A Hierarchical Microservice-Based Collaborative Scheduling Method for High-Concurrency Hydropower Equipment Temperature Data

Le résumé fourni par la source

With the vigorous growth of the new generation of information technology, applications centered around artificial intelligence (AI), big data, and the Internet of Things (IoT) technology are constantly emerging. The high concurrency access of equipment temperature data from 9 power plants in the Wenshan and Lixianjiang watersheds of Yunnan Province poses a challenge to traditional centralized data processing methods. Aiming at the problems of server resources overload and data processing delay exceeding the standard in traditional methods, this paper designs a temperature data cooperative scheduling system for hydropower equipment based on layered microservice combined with edge computing (EC). To optimize the efficiency of edge side intelligent processing, the system adopts a distributed microservice framework based on Roofline theory and Convolutional Neural Network (CNN) model, which achieves computation adaptation and efficient communication in heterogeneous EC networks; At the same time, a data security capability microservice scheduling algorithm based on Kepler Optimization Algorithm (KOA) is adopted to address the problem of load imbalance in high concurrency scenarios, aiming to achieve load balancing and improve the system’s high concurrency processing capability. This article integrates edge computing, microservices, AI, and hydropower operation and maintenance requirements to construct a cross-disciplinary collaborative scheduling framework, efficiently supporting real-time secure scheduling of temperature data for provincial hydropower equipment under high concurrency. Simulation experiments show that the system proposed in this paper has significant effects in balancing server load and reducing task response time.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.