Big Data Optimization Clustering Algorithm for Power Grid CPS Based on PSO

As power systems become increasingly intelligent and internet of things technology finds widespread use, the power grid cyber-physical system (CPS) has become pivotal in real-time monitoring, data processing, and intelligent control. Nonetheless, the generation of large-scale, high-dimensional real-time data within the power grid CPS system poses challenges to traditional data processing and analysis methods. In order to meet this challenge, this paper proposes a PSO-based power grid CPS big data optimization clustering algorithm. By introducing PSO algorithm, the algorithm makes full use of its global search and adaptive characteristics to cluster the massive data in the CPS system of power grid efficiently. Compared with the traditional clustering algorithm, the algorithm proposed in this paper is superior in mining data relations and finding abnormal situations. In the experimental verification stage, we use different scale and complexity power grid data sets to verify the feasibility and performance of the algorithm. The experimental results show that the power grid CPS big data optimization clustering algorithm based on PSO has achieved significant performance improvement in multiple data scenarios. The research results of this paper have important theoretical and practical significance for intelligent management, data mining and anomaly detection of power grid system.