Reinforcement Learning Scheduling Research for Edge Servers
Yonggui Han, Zhongsheng Wang · 2023
The rapid development of the Internet of Things and big data has brought about massive amounts of data and the need for real-time responses, which traditional computing models can no longer meet. Edge computing comes into being, which pushes computing resources and services closer to the source of data generation so that data can be processed and analyzed closer to the user. The scheduling of siting strategies for edge servers is crucial for improving the performance of edge computing networks. Traditional scheduling methods for siting strategies are often based on rules or optimization algorithms, which lack adaptive and intelligent management of the network environment.This paper proposes a reinforcement learning DQN-based edge server siting policy scheduling method, which aims to achieve intelligent management and resource optimization of edge computing networks by learning the optimal policy. Experimental results show that the method has significant performance advantages in terms of delay, load balancing and energy consumption. The experiment adopts DQN algorithm, which is based on Q-learning and guides the agent to make decisions by optimizing Q-value function. In this paper, the reinforcement learning scheduling algorithm of edge server is studied and compared with other three algorithms. According to the experimental results, the proposed reinforcement learning scheduling algorithm reduces the delay by 7%, the energy consumption by 3%, and the load balancing by 20% compared with the other three algorithms. This shows that the algorithm has significant advantages in improving system performance.