Neural Networks (CNN), are a Deep Learning NN designed
to process structured arrays of data such as images. CNNs are highly
performant when detecting patterns in the input data. This makes
them widely used in computer vision tasks, and have become the state
of the art for many visual applications, such as image classification
[CNN-images]. Hence, their current design presents limited
applicability to computer networks.
7.1.4.4. Graph Neural Networks
Graph Neural Networks [GNN] are a type of neural network designed to
work with graph-structured data. A relevant type of GNN with
interesting characteristics for computer networks are Message Passing
Neural Networks (MPNN). In a nutshell, MPNN exchanges a set of
messages between the graph nodes in order to understand the
relationship between the input graph and the expected outputs of the
training dataset. They are composed of three functions, that are
repeated several iterations, depending on the size of the graph:
* Message: encodes information about the relationship of two
contiguous elements of the graph in a message (an n-element
array).
Paillisse, et al. Expires 27 April 2023 [Page 26]
Internet-Draft Network Performance Digital Twin October 2022
* Aggregation: combines the different messages received on a
particular node. It is typically an element-wise summation. The
result is an array of constant length, independently of the number
of received messages.
* Update: combines the hidden states of a node with the aggregated
message. The result of this function is used as input to the next
message-passing iteration.
Note that the internal architecture of a MPNN is re-build for each
input graph.
Such ability to understand graph-structured data naturally renders
them interesting for a Network Performance Digital Twin. Since
computer networks are fundamentally graphs, they have the potential
to take as input a graph of the network, and produce as output
performance estimations of such the input network [qt-precision].
7.1.4.5. NN Comparison
Figure 5 presents a comparison of different types of NN that predict
the delay of a given input network. We use a dataset of the
performance of different network topologies, created with simulation
data (i.e, ground truth) from OMNET++. We measure the error relative
to the delay of the simulation data. In order to evaluate how well
the different NN deal with different network topologies, we train
each NN in three different scenarios:
* Same topology: the training and testing datasets contain the same
network topologies.
* Different topology: the training and testing datasets contain
different sets of network topologies. The objective is
determining if the NN keeps the same performance if we show it a
topology it has never seen.
* Link failures: here we remove a random link from the topology.
+----------------------------------------------------------+
| Mean Average Percentage Error of the delay prediction |
+----------------------+-----------------------------------+
| Scenario | MLP | RNN | GNN |
+----------------------+-----------+-----------+-----------+
| Same topology | 0.123 | 0.1 | 0.020 |
| Different topology | 11.5 | 0.305 | 0.019 |
| Link failures | 1.15 | 0.638 | 0.042 |
+----------------------+-----------+-----------+-----------+
Paillisse, et al. Expires 27 April 2023 [Page 27]
Internet-Draft Network Performance Digital Twin October 2022
Figure 5: Performance comparison of different NN architectures
We can see that all NNs predict with excellent accuracy the network
delay if we don't change the topology used during training. However,
when it comes to new topologies, the error of the MLP is unacceptable
(1150 %), as well as the RNN, around 30%. On the other hand, the GNN
can understand new topologies, with an error below 2%. Similarly, if
a link fails, the RNN has difficulties offering accurate predictions
(60% error), while the GNN maintains the accuracy (4.2%). These
results show the potential of GNNs to build a Network Performance
Digital Twin.
7.1.4.6. Training of ML-based Digital Twins
In the context of Digital Twins based on Machine Learning, they
require a training process before they can be deployed. Commonly,
the training process makes use of a dataset of inputs and expected
outputs, that guides the training process to adjust the internal
architecture of e.g. the neural network. There are some caveats
regarding the training process:
* In order to obtain sufficient accuracy, the training dataset needs
to be representative, that is, contain samples of a wide range of
possible inputs and outputs. In networks, this translates to
samples of a congested network, with a link failure, etc.
Otherwise, the resulting algorithm cannot predict such situations.
