Digital Performance Prediction Model of Power Grid Dispatching Business Based on BP Neural Network

In the wave of enterprise digital transformation, power grid enterprises also need to consider the performance of investment during the digital transformation investment process. In the decision-making process of investment in digital transformation of power grid dispatching business, traditional cost-benefit analysis methods are faced with complex and changeable inputs. parameters, the calculation amount is large and the efficiency is low. This paper proposes a digital investment return prediction method for future status warning of power grid dispatching business based on BP neural network. Through feature selection and machine learning technology, it improves the efficiency and accuracy of future status warning of power grid dispatching digital investment performance analysis. This paper first uses the feature selection method to select features that are highly correlated with the prediction target, and then uses a machine learning model to learn the complex relationship between the input highly correlated features and the output performance to replace the traditional mathematical model and achieve efficient and rapid performance analysis. The experimental results show the performance of BP neural network in predicting future status warning of power grid dispatching investment results, and also verify the important role of feature selection in optimizing model performance.