Real time operation data mining algorithm for power systems based on adaptive incremental clustering algorithm

There are complex correlation relationships and interactive effects between various components and parameters in the power system. Therefore, how to accurately mine these association relationships from real-time data and establish accurate models to describe and predict power system behavior is a challenging task. To improve the safety of the power system, optimize operational efficiency, improve maintenance and management, and support the development of intelligent power systems. A real-time operation data mining algorithm for power systems based on adaptive incremental clustering algorithm has been proposed. Using wavelet packet method to denoise real-time operation data of power system and remove noise from real-time operation data of power system. Using principal component analysis to extract real-time operational data features of power systems. On this basis, based on the adaptive incremental clustering algorithm, the extracted real-time operational data features of the energy system can be explored through adaptive incremental clustering. The experimental results show that this algorithm has high accuracy in real-time data mining of energy systems and can effectively reduce the real-time running time of energy systems.