Skip to main content
SpringerLink
Log in

Accurate four-hour-ahead probabilistic forecast of photovoltaic power generation based on multiple meteorological variables-aided intelligent optimization of numeric weather prediction data

  • RESEARCH
  • Published:
Earth Science Informatics Aims and scope Submit manuscript

Abstract

Accurate four-hour-ahead PV power prediction is crucial to the utilization of PV power. Conventional methods focus on using historical data directly. This paper addresses this issue from a new perspective of Numerical Weather Prediction (NWP) optimization. This paper refers to the predicted PV power given by NWP minus the actual PV power as PV NWP error, analyzes the temporal statistical characteristics of PV NWP error time series through the Ljung-Box test and autocorrelation function, reveals the significant temporal autocorrelation in PV NWP error and verifies the statistical predictability of PV NWP error for the first time. Meanwhile, this paper introduces transfer entropy to verify that introducing multiple meteorological variables including temperature, solar irradiation, clear-sky solar irradiation, cloud thickness, etc. can help predict future PV NWP error better for the first time. Based on the fusion of multiple meteorological variables and artificial neural networks, this paper proposes multiple meteorological variables-aided PV NWP error correction to realize more accurate four-hour-ahead PV power prediction for the first time. Kernel density estimation is used to obtain the probabilistic forecast results. Through experiments in three-year actual data of Brussels, the superiorities of the proposed method and the significant improvement over conventional methods are verified. In comparison to the original NWP method, the proposed approach demonstrates significant improvements in accuracy. Specifically, it achieves a reduction in mean absolute error ranging from 25.04% to 48.12% for 1–4 step predictions, 14.80% to 21.27% for 5–8 step predictions, 6.40% to 11.10% for 9–12 step predictions, and 2.18% to 4.45% for 13–16 step predictions.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Similar content being viewed by others

Data availability

The PV power data can be downloaded from https://www.elia.be/en/grid-data/power-generation/solar-pv-power-generation-data.

References

  • Ahmed R, Sreeram V, Togneri R et al (2022) Computationally expedient Photovoltaic power Forecasting: A LSTM ensemble method augmented with adaptive weighting and data segmentation technique. Energy Convers Manage 258:115563

    Google Scholar 

  • Alharbi FR, Csala D (2022) A Seasonal Autoregressive Integrated Moving Average with Exogenous Factors (SARIMAX) Forecasting Model-Based Time Series Approach. Inventions 7(4):94

    Google Scholar 

  • Amornbunchornvej C, Zheleva E, Berger-Wolf T (2021) Variable-lag granger causality and transfer entropy for time series analysis. ACM Trans Knowl Discov Data (TKDD) 15(4):1–30

    Google Scholar 

  • Aravind A, Srinivas CV, Hegde MN et al (2022) Impact of land surface processes on the simulation of sea breeze circulation and tritium dispersion over the Kaiga complex terrain region near west coast of India using the Weather Research and Forecasting (WRF) model. Atmos Environ X 13:100149

    Google Scholar 

  • Aumann HH, Wilson RC, Geer A et al (2023) Global evaluation of the fidelity of clouds in the ECMWF integrated forecast system. Earth Space Sci 10(5):e2022EA002652

  • Bai M, Liu J, Ma Y et al (2020) Long short-term memory network-based normal pattern group for fault detection of three-shaft marine gas turbine. Energies 14(1):13

    Google Scholar 

  • Bai M, Yang X, Liu J et al (2021) Convolutional neural network-based deep transfer learning for fault detection of gas turbine combustion chambers. Appl Energy 302:117509

    Google Scholar 

  • Bai M, Chen Y, Zhao X et al (2022) Deep attention ConvLSTM-based adaptive fusion of clear-sky physical prior knowledge and multivariable historical information for probabilistic prediction of photovoltaic power. Expert Syst Appl 202:117335

