Abstract The transition toward sustainable energy requires advanced forecasting and management solutions to balance supply and demand efficiently. Artificial Intelligence (AI) is revolutionising energy forecasting and management by integrating machine learning (ML), deep learning (DL), and predictive analytics into renewable energy systems, power grids, and energy markets. This review explores AI-driven methodologies for energy forecasting, focusing on their role in optimising renewable energy integration, improving grid stability, and enhancing energy trading strategies. Recent advancements, such as AI-powered predictive maintenance, smart grid optimisation, and AI-driven demand response, are discussed with case studies from industry leaders like Siemens, Tesla, and BP. AI models such as Long Short-Term Memory (LSTM) networks, Reinforcement Learning (RL), and hybrid models are proving instrumental in forecasting solar and wind energy production with high accuracy. However, challenges such as data privacy, computational costs, and regulatory compliance remain significant barriers to its adoption. This paper highlights emerging trends, including the integration of AI with blockchain and the Internet of Things (IoT) for decentralised energy management. By addressing these challenges and leveraging AI's full potential, energy systems can achieve improved efficiency, reduced carbon emissions, and increased sustainability. The findings emphasise AI's transformative impact on energy forecasting and its crucial role in achieving global energy transition goals.
Umunnawuike et al. (Mon,) studied this question.