Techno-economic feasibility assessment for a standalone hybrid energy system integrating renewable energy sources [dataset]

In this study, techno-economic and environmental analyses (TEEA) of various combinations of hybrid renewable energy systems (HRES) intended to provide electricity to an off-grid location, utilising 100% renewable energy sources have been investigated. The study investigates various scenarios combining wind turbines (WT), photovoltaic (PV) panels, biogas generators (BG), batteries (BAT), and converters (CONV), and assesses their technical and economic performances. Economic analysis reveals that system integrating PV/WT/BAT/CONV/BG, demonstrates the lowest LCOE (0.278 $/kWh) and NPC (1.61 M$) of all the investigated systems. On the other hand, the system comprising BAT/CONV/BG, has the highest LCOE (0.455 $/kWh) and NPC (2.63 M$) among all the configurations investigated. Machine learning techniques are employed to analyze techno-economic and environmental performance data. The Rational Quadratic Gaussian Process Regression model and the Wide Neural Network model achieved the highest accuracy in predicting the levelized cost of electricity (LCOE) and CO2 emissions, respectively. These results provide valuable assessment for the design and optimisation of a standalone HRES in remote areas.