An LSTM Short-Term Solar Irradiance Forecasting Under Complicated Weather Conditions

Complicated weather conditions lead to intermittent, random and volatility in photovoltaic (PV) systems, which makes PV predictions difficult. A recurrent neural network (RNN) is considered to be an effective tool for time-series data prediction. However, when the weather changes intensely, the long-term sequence of multivariate may cause gradient vanishing (exploding) during the training of RNN, leading the prediction results to local optimum. Long short-term memory (LSTM) network is the deep structure of RNN. Due to its special hidden layer unit structure, it can preserve the trend information contained in the long-term sequence, which is allowed to solve the problems of RNN and improve performance. An LSTM-based approach is applied for short-term predictions in this study based on a timescale that encompasses global horizontal irradiance (GHI) one hour in advance and one day in advance. Inaccurate forecasts usually occur on cloudy days, and the results of ANN and SVR in the literature prove this. To improve prediction accuracy on cloudy days, the clearness-index was introduced as an input data for the LSTM model and to classify the type of weather by k-means during the data processing, where cloudy days are classified as the cloudy and the mixed(partially cloudy). NN models are established to compare the accuracy of different approaches and the cross-regional study is to prove whether the method can be generalizable. From the results of hourly forecast, the R2 coefficient of LSTM on cloudy days and mixed days is exceeding 0.9, while the R2 of RNN is only 0.70 and 0.79 in Atlanta and Hawaii. From the results of daily forecast, All R2 on cloudy days is about 0.85. However, the LSTM is still very effective in improving of RNN and more accurate than other models.

[1]  G. Notton,et al.  Solar radiation forecasting using artificial neural network and random forest methods: Application to normal beam, horizontal diffuse and global components , 2019, Renewable Energy.

[2]  F. Creutzig,et al.  The underestimated potential of solar energy to mitigate climate change , 2017, Nature Energy.

[3]  Sam Kwong,et al.  Deep sequential fusion LSTM network for image description , 2018, Neurocomputing.

[4]  Yang Du,et al.  Short-Term Photovoltaic Power Forecasting Based on Long Short Term Memory Neural Network and Attention Mechanism , 2019, IEEE Access.

[5]  J. Xin,et al.  Comparison of short-term solar irradiance forecasting methods when weather conditions are complicated , 2018, Journal of Renewable and Sustainable Energy.

[6]  Hafidh Hasan,et al.  Neural network-based solar irradiance forecast for peak load management of grid-connected microgrid with photovoltaic distributed generation , 2017, 2017 International Conference on Electrical Engineering and Informatics (ICELTICs).

[7]  Renato De Leone,et al.  Photovoltaic energy production forecast using support vector regression , 2015, Neural Computing and Applications.

[8]  Hongda Liu,et al.  Method of identifying the lengths of equivalent clear-sky periods in the time series of DNI measurements based on generalized atmospheric turbidity , 2019, Renewable Energy.

[9]  Saifur Rahman,et al.  Solar irradiance forecast using aerosols measurements: A data driven approach , 2018, Solar Energy.

[10]  Vivek Srikumar,et al.  Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks , 2018 .

[11]  Song-Keun Lee,et al.  Development of algorithm for day ahead PV generation forecasting using data mining method , 2011, 2011 IEEE 54th International Midwest Symposium on Circuits and Systems (MWSCAS).

[12]  Bart De Schutter,et al.  Forecasting spot electricity prices Deep learning approaches and empirical comparison of traditional algorithms , 2018 .

[13]  Zhiyong Feng,et al.  LSTM with sentence representations for document-level sentiment classification , 2018, Neurocomputing.

[14]  Ning Zhang,et al.  Probabilistic individual load forecasting using pinball loss guided LSTM , 2019, Applied Energy.

[15]  L. D. Monache,et al.  An analog ensemble for short-term probabilistic solar power forecast , 2015 .

[16]  R. Urraca,et al.  Review of photovoltaic power forecasting , 2016 .

[17]  Tang Peng-jie,et al.  Multi-objective Layer-wise Optimization and Multi-level Probability Fusion for Image Description Generation Using LSTM , 2018 .

[18]  Joachim Denzler,et al.  Deep learning and process understanding for data-driven Earth system science , 2019, Nature.

[19]  Damien Querlioz,et al.  Vowel recognition with four coupled spin-torque nano-oscillators , 2017, Nature.

