优化物联网设备上分层学习的延迟，提升低功耗边缘推理效率
Optimizing Split Learning Latency in TinyML-Based IoT Systems
- 基于启发式搜索的分层点优化算法，降低端到端推理延迟
- ESP-NOW协议实现3.6秒最低往返时延，适合实时场景
- 适用于资源受限的物联网系统，尤其关注低延迟部署
分层学习（Split Learning, SL）克服了在低功耗边缘/物联网节点上直接运行深度学习推理的限制，通过将部分推理过程在传感器端执行，并将剩余部分卸载到配套设备完成。尽管前景广阔，但在真实低功耗无线协议下，受限硬件上的分层学习推理延迟仍未被充分研究。本文首次在ESP32-S3开发板上对基于TinyML的分层学习进行了实验性延迟基准测试，对比了四种无线通信协议（UDP、TCP、ESP-NOW、BLE）的表现。同时分析了不同模型（MobileNet-V2和ResNet50）在不同分层点下的通信与计算开销，以最小化端到端推理延迟。提出一种基于束搜索（Beam Search）的分层点优化算法，相较于贪心搜索、首因匹配、随机匹配及暴力搜索等方法，在5个设备环境下仅需0.1秒处理时间即可达到近最优延迟，其中ESP-NOW协议实现最低往返时延（3.6秒），成为该算法的基础通信方案。
原文摘要 · Abstract (English)
Split learning (SL) addresses the limitation of running deep learning inference directly on low-power edge/IoT nodes, in which it executes part of the inference process on the sensor and offloading the remainder to a companion device. Despite its promise, the inference latency of SL on constrained hardware under realistic low-power wireless protocols remains unexplored. This paper presents the first experimental latency benchmark of TinyML-based SL on ESP32-S3 boards, comparing four wireless communication protocol solutions (UDP, TCP, ESP-NOW, BLE). We also analyze the impact of the choice of different split points across different models (MobileNet-V2 and ResNet50) in terms of communication and computation overhead as a way to minimize the end-to-end inference latency. We propose a Beam Search-based algorithm for split point optimization that minimizes end-to-end latency, and compare it with other methods, including Greedy Search, First-Fit, Random-Fit, and Brute Force. ESP-NOW achieves the best RTT (3.6 s) and serves as the base protocol for the algorithm, which delivers near-optimal latency with processing time of 0.1 s for 5 devices.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。