FAuNO: Semi-Asynchronous Federated Reinforcement Learning Framework for Task Offloading in Edge Systems

TL;DR

FAuNO introduces a semi-asynchronous federated reinforcement learning framework for decentralized task offloading in edge systems, improving efficiency and reducing latency through a novel actor-critic architecture.

Contribution

It proposes a new federated RL framework with an actor-critic architecture for decentralized edge task offloading, enhancing cooperation and performance.

Findings

Outperforms heuristic and federated multi-agent RL baselines in reducing task loss.

Consistently matches or exceeds baseline performance in dynamic scenarios.

Demonstrates adaptability to edge computing environments.

Abstract

Edge computing addresses the growing data demands of connected-device networks by placing computational resources closer to end users through decentralized infrastructures. This decentralization challenges traditional, fully centralized orchestration, which suffers from latency and resource bottlenecks. We present \textbf{FAuNO} -- \emph{Federated Asynchronous Network Orchestrator} -- a buffered, asynchronous \emph{federated reinforcement-learning} (FRL) framework for decentralized task offloading in edge systems. FAuNO adopts an actor-critic architecture in which local actors learn node-specific dynamics and peer interactions, while a federated critic aggregates experience across agents to encourage efficient cooperation and improve overall system performance. Experiments in the \emph{PeersimGym} environment show that FAuNO consistently matches or exceeds heuristic and federated multi-agent RL baselines in reducing task loss and latency, underscoring its adaptability to dynamic edge-computing scenarios.