Research on an evaluation method of day-ahead wind power consumption capacity of the distribution network based on comprehensive evaluation theory

Abstract

This paper proposes an evaluation method of the distribution network’s day-ahead wind power consumption capacity based on the comprehensive evaluation theory. This aims to evaluate the distribution network’s operational stability, economy, and cleanliness under load and wind power uncertainty. The distribution network’s two-level evaluation index system, including several key consumption evaluation indexes, is constructed. According to the evaluation index system, the index scoring standard is formulated, and the scores of each index are quantified. The analytic hierarchy process determines the index weight of first-level indicators. The K-means clustering algorithm is used to reduce the annual load scenarios, and the weight coefficients of the second-level indicators are determined by the entropy weight method. The BP neural network and the sparrow search algorithm are combined to accurately predict the wind power and load. Based on the 95% confidence interval, the multi-scenario construction evaluation is carried out, the forward and backward generation method is used to solve the power flow of the distribution network, and the sensitivity analysis is carried out to verify the comprehensive evaluation results. The research results show that this method can accurately quantify the wind power consumption capacity and achieve high-precision prediction and system robustness evaluation. It provides a theoretical reference for evaluating the distribution network’s day-ahead wind power consumption capacity.