Intelligent real-time applications, such as video surveillance, demand intensive computation to extract status information from raw sensing data. This poses a substantial challenge in orchestrating computation and communication resources to provide fresh status information. In this paper, we consider a scenario where multiple energy-constrained devices served by an edge server. To extract status information, each device can either do the computation locally or offload it to the edge server. A scheduling policy is needed to determine when and where to compute for each device, taking into account communication and computation capabilities, as well as task-specific timeliness requirements. To that end, we first model the timeliness requirements as general penalty functions of Age of Information (AoI). A convex optimization problem is formulated to provide a lower bound of the minimum AoI penalty given system parameters. Using KKT conditions, we proposed a novel scheduling policy which evaluates status update priorities based on communication and computation delays and task-specific timeliness requirements. The proposed policy is applied to an object tracking application and carried out on a large video dataset. Simulation results show that our policy improves tracking accuracy compared with scheduling policies based on video content information.

翻译：智能实时应用（如视频监控）需要密集计算以从原始感知数据中提取状态信息，这对协调计算与通信资源以提供新鲜状态信息构成了重大挑战。本文考虑由边缘服务器服务的多个能量受限设备的场景。为提取状态信息，每个设备可选择本地计算或将任务卸载至边缘服务器。需制定调度策略，确定每个设备何时何地执行计算，同时兼顾通信与计算能力以及任务特定的时效性需求。为此，我们首先将时效性需求建模为信息年龄（AoI）的通用惩罚函数，通过构建凸优化问题给出在系统参数下最小AoI惩罚的下界。利用KKT条件，我们提出一种新型调度策略，该策略基于通信与计算延迟及任务特定时效性需求评估状态更新优先级。将所提策略应用于目标跟踪应用，并在大型视频数据集上进行验证。仿真结果表明，与基于视频内容信息的调度策略相比，我们的策略显著提升了跟踪精度。