Deterministic network time delay scheduling method and device based on TSN and storage medium
By performing graph theory analysis of the topology of TSN network and combining multi-level priority perception network and deep Q network dynamic optimization scheduling strategy, the problem that traditional TSN network delay scheduling methods are difficult to cope with dynamic changing network environments, and efficient network resource utilization and performance stability are achieved.
Patent Information
- Application Number
- CN202510166844.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-14
- Publication Date
- 2025-03-18
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The delay scheduling method of traditional TSN networks is difficult to cope with dynamically changing network environments and diversified business needs. Especially in the hyper-intensive node deployment scenario, the network topology structure is complex and there are many types of data flows. Traditional scheduling algorithms are difficult to meet the delay requirements of service flows of different priority levels at the same time, which is easy to cause network congestion and performance degradation.
By performing graph theory analysis on the topology of TSN network, combining multi-level priority perception network and deep Q network, a state-action mapping relationship is established, scheduling strategies are dynamically optimized, bandwidth borrowing and time slice redistribution are adopted to improve network resource utilization efficiency.
It significantly improves network resource utilization efficiency, realizes accurate evaluation and dynamic adjustment of network performance, overcomes the limitations of traditional static scheduling methods, and maintains the stability of network performance.