Powering a sustainable future: AI-driven integration of renewables for optimized grid management
Fatma M. Talaat, A.E. Kabeel, Warda M. Shaban
Abstract
This research investigates how Deep Learning (DL) and Artificial Intelligence (AI) can be combined to advance energy systems' sustainability with an eusemphasis on Renewable Energy Sources (RESs). The study analyzes three main datasets: Wind Power Forecasting data from January 2018 to March 2020 and the Global Energy Consumption and Renewable Generation Dataset, which follows the world's energy production from renewable and non-renewable sources from 1997 to 2017. Support Vector Regression (SVR), Long Short-Term Memory (LSTM), and Convolutional Neural Networks (CNN) are the three machine learning algorithms that provide the highest Mean Absolute Error (MAE) of 0.1463, 0.0926, and 0.1463, respectively, when used for wind power forecasting. Additionally, 34 days of data on solar power generation from two solar power plants in India show that Random Forest performs better than other algorithms, with an accuracy of 99.03%, followed by Linear Regression at 98.37%. These results show how AI may be used to optimize energy production, improve the management of RESs, and help accomplish the Sustainable Development Goals (SDGs). According to the findings, AI and DL technologies have the potential to increase energy systems' sustainability and efficiency, especially those that rely on RESs like solar and wind.