A one-day-ahead photovoltaic array power production prediction with combined static and dynamic on-line correction

Abstract In this paper we develop and verify a predictor-corrector method for a one-day-ahead photovoltaic array power production prediction. The most critical inputs to the prediction model are predictions of meteorological variables, such as solar irradiance components and the air temperature, which are the main sources of the power prediction uncertainty. Through a straightforward application of the weather forecast data sequence, photovoltaic array power production prediction is refreshed with the frequency of new forecasts generation by the meteorological service. We show that the prediction sequence quality can be significantly improved by using a neural-network-based corrector which takes into account near-history realizations of the prediction error. In this way it is possible to refresh the prediction sequence as soon as new local measurements become available. Except for predictions of meteorological variables, the prediction model itself is also a source of the prediction uncertainty, which is also taken into account by the proposed approach. The proposed predictor-corrector method is verified on real data over a 2-year time period. It is shown that the proposed approach can reduce the standard deviation of the power production prediction error up to 50%, but only for the first several instances of the prediction sequence (up to 6–8 h ahead) which are in turn the most relevant for real-time operation of predictive control systems that use the photovoltaic array power production prediction, like microgrid energy flows control or distribution network regulation.

[1]  Mato Baotic,et al.  Analysis of microgrid power flow optimization with consideration of residual storages state , 2015, 2015 European Control Conference (ECC).

[2]  Danijel Pavković,et al.  A design of cascade control system and adaptive load compensator for battery/ultracapacitor hybrid energy storage-based direct current microgrid , 2016 .

[3]  Dezso Sera,et al.  Diagnostic method for photovoltaic systems based on light I-V measurements , 2015 .

[4]  J. de la Casa,et al.  Passive Monitoring of the Power Generated in Grid Connected PV Systems. , 2014 .

[5]  Syafrudin Masri,et al.  Challenges of integrating renewable energy sources to smart grids: A review , 2015 .

[6]  Mario Vasak,et al.  Multi-level optimal control of a microgrid-supplied cooling system in a building , 2016, 2016 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe).

[7]  Evangelos Rikos,et al.  A Model Predictive Control Approach to Microgrid Operation Optimization , 2014, IEEE Transactions on Control Systems Technology.

[8]  Matteo De Felice,et al.  Short-Term Predictability of Photovoltaic Production over Italy , 2014, ArXiv.

[9]  John Boland,et al.  Evaluating tilted plane models for solar radiation using comprehensive testing procedures, at a southern hemisphere location , 2013 .

[10]  Mario Vasak,et al.  Load forecast of a university building for application in microgrid power flow optimization , 2014, 2014 IEEE International Energy Conference (ENERGYCON).

[11]  Federico Bizzarri,et al.  Monitoring performance and efficiency of photovoltaic parks , 2015 .

[12]  Alica Bajić,et al.  Forecasting Weather in Croatia Using ALADIN Numerical Weather Prediction Model , 2013 .

[13]  Mario Vasak,et al.  Stochastic model predictive control for optimal economic operation of a residential DC microgrid , 2015, 2015 IEEE International Conference on Industrial Technology (ICIT).

[14]  Maria Grazia De Giorgi,et al.  Error analysis of hybrid photovoltaic power forecasting models: A case study of mediterranean climate , 2015 .

[15]  Wencong Su,et al.  Stochastic Energy Scheduling in Microgrids With Intermittent Renewable Energy Resources , 2014, IEEE Transactions on Smart Grid.

[16]  Eleni Kaplani,et al.  Thermal modelling and experimental assessment of the dependence of PV module temperature on wind velocity and direction, module orientation and inclination , 2014 .

[17]  Mario Vasak,et al.  Photovoltaic panel and array static models for power production prediction: Integration of manufacturers' and on-line data , 2016 .

[19]  Xiangning Xiao,et al.  A modeling method for photovoltaic cells using explicit equations and optimization algorithm , 2014 .

[20]  A. D. Jones,et al.  A thermal model for photovoltaic systems , 2001 .

[21]  Javier Serrano González,et al.  A review of regulatory framework for wind energy in European Union countries: Current state and expected developments , 2016 .

[22]  Jun-Young Park,et al.  A novel datasheet-based parameter extraction method for a single-diode photovoltaic array model , 2015 .

[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]  J. Hay.  Calculation of monthly mean solar radiation for horizontal and inclined surfaces , 1979 .

[25]  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.

[26]  Adel Mellit,et al.  Short-term forecasting of power production in a large-scale photovoltaic plant , 2014 .

[27]  M. Do,et al.  A robust forecasting framework based on the Kalman filtering approach with a twofold parameter tuning procedure: Application to solar and photovoltaic prediction , 2016 .

[28]  Mario Vasak,et al.  Meteorological and weather forecast data-based prediction of electrical power delivery of a photovoltaic panel in a stochastic framework , 2011, 2011 Proceedings of the 34th International Convention MIPRO.

[29]  I. Reda,et al.  Solar position algorithm for solar radiation applications , 2004 .

[30]  B. Hodge,et al.  The value of day-ahead solar power forecasting improvement , 2016 .

[31]  Danijel Pavković,et al.  A methodology for normal distribution-based statistical characterization of long-term insolation by means of historical data , 2015 .

[32]  Asher Tishler,et al.  Can price volatility enhance market power? The case of renewable technologies in competitive electricity markets , 2015 .

[33]  David Hyman Gordon,et al.  Renewable Energy Resources , 1986 .

[34]  O. Perpiñán,et al.  PV power forecast using a nonparametric PV model , 2015 .

[35]  Trine Krogh Boomsma,et al.  Impact of forecast errors on expansion planning of power systems with a renewables target , 2014, Eur. J. Oper. Res..

[36]  M. Journée,et al.  Evaluation of different models to estimate the global solar radiation on inclined surfaces , 2013 .

[37]  Ju Lee,et al.  AC-microgrids versus DC-microgrids with distributed energy resources: A review , 2013 .

[38]  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 .

[39]  Nezihe Yıldıran,et al.  Identification of photovoltaic cell single diode discrete model parameters based on datasheet values , 2016 .

[40]  Mario Vasak,et al.  Dynamical optimal positioning of a photovoltaic panel in all weather conditions , 2013 .

[41]  Diego Torres-Lobera,et al.  Inclusive dynamic thermal and electric simulation model of solar PV systems under varying atmospheric conditions , 2014 .

[42]  H. Troy Nagle,et al.  Performance of the Levenberg–Marquardt neural network training method in electronic nose applications , 2005 .

[43]  Jianzhou Wang,et al.  A novel hybrid model based on artificial neural networks for solar radiation prediction , 2016 .