A TCN-Based Hybrid Forecasting Framework for Hours-Ahead Utility-Scale PV Forecasting

Li, Yiyan; Song, Lidong; Zhang, Si; Kraus, Laura; Adcox, Taylor; Willardson, Roger; Komandur, Abhishek; Lu, Ning

doi:10.1109/tsg.2023.3236992

A TCN-Based Hybrid Forecasting Framework for Hours-Ahead Utility-Scale PV Forecasting

Journal Article · Sun Jan 15 23:00:00 EST 2023 · IEEE Transactions on Smart Grid

DOI:https://doi.org/10.1109/tsg.2023.3236992· OSTI ID:2329476

^[1]; ^[2]; Zhang, Si ^[2]; Kraus, Laura ^[3]; Adcox, Taylor ^[3]; Willardson, Roger ^[3]; ^[3]; ^[2]

Shanghai Jiao Tong University (China); North Carolina State University, Raleigh, NC (United States); North Carolina State University
North Carolina State University, Raleigh, NC (United States)
Strata Clean Energy, Durham, NC (United States)

This paper presents a Temporal Convolutional Network (TCN) based hybrid PV forecasting framework for enhancing hours-ahead utility-scale PV forecasting. The hybrid framework consists of two forecasting models: a physics-based trend forecasting (TF) model and a data-driven fluctuation forecasting (FF) model. Three TCNs are integrated in the framework for: i) blending the inputs from different Numerical Weather Prediction sources for the TF model to achieve superior performance on forecasting hourly PV profiles, ii) capturing spatial-temporal correlations between detector sites and the target site in the FF model to achieve more accurate forecast of intra- hour PV power drops, and iii) reconciling TF and FF results to obtain coherent hours-ahead PV forecast with both hourly trends and intra-hour fluctuations well preserved. To automatically identify the most contributive neighboring sites for forming a detector network, a scenario-based correlation analysis method is developed, which significantly improves the capability of the FF model on capturing large power fluctuations caused by cloud movements. Here, the framework is developed, tested, and validated using actual PV data collected from 95 PV farms in North Carolina. Simulation results show that the performance of 6 hours ahead PV power forecasting is improved by 20% - 30% compared with state-of-the-art methods.

View Accepted Manuscript (DOE)

Research Organization:: North Carolina State University, Raleigh, NC (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office

Grant/Contract Number:: EE0008770

OSTI ID:: 2329476

Journal Information:: IEEE Transactions on Smart Grid, Journal Name: IEEE Transactions on Smart Grid Journal Issue: 5 Vol. 14; ISSN 1949-3053

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (31)

