| Abstrakt: |
Renewable energy usage for remotely located place is helpful for the villagers to improve their lifestyle and in avoiding the fates during the night hours. Usage of multiple renewable sources help in reduction of overall cost of the project and better availability of the electric power. This paper presents an assessment of renewable energy integration at a small coastal community in Mahalunge village, near Goa. The study focuses on the implementation of solar and wind power systems and evaluates their capability, performance, and cost-effectiveness. Various machine learning methodologies are tried for prediction of renewable energy resource availability. Comparative analysis reveals that for solar radiation prediction the Random Forest algorithm performs the best, while the Long Short-Term Memory (LSTM) algorithm is most accurate for wind speed prediction. Implementation plan is based on factors such as solar radiation prediction, residential load, sizing of solar panels, predicted wind speed data, design considerations and cost effectiveness. The findings provide insights into the feasibility and effectiveness of renewable energy integration in small coastal communities. Policymakers, energy planners, and community stakeholders can utilize the research outcomes of this paper to take decisions regarding renewable energy projects. The research work presented here contributes to the advancement of renewable energy integration strategies, supporting the transition towards sustainable and resilient energy systems in coastal regions. The comprehensive evaluation presented in this paper paves the way for the efficient integration of renewable energy sources in small coastal communities, fostering a greener and more sustainable future. [ABSTRACT FROM AUTHOR] |
