Direct Short-Term Forecast of Photovoltaic Power through a Comparative Study between COMS and Himawari-8 Meteorological Satellite Images in a Deep Neural Network

Meteorological satellite images provide crucial information on solar irradiation and weather conditions at spatial and temporal resolutions which are ideal for short-term photovoltaic (PV) power forecasts. Following the introduction of next-generation meteorological satellites, investigating their application on PV forecasts has become imminent. In this study, Communications, Oceans, and Meteorological Satellite (COMS) and Himawari-8 (H8) satellite images were inputted in a deep neural network (DNN) model for 2 hour (h)- and 1 h-ahead PV forecasts. A one-year PV power dataset acquired from two solar power test sites in Korea was used to directly forecast PV power. H8 was used as a proxy for GEO-KOMPSAT-2A (GK2A), the next-generation satellite after COMS, considering their similar resolutions, overlapping geographic coverage, and data availability. In addition, two different data sampling setups were designed to implement the input dataset. The first setup sampled chronologically ordered data using a relatively more inclusive time frame (6 a.m. to 8 p.m. in local time) to create a two-month test dataset, whereas the second setup randomly sampled 25% of data from each month from the one-year input dataset. Regardless of the setup, the DNN model generated superior forecast performance, as indicated by the lowest normalized mean absolute error (NMAE) and normalized root mean squared error (NRMSE) results in comparison to that of the support vector machine (SVM) and artificial neural network (ANN) models. The first setup results revealed that the visible (VIS) band yielded lower NMAE and NRMSE values, while COMS was found to be more influential for 1 h-ahead forecasts. For the second setup, however, the difference in NMAE results between COMS and H8 was not significant enough to distinguish a clear edge in performance. Nevertheless, this marginal difference and similarity of the results suggest that both satellite datasets can be used effectively for direct short-term PV forecasts. Ultimately, the comparative study between satellite datasets as well as spectral bands, time frames, forecast horizons, and forecast models confirms the superiority of the DNN and offers insights on the potential of transitioning to applying GK2A for future PV forecasts.

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

[2]  Mihai Anitescu,et al.  Data-driven model for solar irradiation based on satellite observations , 2014 .

[3]  Clifford W. Hansen,et al.  Pvlib Python: a Python Package for Modeling Solar Energy Systems , 2018, J. Open Source Softw..

[4]  Sameer Al-Dahidi,et al.  Ensemble Approach of Optimized Artificial Neural Networks for Solar Photovoltaic Power Prediction , 2019, IEEE Access.

[5]  M. Nunez,et al.  Development of a method for generating operational solar radiation maps from satellite data for a tropical environment , 2005 .

[6]  A. Hammer,et al.  Short-term forecasting of solar radiation: a statistical approach using satellite data , 1999 .

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

[8]  Hou Jiang,et al.  A deep learning algorithm to estimate hourly global solar radiation from geostationary satellite data , 2019, Renewable and Sustainable Energy Reviews.

[9]  Choi Won Seok,et al.  Solar Irradiance Estimation in Korea by Using Modified Heliosat-II Method and COMS-MI Imagery , 2015 .

[10]  Henrik Madsen,et al.  Online short-term solar power forecasting , 2009 .

[11]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[12]  Michel Journée,et al.  Improving the spatio-temporal distribution of surface solar radiation data by merging ground and satellite measurements , 2010 .

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Dan Keun Sung,et al.  Solar Power Prediction Based on Satellite Images and Support Vector Machine , 2016, IEEE Transactions on Sustainable Energy.

[15]  J. Kleissl,et al.  Cloud motion vectors from a network of ground sensors in a solar power plant , 2013 .

[16]  Blazej Olek,et al.  Review of the methods for evaluation of renewable energy sources penetration and ramping used in the Scenario Outlook and Adequacy Forecast 2015. Case study for Poland , 2017 .

[17]  Andreas Kazantzidis,et al.  Short-term cloudiness forecasting for solar energy purposes in Greece, based on satellite-derived information , 2019, Meteorology and Atmospheric Physics.

