In order to achieve a highly accurate estimation of solar energy resource potential, a novel hybrid ensemble-learning approach, hybridizing Advanced Squirrel-Search Optimization Algorithm (ASSOA) and support vector regression, is utilized to estimate the hourly tilted solar irradiation for selected arid regions in Algeria. Long-term measured meteorological data, including mean-air temperature, relative humidity, wind speed, alongside global horizontal irradiation and extra-terrestrial horizontal irradiance, were obtained for the two cities of Tamanrasset-and-Adrar for two years. Five computational algorithms were considered and analyzed for the suitability of estimation. Further two new algorithms, namely Average Ensemble and Ensemble using support vector regression were developed using the hybridization approach. The accuracy of the developed models was analyzed in terms of five statistical error metrics, as well as the Wilcoxon rank-sum and ANOVA test. Among the previously selected algorithms, K Neighbors Regressor and support vector regression exhibited good performances. However, the newly proposed ensemble algorithms exhibited even better performance. The proposed model showed relative root mean square errors lower than 1.448% and correlation coefficients higher than 0.999. This was further verified by benchmarking the new ensemble against several popular swarm intelligence algorithms. It is concluded that the proposed algorithms are far superior to the commonly adopted ones.

Solar radiation information at the site of solar energy systems is required for proper planning and execution of energy projects. In this work, global and diffuse solar radiations were measured for a period of two years (September, 2013 to August, 2015) in the Humid Subtropical Climatic Region of India in the city of Aligarh (27.89°N, 78.08°E). Secondary standard pyranometers were used to observe solar radiation at the ground level. The measured data for Aligarh were compared with the available data for the neighboring Capital city, New Delhi (28.61°N, 77.21°E). It was observed that Aligarh has a better availability of solar energy and solar energy utilization potential. Annual average global and diffuse solar radiations were observed to be 22.12 and 7.92 MJ/m²-day, respectively, for Aligarh. Using measured solar radiation data for Aligarh, six empirical models were established to assess monthly mean diffuse solar radiation (by correlating the diffuse fraction with the sky-clearness index). Models were analyzed in terms of several statistical indicators and exhibited reasonable agreement with correlation coefficients in the range of 0.7610 to 0.8188. Models were subsequently ranked based on the Global Performance Indicator. The Global Performance Indicator (GPI) of the developed models was in the range of −1.86 to 5.84, and the highest GPI was achieved for the cubic model.