* Taking the latter into account, this means that some kind of
samples, e.g. those of a congested or disrupted network are
difficult to obtain from a production network.
* A way to acquire those samples is in a testbed, although it may
not be possible for some networks, especially those of large
scale. A possible solution in this situation is developing Neural
Networks that are invariant to some of the metrics of the graph,
e.g. number of nodes. That is, the NN does not lose accuracy if
the number of nodes increases. This makes it possible to train
the NN in a testbed, and then deploy it in a network that is
larger than the testbed without losing accuracy.
7.2. Optical Performance Digital Twin Implementation Challenges
Significant challenges to OPDT implementation, deployment and use
relate to e.g. models and instrumentation.
Optical transmission performance is difficult to model accurately
because the different impairments and other factors that determine
performance are not easy to model with high accuracy and system
Paillisse, et al. Expires 27 April 2023 [Page 28]
Internet-Draft Network Performance Digital Twin October 2022
specificity. For example, optical amplifiers are a key determinant
of transmission behaviours and limits, but their gain and noise
characteristics are complicated functions of optical service input
power and spectral profiles, operational set points, etc. In
addition, they vary considerably among amplifier designs, types and
even instances. Yet, transmission systems may contain long chains of
amplifiers, so that accurate end-to-end service modeling requires
highly accurate individual amplifier models. The development of
models that deliver sufficiently accurate performance predictions
across operational circumstances and potentially also amplifier
vendors, types etc., represents a significant challenge.
Nonetheless, promising solution paths have been developed [EDFA1],
[EDFA2].
Transmission performance prediction accuracy may be improved when the
necessary scope of modeling can be reduced through enhancements in
direct measurement of relevant parameters on the physical network.
For example, if optical signal-to-noise ratio and other impairments
can be measured directly on operating services, the available margins
on those optical services is yielded directly. Although significant
advances have been made in this area it will take time before such
improved instrumentation features become widely deployed, and both
usable and susceptible to standardization (e.g. of Measurement
Interfaces).
8. IANA Considerations
This memo includes no request to IANA.
9. Security Considerations
An attacker can alter the software image of the PODT. This could
produce inaccurate performance estimations, that could result in
network misconfigurations, disruptions or outages. Hence, in order
to prevent the accidental deployment of a malicious PODT, the
software image of the PODT MUST be digitally signed by the vendor.
10. References
10.1. Normative References
10.2. Informative References
[OMNET] "https://omnetpp.org/", 2022.
[ns-3] "https://www.nsnam.org/", 2022.
Paillisse, et al. Expires 27 April 2023 [Page 29]
Internet-Draft Network Performance Digital Twin October 2022
[P4Rspec] "https://p4.org/p4-spec/p4runtime/main/P4Runtime-
Spec.html", 2021.
[OFspec] "TS-025: OpenFlow Switch Specification
https://opennetworking.org/wp-content/uploads/2014/10/
openflow-switch-v1.5.1.pdf", 2015.
[NetworkXlib]
"https://networkx.org/", 2022.
[openconfig-rtgwg-gnmi-spec-01]
Shakir, R., Shaikh, A., Borman, P., Hines, M., Lebsack,
C., and C. Morrow, "gRPC Network Management Interface
(gNMI)", March 2018,
<https://datatracker.ietf.org/doc/html/draft-openconfig-
rtgwg-gnmi-spec-01>.
[RFC8040] Bierman, A., Bjorklund, M., and K. Watsen, "RESTCONF
Protocol", RFC 8040, DOI 10.17487/RFC8040, January 2017,
<https://www.rfc-editor.org/info/rfc8040>.
[RFC6241] Enns, R., Ed., Bjorklund, M., Ed., Schoenwaelder, J., Ed.,
and A. Bierman, Ed., "Network Configuration Protocol
(NETCONF)", RFC 6241, DOI 10.17487/RFC6241, June 2011,
<https://www.rfc-editor.org/info/rfc6241>.
