What drives the accuracy of PV output forecasts?

Due to the stochastic nature of photovoltaic (PV) power generation, there is high demand for forecasting PV output to better integrate PV generation into power grids. Systematic knowledge regarding the factors influencing forecast accuracy is crucially important, but still mostly unknown. In this paper, we review 180 papers on PV forecasts and extract a database of forecast errors for statistical analysis. We show that among the forecast models, hybrid models consistently outperform the others and will most likely be the future of PV output forecasting. The use of data processing techniques is positively correlated with the forecast quality, while the lengths of the forecast horizon and out-of-sample test set have negative effects on the forecast accuracy. We also found that the inclusion of numerical weather prediction variables, data normalization, and data resampling are the most effective data processing techniques. Furthermore, we found some evidence for cherry picking in reporting errors and recommend that the test sets be at least one year to better assess model performance. The paper also takes the first step towards establishing a benchmark for assessing PV output forecasts.

[1]  Madan Mohan Tripathi,et al.  K-means clustering based photo voltaic power forecasting using artificial neural network, particle swarm optimization and support vector regression , 2019 .

[2]  Saad Mekhilef,et al.  Review on forecasting of photovoltaic power generation based on machine learning and metaheuristic techniques , 2019, IET Renewable Power Generation.

[3]  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 .

[4]  Emrah Dokur.  Swarm Decomposition Technique Based Hybrid Model for Very Short-Term Solar PV Power Generation Forecast , 2020 .

[5]  Xiong Luo,et al.  Day-Ahead Forecasting of Hourly Photovoltaic Power Based on Robust Multilayer Perception , 2018, Sustainability.

[6]  Boonyang Plangklang,et al.  Forecasting Power output of PV Grid Connected System in Thailand without using Solar Radiation Measurement , 2011 .

[7]  N. Rahim,et al.  Solar photovoltaic generation forecasting methods: A review , 2018 .

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

[9]  C. Coimbra,et al.  Proposed Metric for Evaluation of Solar Forecasting Models , 2013 .

[10]  anonymous.  A review , 2019 .

[11]  Zheng Qian,et al.  Hour-Ahead Photovoltaic Power Forecasting Using an Analog Plus Neural Network Ensemble Method , 2020 .

[12]  Abdul Rahim Pazikadin,et al.  Solar irradiance measurement instrumentation and power solar generation forecasting based on Artificial Neural Networks (ANN): A review of five years research trend. , 2020, The Science of the total environment.

[13]  Dazhi Yang,et al.  Operational photovoltaics power forecasting using seasonal time series ensemble , 2018 .

[14]  Manohar Mishra,et al.  Deep learning and wavelet transform integrated approach for short-term solar PV power prediction , 2020 .

[15]  R. Gross,et al.  A systematic review of the costs and impacts of integrating variable renewables into power grids , 2020 .

[16]  Soteris A. Kalogirou,et al.  Artificial intelligence techniques for photovoltaic applications: A review , 2008 .

[17]  Marco Mussetta,et al.  Robust 24 Hours ahead Forecast in a Microgrid: A Real Case Study , 2019 .

[18]  M. Surya Kalavathi,et al.  Artificial intelligence based forecast models for predicting solar power generation , 2018 .

[19]  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).

[20]  Jaehee Lee,et al.  Day-Ahead Forecasting for Small-Scale Photovoltaic Power Based on Similar Day Detection with Selective Weather Variables , 2020, Electronics.

[21]  Hyun-Jin Lee,et al.  A Review on Deep Learning Models for Forecasting Time Series Data of Solar Irradiance and Photovoltaic Power , 2020, Energies.

[22]  Matthew D. Blackledge,et al.  Techniques and Optimization , 2010 .

[23]  Chao-Ming Huang,et al.  A Weather-Based Hybrid Method for 1-Day Ahead Hourly Forecasting of PV Power Output , 2014, IEEE Transactions on Sustainable Energy.

[24]  Lei Wang,et al.  An ANN-based Approach for Forecasting the Power Output of Photovoltaic System , 2011 .

[25]  H. J. Lu,et al.  A Hybrid Approach for Day-Ahead Forecast of PV Power Generation , 2018 .

[26]  Paras Mandal,et al.  Solar PV power generation forecast using a hybrid intelligent approach , 2013, 2013 IEEE Power & Energy Society General Meeting.