A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network Wang, Kejun; Qi, Xiaoxia; Liu, Hongda Applied Energy, Vol. 251 https://doi.org/10.1016/j.apenergy.2019.113315	journal	October 2019
Ensemble spatiotemporal forecasting of solar irradiation using variational Bayesian convolutional gate recurrent unit network Liu, Yongqi; Qin, Hui; Zhang, Zhendong Applied Energy, Vol. 253 https://doi.org/10.1016/j.apenergy.2019.113596	journal	November 2019
Cross-temporal aggregation: Improving the forecast accuracy of hierarchical electricity consumption Spiliotis, Evangelos; Petropoulos, Fotios; Kourentzes, Nikolaos Applied Energy, Vol. 261 https://doi.org/10.1016/j.apenergy.2019.114339	journal	March 2020
Hierarchical forecast reconciliation with machine learning Spiliotis, Evangelos; Abolghasemi, Mahdi; Hyndman, Rob J. Applied Soft Computing, Vol. 112 https://doi.org/10.1016/j.asoc.2021.107756	journal	November 2021
Load and Renewable Energy Forecasting for a Microgrid using Persistence Technique Dutta, Shreya; Li, Yanling; Venkataraman, Aditya Energy Procedia, Vol. 143 https://doi.org/10.1016/j.egypro.2017.12.736	journal	December 2017
Forecasting with temporal hierarchies Athanasopoulos, George; Hyndman, Rob J.; Kourentzes, Nikolaos European Journal of Operational Research, Vol. 262, Issue 1 https://doi.org/10.1016/j.ejor.2017.02.046	journal	October 2017
A machine learning approach for forecasting hierarchical time series Mancuso, Paolo; Piccialli, Veronica; Sudoso, Antonio M. Expert Systems with Applications, Vol. 182 https://doi.org/10.1016/j.eswa.2021.115102	journal	November 2021
Probabilistic solar power forecasting in smart grids using distributed information Bessa, R. J.; Trindade, A.; Silva, Cátia S. P. International Journal of Electrical Power & Energy Systems, Vol. 72 https://doi.org/10.1016/j.ijepes.2015.02.006	journal	November 2015
Solar irradiance forecasting using spatial-temporal covariance structures and time-forward kriging Yang, Dazhi; Gu, Chaojun; Dong, Zibo Renewable Energy, Vol. 60 https://doi.org/10.1016/j.renene.2013.05.030	journal	December 2013
On the role of lagged exogenous variables and spatio–temporal correlations in improving the accuracy of solar forecasting methods Zagouras, Athanassios; Pedro, Hugo T. C.; Coimbra, Carlos F. M. Renewable Energy, Vol. 78 https://doi.org/10.1016/j.renene.2014.12.071	journal	June 2015
An artificial neural network to assess the impact of neighbouring photovoltaic systems in power forecasting in Utrecht, the Netherlands Vaz, A. G. R.; Elsinga, B.; van Sark, W. G. J. H. M. Renewable Energy, Vol. 85 https://doi.org/10.1016/j.renene.2015.06.061	journal	January 2016
Short-term global horizontal irradiance forecasting based on a hybrid CNN-LSTM model with spatiotemporal correlations Zang, Haixiang; Liu, Ling; Sun, Li Renewable Energy, Vol. 160 https://doi.org/10.1016/j.renene.2020.05.150	journal	November 2020
Forecasting of photovoltaic power generation and model optimization: A review Das, Utpal Kumar; Tey, Kok Soon; Seyedmahmoudian, Mehdi Renewable and Sustainable Energy Reviews, Vol. 81 https://doi.org/10.1016/j.rser.2017.08.017	journal	January 2018
A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization Ahmed, R.; Sreeram, V.; Mishra, Y. Renewable and Sustainable Energy Reviews, Vol. 124 https://doi.org/10.1016/j.rser.2020.109792	journal	May 2020
Review of photovoltaic power forecasting Antonanzas, J.; Osorio, N.; Escobar, R. Solar Energy, Vol. 136 https://doi.org/10.1016/j.solener.2016.06.069	journal	October 2016
Experimental comparison of pyranometer, reflectometer, and spectrophotometer methods for the measurement of roofing product albedo Levinson, Ronnen; Egolf, Mischa; Chen, Sharon Solar Energy, Vol. 206 https://doi.org/10.1016/j.solener.2019.11.103	journal	August 2020
Short-term solar PV forecasting using computer vision: The search for optimal CNN architectures for incorporating sky images and PV generation history Venugopal, Vignesh; Sun, Yuchi; Brandt, Adam R. Journal of Renewable and Sustainable Energy, Vol. 11, Issue 6 https://doi.org/10.1063/1.5122796	journal	November 2019
