Feasibility of Hybrid Neuro-Fuzzy (ANFIS) Machine Learning Model with Classical Multi-Linear Regression (MLR) For the Simulation of Solar Radiation: A Case Study Abuja, Nigeria

The extremely variable nature of solar radiation makes it difficult for power plants to keep up with predicted output and demand curves. As a result, simulation is crucial the efficient design, administration, operation any plant. With only partially satisfactory results, empirical models have been routinely employed in Nigeria predict from easily measurable environmental characteristics like temperature, humidity, cloud cover, etc. Only few machine learning used sun Nigeria, despite global trend toward learning. almost no published work utilizing Abuja as case study, algorithms simulating not sufficiently studied. By contrasting performance conventional Multi-Linear Regression (MLR) model cutting-edge model, ANFIS, this study seeks close gap establish which more suited accurate forecasting Abuja, Nigeria. Data daily measured climatic variables, such maximum minimum temperatures, relative precipitation, wind speeds, sunshine hours, were retrieved over ten years National Space Research Development Agency, (NASDRA) Abuja. R, R2, RMSE, MSE simulate assess various combinations throughout both training testing stages. When compared best MLR simulation, ANFIS 8 was shown generate results.