Forecasting solar power generation using evolutionary mating algorithm-deep neural networks

Mohd Herwan Sulaiman

doi:10.1016/j.egyai.2024.100371

Return

Forecasting solar power generation using evolutionary mating algorithm-deep neural networks

2024-05-01

Mohd Herwan Sulaiman *

Zuriani Mustaffa

DOI：10.1016/j.egyai.2024.100371

Original

Save

View PDF

Abstract

En 中文

This paper proposes an integration of recent metaheuristic algorithm namely Evolutionary Mating Algorithm (EMA) in optimizing the weights and biases of deep neural networks (DNN) for forecasting the solar power generation. The study employs a Feed Forward Neural Network (FFNN) to forecast AC power output using real solar power plant measurements spanning a 34-day period, recorded at 15-minute intervals. The intricate nonlinear relationship between solar irradiation, ambient temperature, and module temperature is captured for accurate prediction. Additionally, the paper conducts a comprehensive comparison with established algorithms, including Differential Evolution (DE-DNN), Barnacles Mating Optimizer (BMO-DNN), Particle Swarm Optimization (PSO-DNN), Harmony Search Algorithm (HSA-DNN), DNN with Adaptive Moment Estimation optimizer (ADAM) and Nonlinear AutoRegressive with eXogenous inputs (NARX). The experimental results distinctly highlight the exceptional performance of EMA-DNN by attaining the lowest Root Mean Squared Error (RMSE) during testing. This contribution not only advances solar power forecasting methodologies but also underscores the potential of merging metaheuristic algorithms with contemporary neural networks for improved accuracy and reliability.

Keywords:

Deep learning neural networks

Evolutionary mating algorithm

Feed forward neural networks

Metaheuristic Optimizers

Solar PV

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.