Deep Neural Network (DNN) based video analytics empowers many computer vision-based applications to achieve high recognition accuracy. To reduce inference delay and bandwidth cost for video analytics, the DNN models can be deployed on the edge nodes, which are proximal to end users. However, the processing capacity of an edge node is limited, potentially incurring substantial delay if the inference requests on an edge node is overloaded. While efforts have been made to enhance video analytics by optimizing the configurations on a single edge node, we observe that multiple edge nodes can work collaboratively by utilizing the idle resources on each other to improve the overall processing capacity and resource utilization. To this end, we propose a Multiagent Reinforcement Learning (MARL) based approach, named as EdgeVision, for collaborative video analytics on distributed edges. The edge nodes can jointly learn the optimal policies for video preprocessing, model selection, and request dispatching by collaborating with each other to minimize the overall cost. We design an actor-critic-based MARL algorithm with an attention mechanism to learn the optimal policies. We build a multi-edge-node testbed and conduct experiments with real-world datasets to evaluate the performance of our method. The experimental results show our method can improve the overall rewards by 33.6%-86.4% compared with the most competitive baseline methods.

翻译：基于深度神经网络（DNN）的视频分析技术为众多计算机视觉应用提供了高精度识别能力。为降低视频分析的推理延迟与带宽成本，可将DNN模型部署在靠近终端用户的边缘节点上。然而，单个边缘节点的处理能力有限，当推理请求过载时可能产生显著延迟。现有研究主要关注通过优化单一边缘节点的配置来提升视频分析性能，但本文观察到，多个边缘节点可通过相互利用空闲资源实现协作，从而提升整体处理能力与资源利用率。为此，我们提出基于多智能体强化学习（MARL）的方法EdgeVision，用于分布式边缘节点上的协作视频分析。边缘节点通过相互协作，共同学习视频预处理、模型选择与请求调度的最优策略，以最小化总体成本。我们设计了一种基于注意力机制的actor-critic型MARL算法来学习最优策略。通过构建多边缘节点测试平台，并采用真实数据集进行实验验证，结果表明，与最具竞争力的基线方法相比，本方法可将整体奖励提升33.6%-86.4%。