[27]  Spyros Theocharides,et al.  Day-ahead photovoltaic power production forecasting methodology based on machine learning and statistical post-processing , 2020 .

[28]  Emanuele Ogliari,et al.  Advanced Methods for Photovoltaic Output Power Forecasting: A Review , 2020, Applied Sciences.

[29]  Paulo C. M. Carvalho,et al.  MLP Back Propagation Artificial Neural Network for Solar Resource Forecasting in Equatorial Areas , 2018 .

[30]  Mohd Yamani Idna Idris,et al.  SVR-Based Model to Forecast PV Power Generation under Different Weather Conditions , 2017 .

[31]  Da Liu,et al.  Random forest solar power forecast based on classification optimization , 2019, Energy.

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

[33]  Yang Bai,et al.  A recursive ensemble model for forecasting the power output of photovoltaic systems , 2019, Solar Energy.

[34]  Kwanho Kim,et al.  Recurrent Neural Network-Based Hourly Prediction of Photovoltaic Power Output Using Meteorological Information , 2019, Energies.

[35]  Shin-Ju Chen,et al.  Optimization of Module Parameters for PV Power Estimation Using a Hybrid Algorithm , 2020, IEEE Transactions on Sustainable Energy.

[36]  M. Raza,et al.  On recent advances in PV output power forecast , 2016 .

[37]  Montserrat Mendoza-Villena,et al.  Short-term power forecasting system for photovoltaic plants , 2012 .

[38]  Chunxiang Yang,et al.  An Improved Photovoltaic Power Forecasting Model With the Assistance of Aerosol Index Data , 2015, IEEE Transactions on Sustainable Energy.

[39]  Chen Changsong,et al.  Forecasting power output for grid-connected photovoltaic power system without using solar radiation measurement , 2010, The 2nd International Symposium on Power Electronics for Distributed Generation Systems.

[40]  Madan Mohan Tripathi,et al.  Short-term PV power forecasting using empirical mode decomposition in integration with back-propagation neural network , 2020, Journal of Information and Optimization Sciences.

[41]  Carlos F.M. Coimbra,et al.  History and trends in solar irradiance and PV power forecasting: A preliminary assessment and review using text mining , 2018, Solar Energy.

[42]  Sonia Leva,et al.  Physical and hybrid methods comparison for the day ahead PV output power forecast , 2017 .

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

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

[45]  Hisham Mahmood,et al.  Short-Term Photovoltaic Power Forecasting Using an LSTM Neural Network and Synthetic Weather Forecast , 2020, IEEE Access.

[46]  Carlos F.M. Coimbra,et al.  Day-ahead forecasting of solar power output from photovoltaic plants in the American Southwest , 2016 .

[47]  H. Pedro,et al.  Assessment of forecasting techniques for solar power production with no exogenous inputs , 2012 .

[48]  Remo Guidieri.  Res , 1995, RES: Anthropology and Aesthetics.

[49]  M. S. Patel,et al.  An introduction to meta-analysis. , 1989, Health Policy.

[50]  Artificial neural network models for global solar energy and photovoltaic power forecasting over India , 2020 .

[51]  Arash Asrari,et al.  A Hybrid Algorithm for Short-Term Solar Power Prediction—Sunshine State Case Study , 2017, IEEE Transactions on Sustainable Energy.

[52]  V. Sreeram,et al.  A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization , 2020 .

[53]  J. Sillmann,et al.  Better seasonal forecasts for the renewable energy industry , 2020 .

[54]  Pearl Brereton,et al.  Lessons from applying the systematic literature review process within the software engineering domain , 2007, J. Syst. Softw..

[55]  Jianjing Li,et al.  Day-ahead power forecasting in a large-scale photovoltaic plant based on weather classification using LSTM , 2019, Energy.

[56]  Abdennaser Bourouhou,et al.  Solar Photovoltaic Power Forecasting , 2020 .

[57]  Federico Silvestro,et al.  A Hybrid Technique for Day-Ahead PV Generation Forecasting Using Clear-Sky Models or Ensemble of Artificial Neural Networks According to a Decision Tree Approach , 2019 .

[58]  Mohit Tawarmalani,et al.  Systematic Analysis Reveals Thermal Separations Are Not Necessarily Most Energy Intensive , 2021 .