[18]  Terrence L. Chambers,et al.  Hour-Ahead Solar Irradiance Forecasting Using Multivariate Gated Recurrent Units , 2019, Energies.

[19]  Kyu-Tae Lee,et al.  Development of GWNU (Gangneung-Wonju National University) one-layer transfer model for calculation of solar radiation distribution of the Korean peninsula , 2014, Asia-Pacific Journal of Atmospheric Sciences.

[20]  Carlos F.M. Coimbra,et al.  Short-term reforecasting of power output from a 48 MWe solar PV plant , 2015 .

[21]  Saad Mekhilef,et al.  Application of extreme learning machine for short term output power forecasting of three grid-connected PV systems , 2017 .

[22]  Carlos F.M. Coimbra,et al.  Hybrid solar forecasting method uses satellite imaging and ground telemetry as inputs to ANNs , 2013 .

[23]  Olivier Pannekoucke,et al.  A benchmark of statistical regression methods for short-term forecasting of photovoltaic electricity production, part I: Deterministic forecast of hourly production , 2014 .

[24]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

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

[26]  Stefan Lessmann,et al.  A comparative study of LSTM neural networks in forecasting day-ahead global horizontal irradiance with satellite data , 2018 .

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

[28]  Oliver Kramer,et al.  Comparing support vector regression for PV power forecasting to a physical modeling approach using measurement, numerical weather prediction, and cloud motion data , 2016 .

[29]  Ahmet Teke,et al.  Evaluation and performance comparison of different models for the estimation of solar radiation , 2015 .

[30]  Hyeong-Dong Park,et al.  Estimation and Mapping of Solar Irradiance for Korea by Using COMS MI Satellite Images and an Artificial Neural Network Model , 2020, Energies.

[31]  Bart De Schutter,et al.  Short-term forecasting of solar irradiance without local telemetry: a generalized model using satellite data , 2018, Solar Energy.

[32]  M. Diagne,et al.  Review of solar irradiance forecasting methods and a proposition for small-scale insular grids , 2013 .

[33]  Dipti Srinivasan,et al.  Automatic hourly solar forecasting using machine learning models , 2019, Renewable and Sustainable Energy Reviews.

[34]  Jin-Young Kim,et al.  Spatial Assessment of Solar Radiation by Machine Learning and Deep Neural Network Models Using Data Provided by the COMS MI Geostationary Satellite: A Case Study in South Korea , 2019, Sensors.

[35]  John Byrne,et al.  The rise and fall of green growth: Korea's energy sector experiment and its lessons for sustainable energy policy , 2019, WIREs Energy and Environment.

[36]  A. Mellit,et al.  Day-Ahead Photovoltaic Forecasting: A Comparison of the Most Effective Techniques , 2019, Energies.

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

[38]  Myoung-Seok Suh,et al.  Development of Himawari-8/Advanced Himawari Imager (AHI) Land Surface Temperature Retrieval Algorithm , 2018, Remote. Sens..

[39]  Mohammed H. Alsharif,et al.  Opportunities and Challenges of Solar and Wind Energy in South Korea: A Review , 2018, Sustainability.

[40]  Carlos F.M. Coimbra,et al.  Direct Power Output Forecasts From Remote Sensing Image Processing , 2018 .

[41]  Andreas Kazantzidis,et al.  Retrieval of surface solar irradiance, based on satellite-derived cloud information, in Greece , 2015 .

[42]  Jin Hur,et al.  Probabilistic Forecasting Model of Solar Power Outputs Based on the Naïve Bayes Classifier and Kriging Models , 2018, Energies.

[43]  Kwon-Ho Lee,et al.  Development of GK-2A AMI Aerosol Detection Algorithm in the East-Asia Region Using Himawari-8 AHI Data , 2019, Asia-Pacific Journal of Atmospheric Sciences.

[44]  J. Kleissl,et al.  Embedded nowcasting method using cloud speed persistence for a photovoltaic power plant , 2015 .