Artificial intelligence and metaheuristic optimization techniques for renewable energy systems and power electronics: A comprehensive review

The accelerating transition toward sustainable energy systems has intensified the need for intelligent and optimization-driven solutions capable of addressing the growing complexity of renewable energy systems (RES) and power electronics (PE). In this context, artificial intelligence (AI) and metaheuristic optimization techniques have emerged as two of the most influential computational paradigms for enhancing forecasting, control, diagnosis, design, and operational decision-making. However, the existing review literature remains largely fragmented, typically treating AI and metaheuristics as separate research streams and examining RES and PE within isolated technical boundaries. To address this gap, this paper presents a comprehensive review of AI and metaheuristic optimization techniques for RES and PE, covering the period from 2016 to 2026. The review proposes a unified taxonomy framework that organizes the field through four interacting dimensions: intelligence layer, optimization layer, application layer, and implementation layer. It further classifies the literature according to functional roles, including prediction, optimization, control, diagnosis, and maintenance, while also incorporating a lifecycle-oriented perspective for PE applications across design, control, and maintenance stages. Major AI techniques, including machine learning, deep learning, reinforcement learning, fuzzy systems, and hybrid intelligent models, are critically analyzed alongside key metaheuristic families such as evolutionary algorithms, swarm intelligence methods, and emerging physics-based optimizers. Their applications are systematically examined in solar, wind, battery storage, smart grids, microgrids, and hybrid AC/DC systems, as well as in converter design, intelligent control, and predictive maintenance. The synthesis yields four principal findings: solar and wind dominate the reviewed literature with 55 and 42 studies respectively; standalone algorithms fell from about 82% of reviewed renewable-energy studies in 2016 to roughly 30% by 2025 as hybrid AI–optimization frameworks expanded; power-electronics research has grown across design, control, and maintenance, with control remaining the largest stage; and validation remains overwhelmingly simulation-based, with only a small minority of studies reporting FPGA-, DSP-, or hardware-in-the-loop verification. In addition, publication trends, hybrid AI–optimization strategies, research gaps, and future directions are synthesized to provide a forward-looking roadmap for next-generation intelligent energy systems. This review offers a unified reference for researchers and practitioners seeking to advance resilient, adaptive, and high-performance renewable energy infrastructures through integrated computational intelligence.

Authors

Institutions

Publication Details

Journal
Next Energy
Published
2026-11-21
DOI
https://doi.org/10.1016/j.nxener.2026.101194
Primary Topic
Metaheuristic Optimization Algorithms Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Artificial intelligence and metaheuristic optimization techniques for renewable energy systems and power electronics: A comprehensive review

Ahmad F. Tazay
Next Energy
Metaheuristic Optimization Algorithms Research
article

Artificial intelligence and metaheuristic optimization techniques for renewable energy systems and power electronics: A comprehensive review

Ahmad F. Tazay
article en

Abstract

The accelerating transition toward sustainable energy systems has intensified the need for intelligent and optimization-driven solutions capable of addressing the growing complexity of renewable energy systems (RES) and power electronics (PE). In this context, artificial intelligence (AI) and metaheuristic optimization techniques have emerged as two of the most influential computational paradigms for enhancing forecasting, control, diagnosis, design, and operational decision-making. However, the existing review literature remains largely fragmented, typically treating AI and metaheuristics as separate research streams and examining RES and PE within isolated technical boundaries. To address this gap, this paper presents a comprehensive review of AI and metaheuristic optimization techniques for RES and PE, covering the period from 2016 to 2026. The review proposes a unified taxonomy framework that organizes the field through four interacting dimensions: intelligence layer, optimization layer, application layer, and implementation layer. It further classifies the literature according to functional roles, including prediction, optimization, control, diagnosis, and maintenance, while also incorporating a lifecycle-oriented perspective for PE applications across design, control, and maintenance stages. Major AI techniques, including machine learning, deep learning, reinforcement learning, fuzzy systems, and hybrid intelligent models, are critically analyzed alongside key metaheuristic families such as evolutionary algorithms, swarm intelligence methods, and emerging physics-based optimizers. Their applications are systematically examined in solar, wind, battery storage, smart grids, microgrids, and hybrid AC/DC systems, as well as in converter design, intelligent control, and predictive maintenance. The synthesis yields four principal findings: solar and wind dominate the reviewed literature with 55 and 42 studies respectively; standalone algorithms fell from about 82% of reviewed renewable-energy studies in 2016 to roughly 30% by 2025 as hybrid AI–optimization frameworks expanded; power-electronics research has grown across design, control, and maintenance, with control remaining the largest stage; and validation remains overwhelmingly simulation-based, with only a small minority of studies reporting FPGA-, DSP-, or hardware-in-the-loop verification. In addition, publication trends, hybrid AI–optimization strategies, research gaps, and future directions are synthesized to provide a forward-looking roadmap for next-generation intelligent energy systems. This review offers a unified reference for researchers and practitioners seeking to advance resilient, adaptive, and high-performance renewable energy infrastructures through integrated computational intelligence.

Next EnergyVol. 14
Al Baha University (SA)
Metaheuristic Optimization Algorithms Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon