Methods for Integrating Extraterrestrial Radiation into Neural Network Models for Day-Ahead PV Generation Forecasting

Variability, intermittency, and limited controllability are inherent characteristics of photovoltaic (PV) generation that result in inaccurate solutions to scheduling problems and the instability of the power grid. As the penetration level of PV generation increases, it becomes more important to mitigate these problems by improving forecasting accuracy. One of the alternatives to improving forecasting performance is to include a seasonal component. Thus, this study proposes using information on extraterrestrial radiation (ETR), which is the solar radiation outside of the atmosphere, in neural network models for day-ahead PV generation forecasting. Specifically, five methods for integrating the ETR into the neural network models are presented: (1) division preprocessing, (2) multiplication preprocessing, (3) replacement of existing input, (4) inclusion as additional input, and (5) inclusion as an intermediate target. The methods were tested using two datasets in Australia using four neural network models: Multilayer perceptron and three recurrent neural network(RNN)-based models including vanilla RNN, long short-term memory, and gated recurrent unit. It was found that, among the integration methods, including the ETR as the intermediate target improved the mean squared error by 4.1% on average, and by 12.28% at most in RNN-based models. These results verify that the integration of ETR into the PV forecasting models based on neural networks can improve the forecasting performance.

[1]  Jiafu Wan,et al.  Visually Interpretable Profile Extraction with an Autoencoder for Health Monitoring of Industrial Systems , 2019, 2019 IEEE 4th International Conference on Advanced Robotics and Mechatronics (ICARM).

[2]  Tao Ding,et al.  Day-ahead photovoltaic power forecasting approach based on deep convolutional neural networks and meta learning , 2020, International Journal of Electrical Power & Energy Systems.

[3]  Kok Soon Tey,et al.  Forecasting of photovoltaic power generation and model optimization: A review , 2018 .

[4]  Josep M. Guerrero,et al.  Decentralized Method for Load Sharing and Power Management in a Hybrid Single/Three-Phase-Islanded Microgrid Consisting of Hybrid Source PV/Battery Units , 2017 .

[5]  Qing Zhu,et al.  Effective long short-term memory with fruit fly optimization algorithm for time series forecasting , 2020, Soft Computing.

[6]  Xu Li,et al.  A Power Prediction Method for Photovoltaic Power Plant Based on Wavelet Decomposition and Artificial Neural Networks , 2015 .

[7]  A. Dolara,et al.  Comparison of different physical models for PV power output prediction , 2015 .

[8]  M. Nicolosi.  Wind power integration and power system flexibility–An empirical analysis of extreme events in Germany under the new negative price regime , 2010 .

[9]  Yu Zhang,et al.  Deep Recurrent Entropy Adaptive Model for System Reliability Monitoring , 2021, IEEE Transactions on Industrial Informatics.

[10]  Li Li,et al.  Mid-to-long term wind and photovoltaic power generation prediction based on copula function and long short term memory network , 2019, Applied Energy.

[11]  Yi Tang,et al.  A Hybrid Ensemble Model for Interval Prediction of Solar Power Output in Ship Onboard Power Systems , 2021, IEEE Transactions on Sustainable Energy.

[12]  Dogan Keles,et al.  Comparison of extended mean-reversion and time series models for electricity spot price simulation considering negative prices , 2012 .

[13]  Mohamed Abdel-Nasser,et al.  Accurate photovoltaic power forecasting models using deep LSTM-RNN , 2017, Neural Computing and Applications.

[14]  Zhao Zhen,et al.  A day-ahead PV power forecasting method based on LSTM-RNN model and time correlation modification under partial daily pattern prediction framework , 2020 .

[15]  Bozhong Wang,et al.  Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach , 2020, IEEE Access.

[16]  R. Belmans,et al.  Voltage fluctuations on distribution level introduced by photovoltaic systems , 2006, IEEE Transactions on Energy Conversion.

[17]  Adel Mellit,et al.  Prediction of daily global solar irradiation data using Bayesian neural network: A comparative study , 2012 .

[18]  Emanuele Crisostomi,et al.  Day-Ahead Hourly Forecasting of Power Generation From Photovoltaic Plants , 2018, IEEE Transactions on Sustainable Energy.

[19]  Shanlin Yang,et al.  A hybrid deep learning model for short-term PV power forecasting , 2020 .

[20]  Yongping Yang,et al.  Forecasting Power Output of Photovoltaic Systems Based on Weather Classification and Support Vector Machines , 2012 .

[21]  Ilhami Colak,et al.  Multi-period Prediction of Solar Radiation Using ARMA and ARIMA Models , 2015, 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA).

[22]  Yuqing Chang,et al.  Gated Recurrent Unit Network-Based Short-Term Photovoltaic Forecasting , 2018, Energies.

[23]  Yan Su,et al.  An ARMAX model for forecasting the power output of a grid connected photovoltaic system , 2014 .

[24]  Juan C. Vasquez,et al.  Mixed-Integer-Linear-Programming-Based Energy Management System for Hybrid PV-Wind-Battery Microgrids: Modeling, Design, and Experimental Verification , 2017, IEEE Transactions on Power Electronics.

[25]  Bikash C. Pal,et al.  Stochastic Distribution System Operation Considering Voltage Regulation Risks in the Presence of PV Generation , 2015, IEEE Transactions on Sustainable Energy.

[26]  Mincong Tang,et al.  Deflated reputation using multiplicative long short-term memory neural networks , 2021, Future Gener. Comput. Syst..

[27]  S. Mehraeen,et al.  Challenges of PV Integration in Low-Voltage Secondary Networks , 2017, IEEE Transactions on Power Delivery.