Assessing the Feasibility of Integrating Renewable Energy: Decision Tree Analysis for Parameter Evaluation and LSTM Forecasting for Solar and Wind Power Generation in a Campus Microgrid

Abstract

The world has embarked on a road to sustainable energy production. As a result, countries have turned to microgrid developments. This article aims to study the feasibility of renewable sources such as solar PV and wind power for integrating a microgrid campus, taking the example of a case in East Africa, precisely the case of the University of Djibouti. We applied the weather parameters to evaluate the solar and wind potential with the Decision Tree method for analyzing and classifying the degrees of solar radiation and the consistency of wind speed. These data are spread over eight years to establish and capture seasonal changes and prove the accessibility of renewable sources in a specific site. The results were compared to Random Forest, Logistic Regression, K-Nearest Neighbors, Support Vector Machine, and Naïve Bayes classifiers, which showed that the performance of classifying the Decision tree outperformed all other methods with an accuracy of 0.99321. The second work of this article explored the forecasting of the possible powers predicted with the LSTM deep learning method by the generation of the Solar PV array and wind turbines which were simulated on PVLib and Windpowerlib. The results are favorable, and the LSTM has performed well on the different hyperparameters. With the combination of machine learning and deep learning, it was possible to theoretically conclude the integration of renewable energies since we investigated all the potential possibilities in evaluating meteorological parameters and power predictions. Finally, decision scores from the Decision Tree architecture and the LSTM features were integrated to form a hybrid Tree-LSTM fusion method. It introduces a novel architectural concept that can effectively address sequential data and harness the non-linear capabilities of decision trees. The proposed model was validated by tuning the hyperparameters. Enhancing the maximum depth of the model increases the performance at a certain point, and conversely, reducing the minimum sample split improves the model performance. These contributions will help to create sustainable energy systems and increase the transition to a clean CO2 environment.