Multi-access Edge Computing (MEC) aims to reduce mobile services latency and free users from resource constraints by deploying cloud services closer to users. However, with the change of network condition, the service requirements of users cannot be fulfilled due to the fixed deployment of MEC nodes. In this case, the placement of MEC nodes attracts more and more researchers’ attentions. Particularly, in the circumstance with Network Function Virtualization (NFV), MEC functions are allowed to be deployed on any edge node that has the NFV Infrastructure (NFVI), and these MEC-function-enabled edge nodes can become MEC nodes. In this case, how to deploy these MEC nodes flexibly to cope with the dynamic changes of network load becomes very important. In this paper, we propose an Online Adjustment based MEC node Placement mechanism (OAMP). First, the node placement problem is constructed as a class of set coverage problem based on the average historical load of nodes. The backtracking algorithm of depth-first search is used to obtain the optimal initial placement strategy. Then, based on users’ QoE (quality of experience), the fuzzy neural network is used to determine whether the deployment of MEC nodes needs to be adjusted. Finally, the number and location of MEC nodes are updated intelligently by Deep Q-Network (DQN) algorithm. The proposed OAMP aims to solve where to deploy MEC nodes, and how to adjust the deployment in response to dynamic changes in the network. Simulation results show that OAMP can effectively reduce the deployment cost while ensuring users’ QoE, and achieve lower Service Level Agreement (SLA) violation rate.

多接入边缘计算 (MEC) 旨在通过部署更靠近用户的云服务来减少移动服务延迟并使用户摆脱资源限制。但是，随着网络条件的变化，由于MEC节点的固定部署，用户的业务需求无法得到满足。在这种情况下，MEC节点的放置吸引了越来越多的研究人员的关注。特别是在网络功能虚拟化（NFV）的情况下，允许MEC功能部署在任何具有NFV基础设施（NFVI）的边缘节点上，这些启用了MEC功能的边缘节点可以成为MEC节点。在这种情况下，如何灵活部署这些 MEC 节点以应对网络负载的动态变化就变得非常重要。在本文中，我们提出了一种基于在线调整的 MEC 节点放置机制（OAMP）。第一的，节点放置问题被构建为基于节点平均历史负载的一类集合覆盖问题。采用深度优先搜索的回溯算法来获得最优的初始放置策略。然后，根据用户的 QoE（体验质量），使用模糊神经网络来判断 MEC 节点的部署是否需要调整。最后，通过深度 Q 网络 (DQN) 算法智能更新 MEC 节点的数量和位置。提出的 OAMP 旨在解决 MEC 节点的部署位置，以及如何根据网络的动态变化调整部署。仿真结果表明，OAMP能够在保证用户QoE的同时有效降低部署成本，实现更低的服务水平协议（SLA）违反率。