The need for renewable energy sources in addressing global energy demands is growing, especially in Nigeria where electricity demand often exceeds supply. Solar photovoltaic (PV) systems have become a viable solution, with federal universities in Nigeria, as major electricity consumers, recognizing their potential. However, determining the right size of PV systems for individual faculties within these universities is a complex task. This study attempted to simplify this process by introducing an innovative approach to size PV systems in these faculties. The research method used the Extended Kalman Artificial Neural Network (EKF-ANN) and the Crow Search Algorithm (CSA) to enhance the accuracy of PV system sizing. Data was collected on the study site, load demand, weather conditions, system components, and operational control and systems models to establish sizing criteria. The study focused on the optimal size of a solar PV system at the Faculty of Law building, University of Port-Harcourt, and how to improve its accuracy. The results showed that using global solar insolation parameters, EKF-ANN predicted values for global temperature, flock size, and maximal iteration. This optimized system could generate surplus power for effective grid supply. The study found that the optimal size of the series-connected panels for the Faculty of Law building was 96, 83, 73, and 65 units, with corresponding insolation values ranging from 3.737 to 4.368 kW/m2. It was concluded that the combination of CSA and EKF-ANN in solar PV sizing is suitable forachieving optimal outcomes for energy storage and grid supply. Nonetheless, the study recommended additional investigation into real-time and grid-connected solutions to enhance the proposed approach's effectiveness.
Buy article PDF