智能调节压缩与同步，让物联网雨量预测更省带宽、更稳定。
Adaptive Joint Compression and Synchronisation in Federated Split Learning for IoT Rainfall Prediction
- 根据延迟动态调整压缩率和同步频率，结合客户端平滑优化。
- 在树莓派上实现87%上传量减少，54%同步流量下降。
- 适合资源受限的物联网雨量预测场景，抗网络波动强。
联邦分割学习（FSL）使带宽受限的物联网设备可协同训练，但频繁激活与梯度交换导致通信瓶颈。现有工作仅单独优化激活压缩或同步频率。本文提出一种面向物联网雨量预测的FSL框架，通过服务器端基于延迟驱动的调度器联合调控激活压缩与同步间隔ρ，采用每客户端指数移动平均（EMA）平滑。在11个气象站的小时级ERA5数据上进行17种场景仿真，并在真实广域链路上部署4种场景的树莓派验证。仿真验证了调度器在低、高及混合延迟下的切换能力，树莓派部署验证了该策略选择的高延迟端点。不同配置下AUPRC变化极小（仿真中0.6381–0.6484；树莓派上波动小于0.011），表明激进量化与稀疏聚合未显著影响预测性能。在树莓派上，选定端点（int8, ρ=3）相比float32基线，激活上传量减少87%，同步流量降低54%，运行时抖动由±688秒降至±10秒。
原文摘要 · Abstract (English)
Federated split learning (FSL) enables collaborative training across bandwidth-constrained IoT devices, but repeated activation and gradient exchange creates a communication bot-tleneck. Prior work optimises either activation compression or synchronisation frequency in isolation. This paper presents an FSL framework for IoT rainfall prediction that jointly regulates activation compression and the synchronisation interval \r{ho} via a latency driven scheduler on a server with per client EMA smoothing. The system is evaluated on hourly ERA5 data from 11 weather stations through a 17 scenario simulation matrix and a four scenario Raspberry Pi deployment over a real wide-area link. The simulation matrix validates scheduler switching across low, high, and mixed latency profiles, while the Pi deployment validates the high latency endpoint selected by the same policy. AUPRC varies only slightly across configurations (0.6381-0.6484 in simulation; within 0.011 on Pi), indicating that aggressive quantisation and sparser aggregation do not materially degrade predictive quality in this setting. On Pi, the selected endpoint (int8 with rho=3) achieves an 87% reduction in activation upload payload and a 54% reduction in synchronisation traffic relative to the float32 baseline, while reducing runtime jitter from +/-688 s to +/-10 s.
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。