Power Demand Forecasting Method for Important users based on Power Big Data and Neural Network

The electricity consumption of Chinese users is constantly increasing with the development of the economy. With the continuous enrichment of residents’ lives and the diversification of activity forms, the electricity consumption, characteristics and types of electricity among different users present rich, diverse and diverse characteristics. In order to achieve effective electricity consumption for different users, ensure the reliability and safety of user power supply, achieve energy conservation, emission reduction and sustainable development, ensuring a safer and more reliable electricity supply for users has become a basic requirement and responsibility of the power sector today. This paper discussed the power demand forecasting method for important users based on power big data and neural network. First, it briefly introduced power big data and neural network and discussed the construction of power demand forecasting model for users based on power big data. Finally, the comparative experimental analysis verified that the accuracy of the power demand forecasting model based on big data and LSTM (Long Short Term Memory networks) was higher than that of the power demand forecasting model based on LSTM (the average value of MAPE decreased by 0.689%).