In this paper, we study a new latency optimization problem for Blockchain-based federated learning (BFL) in multi-server edge computing. In this system model, distributed mobile devices (MDs) communicate with a set of edge servers (ESs) to handle both machine learning (ML) model training and block mining simultaneously. To assist the ML model training for resource-constrained MDs, we develop an offloading strategy that enables MDs to transmit their data to one of the associated ESs. We then propose a new decentralized ML model aggregation solution at the edge layer based on a consensus mechanism to build a global ML model via peer-to-peer (P2P)-based Blockchain communications. We then formulate latency-aware BFL as an optimization aiming to minimize the system latency via joint consideration of the data offloading decisions, MDs' transmit power, channel bandwidth allocation for MDs' data offloading, MDs' computational allocation, and hash power allocation. To address the mixed action space of discrete offloading and continuous allocation variables, we propose a novel deep reinforcement learning scheme with a holistic design of a parameterized advantage actor critic (A2C) algorithm. Additionally, we theoretically characterize the convergence properties of the proposed BFL system in terms of the aggregation delay, mini-batch size, and number of P2P communication rounds. Our subsequent numerical evaluation demonstrates the superior performance of our proposed scheme over existing approaches in terms of model training efficiency, convergence rate, and system latency.

本文研究了面向多服务器边缘计算的基于区块链的联邦学习的延迟优化问题，利用区块链的共识机制建立了去中心化的基于点对点的 ML 模型聚合方案，并通过深度强化学习算法实现了数据卸载决策、移动设备传输功率、频道带宽分配、移动设备的计算分配和哈希功率分配等多个因素的联合考虑来实际降低了系统的延迟、提升了模型训练效率和收敛速率，并提供了对一些重要参数的理论分析和对抗模型污染攻击的防御。

基于区块链的联邦学习在多服务器边缘计算中的延迟优化