[RFC6830] Farinacci, D., Fuller, V., Meyer, D., and D. Lewis, "The
Locator/ID Separation Protocol (LISP)", RFC 6830,
DOI 10.17487/RFC6830, January 2013,
<https://www.rfc-editor.org/info/rfc6830>.
[RFC4655] Farrel, A., Vasseur, J.-P., and J. Ash, "A Path
Computation Element (PCE)-Based Architecture", RFC 4655,
DOI 10.17487/RFC4655, August 2006,
<https://www.rfc-editor.org/info/rfc4655>.
[RFC7047] Pfaff, B. and B. Davie, Ed., "The Open vSwitch Database
Management Protocol", RFC 7047, DOI 10.17487/RFC7047,
December 2013, <https://www.rfc-editor.org/info/rfc7047>.
[RFC3954] Claise, B., Ed., "Cisco Systems NetFlow Services Export
Version 9", RFC 3954, DOI 10.17487/RFC3954, October 2004,
<https://www.rfc-editor.org/info/rfc3954>.
[I-D.draft-zhou-nmrg-digitaltwin-network-concepts]
Zhou, C., Yang, H., Duana, X., Lopez, D., Pastor, A., Wu,
Q., Boucadir, M., and C. Jacquenet, "Digital Twin Network:
Concepts and Reference Architecture", Work in Progress,
Paillisse, et al. Expires 27 April 2023 [Page 30]
Internet-Draft Network Performance Digital Twin October 2022
Internet-Draft, draft-zhou-nmrg-digitaltwin-network-
concepts-06, 2 December 2021,
<https://datatracker.ietf.org/doc/html/draft-zhou-nmrg-
digitaltwin-network-concepts-06>.
[irtf-nmrg-ibn-concepts-definitions-09]
Clemm, A., Ciavaglia, L., Granville, L. Z., and J.
Tantsura, "Intent-Based Networking - Concepts and
Definitions", March 2022,
<https://datatracker.ietf.org/doc/html/draft-irtf-nmrg-
ibn-concepts-definitions-09>.
[digital-twin-5G]
Nguyen, H. X., Trestian, R., To, D., and M. Tatipamula,
"Digital Twin for 5G and Beyond", 2021,
<https://doi.org/10.1109/MCOM.001.2000343>.
[digital-twin-vanets]
Zhao, L., Han, G., Li, Z., and L. Shu, "Intelligent
Digital Twin-Based Software-Defined Vehicular Networks",
2020, <https://doi.org/10.1109/MNET.011.1900587>.
[digital-twin-industry]
Groshev, M., Guimarães, C., Martín-Pérez, J., and A. D. L.
Oliva, "Toward Intelligent Cyber-Physical Systems: Digital
Twin Meets Artificial Intelligence", 2021,
<https://doi.org/10.1109/MCOM.001.2001237>.
[streaming-telemetry]
Gupta, A., Harrison, R., Canini, M., Feamster, N.,
Rexford, J., and W. Willinger, "Sonata: Query-Driven
Streaming Network Telemetry", 2018,
<https://doi.org/10.1145/3230543.3230555>.
[network-capacity]
Ellis, A. D., Suibhne, N. M., Saad, D., and D. N. Payne,
"Communication networks beyond the capacity crunch", 2016,
<https://royalsocietypublishing.org/doi/abs/10.1098/
rsta.2015.0191>.
[planning-scalability]
Zhu, H., Gupta, V., Ahuja, S. S., Tian, Y., Zhang, Y., and
X. Jin, "Network Planning with Deep Reinforcement
Learning", 2021,
<https://doi.org/10.1145/3452296.3472902>.
Paillisse, et al. Expires 27 April 2023 [Page 31]
Internet-Draft Network Performance Digital Twin October 2022
[limitations-net-sim]
Rampfl, S., "Network simulation and its limitations",
2013, <https://doi.org/10.2313/NET-2013-08-1_08>.
