Spacecraft Solar Arrays Degradation Forecasting with Evolutionary Designed ANN-based Predictors

Semenkina, Maria; Akhmedova, Shakhnaz; Semenkin, ‪Eugene; Ryzhikov, Ivan

doi:10.5220/0005122004210428

Cited by 2 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is another important point that the ANN models exhibite superior predictive abilities among the compared time series analysis, as well as are shown a very high predictive power according to the MAPE criterion (<10%). Nitisanon & Hoonchareon (2018) and Semenkina et al (2014) were proposed ANN based models, which used to input as irradiance, the MAPE results were 5.85% and 4.39%, respectively. In this study, the accuracy results of Model-2 based on MAPE value (=1.95) is also more satisfactory.…”

Section: Table 6 Arima Model Parametersmentioning

confidence: 99%

Prediction of Photovoltaic Panel Power Outputs using Time Series and Artificial Neural Network Methods

Altan

Diken

Kayişoğlu

2021

Tekirdağ Ziraat Fakültesi Dergisi

View full text Add to dashboard Cite

Solar energy is one of the renewable energy sources that has been in high demand in the last decades. With the increasing penetration of photovoltaic (PV) systems in around the world, accurate estimation of the power output of PV systems has become an important issue. Since PV systems directly convert sunlight into electrical energy, PV power output varies depending on environmental conditions. In order to deal with the periodic and nonstationary problems of PV output power, modelling methods are widely use for forecasting. The main purpose of this study is to lead an assessment of forecasting of the PV power outputs in short-time. For this purpose, data are obtained from experimental activities carried out on a real 250 kWp PV stystem, which is located in T.C Tekirdağ Namık Kemal University, Süleymanpaşa district of Tekirdağ province. All parametres are measured hourly with three times according to inclination of the panel setups (0˚, 30˚,60˚). In this sense, this study differs from the previously studies in literature, as it expands the forecasting model with considering of different panel angle. In the first stage, the significant variables for predicting PV power output are identified based on both correlation analysis and stepwise regression analysis. The findings are shown that solar radiation and angle of inclination of the panel are significant predictors of the generation of PV power. In the second stage, three different model are proposed based on Time Series Analysis (TSA) and Artificial Neural Network (ANN) approaches in order to predict power production of PV system. Furthermore, the accuracies of the models are analyzed in order to better understand the internal errors that occur in energy estimation applications and to evaluate their potential. All models are compared in terms of the correlation coefficient (R), coefficient of determination (R 2 ), mean absolute percentage error (MAPE). The results of analyses show that the ANN models have higher accuracy than the TSA model for forecasting PV power.

show abstract

Section: Table 6 Arima Model Parametersmentioning

confidence: 99%