MADDPG-based Task Offloading and Resource Management for Edge System

With the development of the Internet of Things, the number of smart devices connected to the 6th generation wireless mobile network (6G) has increased dramatically, which will produce a variety of real-time application scenarios. Edge computing is close to terminal equipment, which can improve user experience and reduce network costs. However, due to the coexistence of multi-dimensional network resources, heterogeneous network devices, and complex and time-varying network structures, this brings unprecedented challenges to wireless networks, and it is difficult to meet the needs of terminal devices for ultra-low latency, high reliability, and low power consumption services. The next generation edge computing architecture is considered to be an effective solution to the time sensitive network and communication congestion. This paper integrates artificial intelligence into the edge computing architecture, and proposes a multi-agent deep deterministic strategy gradient (MADDPG), which maximizes processing efficiency by jointly optimizing task hierarchical offloading and resource allocation.