Abstract
Precise forecasts of photo-voltaic (PV) energy production are necessary for its planning, utilization and integration into the electrical grid. Intra-day or daily statistical models, using only the latest weather observations and power data measurements, can predict PV power for a plant-specific location and condition on time. Numerical weather prediction (NWP) systems are run every 6 h to produce free prognoses of local cloudiness with a considerable delay and usually not in operational quality. Differential polynomial neural network (D-PNN) is a novel neuro-computing technique able to model complex weather patterns. D-PNN decomposes the n-variable partial differential equation (PDE), allowing complex representation of the near-ground atmospheric dynamics, into a set of 2-input node sub-PDEs. These are converted and substituted using the Laplace transformation according to operational calculus. D-PNN produces applicable PDE components which extend, one by one, its composite models using the selected optimal inputs. The models are developed with historical spatial data from estimated daily training periods for a specific inputs- > output time-shift to predict clear-sky index. Multi-step 1–9 h and one-step 24-h PV power predictions using machine learning and regression are compared to assess the performance of their models for both of the approaches. The presented spatial models obtain a better prediction accuracy than those post-processing NWP data, using a few variables only. The daily statistical models allow prediction of full PVP cycles in one step with an adequate accuracy in the morning and afternoon hours. This is inevitable in management of PV plant energy production and consumption.
Similar content being viewed by others
References
Anastasakis L, Mort N (2001) The development of self-organization techniques in modelling: a review of the group method of data handling (GMDH). The University of Sheffield
Barzegar R, Fijani E, Moghaddama AA, Tziritis E (2017) Forecasting of groundwater level fluctuations using ensemble hybrid multi-wavelet neural network-based models. Sci Total Environ 599:20–31
Chen C, Duan S, Cai T, Liu B (2011) Online 24-h solar power forecasting based on weather type classification using artificial neural network. Sol Energy 85:2856–2870
Coimbra C, Kleissl J, Marquez R (2013) Overview of solar forecasting methods and a metric for accuracy evaluation, pp 171–194. Elsevier
Dong Z, Yang D, Reindl T, Walsh WM (2014) Satellite image analysis and a hybrid esss/ann model to forecast solar irradiance in the tropics. Energy Convers Manag 79:66–73
Pei D, Wang J, Yang W, Niu T (2018) Multi-step ahead forecasting in electrical power system using a hybrid forecasting system. Renew Energy 122:533–550
Foley AM, Leahy PG, Marvuglia A, McKeogh EJ (2012) Current methods and advances in forecasting of wind power generation. Renewable Energy 37:1–8
Geneva N, Zabaras N (2020) Modeling the dynamics of pde systems with physics-constrained deep auto-regressive networks. J Comput Phys 403:1–32
Grazia De Giorgi M, Congedo PM, Malvoni M, Laforgia D (2015) Error analysis of hybrid photovoltaic power forecasting models: a case study of mediterranean climate. Energy Convers Manag 100:117–130
De Grazia De Giorgi M, Malvoni M, Congedo PM (2016) Comparison of strategies for multi-step ahead photovoltaic power forecasting models based on hybrid group method of data handling networks and least square support vector machine. Energy 107:360–373
Leva S, Dolara A, Grimaccia F, Mussetta M, Ogliari E (2016) Analysis and validation of 24 hours ahead neural network forecasting of photovoltaic output power. Math Comput Simul 131:88–100
Liu H, Tian H-Q, Chen C, Li YF (2010) A hybrid statistical method to predict wind speed and wind power. Renew Energy 35:1857–1861
Long H, Zhang Z, Yan S (2014) Analysis of daily solar power prediction with data-driven approaches. Appl Energy 126:29–37
Lorenz E, Hurka J, Heinemann D, Beyer HG (2009) Irradiance forecasting for the power prediction of grid-connected photovoltaic systems. J Select Top Appl Earth Observ Remote Sens 2:2–10
Malvoni M, Grazia De Giorgi M, Congedo PM (2017) Energy procedia. Energy Convers Manag 126:651–658
Meng X, Li Z, Zhang D, Karniadakis G (2020) Parareal physics-informed neural network for time-dependent pdes. Comput Methods Appl Mech Eng 370:1–16
Ma mouna Diagne H, David M, Lauret P, Boland J, Schmutz N (2013) Review of solar irradiance forecasting methods and a proposition for small-scale insular grids. Renew Sustain Energy Rev 27:65–76
Nikolaev NY, Iba H (2006) Adaptive learning of polynomial networks. Genetic and evolutionary computation. Springer, New York
Pelland S, Remund J, Kleissl J, Oozeki T, De Brabandere K (2013) Photovoltaic and solar forecasting: state of the art. Photovoltaic Power Systems Programme. IEA International Energy Agency, Paris
Samaniego E, Anitescu C, Goswami S, Nguyen-Thanh VM, Guo H, Hamdia K, Zhuang X, Rabczuk T (2020) An energy approach to the solution of partial differential equations in computational mechanics via machine learning: concepts, implementation and applications. Comput Methods Appl Mech Eng 362:1–29
Shamim MA, Remesan R, Bray M, Han D (2015) An improved technique for global solar radiation estimation using numerical weather prediction. J Atmos Solar Terr Phys 129:13–22
Shi J, Lee W-J, Liu Y, Yang Y, Wang P (2012) Forecasting power output of photovoltaic systems based on weather classification and support vector machines. IEEE Trans Ind Appl 148:1064–1069
Vannitsem S (2008) Dynamical properties of mos forecasts: analysis of the ecmwf operational forecasting system. Weather Forecast 23:1032–1043
Wan C, Zhao J, Song Y, Zhao X, Lin J, Zechun H (2015) Photovoltaic and solar power forecasting for smart grid energy management. CSEE J Power Energy Syst 1:38–46
Kailiang W, Xiu D (2020) Data-driven deep learning of partial differential equations in modal space. J Comput Phys 408:1–20
Zjavka L (2015) Wind speed forecast correction models using polynomial neural networks. Renew Energy 83:998–1006
Zjavka L (2016) Numerical weather prediction revisions using the locally trained differential polynomial network. Expert Syst Appl 44:265–274
Zjavka L, Krömer P, Mišák S, Snášel V (2017) Modeling the photovoltaic output power using the differential polynomial network and evolutional fuzzy rules. Math Modell Anal 22:78–94
Zjavka L, Pedrycz W (2016) Constructing general partial differential equations using polynomial and neural network. Neural Netw 73:58–69
Zjavka L, Snášel V (2016) Short-term power load forecasting with ordinary differential equation substitutions of polynomial networks. Electric Power Syst Res 137:113–123
Acknowledgements
This work was supported by SGS, VŠB-Technical University of Ostrava, Czech Republic, under the grant No. SP2021/24 “Parallel processing of Big Data VIII”.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zjavka, L. Photo-voltaic power intra-day and daily statistical predictions using sum models composed from L-transformed PDE components in nodes of step by step developed polynomial neural networks. Electr Eng 103, 1183–1197 (2021). https://doi.org/10.1007/s00202-020-01153-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00202-020-01153-w