Edge Computing Task Offloading Method for Load Balancing and Delay Optimization

With the increasing popularity of mobile applications, the task quality of service requirements can be effectively guaranteed by offloading the computing tasks of mobile devices to the edge servers. However, it is difficult for the existing schemes to effectively consider both task quality assurance and network load balancing. Therefore, this paper proposes an edge computing task offloading method based on deep reinforcement learning. Firstly, considering the time delay of task queuing and the time delay of computation, a load balancing model is designed to measure the load balancing degree of network computing resource. Then, a task offloading optimization model is constructed for the time delay and load balancing. Second, the problem is transformed into a Markov decision process, and a task offloading algorithm based on deep deterministic strategy gradient is designed. The simulation results show that the proposed method can effectively reduce the delay and improve the load balancing.