Sustainable Marine Structures

Edge AI and Explainable Models for Real-Time Decision-Making in Ocean Renewable Energy Systems

Ghanasham Chandrakant Sarode

Department of Civil Engineering, Dr. D. Y. Patil Institute of Technology, Sant Tukaram Nagar, Pimpri, Pune, Maharashtra 411018, India School of Technology and Research, Dr. D. Y. Patil Dnyan Prasad University, Sant Tukaram Nagar, Pimpri, Pune, Maharashtra 411018, India  

Puja Gholap

Department of Computer Engineering, Sharadchandra Pawar College of Engineering, Dumberwadi (Otur), Junnar, Pune, Maharashtra 412409, India

Kishor Renukadasrao Pathak

Department of Information Technology, Vishwakarma Institute of Information Technology, Pune, Maharashtra 411048, India

P. S. N. Masthan Vali

Department of Mechanical Engineering, Koneru Lakshmaiah Education Foundation, Guntur, Andhra Pradesh 522502, India

Upendrra Saharkar

Department of Civil Engineering, Dr. D. Y. Patil Institute of Engineering and Technology, Ambi, Pune, Maharashtra 410506, India

Govindarajan Murali

Department of Mechanical Engineering, Koneru Lakshmaiah Education Foundation, Guntur, Andhra Pradesh 522502, India

Dr. Anant Kurhade

DYPIOT

DOI: https://doi.org/10.36956/sms.v7i3.2239

Received: 30 May 2025; Published: 10 July 2025

Abstract

Ocean Renewable Energy (ORE) systems—comprising wind, wave, tidal, and ocean thermal energy—are increasingly seen as viable alternatives to fossil fuels. However, their integration into the power grid is hindered by environmental sensitivity, dynamic ocean conditions, and high maintenance demands. Artificial Intelligence (AI) offers promising solutions to these challenges by enabling intelligent, adaptive, and resilient energy systems. This review explores AI applications in ORE, focusing on three critical domains: optimization, forecasting, and control. Optimization techniques, including Genetic Algorithms (GA) and Swarm Intelligence (SI), are employed to enhance device efficiency, improve energy capture, optimize farm layouts, reduce environmental impacts, and lower installation costs. Forecasting uses Machine Learning (ML) and Deep Learning (DL) models to predict wave height, tidal flow, and energy output, aiding in grid integration and energy scheduling. In control systems, AI approaches like Reinforcement Learning (RL) and Fuzzy Logic ensure real-time responsiveness and predictive maintenance, improving system reliability in dynamic marine environments. Emerging technologies such as Edge AI enable decentralized computation for real-time decision-making, while Digital Twin frameworks simulate and predict system performance before deployment. Explainable AI (XAI) is also discussed to ensure transparent and trustworthy decision-making. Ethical and regulatory concerns are acknowledged to ensure responsible AI integration in ocean settings. Overall this review offers a comprehensive synthesis of how AI enhances the performance, efficiency, and scalability of ORE systems. It serves as a valuable resource for researchers, policymakers, and industry professionals seeking to advance clean, smart, and sustainable ocean energy solutions.

Keywords: Artificial Intelligence, Forecasting, Machine Learning, Ocean Renewable Energy, Optimization, Smart Control

References