Machine Learning Integration for Enhanced Solar Power Generation Forecasting

^* Assistant Professor, School of Business and Management, CHRIST (Deemed to be University ) Bangalore Yeshwantpur Campus
^† Associate Professor, Scool of Business and Management, Christ university, Yeshwanthpur Campus, Bengaluru .
^‡ Department of Computer Science & Engineering, IES College of Technology, IES University, Madhya Pradesh 462044 India, Bhopal .
^§ Department of Management Uttaranchal Institute of Management, Uttaranchal University, Dehradun-248007, India .
^** The Islamic university, Najaf, Iraq .
⁶ Engineering Manager, Altimetrik India Pvt Ltd, India anishdhablia@gmail.com, Pune, Maharashtra .

^* Corresponding Author :david.winster@christuniversity.in
^† madeswaran.a@christ university.in
^‡ research@iesbpl.ac.in
^§ deepti.sharma.sama@gmail.com
^** abathermahmood560@gmail.com

Abstract

This paper reviews the advancements in machine learning techniques for enhanced solar power generation forecasting. Solar energy, a potent alternative to traditional energy sources, is inherently intermittent due to its weather-dependent nature. Accurate forecasting of photovoltaic power generation (PVPG) is paramount for the stability and reliability of power systems. The review delves into a deep learning framework that leverages the long short-term memory (LSTM) network for precise PVPG forecasting. A novel approach, the physics-constrained LSTM (PCLSTM), is introduced, addressing the limitations of conventional machine learning algorithms that rely heavily on vast data. The PC-LSTM model showcases superior forecasting capabilities, especially with sparse data, outperforming standard LSTM and other traditional methods. Furthermore, the paper examines a comprehensive study from Morocco, comparing six machine learning algorithms for solar energy production forecasting. The study underscores the Artificial Neural Network (ANN) as the most effective predictive model, offering optimal parameters for real-world applications. Such advancements not only bolster the accuracy of solar energy forecasting but also pave the way for sustainable energy solutions, emphasizing the integration of these findings in practical applications like predictive maintenance of PV power plants.