【Author】
Pokhrel, Shiva Raj; Choi, Jinho
【Source】2020 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE WORKSHOPS (WCNCW)
【Abstract】In this paper, we propose an autonomous blockchain-based federated learning (BFL) design for privacy-aware and efficient vehicular communication networking, where local on-vehicle machine learning (oVML) model updates are exchanged and verified in a distributed fashion. BFL enables on-vehicle machine learning without any centralized training data or coordination by utilizing the consensus mechanism of the blockchain. Relying on a renewal reward approach, we develop a mathematical framework that features the controllable network and BFL parameters, such as the retransmission limit, block size, block arrival rate, and the frame sizes, so as to capture their impact on the system-level performance. More importantly, our rigorous analysis of oVML system dynamics quantifies the end-to-end delay with BFL, which provides important insights into deriving optimal block arrival rate by considering communication and consensus delays.
【Keywords】on-Vehicle Machine Learning; Federated learning; Blockchain; Delay Analysis; consensus delay; low delay
【标题】一种用于联网自动驾驶汽车的分散式联邦学习方法
【摘要】在本文中，我们提出了一种基于自主区块链的联邦学习 (BFL) 设计，用于隐私感知和高效的车载通信网络，其中本地车载机器学习 (oVML) 模型更新以分布式方式进行交换和验证。 BFL 利用区块链的共识机制，无需任何集中的训练数据或协调即可实现车载机器学习。依靠更新奖励方法，我们开发了一个以可控网络和BFL参数为特征的数学框架，例如重传限制、块大小、块到达率和帧大小，以捕捉它们对系统级的影响表现。更重要的是，我们对 oVML 系统动力学的严格分析量化了 BFL 的端到端延迟，这为通过考虑通信和共识延迟来推导最佳块到达率提供了重要的见解。
【关键词】车载机器学习；联邦学习；区块链；延迟分析；共识延迟；低延迟
评论