A hybrid long-term industrial electrical load forecasting model using optimized ANFIS with gene expression programming

• Published in: Energy reports Vol. 11; pp. 5831 - 5844
• Main Authors: Bakare, Mutiu Shola, Abdulkarim, Abubakar, Shuaibu, Aliyu Nuhu, Muhamad, Mundu Mustafa
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01-06-2024
• Subjects: ANFIS model; Electricity Consumption; Forecast Model; GEP; GEP-ANFIS Model; long-time load forecasting; ANN; MTLF; DNN; GPR; KNN; GRNN; ABPA; SVR; BPNN; VSTLF; RNN; IA; GBANFIS; ANFIS; ML; Electricity Consumption; LTLF; Forecast Model; LSTM; EED; AI; MAPE; RMSE; GEP-ANFIS Model; long-time load forecasting; MAE; MAD; GEP; APE; ARIMA; CVRMSE; LF; ELD; STLF; ANFIS model
• ISSN: 2352-4847; 2352-4847
• DOI: 10.1016/j.egyr.2024.05.045

Electric energy demand forecasting is vital in contemporary power systems, especially amidst market deregulation trends and the increasing influence of industrial customers on power dynamics. However, existing forecasting models encounter challenges such as slow convergence and high complexity. Addressing these issues, this study proposes a hybrid forecasting model that combines the Adaptive Neuro-Fuzzy Inference System (ANFIS) with Gene Expression Programming (GEP) to enhance predictions of electrical energy consumption. Validated using real-time monthly electrical load data from an industrial user in Uganda, the hybrid model outperforms individual ANFIS and GEP models, demonstrating reduced errors and minimal computation time. The application of this hybrid model presents promising results, showcasing exceptional predictive capabilities and offering potential improvements in efficiency and precision for electrical energy consumption forecasting amidst market deregulation and evolving industrial dynamics.
•This study integrates two different intelligent algorithms to create a unique composite model for predicting long-term electric demand. The method efficiently combines the advantages of ANFIS and GEP to provide an accurate predicting results.•Comparing the effectiveness of the proposed GEP-ANFIS model to other well-known hybrid models should be done using a variety of statistical metrics, such as Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Deviation (MAD), among others.•This optimized GEP-ANFIS model showcases exceptional predictive capabilities when applied to long-term consumption data.