服务器的性能评估方法及装置
By combining a neurofuzzy inference model and an improved particle swarm optimization algorithm, and dynamically adjusting the particle swarm inertia weights, fault diagnosis model parameters are generated. This solves the efficiency and accuracy problems of performance evaluation and fault diagnosis in high-density, heterogeneous server clusters, and enables rapid fault location and self-healing capabilities in large-scale data centers.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- INSPUR SUZHOU INTELLIGENT TECH CO LTD
- Filing Date
- 2026-05-22
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to balance startup efficiency, energy consumption control, and fault diagnosis accuracy in performance evaluation and fault diagnosis of high-density, heterogeneous server clusters, failing to meet the needs of large-scale data centers for rapid fault location and self-healing.
A method combining a neurofuzzy inference model and an improved particle swarm optimization algorithm is adopted to dynamically adjust the particle swarm inertia weights. The parameters of the target fault diagnosis model are generated through iterative optimization calculation, and the performance evaluation and fault diagnosis are performed in combination with the operating data of the baseboard management controller.
It improves the accuracy and real-time performance of fault diagnosis, reduces the total power consumption of the BMC cluster, reduces resource contention conflicts, and enhances the overall performance and reliability of fault diagnosis systems in large-scale data centers.
Smart Images
Figure CN122240442B_ABST