EdgeRL用强化学习动态优化边缘设备推理，平衡速度、精度与能耗。
EdgeRL: Reinforcement Learning-driven Deep Learning Model Inference Optimization at Edge
- 采用A2C强化学习动态调整深度神经网络推理参数。
- 实测在边缘设备上实现能耗降低、准确率提升与延迟减少。
- 适合需要实时性与能效的移动边缘智能应用。
在临时边缘环境中，深度学习模型推理需兼顾处理延迟、结果准确率和终端设备能耗等相互冲突的性能指标，这极具挑战性。本文提出EdgeRL框架，通过优势行动者-评论家（A2C）强化学习方法，动态选择最优运行时深度神经网络（DNN）推理参数，根据应用需求协调各项性能指标。基于真实深度学习模型与硬件测试平台，我们评估了EdgeRL在终端设备能耗节省、推理准确率提升及端到端推理延迟降低方面的收益。
原文摘要 · Abstract (English)
Balancing mutually diverging performance metrics, such as, processing latency, outcome accuracy, and end device energy consumption is a challenging undertaking for deep learning model inference in ad-hoc edge environments. In this paper, we propose EdgeRL framework that seeks to strike such balance by using an Advantage Actor-Critic (A2C) Reinforcement Learning (RL) approach that can choose optimal run-time DNN inference parameters and aligns the performance metrics based on the application requirements. Using real world deep learning model and a hardware testbed, we evaluate the benefits of EdgeRL framework in terms of end device energy savings, inference accuracy improvement, and end-to-end inference latency reduction.
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。