We study the problem of optimal sampling in an edge-based video analytics system (VAS), where sensor samples collected at a terminal device are offloaded to a back-end server that processes them and generates feedback for a user. Sampling the system with the maximum allowed frequency results in the timely detection of relevant events with minimum delay. However, it incurs high energy costs and causes unnecessary usage of network and compute resources via communication and processing of redundant samples. On the other hand, an infrequent sampling result in a higher delay in detecting the relevant event, thus increasing the idle energy usage and degrading the quality of experience in terms of responsiveness of the system. We quantify this sampling frequency trade-off as a weighted function between the number of samples and the responsiveness. We propose an energy-optimal aperiodic sampling policy that improves over the state-of-the-art optimal periodic sampling policy. Numerically, we show the proposed policy provides a consistent improvement of more than 10$\mathbf{\%}$ over the state-of-the-art.

翻译：我们研究边缘视频分析系统中的最优采样问题。在此类系统中，终端设备采集的传感器样本被卸载至后端服务器进行处理，并生成面向用户的反馈。以最大允许频率进行采样虽能以最小延迟及时检测相关事件，但会导致高能耗，且因通信与处理冗余样本而引发网络与计算资源的非必要占用。反之，低频采样会延长相关事件的检测延迟，从而增加空闲能耗，并因系统响应性降低而削弱用户体验质量。我们将该采样频率权衡量化为样本数量与响应性之间的加权函数，并提出一种能量最优的非周期采样策略，该策略优于现有最优周期采样方案。数值结果表明，所提策略相较于现有最优方案可实现超过10%的一致性改进。