Electrical load forecasting and new energy integration strategy based on intelligent decision-making algorithm

• Use intelligent decision-making algorithms to construct an innovative power load forecasting model and new energy integration strategy. • By comprehensively considering multi-source data such as historical load, meteorology, socio-economics, and new energy generation, a hybrid deep learning architecture combining long short-term memory network (LSTM) and convolutional neural network (CNN) is adopted to significantly improve the accuracy of power load forecasting. • Provides strong support for the efficient planning and operation of the power system and is of great significance to promoting the green transformation of the energy structure. Against the background of rapid global industrialization and urbanization, electricity demand has increased dramatically, and the development of new energy technologies has become a focus. This study uses intelligent decision-making algorithms to construct an innovative power load forecasting model and new energy integration strategy. By comprehensively considering multi-source data such as historical load, meteorology, socio-economics, and new energy generation, a hybrid deep learning architecture combining long short-term memory network (LSTM) and convolutional neural network (CNN) is adopted to significantly improve the accuracy of power load forecasting. The experimental results show that compared with traditional forecasting methods, the mean absolute error (MAE) of the proposed model is reduced by 20%, from the original 1.0 MW to 0.8 MW; the root mean square error (RMSE) is reduced by 25%, from 1.5 MW to 1.125 MW, and the coefficient of determination (R²) is increased from 0.9 to 0.95. In terms of new energy integration strategy, the carefully designed multi-objective optimization algorithm has achieved an increase in the utilization rate of new energy from 70% to 85%, a 15% reduction in operating costs, and a reduction in operating costs per kilowatt-hour from 0.12 yuan to 0.102 yuan, while ensuring the safe and stable operation of the power grid. This study provides strong support for the efficient planning and operation of the power system and is of great significance to promoting the green transformation of the energy structure.