[emulation-perf]
Jurgelionis, A., Laulajainen, J., Hirvonen, M., and A. I.
Wang, "An Empirical Study of NetEm Network Emulation
Functionalities", 2011,
<https://doi.org/10.1109/ICCCN.2011.6005933>.
[qt-precision]
Ferriol-Galmés, M., Rusek, K., Suárez-Varela, J., Xiao,
S., Cheng, X., Barlet-Ros, P., and A. Cabellos-Aparicio,
"RouteNet-Erlang: A Graph Neural Network for Network
Performance Evaluation", 2022,
<https://arxiv.org/abs/2202.13956>.
[inet-traffic]
Popoola, J. and R. Ipinyomi, "Empirical Performance of
Weibull Self-Similar Tele-traffic Model", 2017.
[MLP] Pal, S. and S. Mitra, "Multilayer perceptron, fuzzy sets,
and classification", 1992,
<https://doi.org/10.1109/72.159058>.
[RNN] Hochreiter, S. and J. Schmidhuber, "Long Short-Term
Memory", 1997,
<https://doi.org/10.1162/neco.1997.9.8.1735>.
[RNN-speech]
Mikolov, T., Kombrink, S., Burget, L., Černocký, J., and
S. Khudanpur, "Extensions of recurrent neural network
language model", 2011,
<https://doi.org/10.1109/ICASSP.2011.5947611>.
[GNN] Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M.,
and G. Monfardini, "The Graph Neural Network Model", 2009,
<https://doi.org/10.1109/TNN.2008.2005605>.
[DEFO] Hartert, R., Vissicchio, S., Schaus, P., Bonaventure, O.,
Filsfils, C., Telkamp, T., and P. Francois, "A Declarative
and Expressive Approach to Control Forwarding Paths in
Carrier-Grade Networks", 2015,
<https://doi.org/10.1145/2785956.2787495>.
Paillisse, et al. Expires 27 April 2023 [Page 32]
Internet-Draft Network Performance Digital Twin October 2022
[facebook-config]
Sung, Y. E., Tie, X., Wong, S. H., and H. Zeng, "Robotron:
Top-down Network Management at Facebook Scale", 2016,
<https://doi.org/10.1145/2934872.2934874>.
[auto-dc-topology]
Salman, S., Streiffer, C., Chen, H., Benson, T., and A.
Kadav, "DeepConf: Automating Data Center Network
Topologies Management with Machine Learning", 2018,
<https://doi.org/10.1145/3229543.3229554>.
[CNN-images]
Krizhevsky, A., Sutskever, I., and G. E. Hinton, "ImageNet
Classification with Deep Convolutional Neural Networks",
2012, <https://proceedings.neurips.cc/paper/2012/file/
c399862d3b9d6b76c8436e924a68c45b-Paper.pdf>.
[MARL-TE] Bernárdez, G., Suárez-Varela, J., López, A., Wu, B., Xiao,
S., Cheng, X., Barlet-Ros, P., and A. Cabellos-Aparicio,
"Is Machine Learning Ready for Traffic Engineering
Optimization?", 2021,
<https://doi.org/10.1109/ICNP52444.2021.9651930>.
[LS] Gay, S., Hartert, R., and S. Vissicchio, "Expect the
unexpected: Sub-second optimization for segment routing",
2017, <https://doi.org/10.1109/INFOCOM.2017.8056971>.
[DNN-TM] Valadarsky, A., Schapira, M., Shahaf, D., and A. Tamar,
"Learning to Route", 2017,
<https://doi.org/10.1145/3152434.3152441>.
[ReRoute-Cost]
Zheng, J., Xu, Y., Wang, L., Dai, H., and G. Chen, "Online
Joint Optimization on Traffic Engineering and Network
Update in Software-defined WANs", 2021,
<https://doi.org/10.1109/INFOCOM42981.2021.9488837>.
[NLP] Chowdhary, K. R., "Natural Language Processing", 2020,
<https://doi.org/10.1007/978-81-322-3972-7_19>.
