Hierarchical Federated MADRL for Sustainable Cloud-Edge Resource Orchestration


Date Published : 20 August 2026

Contributors

Saurabh Singhal

Greater Noida Institute of Technology
Author

Pawan Kumar Verma

Lincoln University College, Petaling Jaya, Malaysia
Author

Keywords

Cloud-Edge Computing; Federated Learning; Multi-Agent Reinforcement Learning; Resource Orchestration; Sustainable Computing.

Proceeding

Track

General Track

License

Copyright (c) 2026 Sustainable Global Societies Initiative

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Abstract

Cloud edge computing is a necessity for latency-sensitive applications such as smart cities and IoT, although efficient resource management is difficult due to dynamic workload and tight SLAs. Existing approaches suffer from scalability problems with the centralisation approach for resource management or the lack of coordination with the decentralisation approach. In this paper, we discuss the literature survey for the sustainable orchestration of resources. Our goal is to propose a framework that maximises the optimisation for task allocation, resource utilisation, SLA compliance, latency, and energy consumption while minimising the carbon footprint.

References

No References

Downloads

How to Cite

Singhal, S., & Verma, P. K. . (2026). Hierarchical Federated MADRL for Sustainable Cloud-Edge Resource Orchestration. Sustainable Global Societies Initiative, 1(8). https://vectmag.com/sgsi/paper/view/1146