    Google Scholar 

  • Binder W (2022) Technology as (Dis-) Enchantment. AlphaGo and the Meaning-Making of Artificial Intelligence. Cult Sociol 17499755221138720

  • Bosilovich M, Cullather R, National Center for Atmospheric Research Staff (2017) The climate data guide: NASA’s MERRA2 reanalysis. https://climatedataguide.ucar.edu/climate-data/nasas-merra2-reanalysis. Accessed 1 Jan 2023

  • Brockwell PJ, Davis RA (2016) Introduction to time series and forecasting. Springer

  • Cao Z, Xu Q, Zhang DL (2023) Impact of cyclone‐cyclone interaction on lake‐effect snowbands: a false alarm. J Geophys Res Atmos 128(2):e2022JD037064

  • Chen Z, Han F, Wu L et al (2018) Random forest based intelligent fault diagnosis for PV arrays using array voltage and string currents. Energy Convers Manage 178:250–264

    Google Scholar 

  • Dowling M, Lucey B (2023) ChatGPT for (finance) research: the Bananarama conjecture. Finan Res Lett 53:103662

  • Enders W (2008) Applied econometric time series. John Wiley & Sons

  • Fang H, Li J, Song W (2018) Sustainable site selection for photovoltaic power plant: An integrated approach based on prospect theory. Energy Convers Manage 174:755–768

    Google Scholar 

  • Gungor O, Rosing T, Aksanli B (2022) STEWART: STacking Ensemble for White-Box AdversaRial Attacks Towards more resilient data-driven predictive maintenance. Comput Ind 140:103660

    Google Scholar 

  • Hassani H, Yeganegi MR (2019) Sum of squared ACF and the Ljung-Box statistics. Physica A 520:81–86

    Google Scholar 

  • Hlavácková-Schindler K (2011) Equivalence of granger causality and transfer entropy: A generalization. Appl Math Sci 5(73):3637–3648

    Google Scholar 

  • Huang GB, Zhu QY, Siew CK (2004) Extreme learning machine: a new learning scheme of feedforward neural networks. Neural Netw 2:985–990

    Google Scholar 

  • Jimenez PA, Hacker JP, Dudhia J et al (2016) WRF-Solar: Description and clear-sky assessment of an augmented NWP model for solar power prediction. Bull Am Meteor Soc 97(7):1249–1264

    Google Scholar 

  • Lam R, Sanchez-Gonzalez A, Willson M et al (2022) GraphCast: Learning skillful medium-range global weather forecasting[J]. arXiv preprint arXiv:2212.12794

  • Lee T (2022) Wild bootstrap Ljung–Box test for residuals of ARMA models robust to variance change. J Korean Stat Soc 1–16

  • Li Y, Su Y, Shu L (2014) An ARMAX model for forecasting the power output of a grid connected photovoltaic system. Renew Energy 66:78–89

    Google Scholar 

  • Li X, Ma L, Chen P et al (2022) Probabilistic solar irradiance forecasting based on XGBoost. Energy Rep 8:1087–1095

    Google Scholar 

  • Lichiheb N, Hicks BB, Myles LT (2023) An evaluation of meteorological data prediction over Washington, DC: Comparison of DCNet observations and NAM model outputs. Urban Climate 48:101410

    Google Scholar 

  • Lima MAFB, Fernández Ramírez LM, Carvalho PCM et al (2022) A comparison between deep learning and support vector regression techniques applied to solar forecast in Spain. J SolEnergy Eng 144(1):010802

    Google Scholar 

  • Liu J, Bai M, Jiang N et al (2019) A novel measure of attribute significance with complexity weight. Appl Soft Comput 82:105543

    Google Scholar 

  • Liu J, Bai M, Jiang N et al (2020) Structural risk minimization of rough set-based classifier. Soft Comput 24(3):2049–2066

    Google Scholar 

  • Liu J, Bai M, Jiang N et al (2021) Interclass interference suppression in multi-class problems. Appl Sci 11(1):450

