Re-thinking computation offload for efficient inference on IoT devices with duty-cycled radios
Re-thinking computation offload for efficient inference on IoT devices with duty-cycled radios
复制标题
DOI：
10.1145/3570361.3592514
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
Jin Huang;H. Guan;Deepak Ganesan
中科院分区：
文献类型：
--
作者：
Jin Huang;H. Guan;Deepak Ganesan
虽然近期的一些研究已经探索了使用“云卸载”在物联网设备上实现深度学习，但这些研究都没有假设使用像蓝牙低功耗（BLE）这样的占空比循环无线电。我们认为，无线电占空比循环会显著降低现有云卸载方法的性能。我们通过利用一个之前未被探索的机会来解决这个问题，即使用具有优先级通信、动态池化和特征动态融合的提前退出卸载。我们表明，与一系列深度神经网络模型、数据集和物联网平台上的最先进的本地提前退出、远程处理和模型划分方案相比，我们的系统FLEET在准确性、延迟和计算预算方面取得了显著的优势。
While a number of recent efforts have explored the use of "cloud offload" to enable deep learning on IoT devices, these have not assumed the use of duty-cycled radios like BLE. We argue that radio duty-cycling significantly diminishes the performance of existing cloud-offload methods. We tackle this problem by leveraging a previously unexplored opportunity to use early-exit offload enhanced with prioritized communication, dynamic pooling, and dynamic fusion of features. We show that our system, FLEET, achieves significant benefits in accuracy, latency, and compute budget compared to state-of-art local early exit, remote processing, and model partitioning schemes across a range of DNN models, datasets, and IoT platforms.