Predictive Models for Photovoltaic Electricity Production in Hot Weather Conditions

Abstract

Abstract:The process of finding a correct forecast equation for photovoltaic electricity production from renewable sources is an important matter, since knowing the factors affecting the increase in the proportion of renewable energy production and reducing the cost of the product has economic and scientific benefits. This paper proposes a mathematical model for forecasting energy production in photovoltaic (PV) panels based on a self-organizing feature map (SOFM) model. The proposed model is compared with other models, including the multi-layer perceptron (MLP) and support vector machine (SVM) models. Moreover, a mathematical model based on a polynomial function for fitting the desired output is proposed. Different practical measurement methods are used to validate the findings of the proposed neural and mathematical models such as mean square error (MSE), mean absolute error (MAE), correlation (R), and coefficient of determination (R 2 ). The proposed SOFM model achieved a final MSE of 0.0007 in the training phase and 0.0005 in the cross-validation phase. In contrast, the SVM model resulted in a small MSE value equal to 0.0058, while the MLP model achieved a final MSE of 0.026 with a correlation coefficient of 0.9989, which indicates a strong relationship between input and output variables. The proposed SOFM model closely fits the desired results based on the R 2 value, which is equal to 0.9555. Finally, the comparison results of MAE for the three models show that the SOFM model achieved a best result of 0.36156, whereas the SVM and MLP models yielded 4.53761 and 3.63927, respectively. A small MAE value indicates that the output of the SOFM model closely fits the actual results and predicts the desired output.

Simulation and Comparison of Mathematical Models of PV Cells with Growing Levels of Complexity

“…By targeting a renewable energy based economy and a circular economy at the same time could be the way achieve the Energy Union Framework Strategy targets [1]. Although free and available on a planetary scale, the role in the global energy mix is unobtrusive, competing not only with other forms of non-renewable energy, such as gas and coal [6], but also with its more direct rival-the wind renewable energy source [7]. Except for a very limited number of countries where proactive and generous income policies were implemented at the beginning of the last decade, there has been a more recent mobilization of European governments in this sector, legislating on specific instruments to stimulate production decentralized and small scale power [8].…”

Sensorless PV Power Forecasting in Grid-Connected Buildings through Deep Learning

“…The number of neurons in the three hidden layers were 50, 30, and 1, respectively. Yousif et al [ 30 ] used a Self-Organizing Feature Map (SOFM) with one hidden layer to predict daily power output using the solar radiation and ambient temperature data measured at the site. In comparison with these works, our work uses a larger feedforward neural network with multiple hidden layers and a large number of neurons in each hidden layer.…”

Evaluation of Photovoltaic Power Generation by Using Deep Learning in Solar Panels Installed in Buildings

“…For instance, Urraca et al [42] compared the prediction results of support vector regression with those of random forests, linear regression (LR) and kNN. Yousif et al [43] compared a self-organizing feature map with multilayer perceptron and support vector machine for forecasting energy production in PV panels. The aforementioned studies have successfully applied their methods in either forecasting future solar resource or estimating solar resource.…”