Multidimensional Meteorological Data Analysis of Power System and Construction of Multi Temporal and Spatial Scale Prediction Model

In this article, we introduce a novel Convolutional Neural Network Long Short Term Memory Network (CNN-LSTM) model aimed at predicting multidimensional meteorological data that affects the power system. Given the continuous growth of global climate change and energy demand, the power system is often affected by extreme weather events, which pose serious challenges to power supply. Therefore, developing a model that can accurately predict changes in power load is extremely important for the management and scheduling of the power system. Our experimental results show that the average absolute error of the CNN-LSTM model in temperature prediction is about 2°C, humidity is 3%, and wind speed is 1.5 m/s. The above data results indicate that its effectiveness and reliability in processing complex meteorological data are of great significance for meteorological risk management in power systems.