Automated Monitoring Method for Enterprise Microservices Network Operation Status Based on Database Knowledge Graph
Qidi Hu, Yujiang Long, Ye Zhong, Guangyi Zhang, Wei Wei · 2024
This thesis presents an innovative method for automated monitoring of enterprise microservices networks using a database knowledge graph, addressing the challenges of traditional monitoring systems that often fail to effectively manage the complex dynamics of microservices architectures. By integrating advanced Natural Language Processing (NLP) and Long Short-Term Memory (LSTM) networks, this method processes vast amounts of real-time and historical data to proactively predict system failures and optimize resource allocation. The key innovation lies in the application of a knowledge graph that enhances predictive maintenance capabilities and facilitates performance optimization through intelligent data analysis and pattern recognition. This approach not only improves operational efficiency but also reduces downtime, thereby significantly enhancing network management in enterprise environments. Our research confirms that knowledge graphs can provide a scalable and dynamic solution to adapt to diverse enterprise requirements.