A high-performance computing cluster resource scheduling method and system based on TR-DQN
By using a two-level neural network based on TR-DQN and a deep reinforcement learning method, the dynamic adaptability and efficiency problems in resource scheduling of high-performance computing clusters are solved, achieving efficient resource utilization and rapid response.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WUHAN UNIV
- Filing Date
- 2023-11-06
- Publication Date
- 2026-07-21
AI Technical Summary
Traditional high-performance computing cluster resource scheduling algorithms cannot adapt to dynamic changes in cluster status and nodes, resulting in job starvation and high computing resource requirements, leading to low scheduling efficiency.
We employ a two-level neural network based on TR-DQN and a deep reinforcement learning method. We use a window access waiting queue and combine task priority and node information for scheduling. We design a specific reward function to optimize resource utilization and response time.
It achieves adaptive scheduling of high-performance computing cluster resources, reduces job starvation, and improves resource utilization and task response speed.
Smart Images

Figure CN117591273B_ABST