Data-driven Analysis of Regional Load Dynamic Characteristics

With the continuous development of China’s new power system, provinces have been carrying out pilot projects such as demand response and auxiliary services. Accurately grasping the dynamic characteristics of flexible loads across different industries within the region is crucial for the effective implementation of the aforementioned pilot projects. This paper introduces a data-driven approach to analyze the dynamic characteristics of regional loads. Firstly, the algorithm extracts the typical daily load curves using the power load data from different industries in the region via the k-means clustering method. Then, the paper defines four load types: peak-facing, valley-filling, continuous, and cycle types. It analyzes the load characteristics of various industries in depth based on four key indicators: daily load rate, daily minimum load rate, daily peak-valley difference rate, and day and night load rate. Finally, the method’s effectiveness is validated through a case study analysis.