GreenFLag: A Green Agentic Approach for Energy-Efficient Federated Learning

2026-03-31

AI Summary

This work addresses the high energy consumption and heavy reliance on grid electricity in federated learning, which currently underutilizes renewable energy sources. To tackle this issue, the authors propose GreenFLag, an agent-based resource orchestration framework that, for the first time, integrates dynamic renewable energy supply into federated learning scheduling. GreenFLag employs the Soft Actor-Critic reinforcement learning algorithm to jointly optimize computation and communication resources, enabling green, efficient, and adaptive coordination while preserving model performance. Experimental evaluation on the real-world Copernicus dataset demonstrates that GreenFLag reduces grid energy consumption by 94.8% on average compared to three state-of-the-art baselines, with training predominantly powered by renewable energy.

Abstract

Progressing toward a new generation of mobile networks, a clear focus on integrating distributed intelligence across the system is observed to drive performance, autonomy, and real-time adaptability. Federated learning (FL) stands out as a key emerging technique, enabling on-device model training while preserving data locality. However, its operation introduces substantial energy and resource demands. Energy needs are mostly met by grid power sources, while FL resource orchestration strategies remain limited. This work introduces GreenFLag, an agentic resource orchestration framework designed to minimize the energy consumption from the grid power to complete FL workflows, guarantee FL model performance, and reduce grid power reliance by incorporating renewable sources into the system. GreenFLag leverages a Soft-Actor Critic reinforcement learning approach to jointly optimize computational and communication resources, while accounting for communication contention and the dynamic availability of renewable energy. Evaluations using a real-world open dataset from Copernicus, demonstrate that GreenFLag significantly reduces grid energy consumption by 94.8% on average, compared to three state-of-the-art baselines, while primarily relying on green power.

Problem

• Federated Learning
• Energy Efficiency
• Renewable Energy
• Resource Orchestration
• Grid Power

Innovation

• GreenFLag
• Energy-Efficient Federated Learning
• Agentic Resource Orchestration
• Soft Actor-Critic
• Renewable Energy Integration