Cognition of Data Center Operation and Maintenance Based on Heterogeneous Computing

Zihao Chen; Haofei Guo; Yongbo Wei

doi:10.54097/s9wa4j25

Authors

Zihao Chen
Haofei Guo
Yongbo Wei

DOI:

https://doi.org/10.54097/s9wa4j25

Keywords:

Heterogeneous computing, Data center operation and maintenance, Cognitive enhancement, Monitor.

Abstract

The traditional operation and maintenance mode faces core challenges in achieving efficient monitoring and personnel ability training under consumer hardware conditions, leading to a significant disconnect between management and talent development. To address this, we designed and developed an intelligent operation and maintenance cognitive enhancement system based on Java technology. The system adopts a three-layer multimodal technology architecture of "presentation layer-logic layer-data layer" to realize the deep integration of hardware resources and software functions. It introduces an innovative "monitoring-education" dual closed-loop coordination mechanism: the monitoring loop ensures millisecond-level response for large-scale equipment leveraging CPU multi-core parallel computing, while the learning loop dynamically updates knowledge graphs and pushes personalized resources. This system demonstrates a 47% improvement in monitoring efficiency and over 30% reduction in training costs, effectively bridging the gap between operational practice and cognitive skill development.

References

[1] Cheng H, Liu S, Fan C,e t al. LLM4HIN: Discovering Meta-path with Large Language Model for Reasoning on Complex Heterogeneous Information Networks[J]. 2024 IEEE International Conferences on Internet of Things (iThings) and IEEE Green Computing & Communications (GreenCom) and IEEE Cyber, Physical & Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics, 2024:527-534.

[2] Li J, Li H, Zheng L R L J L. Action-dependent heuristic dynamic programming for hybrid-order systems based on dynamic event-triggered mechanism[J]. Neurocomputing, 2024, 600(Oct.1): 1.1-1.13.

[3] Jha V, Tripathi P. Decentralized knowledge discovery using massive heterogenous data in Cognitive IoT[J]. Cluster Computing, 2024, 27(3):3657-3682.

[4] Aishwarya B, Sharma S, Revathi V, et al. Semantic Reasoning and Knowledge Discovery in Biomedical Informatics Using Domain-Specific Ontologies[J]. 2024 International Conference on Trends in Quantum Computing and Emerging Business Technologies, 2024:1-6.

[5] Soliz J, Fernandez I S, Romero A Z, et al. Design, Manufacture and Implementation of an Educational Satellite for Training in Space Communications[J]. 2024 IEEE Latin-American Conference on Communications (LATINCOM), 2024:1-6.

[6] Poloni S, Kraenkel, Roberto André, Mendes Coutinho R. Biological invasions forming intraguild predation communities in homogeneous and heterogeneous landscapes[J]. Theoretical Ecology, 2025, 18(1):1-16.

[7] Yang H, Wan Z, Raj R, et al. NSFlow: An End-to-End FPGA Framework with Scalable Dataflow Architecture for Neuro-Symbolic AI[C] 2025.

[8] Wang C, Tang Z, Xu H. WSSGCN: Wide Sub-stage Graph Convolutional Networks[J]. Neurocomputing, 2024, 602(000): 11.

[9] Kannan R, Gulhane M, Mirza K, et al. Architectural Innovations for AI Chips, Testing, and High Performance Computing[J]. 2024 IEEE 6th International Conference on Cybernetics, Cognition and Machine Learning Applications (ICCCMLA), 2024:365-369.

[10] Vlieger R, Austin D, Apthorp D, et al. The use of event-related potentials in the investigation of cognitive performance in people with Multiple Sclerosis: Systematic review[J]. Brain Research, 2024, 1832.