[Google-Clos]
Singh, A., Ong, J., Agarwal, A., Anderson, G., Armistead,
A., Bannon, R., Boving, S., Desai, G., Felderman, B.,
Germano, P., Kanagala, A., Provost, J., Simmons, J.,
Tanda, E., Wanderer, J., H\"{o}lzle, U., Stuart, S., and
A. Vahdat, "Jupiter Rising: A Decade of Clos Topologies
and Centralized Control in Google's Datacenter Network",
2015, <https://doi.org/10.1145/2785956.2787508>.
Paillisse, et al. Expires 27 April 2023 [Page 33]
Internet-Draft Network Performance Digital Twin October 2022
[digital-twin-AI]
Mozo, A., Karamchandani, A., Gómez-Canaval, S., Sanz, M.,
Moreno, J. I., and A. Pastor, "B5GEMINI: AI-Driven Network
Digital Twin", 2022,
<https://www.mdpi.com/1424-8220/22/11/4106>.
[OPDT] Janz, C., You, Y., Hemmati, M., Jiang, Z., Javadtalab, A.,
and J. Mitra, "Digital Twin for the Optical Network: Key
Technologies and Enabled Automation Applications", 2022,
<https://doi.org/10.1109/NOMS54207.2022.9789844>.
[EDFA1] You, Y., Jiang, Z., and C. Janz, "Machine Learning-Based
EDFA Gain Model", 2018,
<https://doi.org/10.1109/ECOC.2018.8535397>.
[EDFA2] You, Y., Jiang, Z., and C. Janz, "OSNR prediction using
machine learning-based EDFA models", 2019,
<https://doi.org/10.1049/cp.2019.1044>.
[RFC8345] Clemm, A., Medved, J., Varga, R., Bahadur, N.,
Ananthakrishnan, H., and X. Liu, "A YANG Data Model for
Network Topologies", RFC 8345, DOI 10.17487/RFC8345, March
2018, <https://www.rfc-editor.org/info/rfc8345>.
[RFC8795] Liu, X., Bryskin, I., Beeram, V., Saad, T., Shah, H., and
O. Gonzalez de Dios, "YANG Data Model for Traffic
Engineering (TE) Topologies", RFC 8795,
DOI 10.17487/RFC8795, August 2020,
<https://www.rfc-editor.org/info/rfc8795>.
[RFC9094] Zheng, H., Lee, Y., Guo, A., Lopez, V., and D. King, "A
YANG Data Model for Wavelength Switched Optical Networks
(WSONs)", RFC 9094, DOI 10.17487/RFC9094, August 2021,
<https://www.rfc-editor.org/info/rfc9094>.
[I-D.ietf-ccamp-flexigrid-yang]
Jorge Lopez de Vergara Mendez, E., Burrero, D. P., King,
D., Lee, Y., and H. Zheng, "A YANG Data Model for Flexi-
Grid Optical Networks", Work in Progress, Internet-Draft,
draft-ietf-ccamp-flexigrid-yang-13, 10 July 2022,
<https://www.ietf.org/archive/id/draft-ietf-ccamp-
flexigrid-yang-13.txt>.
Paillisse, et al. Expires 27 April 2023 [Page 34]
Internet-Draft Network Performance Digital Twin October 2022
[I-D.ietf-ccamp-optical-impairment-topology-yang]
Beller, D., Rouzic, E. L., Belotti, S., Galimberti, G.,
and I. Busi, "A YANG Data Model for Optical Impairment-
aware Topology", Work in Progress, Internet-Draft, draft-
ietf-ccamp-optical-impairment-topology-yang-10, 11 July
2022, <https://www.ietf.org/archive/id/draft-ietf-ccamp-
optical-impairment-topology-yang-10.txt>.
