<p>The purpose of this work is to help enhance Botswana’s countryside electrification by finding the best MRES (mixed renewable energy system), which will eventually solve the intermittency issue and thereby reduce the associated high cost of infrastructure. The paper advises a bi-level optimization approach, which comprises a TOPSIS (technique for order preference by similarity to ideal solution) and a MO-Jaya (multi-objective Jaya) approaches. The research first envisaged the extent to which climatical changes alter solar radiation by operating a machine learning. Then, it used the MO-Jaya to augment the electricity expense. Subsequently, the MO-Jaya was corroborated by standard benchmark mapping. Lastly, the paper used six significant techno-economic aspects in the TOPSIS setting to discover the best MRES. From the findings, it is evident that ‘efficiency of costs’ is the main priority for the stakeholders, which has a percentage of 31.48%, followed by ‘minimal intermittency’, which has a percentage of 25.37%. From MO-Jaya optimization outcomes, it is evident that there is a decrease in the cost of electricity to 0.723 BWP/kWh. This is a significant decrease compared to the cost obtained using the ordinary Jaya and the Class-Topper optimizations, which have a cost of 0.766 BWP/kWh and 0.745 BWP/kWh, respectively. From the TOPSIS findings, solar-only and solar-plus-battery systems appear to be two optimal strategies that have the highest precedence ratings of 23.36% and 20.31%, correspondingly. This is the initial effort in Bostwana that applied MO-Jaya and machine learning to evaluate mixed renewable energy schemes for rural electrification. It augments green energy strategizing discipline through formulating a robust bi-level decision-making template to tackle the complexities of the obstruction with the concern of the macroeconomic constraints.</p>