Industrial Deterministic Computation and Networking Resource Scheduling Based on Deep Reinforcement Learning

In this paper, D3QN-based resource scheduling algorithm is designed for different bandwidth application scenarios in industrial environment to realize the flexible adaptation of network resources. In the considered network environment, the TSN-5G network architecture, primarily composed of TSN switches and 5G base stations, will be utilized to simulate the Industrial Internet of Things. Additionally, within this environment, various reinforcement learning algorithms will be subject to comparative performance testing. The results show that when network resources are limited, the D3QN-based resource scheduling algorithm can significantly improve the efficiency of task allocation, making it an ideal solution for reducing latency and optimizing resource usage in industrial applications.