EcoFL: Resource Allocation for Energy-Efficient Federated Learning in Multi-RAT ORAN Networks

TL;DR

EcoFL introduces a novel framework leveraging multi-RAT ORAN networks with RL and CNN components to optimize resource allocation, significantly reducing energy consumption while maintaining effective federated learning in dynamic wireless environments.

Contribution

The paper presents EcoFL, a new integrated FL framework using ORAN architecture with RL and CNN modules for energy-efficient, robust federated learning in multi-RAT wireless networks.

Findings

19% lower power consumption compared to baselines

Enhanced communication resilience under network fluctuations

Maintained competitive FL model performance

Abstract

Federated Learning (FL) enables distributed model training on edge devices while preserving data privacy. However, FL deployments in wireless networks face significant challenges, including communication overhead, unreliable connectivity, and high energy consumption, particularly in dynamic environments. This paper proposes EcoFL, an integrated FL framework that leverages the Open Radio Access Network (ORAN) architecture with multiple Radio Access Technologies (RATs) to enhance communication efficiency and ensure robust FL operations. EcoFL implements a two-stage optimisation approach: an RL-based rApp for dynamic RAT selection that balances energy efficiency with network performance, and a CNN-based xApp for near real-time resource allocation with adaptive policies. This coordinated approach significantly enhances communication resilience under fluctuating network conditions. Experimental results demonstrate competitive FL model performance with 19\% lower power consumption compared to baseline approaches, highlighting substantial potential for scalable, energy-efficient collaborative learning applications.