Electric Load Forecasting Based on Artificial Intelligence

In modern power systems, the stable operation of the power grid depends on accurate electrical load forecasting. Especially against the backdrop of the country's "dual carbon" goal, accurate electrical load forecasting can effectively verify the security and economic efficiency of the operation of the electrical system. Based on this background, firstly, the basic situation of load forecasting in today's electrical systems is expounded. Then, a load forecasting method ground on the Long Short-Term Memory network (LSTM) optimized by the Quantum Particle Swarm Optimization (QPSO) algorithm is put forward. Through case studies, in order to reflect the prediction accuracy of these models, the Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) of different models are compared. Ultimately, according to the results, we find that the hyperparameter load forecasting method ground on the Long Short-Term Memory network (LSTM) optimized by the Quantum Particle Swarm Optimization (QPSO) algorithm performs better than other methods. Its RMSE and MAPE values are the smallest among all the models, indicating that the load forecasting method ground on the Long Short-Term Memory network (LSTM) optimized by the Quantum Particle Swarm Optimization (QPSO) algorithm has a higher learning rate and stronger data processing ability compared with the several methods studied by us.