This paper investigates a mobile edge computing environment for video analysis tasks where edge nodes provide their computation capacities to process the computation intensive tasks submitted by end users. First, we introduce a Cloudlet Assisted Cooperative Task Assignment (CACTA) system that organizes edge nodes that are geographically close to an end user into a cluster to collaboratively work on the user’s tasks. It is challenging for the system to find an optimal strategy that assigns workload to edge nodes to meet the user’s optimization goal. To address the challenge, this paper proposes multiple algorithms for different situations. Firstly, considering the situation that historical data cannot be obtained, a multi-round allocation algorithm based on EMA prediction is proposed, and the experimental results prove the efficiency and necessity of multiple rounds of transmission. To address the second case of obtaining historical data, this paper introduces a prediction-based dynamic task assignment algorithm that assigns workload to edge nodes in each time slot based on the prediction of their capacities/costs and an empirical optimal allocation strategy which is learned from an offline optimal solution from historical data. Experimental results demonstrate that our proposed algorithm achieves significantly higher performance than several other algorithms, and especially its performance is very close to that of an offline optimal solution. Finally, we propose an online task assignment algorithm based on Q-learning, which uses the model-free Q-learning algorithm to actively learn the allocation strategy of the system, and the experimental results verify the superiority and effectiveness of this algorithm.

本文研究了用于视频分析任务的移动边缘计算环境，其中边缘节点提供其计算能力来处理最终用户提交的计算密集型任务。首先，我们引入了Cloudlet辅助合作任务分配（CACTA）系统，该系统将地理上最接近最终用户的边缘节点组织到一个集群中，以协同工作于用户的任务。对于系统而言，寻找一种最佳策略以将工作负载分配给边缘节点以满足用户的优化目标具有挑战性。为了应对这一挑战，本文提出了针对不同情况的多种算法。首先，考虑到无法获得历史数据的情况，提出了一种基于EMA预测的多轮分配算法，实验结果证明了多轮传输的有效性和必要性。为了解决获取历史数据的第二种情况，本文介绍了一种基于预测的动态任务分配算法，该算法基于对边缘节点的容量/成本的预测，并根据经验学习的最优分配策略，将工作负载分配给每个时隙中的边缘节点历史数据的离线最佳解决方案。实验结果表明，我们提出的算法比其他几种算法具有更高的性能，尤其是其性能非常接近离线优化解决方案。最后，我们提出了一种基于Q学习的在线任务分配算法，该算法使用无模型Q学习算法主动学习系统的分配策略，