Comparison of SARIMAX, SARIMA, modified SARIMA and ANN-based models for short-term PV generation forecasting Vagropoulos, Stylianos I.; Chouliaras, G. I.; Kardakos, E. G. 2016 IEEE International Energy Conference (ENERGYCON) https://doi.org/10.1109/ENERGYCON.2016.7514029	conference	April 2016
Irradiance Forecasting for the Power Prediction of Grid-Connected Photovoltaic Systems Lorenz, Elke; Hurka, Johannes; Heinemann, Detlev IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 2, Issue 1, p. 2-10 https://doi.org/10.1109/JSTARS.2009.2020300	journal	March 2009
Data-Driven Photovoltaic Generation Forecasting Based on a Bayesian Network With Spatial–Temporal Correlation Analysis Zhang, Ruiyuan; Ma, Hui; Hua, Wen IEEE Transactions on Industrial Informatics, Vol. 16, Issue 3 https://doi.org/10.1109/TII.2019.2925018	journal	March 2020
Deep Learning Based Multistep Solar Forecasting for PV Ramp-Rate Control Using Sky Images Wen, Haoran; Du, Yang; Chen, Xiaoyang IEEE Transactions on Industrial Informatics, Vol. 17, Issue 2 https://doi.org/10.1109/TII.2020.2987916	journal	February 2021
Least Squares-based Optimal Reconciliation Method for Hierarchical Forecasts of Wind Power Generation Zhang, Yao; Dong, Jiaojiao IEEE Transactions on Power Systems https://doi.org/10.1109/TPWRS.2018.2868175	journal	January 2024
Multitime-Scale Data-Driven Spatio-Temporal Forecast of Photovoltaic Generation Yang, Chen; Thatte, Anupam A.; Xie, Le IEEE Transactions on Sustainable Energy, Vol. 6, Issue 1 https://doi.org/10.1109/TSTE.2014.2359974	journal	January 2015
Compressive Spatio-Temporal Forecasting of Meteorological Quantities and Photovoltaic Power Tascikaraoglu, Akin; Sanandaji, Borhan M.; Chicco, Gianfranco IEEE Transactions on Sustainable Energy, Vol. 7, Issue 3 https://doi.org/10.1109/TSTE.2016.2544929	journal	July 2016
Short-Term Spatio-Temporal Forecasting of Photovoltaic Power Production Agoua, Xwegnon Ghislain; Girard, Robin; Kariniotakis, George IEEE Transactions on Sustainable Energy, Vol. 9, Issue 2 https://doi.org/10.1109/TSTE.2017.2747765	journal	April 2018
Probabilistic Solar Power Forecasting Based on Bivariate Conditional Solar Irradiation Distributions Kim, Hyeonjin; Lee, Duehee IEEE Transactions on Sustainable Energy, Vol. 12, Issue 4 https://doi.org/10.1109/TSTE.2021.3077001	journal	October 2021
Spatio-Temporal Graph Neural Networks for Multi-Site PV Power Forecasting Simeunovic, Jelena; Schubnel, Baptiste; Alet, Pierre-Jean IEEE Transactions on Sustainable Energy, Vol. 13, Issue 2 https://doi.org/10.1109/TSTE.2021.3125200	journal	April 2022
pvlib python: a python package for modeling solar energy systems F. Holmgren, William; W. Hansen, Clifford; A. Mikofski, Mark Journal of Open Source Software, Vol. 3, Issue 29 https://doi.org/10.21105/joss.00884	journal	September 2018
Temporal Convolutional Networks Applied to Energy-Related Time Series Forecasting Lara-Benítez, Pedro; Carranza-García, Manuel; Luna-Romera, José M. Applied Sciences, Vol. 10, Issue 7 https://doi.org/10.3390/app10072322	journal	March 2020
Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting Wan, Renzhuo; Mei, Shuping; Wang, Jun Electronics, Vol. 8, Issue 8 https://doi.org/10.3390/electronics8080876	journal	August 2019
Multi-Site Photovoltaic Forecasting Exploiting Space-Time Convolutional Neural Network Jeong, Jaeik; Kim, Hongseok Energies, Vol. 12, Issue 23 https://doi.org/10.3390/en12234490	journal	November 2019

Similar Records

Intra-Hour Dispatch and Automatic Generator Control Demonstration with Solar Forecasting - Final Report

Technical Report · Wed Feb 24 23:00:00 EST 2016 · OSTI ID:1245475

Convolutional neural networks for intra-hour solar forecasting based on sky image sequences

Journal Article · Fri Jan 28 23:00:00 EST 2022 · Applied Energy · OSTI ID:1845678

Probabilistic Day-Ahead Forecasting Using an Analog Ensemble Approach for Wind Farm Grid Services

Conference · Fri Sep 24 00:00:00 EDT 2021 · OSTI ID:1823425

Related Subjects

42 ENGINEERING
Detector network
NWP blending
neighbor selection
physics-based model
short-term PV forecast
spatial-temporal forecasting
temporal convolutional network

A TCN-Based Hybrid Forecasting Framework for Hours-Ahead Utility-Scale PV Forecasting

Citation Formats

References (31)

Similar Records

Related Subjects