Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Fair Federated Learning Framework for Collaborative Network Traffic Prediction and Resource Allocation

Saroj Kumar Panda, Tania Panayiotou, Georgios Ellinas, Sadananda Behera

TL;DR

This paper tackles privacy and fairness in collaborative network traffic prediction and resource allocation by introducing a $q$-Fair Federated Learning ($q$-FFL) framework. Using non-iid, imbalanced real-world traffic traces in an elastic optical network, it demonstrates that increasing the fairness parameter $q$ improves cross-client prediction fairness (lower CV across operators) while maintaining global accuracy, and that fair predictions translate into fairer QoS across connections. The study quantitatively shows up to 16% improvement in cross-operator fairness and up to 6% improvement in QoS fairness, with substantial gains (up to 80%) in the balance of over- and under-provisioning. The framework supports privacy-preserving, DT-enabled collaboration among operators and points to future work on automatic fairness tuning and explainable AI for FL in networked systems.

Abstract

In the beyond 5G era, AI/ML empowered realworld digital twins (DTs) will enable diverse network operators to collaboratively optimize their networks, ultimately improving end-user experience. Although centralized AI-based learning techniques have been shown to achieve significant network traffic accuracy, resulting in efficient network operations, they require sharing of sensitive data among operators, leading to privacy and security concerns. Distributed learning, and specifically federated learning (FL), that keeps data isolated at local clients, has emerged as an effective and promising solution for mitigating such concerns. Federated learning poses, however, new challenges in ensuring fairness both in terms of collaborative training contributions from heterogeneous data and in mitigating bias in model predictions with respect to sensitive attributes. To address these challenges, a fair FL framework is proposed for collaborative network traffic prediction and resource allocation. To demonstrate the effectiveness of the proposed approach, noniid and imbalanced federated datasets based on real-word traffic traces are utilized for an elastic optical network. The assumption is that different optical nodes may be managed by different operators. Fairness is evaluated according to the coefficient of variations measure in terms of accuracy across the operators and in terms of quality-of-service across the connections (i.e., reflecting end-user experience). It is shown that fair traffic prediction across the operators result in fairer resource allocations across the connections.

A Fair Federated Learning Framework for Collaborative Network Traffic Prediction and Resource Allocation

TL;DR

This paper tackles privacy and fairness in collaborative network traffic prediction and resource allocation by introducing a -Fair Federated Learning (-FFL) framework. Using non-iid, imbalanced real-world traffic traces in an elastic optical network, it demonstrates that increasing the fairness parameter improves cross-client prediction fairness (lower CV across operators) while maintaining global accuracy, and that fair predictions translate into fairer QoS across connections. The study quantitatively shows up to 16% improvement in cross-operator fairness and up to 6% improvement in QoS fairness, with substantial gains (up to 80%) in the balance of over- and under-provisioning. The framework supports privacy-preserving, DT-enabled collaboration among operators and points to future work on automatic fairness tuning and explainable AI for FL in networked systems.

Abstract

In the beyond 5G era, AI/ML empowered realworld digital twins (DTs) will enable diverse network operators to collaboratively optimize their networks, ultimately improving end-user experience. Although centralized AI-based learning techniques have been shown to achieve significant network traffic accuracy, resulting in efficient network operations, they require sharing of sensitive data among operators, leading to privacy and security concerns. Distributed learning, and specifically federated learning (FL), that keeps data isolated at local clients, has emerged as an effective and promising solution for mitigating such concerns. Federated learning poses, however, new challenges in ensuring fairness both in terms of collaborative training contributions from heterogeneous data and in mitigating bias in model predictions with respect to sensitive attributes. To address these challenges, a fair FL framework is proposed for collaborative network traffic prediction and resource allocation. To demonstrate the effectiveness of the proposed approach, noniid and imbalanced federated datasets based on real-word traffic traces are utilized for an elastic optical network. The assumption is that different optical nodes may be managed by different operators. Fairness is evaluated according to the coefficient of variations measure in terms of accuracy across the operators and in terms of quality-of-service across the connections (i.e., reflecting end-user experience). It is shown that fair traffic prediction across the operators result in fairer resource allocations across the connections.

Paper Structure

This paper contains 11 sections, 7 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Contribution
  4. Fair Federated Traffic Modeling
  5. Fair Federated Learning Preliminaries
  6. $q$-FFL Algorithm
  7. Traffic Prediction Modeling and Formulation
  8. Federated Dataset Generation
  9. Fair FL Training and Evaluation
  10. Fair Traffic-Driven Resource Allocation and Evaluation
  11. Conclusions

Figures (4)

  • Figure 1: The global loss $f_q$ across all clients for different $q$ values.
  • Figure 2: $CV$ of accuracy across all clients for various $q$ values.
  • Figure 3: CV of QoS across all the connections for various $q$ values.
  • Figure 4: CV across over- and under-provisioning for various $q$ values.