具有硬截止期的边缘推理系统的动态压缩比选择
Dynamic Compression Ratio Selection for Edge Inference Systems with Hard Deadlines
摘要：
在物联网（IoT）设备上实现机器学习算法对于自动驾驶、环境监测等新兴应用至关重要。但是计算能力和能耗的限制使得在物联网设备上运行复杂的机器学习算法变得困难，特别是当存在延迟期限时。一种解决方案是将计算密集型任务卸载到边缘服务器。然而，原始数据的无线上传是耗时的，并且可能导致违反最后期限。为了减少通信开销，可以利用有损数据压缩来进行推理任务，但是可能带来更多错误的推理结果。本文针对具有硬截止期的边缘推理系统，提出了一种动态压缩比选择方案。其关键思想是平衡通信成本和推理精度之间的折衷。通过动态选择最优压缩比与排队任务的剩余期限预算，更多的任务可以在有限的通信资源，及时完成正确的推理。此外，信息增强，重发较少的压缩数据的错误推理的任务，提出了提高精度的性能。虽然通常很难知道推断的正确性，但我们使用不确定性来估计推断的置信度，并在此基础上，联合优化信息增强和压缩比选择。最后，考虑到无线传输的错误，我们进一步设计了一个重传方案，以减少由于数据包丢失造成的性能下降。仿真结果表明，所提出的方案在不同的截止时间和任务到达率的性能。
英文摘要：
Implementing machine learning algorithms on Internet of things (IoT) devices has become essential for emerging applications, such as autonomous driving, environment monitoring. But the limitations of computation capability and energy consumption make it difficult to run complex machine learning algorithms on IoT devices, especially when latency deadline exists. One solution is to offload the computation intensive tasks to the edge server. However, the wireless uploading of the raw data is time consuming and may lead to deadline violation. To reduce the communication cost, lossy data compression can be exploited for inference tasks, but may bring more erroneous inference results. In this paper, we propose a dynamic compression ratio selection scheme for edge inference system with hard deadlines. The key idea is to balance the tradeoff between communication cost and inference accuracy. By dynamically selecting the optimal compression ratio with the remaining deadline budgets for queued tasks, more tasks can be timely completed with correct inference under limited communication resources. Furthermore, information augmentation that retransmits less compressed data of task with erroneous inference, is proposed to enhance the accuracy performance. While it is often hard to know the correctness of inference, we use uncertainty to estimate the confidence of the inference, and based on that, jointly optimize the information augmentation and compression ratio selection. Lastly, considering the wireless transmission errors, we further design a retransmission scheme to reduce performance degradation due to packet losses. Simulation results show the performance of the proposed schemes under different deadlines and task arrival rates.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
