Energy Optimization Problems: A Comprehensive Review of

Metaheuristic Algorithms and Recent Advances

Safina Shokeen1,* Vishal Srivastava 2

1 School of Engineering and Technology VIPS-TC, India

2 Department of Industrial Internet of Things, School of Engineering and Technology, Vivekananda Institute of Professional Studies,

Technical Campus, Delhi - 110034, India

Received: January 16, 2026 Revised: March 07, 2026 Accepted: April 22, 2026 ⋆ Corresponding author

ABSTRACT

Introducing renewable energy into contemporary power systems is crucial to guaranteeing sustainable solutions

and improving energy performance. Optimizing energy generation, demand forecasting, and system stability have

become difficult with the increasing popularity of renewable energy sources like wind and solar energy systems.

This literature review explores recent advances in addressing these challenges by applying artificial intelligence (AI),

machine learning (ML), and metaheuristic optimization algorithms. Some of those papers are reviewed because

they show advancements in forecasting renewable energy generation, controlling hybrid microgrids, and managing

energy in smart grids. Particular attention is given to innovative models such as adaptive dynamic grey wolf-dipper

throated optimization (ADGWDTO) for wind speed prediction, the Evolutionary Neural Machine Inference Model

(ENMIM) for residential energy consumption, and the Wolf-Inspired Optimized Support Vector Regression (WIOSVR)

for building energy forecasts. Further, the review discusses the emergence of hybrid renewable energy systems

and evaluates advancements in techno-economic optimization. The works under review explore advancements in

prediction performance, system availability, and cost, thus making a real contribution to further developing reliable

and effective energy systems. Thus, these findings may be used to change to more sustainable energy systems in

urban and off-grid environments. It will also lead to further exploration of new optimization techniques and improved

synergistic application of renewable energy into electricity networks worldwide.

Keywords: Renewable energy Optimization algorithms Machine learning Forecasting Smart grids

1. INTRODUCTION

The use of metaheuristic algorithms in solving energy optimization

problems has emerged as an important research

focus given the measurement upturn in demand for efficient

and effective energy solutions worldwide. Such algorithms

mimic natural processes with the ability to function effectively

and independently address optimization problems in

other disciplines. For example, the relatively recent Greylag

Goose Optimization was proposed as a bio-inspired optimization

method that is described as promising for addressing

energy issues [1]. Likewise, an optimization algorithm is

used in other fields, such as classifying roads for self-driving

cars using the Adaptive Mutation Dipper Throated Optimization.

Metaheuristic algorithms do not only apply in energy optimization

but also environmental conditions and system design

aspects. For instance, energy extraction in photovoltaic

systems influenced by environmental factors has also been

assessed using these algorithms and has demonstrated how