[I-D.ietf-teas-yang-te]
Saad, T., Gandhi, R., Liu, X., Beeram, V. P., Bryskin, I.,
and O. G. D. Dios, "A YANG Data Model for Traffic
Engineering Tunnels, Label Switched Paths and Interfaces",
Work in Progress, Internet-Draft, draft-ietf-teas-yang-te-
30, 11 July 2022, <https://www.ietf.org/archive/id/draft-
ietf-teas-yang-te-30.txt>.
[I-D.ietf-ccamp-wson-tunnel-model]
Lee, Y., Zheng, H., Guo, A., Lopez, V., King, D., Yoon, B.
Y., and R. Vilalta, "A Yang Data Model for WSON Tunnel",
Work in Progress, Internet-Draft, draft-ietf-ccamp-wson-
tunnel-model-07, 11 July 2022,
<https://www.ietf.org/archive/id/draft-ietf-ccamp-wson-
tunnel-model-07.txt>.
[I-D.ietf-ccamp-flexigrid-tunnel-yang]
Jorge Lopez de Vergara Mendez, E., Burrero, D. P., King,
D., Lopez, V., Busi, I., Belotti, S., and G. Galimberti,
"A YANG Data Model for Flexi-Grid Tunnels", Work in
Progress, Internet-Draft, draft-ietf-ccamp-flexigrid-
tunnel-yang-01, 11 July 2022,
<https://www.ietf.org/archive/id/draft-ietf-ccamp-
flexigrid-tunnel-yang-01.txt>.
[I-D.yg3bp-ccamp-network-inventory-yang]
Yu, C., Busi, I., Guo, A., Belotti, S., Bouquier, J.,
Peruzzini, F., Dios, O. G. D., and V. Lopez, "A YANG Data
Model for Network Hardware Inventory", Work in Progress,
Internet-Draft, draft-yg3bp-ccamp-network-inventory-yang-
02, 24 October 2022,
<https://datatracker.ietf.org/api/v1/doc/document/draft-
yg3bp-ccamp-network-inventory-yang/>.
Acknowledgements
TBD
Authors' Addresses
Paillisse, et al. Expires 27 April 2023 [Page 35]
Internet-Draft Network Performance Digital Twin October 2022
Jordi Paillisse
UPC-BarcelonaTech
c/ Jordi Girona 1-3
08034 Barcelona Catalonia
Spain
Email: jordi.paillisse@upc.edu
Paul Almasan
UPC-BarcelonaTech
c/ Jordi Girona 1-3
08034 Barcelona Catalonia
Spain
Email: felician.paul.almasan@upc.edu
Miquel Ferriol
UPC-BarcelonaTech
c/ Jordi Girona 1-3
08034 Barcelona Catalonia
Spain
Email: miquel.ferriol@upc.edu
Pere Barlet
UPC-BarcelonaTech
c/ Jordi Girona 1-3
08034 Barcelona Catalonia
Spain
Email: pere.barlet@upc.edu
Albert Cabellos
UPC-BarcelonaTech
c/ Jordi Girona 1-3
08034 Barcelona Catalonia
Spain
Email: alberto.cabellos@upc.edu
Shihan Xiao
Huawei
China
Email: xiaoshihan@huawei.com
Paillisse, et al. Expires 27 April 2023 [Page 36]
Internet-Draft Network Performance Digital Twin October 2022
Xiang Shi
Huawei
China
Email: shixiang16@huawei.com
Xiangle Cheng
Huawei
China
Email: chengxiangle1@huawei.com
Christopher Janz
Huawei
Canada
Email: christopher.janz@huawei.com
Aihua Guo
Futurewei
United States of America
Email: aihua.guo@futurewei.com
Diego Perino
Telefonica I+D
Barcelona
Spain
Email: diego.perino@telefonica.com
Diego Lopez
Telefonica I+D
Seville
Spain
Email: diego.r.lopez@telefonica.com
Antonio Pastor
Telefonica I+D
Madrid
Spain
Email: antonio.pastorperales@telefonica.com
Paillisse, et al. Expires 27 April 2023 [Page 37]
