Power System Risk Assessment Strategy Based on Weighted Comprehensive Allocation and Improved BP Neural Network

In the operation and maintenance process of the power system, factors such as power failures and supply-demand imbalances can have adverse effects on the normal power supply process. It is necessary to reduce or even solve this problem through corresponding power system risk warning. Based on this, the article proposes a self-assessment and early warning strategy for power system risks based on improved ant colony optimization algorithm (IACO) and BP neural network. Firstly, a combination of Analytic Hierarchy Process (AHP) and Entropy Weighting Method (EWM) is used to comprehensively assign weights to indicators that have a significant impact on the stability and safety of power system operation, avoiding the negative impact of subjective experience or objective factors on the weight allocation results. Secondly, multiple regression analysis is used to calculate the risk assessment results of the selected indicators and weights corresponding to the power system. According to the above weight allocation process, training and testing samples for the BP neural network were calculated and obtained. Then, IACO is used to global optimization the weights and thresholds of the BP neural network, and an improved BP neural network model for power system risk independent assessment is established. Finally, the designed risk assessment and warning strategy was tested. The results indicate that the proposed power system risk assessment and early warning method can accurately predict the actual working status of the power system based on weight values, providing data reference for technical personnel, and thereby improving power supply quality. Key words：Power system; Risk assessment; Comprehensive empowerment; Improved ant colony optimization algorithm; BP neural network.