oa Intelligent Retrieval Paradigm for Solar Sustainability: Leveraging Advanced Learning Methods for Harnessing Solar Hotspots

The increase in population and need for energy in the world's fastest developing economies like India, make it critical to increase the supply of energy and augment its utilization. According to most of the energy projections, the expected future global and current demand patterns of energy are not sustainable. Thus, India will soon run out of its non-renewable energy sources. As per the study analysis, India receives 657.4 MW of solar radiation which when converted to power can be utilized to attain the energy demand of India. Solar hotspots represent geographical areas that receive abundant solar energy and offer significant prospects for commercial energy generation. Our study reveals that approximately 58% of India's geological zones qualify as sun-based hotspots. Furthermore, we propose an economically viable setup of solar plants based on the identified hotspots. To analyze these solar hotspots in India, we have employed a density-based 3-D clustering approach. In our research, we have substantially enhanced the efficiency of the 3-D DBSCAN spatial clustering method by incorporating KD-Trees and spatial indexing for 3D data. We conducted a comparative analysis between two techniques: 3D DBSCAN using the Euclidean distance as the distance metric and 3D DBSCAN Spatial clustering with KD-Trees as the distance function, aiming to optimize nearest neighbor searches. Our analysis demonstrates that, particularly when evaluating solar hotspots, utilizing 3D DBSCAN spatial clustering with KD-Trees yields more accurate results, especially when considering statistical parameters like the Silhouette Score and Dunn Index.