Beyond site suitability: Investigating temporal variability for utility-scale solar-PV using soft computing techniques. (December 2021)

• Record Type: Journal Article
• Authors: Adedeji, Paul A.; Akinlabi, Stephen A.; Madushele, Nkosinathi; Olatunji, Obafemi O.
• Is Part Of: Renewable energy focus. Volume 39(2021)
• Page Start: 72
• Page End: 89
• Publication Date: 2021-12
• Subjects: Renewable energy sources -- Periodicals; Solar energy -- Periodicals; 333.79405
• DOI: 10.1016/j.ref.2021.07.008
• Languages: English
• ISSNs: 1755-0084

Abstract

Highlights: Resource variability investigation is beneficial for strategic planning. Soft computing techniques are helpful to understand solar resource variability. Model complexity is not concomitant to increased model performance. Abstract : Site suitability is highly essential for utility-scale solar-PV exploration, however, beyond this phase, the need to investigate solar resource variability in suitable site is very vital to strategic planning and grid-integration. This study investigates solar resource variability in a suitable site obtained from geographical information system (GIS)-based site suitability analysis using soft computing techniques. The Western Cape Province, South Africa was used as a case study and climatological, topographic, and location factors were considered for the site suitability analysis for solar-PV in the province. Five soft computing techniques were applied on a candidate site chosen from the final suitability map. These are: gradient descent with adaptive learning rate neural network (GDALRNN), resilient backpropagation neural network (RBNN), adaptive neurofuzzy inference system (ANFIS), genetic algorithm-based ANFIS (GA-ANFIS) and particle swarm optimization based ANFIS (PSO-ANFIS). Each model was trained and tested with 70% and 30% of the data obtained from the representative site respectively. The GDALRNN model outperforms all other models with a root mean square error (RMSE) of 0.0316, coefficient of variation of RMSE (CV(RMSE)) of 4.7590%, relative mean bias error of −0.2951%, mean absolute percentage error of 4.0998, robust coefficient of variation of 0.0403, skill score of 10.7345 and computational time of 9.71 s. Finally, the possibility of integrating resource variability investigation into site suitability and the relevance of simple intelligent models over complex hybrid ones in solar resource variability modelling were established.