Energy-Efficient Federated Edge Learning with Streaming Data: A Lyapunov Optimization Approach

TL;DR

This paper proposes a Lyapunov optimization-based dynamic resource management algorithm for energy-efficient federated edge learning with streaming data, addressing randomness in data arrivals and resource constraints to improve training efficiency.

Contribution

It introduces a novel Lyapunov drift-plus-penalty framework for adaptive scheduling and resource allocation in FEEL with streaming data, considering long-term energy constraints and system dynamics.

Findings

Enhanced learning performance in simulations

Improved energy efficiency over baseline schemes

Effective handling of data and resource randomness

Abstract

Federated learning (FL) has received significant attention in recent years for its advantages in efficient training of machine learning models across distributed clients without disclosing user-sensitive data. Specifically, in federated edge learning (FEEL) systems, the time-varying nature of wireless channels introduces inevitable system dynamics in the communication process, thereby affecting training latency and energy consumption. In this work, we further consider a streaming data scenario where new training data samples are randomly generated over time at edge devices. Our goal is to develop a dynamic scheduling and resource allocation algorithm to address the inherent randomness in data arrivals and resource availability under long-term energy constraints. To achieve this, we formulate a stochastic network optimization problem and use the Lyapunov drift-plus-penalty framework to obtain a dynamic resource management design. Our proposed algorithm makes adaptive decisions on device scheduling, computational capacity adjustment, and allocation of bandwidth and transmit power in every round. We provide convergence analysis for the considered setting with heterogeneous data and time-varying objective functions, which supports the rationale behind our proposed scheduling design. The effectiveness of our scheme is verified through simulation results, demonstrating improved learning performance and energy efficiency as compared to baseline schemes.