    Google Scholar 

  • Liu Z, Li P, Wei D et al (2023) Forecasting system with sub-model selection strategy for photovoltaic power output forecasting. Earth Sci Inform 16(1):287–313

  • Loh WY (2014) Classification and regression tree methods. Int Stat Rev 82(3):329–348

  • Lord SJ, Wu X, Tallapragada V et al (2023) The Impact of Dropsonde Data on the Performance of the NCEP Global Forecast System during the 2020 Atmospheric Rivers Observing Campaign. Part I: Precipitation. Weather Forecast 38(1):17–45

    Google Scholar 

  • Lundstrom L (2016) camsRad: Client for CAMS Radiation Service, R package version 0.3.0

  • Mansoury I, El Bourakadi D, Yahyaouy A et al (2022) Hourly Solar Power Forecasting Using Optimized Extreme Learning Machine[M]//Digital Technologies and Applications: Proceedings of ICDTA’22, Fez, Morocco, Volume 2. Cham: Springer International Publishing, 629–637

  • Mayer MJ (2022) Benefits of physical and machine learning hybridization for photovoltaic power forecasting. Renew Sustain Energy Rev 168:112772

    Google Scholar 

  • Okoro EE, Obomanu T, Sanni SE et al (2022) Application of artificial intelligence in predicting the dynamics of bottom hole pressure for under-balanced drilling: extra tree compared with feed forward neural network model. Petroleum 8(2):227–236

    Google Scholar 

  • Omer ZM, Shareef H (2022) Comparison of decision tree based ensemble methods for prediction of photovoltaic maximum current. Energy Convers Manag X 16:100333

    Google Scholar 

  • Orcellet EE, Villanova M, Noir JO et al (2022) Atmospheric dispersion of hydrogen sulfide using a modified ARPS model: a case study. Ecotoxicol Environ Contam 17(1):93–105

  • Pathak J, Subramanian S, Harrington P et al (2022) Fourcastnet: A global data-driven high-resolution weather model using adaptive fourier neural operators. arXiv preprint arXiv:2202.11214

  • Qin J, Jiang H, Lu N et al (2022) Enhancing solar PV output forecast by integrating ground and satellite observations with deep learning. Renew Sustain Energy Rev 167:112680

    Google Scholar 

  • Shan S, Li C, Ding Z et al (2022) Ensemble learning based multi-modal intra-hour irradiance forecasting. Energy Convers Manage 270:116206

    Google Scholar 

  • Smola AJ, Schölkopf B (2004) A tutorial on support vector regression. Stat Comput 14(3):199–222

    Google Scholar 

  • Sun R, Wang G, Zhang W et al (2020) A gradient boosting decision tree based GPS signal reception classification algorithm. Appl Soft Comput 86:105942

    Google Scholar 

  • Wang F, Lu X, Mei S et al (2022a) A satellite image data based ultra-short-term solar PV power forecasting method considering cloud information from neighboring plant. Energy 238:121946

    Google Scholar 

  • Wang W, Yang D, Hong T et al (2022b) An archived dataset from the ECMWF Ensemble Prediction System for probabilistic solar power forecasting. Sol Energy 248:64–75

    Google Scholar 

  • Wang W, Yang D, Huang N et al (2022c) Irradiance-to-power conversion based on physical model chain: An application on the optimal configuration of multi-energy microgrid in cold climate. Renew Sustain Energy Rev 161:112356

    Google Scholar 

  • Xiao B, Zhu H, Zhang S et al (2022) Gray-related support vector machine optimization strategy and its implementation in forecasting photovoltaic output power. Int J Photoenergy 2022:1–9

  • Xu W, Ning L, Luo Y (2020) Wind speed forecast based on post-processing of numerical weather predictions using a gradient boosting decision tree algorithm. Atmosphere 11(7):738

    Google Scholar 

  • Yang D, Dong Z (2018) Operational photovoltaics power forecasting using seasonal time series ensemble. Sol Energy 166:529–541

