AI-Driven Biomimetic Networks for Autonomous and Self-Optimizing Marine Power Generation
Mohammad Barr1, Tawfeeq Shawly2, Ahmed A. Alsheikhy3,*, Shaaban M. Shaaban4, Aws AbuEid5, Yahia Said4
1 Department of Electrical Engineering, College of Engineering, Northern Border University, Arar, Saudi Arabia
2 Department of Electrical Engineering, Faculty of Engineering at Rabigh, King Abdulaziz University, Jeddah, Saudi Arabia
3 Department of Computer and Network Engineering, College of Computer Science and Engineering, University of Jeddah, Jeddah, Saudi Arabia
4 Center for Scientific Research and Entrepreneurship, Northern Border University, Arar, Saudi Arabia
5 Director of the Artificial Intelligence Center, Arab Open University, Headquarters, Ardiya, Kuwait
* Corresponding Author: Ahmed A. Alsheikhy. Email: 
(This article belongs to the Special Issue: Advanced Artificial Intelligence and Machine Learning Methods Applied to Energy Systems, 2nd Edition)
Computer Modeling in Engineering & Sciences https://doi.org/10.32604/cmes.2026.085040
Received 04 May 2026; Accepted 06 July 2026; Published online 14 September 2026
Abstract
The worldwide shift toward renewable energy has generated considerable interest in harnessing the vast potential of ocean energy sources, including wave, tidal, and offshore wind energy. Nevertheless, current marine energy technologies face challenges stemming from unpredictable environmental conditions, low energy-conversion efficiency, and high maintenance costs. It is essential to tackle these issues to realize sustainable and large-scale marine energy solutions. To confront these challenges, we present a novel AI-driven biomimetic energy farm that integrates nature-inspired modular designs with a hierarchical AI control system, enabling an autonomous and self-optimizing marine energy network. This network comprises three components: (1) neural surrogate models that simulate complex fluid-structure interactions more swiftly than traditional computational fluid dynamics (CFD), facilitating real-time performance enhancements, (2) a Distributed Swarm Intelligence reinforcement learning (RL) framework that enables individual energy harvesters, inspired by kelp, jellyfish, and schooling fish, to collaboratively adjust their configurations using a bio-inspired digital twin of ocean dynamics, and (3) Proactive Resilience AI, which utilizes a graph neural network (GNN). This module predicts mechanical failures up to 72 h in advance by analyzing vibration signatures and environmental stress factors. The conducted simulation results demonstrated a 30%–50% improvement, with an average of 45.7% in the energy extraction efficiency, compared with conventional systems, from 15,000 to 22,000 MWh, together with a 20% reduction in maintenance costs from $100,000 to $80,000 through AI-enhanced diagnostics for 20 harvesters. Potential applications include offshore power networks, energy supply for remote islands, and integrated maritime surveillance systems.
Keywords
Ocean energy harvesting; AI-driven biomimicry; renewable energy optimization; smart swarm systems; marine energy resilience; biomimetic wave converters
Open Access
Login
Register
Submit a Paper
Propose a Special lssue
Download PDF
Downloads
Citation Tools
