Machine Learning Modeling of Horizontal Photovoltaics Using Weather and Location Data

Abstract

Solar energy is a key renewable energy source; however, its intermittent nature and potential for use in distributed systems make power prediction an important aspect of grid integration. This research analyzed a variety of machine learning techniques to predict power output for horizontal solar panels using 14 months of data collected from 12 northern-hemisphere locations. We performed our data collection and analysis in the absence of irradiation data—an approach not commonly found in prior literature. Using latitude, month, hour, ambient temperature, pressure, humidity, wind speed, and cloud ceiling as independent variables, a distributed random forest regression algorithm modeled the combined dataset with an R2 value of 0.94. As a comparative measure, other machine learning algorithms resulted in R2 values of 0.50–0.94. Additionally, the data from each location was modeled separately with R2 values ranging from 0.91 to 0.97, indicating a range of consistency across all sites. Using an input variable permutation approach with the random forest algorithm, we found that the three most important variables for power prediction were ambient temperature, humidity, and cloud ceiling. The analysis showed that machine learning potentially allowed for accurate power prediction while avoiding the challenges associated with modeled irradiation data.

How the morning-afternoon cloudiness asymmetry affects the energy-maximizing azimuth direction of fixed-tilt monofacial solar panels

“…In the Northern/Southern Hemisphere, fixed-tilt monofacial solar panels conventionally face south/ north, because the southern/northern azimuth may ensure maximal solar energy [1][2][3][4][5][6][7][8][9]. Monofacial panels collect light only from their photovoltaic front side, while bifacial panels use special solar cells and a transparent cover to collect light not only from the front, but also from the rear side [10].…”

Solar Irradiance Prediction with Machine Learning Algorithms: A Brazilian Case Study on Photovoltaic Electricity Generation

“…Several papers also propose comparing the performance of different ML models to predict solar radiation on a specific site, understanding the best suitable model for each location. The authors in [24] compared the performance of six different ML algorithms in the context of the United States of America (USA): Distributed Random Forest (DRF), Extremely Randomized Trees (XRT), stacked ensemble build, Gradient Boosting Machine (GBM), and Deep Learning and Generalized Linear Model (GLM). DRF presented the fewest errors (MAE and RMSE) on a first test and was therefore implemented to predict solar radiation in 12 different locations in the USA.…”

“…DRF presented the fewest errors (MAE and RMSE) on a first test and was therefore implemented to predict solar radiation in 12 different locations in the USA. The algorithm presented a different performance in each location, emphasizing the need to choose the locally best and most suitable algorithm [24].…”

Solar Irradiance Forecast Based on Cloud Movement Prediction

“…Some studies have introduced artificial neural networks or deep learning with extensive data sets. Examples of solar radiation prediction based on machine learning [1][2][3][4][5][6] showed that solar radiation prediction could be affected by different input parameters for artificial neural networks and multilayer perceptrons. The other machine learning method based on publicly available weather reports showed the approach for a prediction horizon of 24 h [7].…”