Research on short term load forecasting model based on Adaptive Neuro Fuzzy Inference System

摘要

A short-term load forecasting model based on adaptive neuro-fuzzy inference system (ANFIS) and descending step-length Drosophila algorithm-singular regression neural network (SFOA-GRNN) was constructed, and the model was trained and tested by historical load data. Through MATLAB simulation comparison, it can be clearly seen that SFOA-GRNN can predict short-term power load more efficiently than ANFIS. The SFOA-GRNN model has great advantages in terms of convergence time and prediction accuracy compared to the ANFIS model. The SFOA-GRNN model has excellent performance and stability, and can meet the requirements of short-term power load forecasting.