    Google Scholar 

  • Yang D, Kleissl J, Gueymard CA et al (2018) History and trends in solar irradiance and PV power forecasting: A preliminary assessment and review using text mining. Sol Energy 168:60–101

    Google Scholar 

  • Yang X, Bai M, Liu J et al (2021) Gas path fault diagnosis for gas turbine group based on deep transfer learning. Measurement 181:109631

    Google Scholar 

  • Yang D, Wang W, Xia X (2022a) A concise overview on solar resource assessment and forecasting. Adv Atmos Sci 39(8):1239–1251

    Google Scholar 

  • Yang D, Wang W, Gueymard CA et al (2022b) A review of solar forecasting, its dependence on atmospheric sciences and implications for grid integration: Towards carbon neutrality. Renew Sustain Energy Rev 161:112348

    Google Scholar 

  • Yang D, Wang W, Hong T (2022c) A historical weather forecast dataset from the European Centre for Medium-Range Weather Forecasts (ECMWF) for energy forecasting. Sol Energy 232:263–274

    Google Scholar 

  • Yang D, Wang W, Bright JM et al (2022d) Verifying operational intra-day solar forecasts from ECMWF and NOAA. Sol Energy 236:743–755

    Google Scholar 

  • Yang D (2019) A guideline to solar forecasting research practice: reproducible, operational, probabilistic or physically-based, ensemble, and skill (ROPES). J Renew Sustain Energy 11(2):1–20

  • Yu T, Huo Y (2022) Complexity analysis of consumer finance following computer LightGBM algorithm under industrial economy. Mob Inf Syst 2022:1–9

  • Zhao X, Liu J, Yu D et al (2018) One-day-ahead probabilistic wind speed forecast based on optimized numerical weather prediction data. Energy Convers Manage 164:560–569

    Google Scholar 

  • Zhao X, Bai M, Yang X et al (2021) Short-term probabilistic predictions of wind multi-parameter based on one-dimensional convolutional neural network with attention mechanism and multivariate copula distribution estimation. Energy 234:121306

    Google Scholar 

  • Zhou Y, Liu Y, Wang D et al (2021) A review on global solar radiation prediction with machine learning models in a comprehensive perspective. Energy Convers Manage 235:113960

    Google Scholar 

  • Zhou G, Bai M, Zhao X et al (2022a) Study on the distribution characteristics and uncertainty of multiple energy load patterns for building group to enhance demand side management. Energy Build 263:112038

    Google Scholar 

  • Zhou Y, Wang J, Li Z et al (2022b) Short-term photovoltaic power forecasting based on signal decomposition and machine learning optimization. Energy Convers Manage 267:115944

    Google Scholar 

Download references

Funding

This research was supported by the National Key R&D Program of China No. 2017YFB0902100.

Author information

Authors and Affiliations

  1. Harbin Institute of Technology, Harbin, 150001, Heilongjiang, China

    Mingliang Bai, Zhihao Zhou, Yunxiao Chen, Jinfu Liu & Daren Yu

Authors
  1. Mingliang Bai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhihao Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yunxiao Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jinfu Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Daren Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Mingliang Bai: Software, Conceptualization, Writing- Original draft preparation.

Zhihao Zhou: Software, Methodology.

Yunxiao Chen: Software, Methodology.

Jinfu Liu: Supervision, Conceptualization.

Daren Yu: Supervision, Conceptualization.

Corresponding author

Correspondence to Jinfu Liu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Communicated by: H. Babaie

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bai, M., Zhou, Z., Chen, Y. et al. Accurate four-hour-ahead probabilistic forecast of photovoltaic power generation based on multiple meteorological variables-aided intelligent optimization of numeric weather prediction data. Earth Sci Inform 16, 2741–2766 (2023). https://doi.org/10.1007/s12145-023-01066-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12145-023-01066-9

Keywords

Search

Navigation