Energy Production Forecasting From Solar Photovoltaic Plants Based on Meteorological Parameters for Qassim Region, Saudi Arabia

Abstract

Due to the increasing cost of crude oil because of pandemic COVID-19 and global environmental threats, the exploitation of fossil fuels for power generation is discouraged. Further, the demand for electrical power is increasing drastically, and therefore, the exploitation of renewable energy resources, particularly solar photovoltaic-based technology for power generation is invigorated. However, the large-scale penetration of solar photovoltaic is becoming a major challenge in terms of stability, reliability of power when integrated with the grid. Thus, it becomes important to develop a novel approach or strategy which is useful to improve power quality, reliability, and grid stability. Solar photovoltaic power forecasting is a key tool for this new era and becoming the main component for a smart grid environment. Here, in this paper, the ensemble trees approach-based machine learning approach is utilized to forecast the solar photovoltaic power with the help of various meteorological parameters. The high-quality measured data for meteorological parameters for Qassim, Saudi Arabia is used in this research. The performance of the proposed model is evaluated with the help of statistical indices such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Square Error (MSE), Mean Absolute Percentage Error (MAPE), Training Time (TT) and found within the desired limits. To validate the obtained results a comparative analysis with other machine learning models is carried out. Moreover, the proposed research may provide the roadmap in achieving the vision 2030 of the government of Saudi Arabia.

Computational solar energy – Ensemble learning methods for prediction of solar power generation based on meteorological parameters in Eastern India

“…In this work, major environmental parameters which directly influence PV power generation have been considered. To validate our analysis of features and their importance in predictions, it has been shown that the power generation calculated using certain environmental parameters by [36] is close to actual power generated. The various 4 and Table 5.…”

“…In Table 6, a random sample range of 20 observations of power generation calculated using DR_Avg and WS_Avg and actual power has been tabulated. Using this method [36] a root mean squared error (RMSE) of 799.25 is observed against the actual power generated. Hence choice of environmental parameters heavily affects the results.…”

Structural Changes, Efficiency Improvements, and Energy Demand Forecasting Based on Empirical Analysis of Decomposition Models

“…In the spot market, the intraday market will gradually play a more important role and balance the transaction volume in the market in real time. will increase, and at the same time, the volatility of the electricity spot market clearing price will increase [18][19].…”

A hybrid deep learning model with error correction for photovoltaic power forecasting

“…In addition, ensemble learning, as a kind of shallow learning, has received extensive attention in recent years. Common ensemble learning includes extreme gradient boosting (XGBoost) (Li et al, 2022), ensemble trees (Alaraj et al, 2021), random forest (RF) (Kumar and Thenmozhi, 2006), LGBM (Wang Y et al, 2020), and CatBoost (Prokhorenkova et al, 2018). In (Li et al, 2022), the authors propose a prediction model of solar irradiance based on XGBoost.…”

“…In (Li et al, 2022), the authors propose a prediction model of solar irradiance based on XGBoost. In (Alaraj et al, 2021), the ensemble trees based machine learning approach considering various meteorological parameters is proposed for PV power forecasting. However, with the development of big data technology and intelligence optimization theories in recent years, the drawback of shallow learning models will be prone to the curse of dimensionality and under-fitting, which makes it difficult to forecast PV power data in a big data era (Soares et al, 2016).…”