Citation :

Nalla Akhila, Suneel Pappala, Sripada Rama Sree, "FED-XML-GA++: FEDerated eXplainable Adaptable Genetic Algorithm for Multi-Objectival Optimization (GA++) and SHAP-Mutated Surrogates (XML) to Oversee QoS in Wireless Dynamic Heterogeneous Networks," International Journal of Electronics and Communication Engineering, vol. 13, no. 7, pp. 214-230, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I7P115

Abstract

Different wireless communication systems like IoT, Mobile Ad Hoc Networks (MANETs), and future 6G have different density, mobility and traffic patterns of Quality of Service (QoS). Similar to many multiobjective Quality of Service (QoS) optimisations using Machine Learning-based Genetic Algorithms (ML-GAs), we have till now mostly relied on surrogate models with usually unit-level simulation and generally without adaptation for drift and explainability in the models. Here, we improve the framework, FED-XML-GA++, which includes federated surrogate learning, explainability (using SHAP), adaptation of the drift, and a new mutation operator, mainly based on SHAP, in NSGA-II. We use real traffic, human movement dataset and statistically generated dataset (UNSW-NB15) to study the framework. The idea is to use federated surrogate models for a Quality of Service (QoS) prediction. The optimization model is the NSGA-II equipped with adaptive mutation from the importance of the features using Shapley Multilevel Additive SHAP. The ADWIN drift detector also plays an important part in the adaptive training of models. The simulation shows the system is providing better performance with higher throughput (20.4%), low latency (27.8%), with less energy (15.9%) consumption and has improved convergence with fast adaptation with the drift detection system with differing load and network quality. The key system has interpretability, scalability and speed of the optimization procedure, and the final system can be deployed to next-generation networks.

Keywords

Federated Learning, Multi-objective optimization, NSGA-II, QoS Management, SHAP Explainability, Concept Drift Detection, Genetic Algorithms, Wireless Networks, Surrogate Modeling.

References

1. Mahdi Beitollahi, and Ning Lu, “Federated Learning Over Wireless Networks: Challenges and Solutions,” IEEE Internet of Things Journal, vol. 10, no. 16, pp. 14749-14763, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Rachid El Mokadem, Yann Ben Maissa, and Zineb El Akkaoui, “Federated Learning Communications Optimization Using Sparse Single-Layer Updates,” Procedia Computer Science, vol. 236, pp. 168-176, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Betul Yurdem et al., “Federated Learning: Overview, Strategies, Applications, Tools and Future Directions,” Heliyon, vol. 10, no. 19, pp. 1-24, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Guangchen Lan et al., “Communication-Efficient Federated Learning for Resource-Constrained Edge Devices,” IEEE Transactions on Machine Learning in Communications and Networking, vol. 1, pp. 210-224, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Zhixiong Chen et al., “Robust Federated Learning for Unreliable and Resource-Limited Wireless Networks,” IEEE Transactions on Wireless Communications, vol. 23, no. 8, pp. 9793-9809, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Yuchang Sun et al., “Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning,” IEEE Transactions on Wireless Communications, vol. 23, no. 7, pp. 6905-6920, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Jianxin Liu et al., “Wireless Federated Learning for PR Identification and Analysis based on Generalized Information,” Intelligent Systems with Applications, vol. 23, pp. 1-8, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Mingzhe Chen, and Shuguang Cui, Communication Efficient Federated Learning for Wireless Networks, 1^st ed., Springer Cham, pp. 1-179, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Xuan-Toan Dang et al., “A Survey on Energy-Efficient Design for Federated Learning over Wireless Networks,” Energies, vol. 17, no. 24, pp. 1-28, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Nikolaos Koursioumpas et al., “DISTINQT: A Distributed Privacy Aware Learning Framework for QoS Prediction for Future Mobile and Wireless Networks,” Future Internet, vol. 74, no. 6, pp. 9790-9801, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Tarik Taleb et al., “On Multi-Access Edge Computing: A Survey of the Emerging 5G Network Edge Cloud Architecture and Orchestration,” IEEE Communications Surveys & Tutorials, vol. 19, no. 3, pp. 1657-1681, 2017.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Yuyi Mao et al., “A Survey on Mobile Edge Computing: The Communication Perspective,” IEEE Communications Surveys & Tutorials, vol. 19, no. 4, pp. 2322-2358, 2017.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Yaohua Sun, Mugen Peng, and Shiwen Mao, “Deep Reinforcement Learning-Based Mode Selection and Resource Management for Green Fog Radio Access Networks,” IEEE Internet of Things Journal, vol. 6, no. 2, pp. 1960-1971, 2019.
    [CrossRef] [Google Scholar] [Publisher Link]
14. C.A. Coello Coello, “Evolutionary Multi-Objective Optimization: A Historical View of the Field,” IEEE Computational Intelligence Magazine, vol. 1, no. 1, pp. 28-36, 2006.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Kalyanmoy Deb, Multi-Objective Optimization using Evolutionary Algorithms, Wiley, pp. 1-497, 2001.
    [Google Scholar] [Publisher Link]
16. Brendan McMahan et al., “Communication-Efficient Learning of Deep Networks from Decentralized Data,” Proceedings of the 20^th International Conference on Artificial Intelligence and Statistics, vol. 54, pp. 1273-1282, 2017.
    [Google Scholar] [Publisher Link]
17. Peter Kairouz, and H. Brendan McMahan, “Advances and Open Problems in Federated Learning,” Foundations and Trends in Machine Learning, vol. 14, no. 1-2, pp. 1-210, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Jihong Park et al., “Wireless Network Intelligence at the Edge,” Proceedings of the IEEE, vol. 107, no. 11, pp. 2204-2239, 2019.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Scott M Lundberg, and Su-In Lee, “A Unified Approach to Interpreting Model Predictions,” 31^st Conference on Advances in Neural Information Processing Systems, Long Beach, CA, USA, pp. 1-10, 2017.
    [Google Scholar] [Publisher Link]
20. Wojciech Samek et al., Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, Springer Cham, 1^st ed., pp. 1-439, 2019.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Albert Bifet, and Ricard Gavaldà, “Learning from Time-Changing Data with Adaptive Windowing,” Proceedings of the 2007 SIAM International Conference on Data Mining, Minneapolis, Minnesota, pp. 443-448, 2007.
    [CrossRef] [Google Scholar] [Publisher Link]
22. João Gama et al., “A Survey on Concept Drift Adaptation,” ACM Computing Surveys, vol. 46, no. 4, pp. 1-37, 2014.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Huaqing Zhang et al., “Computing Resource Allocation in Three-Tier IoT Fog Networks: A Joint Optimization Approach Combining Stackelberg Game and Matching,” IEEE Internet of Things Journal, vol. 4, no. 5, pp. 1204-1215, 2017.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Nguyen H. Tran et al., “Federated Learning over Wireless Networks: Optimization Model Design and Analysis,” IEEE INFOCOM 2019 - IEEE Conference on Computer Communications, Paris, France, pp. 1387-1395, 2019.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Mehryar Mohri et al., “Agnostic Federated Learning,” Proceedings of the 36^th International Conference on Machine Learning, Long Beach, California, pp. 4615-4625, 2019.
    [Google Scholar] [Publisher Link]