Deep Neural Network (DNN)-based IoT solutions are enabling automation in smart manufacturing. However, the execution of these compute-intensive solutions in real/near-real time is still a challenging issue. Edge-AI solutions utilize the partial computational offloading-based DNN splitting schemes, which employ collaborative computing to minimize the execution time of compute-intensive DNN task(s). Single-task DNN splitting solutions did not consider multi-task aspects and multi-task-based splitting schemes suffer from additional issues that deteriorate their performance in multi-task smart manufacturing scenarios. This work proposes a Task Aware DNN splitting (TADS) scheme that addresses the above issues. TADS collectively utilizes the number and type of tasks, computing, and communication resources to select the DNN splitting policy from the policy pool to minimize average task execution time in smart manufacturing scenarios. It executes policy pool update, candidate policy selection, and optimal policy selection phases iteratively to determine the final DNN splitting policy. Three DNN models (including a product quality inspection use-case) are evaluated under various scenarios by varying the number of tasks, task inter-arrival time, and bandwidth. The simulation results and comparative analysis with ECN-only, ES-only, DNN-off, and Greedy based DNN splitting approaches under various scenarios in terms of average task execution time indicate the efficacy of the TADS scheme. The scheme is also evaluated on a hardware-based testbed for vision-based quality inspection use-case to indicate the utility and efficiency of proposed work in multi-task smart manufacturing scenarios. A NodeJS based web API is developed for vision-based quality inspection application.

基于深度神经网络 (DNN) 的物联网解决方案正在实现智能制造的自动化。然而，实时/近实时地执行这些计算密集型解决方案仍然是一个具有挑战性的问题。Edge-AI 解决方案利用基于部分计算卸载的 DNN 拆分方案，该方案采用协作计算来最小化计算密集型 DNN 任务的执行时间。单任务 DNN 拆分解决方案没有考虑多任务方面，基于多任务的拆分方案存在其他问题，这些问题会降低其在多任务智能制造场景中的性能。这项工作提出了一种任务感知 DNN 拆分 (TADS)方案来解决上述问题。TADS共同利用任务的数量和类型、计算和通信资源从策略池中选择 DNN 拆分策略，以最小化智能制造场景中的平均任务执行时间。它迭代执行策略池更新、候选策略选择和最优策略选择阶段，以确定最终的 DNN 分裂策略。通过改变任务数量、任务到达间隔时间和带宽，在各种场景下评估三个 DNN 模型（包括产品质量检测用例）。在平均任务执行时间方面，在各种场景下与 ECN-only、ES-only、DNN-off 和基于贪婪的 DNN 拆分方法的仿真结果和比较分析表明了 TADS 方案的有效性。该方案还在基于视觉的质量检测用例的基于硬件的测试平台上进行了评估，以表明所提议的工作在多任务智能制造场景中的效用和效率。基于 NodeJS 的 Web API 是为基于视觉的质量检测应用程序开发的。