Enhanced adaptive neuro-fuzzy inference system using genetic algorithm: a case study in predicting electricity consumption

Abstract Energy forecasting is crucial for efficient energy management and planning future needs. Previous studies have employed hybrid modeling techniques, but insufficient attention has been given to hyper-parameter tuning parameter selection. In this study, we present a model, which combines fuzzy c-means clustered adaptive neuro-fuzzy inference system (ANFIS) genetic algorithm (GA), named GA–ANFIS–FCM, model electricity consumption in Lagos districts, Nigeria. The simulated using the algorithms’ control settings, best identified after assessing their performance renowned statistical indicators. To further narrow down viable impact of core GA on GA–ANFIS–FCM optimal examined by varying crossover percentage range 0.2–0.6. Firstly, results reveal better hybridized ANFIS than standalone model. Additionally, obtained with four clusters at 0.4, mean absolute error (MAPE), (MAE), coefficient root square (CVRMSE), (RMSE) values 7.6345 (signifying forecast accuracy 92.4%), 706.0547, 9.4913, 918.6518 during testing phase, respectively. study demonstrates potential proposed as reliable tool forecasting.