[20]  Yonghua Song,et al.  Distributed photovoltaic generation in the electricity market: status, mode and strategy , 2018, CSEE Journal of Power and Energy Systems.

[21]  Shahzad Muzaffar,et al.  Short-Term Load Forecasts Using LSTM Networks , 2019, Energy Procedia.

[22]  Clifford W. Hansen,et al.  Identification of periods of clear sky irradiance in time series of GHI measurements , 2016 .

[23]  Yuansheng Huang,et al.  Grey relational analysis, principal component analysis and forecasting of carbon emissions based on long short-term memory in China , 2019, Journal of Cleaner Production.

[24]  Anil Kumar Sao,et al.  Solar radiation forecasting with multiple parameters neural networks , 2015 .

[25]  Will Gorman,et al.  The practicality of distributed PV-battery systems to reduce household grid reliance , 2017 .

[26]  Ryan Wiser,et al.  The climate and air-quality benefits of wind and solar power in the United States , 2017, Nature Energy.

[27]  Mohamed Tabaa,et al.  Short-term nonlinear autoregressive photovoltaic power forecasting using statistical learning approaches and in-situ observations , 2019, International Journal of Energy and Environmental Engineering.

[28]  Guochang Wang,et al.  One-day-ahead daily power forecasting of photovoltaic systems based on partial functional linear regression models , 2016 .

[29]  G. W. Chang,et al.  Enhanced Grey Theory System Model with Weight Table for Now-casting PV Power Generation Forecast , 2018, 2018 IEEE Innovative Smart Grid Technologies - Asia (ISGT Asia).

[30]  Durga Toshniwal,et al.  Deep learning framework to forecast electricity demand , 2019, Applied Energy.

[31]  Rui Liu,et al.  Effective long short-term memory with differential evolution algorithm for electricity price prediction , 2018, Energy.

[32]  Tingyan Wang,et al.  Predictive Modeling of the Progression of Alzheimer’s Disease with Recurrent Neural Networks , 2018, Scientific Reports.

[33]  Rafael Waters,et al.  Net load variability in Nordic countries with a highly or fully renewable power system , 2016, Nature Energy.

[34]  Hao Wang,et al.  Sentiment Analysis of Chinese Microblog Based on Stacked Bidirectional LSTM , 2019, IEEE Access.

[35]  Dejun Mu,et al.  A LSTM Based Model for Personalized Context-Aware Citation Recommendation , 2018, IEEE Access.

[36]  Tara L. Jensen,et al.  Forecasting ground-level irradiance over short horizons: Time series, meteorological, and time-varying parameter models , 2017 .

[37]  Shouxiang Wang,et al.  A novel deep learning method for the classification of power quality disturbances using deep convolutional neural network , 2019, Applied Energy.

[38]  Geoffrey Zweig,et al.  LSTM time and frequency recurrence for automatic speech recognition , 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

[39]  Vishal Kushwaha,et al.  Very short-term solar PV generation forecast using SARIMA model: A case study , 2017, 2017 7th International Conference on Power Systems (ICPS).

[40]  Jun Wang,et al.  Crude oil price prediction model with long short term memory deep learning based on prior knowledge data transfer , 2019, Energy.

[41]  Apostolos Pesyridis,et al.  Machine Learning for the prediction of the dynamic behavior of a small scale ORC system , 2019, Energy.

[42]  Aron Habte,et al.  Evaluation of the National Solar Radiation Database (NSRDB): 1998-2015 , 2017 .

[43]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[44]  Vishwamitra Oree,et al.  A hybrid method for forecasting the energy output of photovoltaic systems , 2015 .

[45]  Francesco Grimaccia,et al.  Analysis and validation of 24 hours ahead neural network forecasting of photovoltaic output power , 2017, Math. Comput. Simul..

[46]  Max Maurer,et al.  City-integrated renewable energy for urban sustainability , 2016 .

[47]  Adam R. Brandt,et al.  Convolutional Neural Network for Short-term Solar Panel Output Prediction , 2018, 2018 IEEE 7th World Conference on Photovoltaic Energy Conversion (WCPEC) (A Joint Conference of 45th IEEE PVSC, 28th PVSEC & 34th EU PVSEC).

[48]  S. Krauter,et al.  Photovoltaic yield prediction using an irradiance forecast model based on multiple neural networks , 2018 .