Replica-Aware Split Inference：让 IoT 设备故障不中断推理
Replica-Aware Split Inference for Edge IoT Systems
搞边缘 IoT 部署的可以看看：设备挂了副本自动顶上，用 MILP 算最优放置，实测延迟比随机方案低 18.3%。
这篇 arXiv 论文（编号 2611.04779）针对 Split Inference 中设备故障中断推理的问题，提出在存活设备上部署 TinyML 模型分段副本的恢复方案。作者将副本主机选择与通信协议选择联合建模为 MILP 优化问题，目标是在闪存和运行内存约束下最小化重配置后的推理延迟。实验在 15 台 IoT 设备组成的网络上进行，链路速率最大降低 75%，使用 MobileNetV2 仿真并与四个基线对比。结果显示该方案的端到端推理延迟比 Computation Greedy 平均低 6.8%，比 Random 低 18.3%。
Replica-Aware Split Inference for Edge IoT Systems
Split Inference (SI) addresses the hardware resource limitations of Internet of Things (IoT) devices by distributing tiny Machine Learning (TinyML) model segments across multiple IoT devices. However, a device failure can interrupt the inference pipeline. This paper proposes a replica-aware recovery approach that deploys replicas of TinyML model segments originally hosted on failed devices onto surviving devices. We formulate the joint selection of replica hosts and communication protocols as a mixed-integer linear programming (MILP) problem that minimizes post-reconfiguration inference latency, accounting for computation and transmission latencies, under flash memory and runtime memory constraints. Simulations using MobileNetV2 on heterogeneous IoT networks compare the proposed approach with four baselines. We implement the model in a network of 15 IoT devices with a maximum link-rate reduction of 75%, and show that MILP approach achieves an average modeled end-to-end inference latency that is 6.8% lower than that of Computation Greedy and 18.3% lower than that of Random. Index Terms TinyML, split inference, Internet of Things, fault tolerance, replica placement.