[59]  C. K. Simoglou,et al.  Comparison of SARIMAX, SARIMA, modified SARIMA and ANN-based models for short-term PV generation forecasting , 2016, 2016 IEEE International Energy Conference (ENERGYCON).

[60]  Tomonobu Senjyu,et al.  Data Fusion Based Hybrid Deep Neural Network Method for Solar PV Power Forecasting , 2019, 2019 North American Power Symposium (NAPS).

[61]  Maria Grazia De Giorgi,et al.  Photovoltaic power forecasting using statistical methods: impact of weather data , 2014 .

[62]  Jian Xiao,et al.  Short-Term Solar Power Forecasting Based on Weighted Gaussian Process Regression , 2018, IEEE Transactions on Industrial Electronics.

[63]  A. Massi Pavan,et al.  A hybrid model (SARIMA-SVM) for short-term power forecasting of a small-scale grid-connected photovoltaic plant , 2013 .

[64]  Ling Liu,et al.  Forecasting Day-Ahead Hourly Photovoltaic Power Generation Using Convolutional Self-Attention Based Long Short-Term Memory , 2020 .

[65]  Bangyin Liu,et al.  Online 24-h solar power forecasting based on weather type classification using artificial neural network , 2011 .

[66]  Mehdi Seyedmahmoudian,et al.  Short-term PV power forecasting using hybrid GASVM technique , 2019, Renewable Energy.

[67]  Matteo De Felice,et al.  Multi-Model Ensemble for day ahead prediction of photovoltaic power generation , 2016 .

[68]  Mohammad Yusri Hassan,et al.  Short-term forecasting of solar photovoltaic output power for tropical climate using ground-based measurement data , 2016 .

[69]  Abinet Tesfaye Eseye,et al.  Short-term photovoltaic solar power forecasting using a hybrid Wavelet-PSO-SVM model based on SCADA and Meteorological information , 2018 .

[70]  Dragana Nikodinoska,et al.  Solar and wind power generation forecasts using elastic net in time-varying forecast combinations , 2022, Applied Energy.

[71]  Mashud Rana,et al.  Multiple steps ahead solar photovoltaic power forecasting based on univariate machine learning models and data re-sampling , 2020 .

[72]  Tomonobu Senjyu,et al.  Solar PV Power Prediction Using A New Approach Based on Hybrid Deep Neural Network , 2019, 2019 IEEE Power & Energy Society General Meeting (PESGM).

[73]  A. Mellit,et al.  A 24-h forecast of solar irradiance using artificial neural network: Application for performance prediction of a grid-connected PV plant at Trieste, Italy , 2010 .

[74]  Jianhua Zhang,et al.  PV power forecasting using an integrated GA-PSO-ANFIS approach and Gaussian process regression based feature selection strategy , 2018, CSEE Journal of Power and Energy Systems.

[75]  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.

[76]  Haibin Yu,et al.  Day-ahead hourly photovoltaic generation forecasting using extreme learning machine , 2015, 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER).

[77]  Uma Nangia,et al.  A Hybrid Intelligent Approach for Solar Photovoltaic Power Forecasting: Impact of Aerosol Data , 2020, Arabian Journal for Science and Engineering.

[78]  Luca Massidda,et al.  Use of Multilinear Adaptive Regression Splines and numerical weather prediction to forecast the power output of a PV plant in Borkum, Germany , 2017 .

[79]  Lijun Wu,et al.  Hour-ahead photovoltaic power forecast using a hybrid GRA-LSTM model based on multivariate meteorological factors and historical power datasets , 2020, IOP Conference Series: Earth and Environmental Science.

[80]  Hossein Sangrody,et al.  Similarity-Based Models for Day-Ahead Solar PV Generation Forecasting , 2020, IEEE Access.

[81]  Kwang Y. Lee,et al.  An Ensemble Framework for Day-Ahead Forecast of PV Output Power in Smart Grids , 2018, IEEE Transactions on Industrial Informatics.

[82]  Eduardo F. Fernández,et al.  A methodology based on dynamic artificial neural network for short-term forecasting of the power output of a PV generator , 2014 .

[83]  Amit Kumar Yadav,et al.  Identification of relevant input variables for prediction of 1-minute time-step photovoltaic module power using Artificial Neural Network and Multiple Linear Regression Models , 2017 .

[84]  Sumedha Rajakaruna,et al.  Very short-term photovoltaic power forecasting with cloud modeling: A review , 2017 .