Optimization of solar power forecasting employing an advanced hybrid machine learning approach

Journal of Computational Electronics · Springer Nature · 2026-10-13 · DOI: 10.1007/s12667-026-00839-7

Аннотация

Although India's solar power generation capacity is substantial, accurate forecasting of this capacity is challenging because to the country's extreme weather variability. Projections of future solar power generation are now less precise than they once were because of these fluctuations caused by things like seasons and erratic weather predictions. In this paper we have focused on three objectives, first is to identify the prominent locations in India where the abundant solar power is available and can be harnessed to maintain the system's sustainability. The second is to hybridize the two well-known machine learning algorithms to develop an efficient and effective hybrid ML Algorithm to achieve more accurate forecasting results; furthermore, to improve the ML model's efficiency and reduce the iteration time, the optimization of the hyperparameters has been performed with the genetic algorithm technique. The other and last objective is to train the developed model with the historical data of the proposed region on the developed hybrid ML model to testify our results and forecast the solar power with higher accuracy. According to the proposed strategy, the Jodhpur location has been chosen with the available historical meteorological data. Based on the collected meteorological and solar energy data, three separate non-overlapping groups are formed: training data (the upper 70% of the data), validation data (the lower 30% of the data), and testing data (the upper 10% of the data). In this study, the solar power forecasting task is formulated as a supervised regression problem in which continuous-valued daily photovoltaic energy generation is predicted from meteorological and solar irradiance variables such as temperature, sunshine duration, and global solar radiation. By helping the power system operator better manage power pooling at the central grid and reducing the difficulties associated with solar power output uncertainty, the suggested hybrid algorithm has demonstrated the system's dependability potential. For the past seven months, Jaipur's 120 kW SPV power plant has likewise relied on this suggested method to predict solar electricity output. Later, It was observed that the actual and predicted power were accurate, with a percentage error of 0.121% in May’2023. In this work, a total of 95 papers were analyzed, and it has been identified that 75% of the documents were under the SDGs of affordable and clean energy and climate actions. Perhaps there is a lack of research in the solar domain related to the SDGs. The effect of solar photovoltaic (PV) system usage on the SDGs is the focus of this investigation. Graphical abstract

Читать у издателя →

Похожие статьи