CFP last date
22 July 2024
Reseach Article

Short-Term Forecasting of Solar Irradiance using STL, Wavelet and LSTM

by Vivek Vijay, Rakesh Kumar, Ashish Sharma, Abhishek Kumar
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 183 - Number 46
Year of Publication: 2022
Authors: Vivek Vijay, Rakesh Kumar, Ashish Sharma, Abhishek Kumar
10.5120/ijca2022921829

Vivek Vijay, Rakesh Kumar, Ashish Sharma, Abhishek Kumar . Short-Term Forecasting of Solar Irradiance using STL, Wavelet and LSTM. International Journal of Computer Applications. 183, 46 ( Jan 2022), 9-17. DOI=10.5120/ijca2022921829

@article{ 10.5120/ijca2022921829,
author = { Vivek Vijay, Rakesh Kumar, Ashish Sharma, Abhishek Kumar },
title = { Short-Term Forecasting of Solar Irradiance using STL, Wavelet and LSTM },
journal = { International Journal of Computer Applications },
issue_date = { Jan 2022 },
volume = { 183 },
number = { 46 },
month = { Jan },
year = { 2022 },
issn = { 0975-8887 },
pages = { 9-17 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume183/number46/32237-2022921829/ },
doi = { 10.5120/ijca2022921829 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T01:20:06.530517+05:30
%A Vivek Vijay
%A Rakesh Kumar
%A Ashish Sharma
%A Abhishek Kumar
%T Short-Term Forecasting of Solar Irradiance using STL, Wavelet and LSTM
%J International Journal of Computer Applications
%@ 0975-8887
%V 183
%N 46
%P 9-17
%D 2022
%I Foundation of Computer Science (FCS), NY, USA
Abstract

We propose a hybrid framework for short-term forecasting based on decomposition techniques and LSTM (Large Short Term Memory) algorithm. The study aims to analyze and quantify solar irradiance forecast using two types of decomposition techniques: decomposition of time series into the time domain and frequency domain via locally weighted regression based on Loess (STL) and using discrete wavelet transformation (DWT) respectively. LSTM is used to forecast the decomposed detail and approximation components. The final forecast of GHI (Global Horizontal Irradiance) is then obtained by combining these components using inverse wavelet transform. Hourly data from the Indian Meteorological Department (IMD) Jodhpur Rajasthan from January 2017 to June 2019 is used to demonstrate the proposed algorithm. The forecast accuracy of the proposed model is compared with other competitive models. The observed results show that the proposed combination of STL, wavelet transform, and LSTM outperforms (1) LSTM, (2) combination of STL and LSTM, (3) Bi-LSTM and (4) the persistence model.

References
  1. A. Alzahrani, P. Shamsi, M. Ferdowsi, and C. Dagli. Solar irradiance forecasting using deep recurrent neural networks. pages 988–994, 2017.
  2. J Antonanzas, N Osorio, R Escobar, R Urraca, FJ Martinezde Pison, and F Antonanzas-Torres. Review of photovoltaic power forecasting. Solar Energy, 136:78–111, 2016.
  3. R Azimi, M Ghayekhloo, and M Ghofrani. A hybrid method based on a new clustering technique and multilayer perceptron neural networks for hourly solar radiation forecasting. Energy Conversion and Management, 118:331–344, 2016.
  4. Jay Prakash Bijarniya, K Sudhakar, and Prashant Baredar. Concentrated solar power technology in india: A review. Renewable and Sustainable Energy Reviews, 63:593–603, 2016.
  5. Banalaxmi Brahma and Rajesh Wadhvani. Solar irradiance forecasting based on deep learning methodologies and multisite data. Symmetry, 12(11), 2020.
  6. JCSH Cao Cao and SH Cao. Study of forecasting solar irradiance using neural networks with preprocessing sample data by wavelet analysis. Energy, 31(15):3435–3445, 2006.
  7. Robert B Cleveland,William S Cleveland, Jean E McRae, and Irma Terpenning. Stl: A seasonal-trend decomposition procedure based on loess. Journal of Official Statistics, 6(1):3–73, 1990.
  8. William S Cleveland and Susan J Devlin. Locally weighted regression: an approach to regression analysis by local fitting. Journal of the American statistical association, 83(403):596– 610, 1988.
  9. Carlos FM Coimbra, Jan Kleissl, and Ricardo Marquez. Overview of solar-forecasting methods and a metric for accuracy evaluation-chapter 8. pages 171–194, 2013.
  10. Geoffrey E. Hinton Ronald J. Williams David E. Rumelhart. Learning representations by back-propagating errors. Nature, 323(533–536), 1986.
  11. Zibo Dong, Dazhi Yang, Thomas Reindl, and Wilfred M Walsh. Satellite image analysis and a hybrid esss/ann model to forecast solar irradiance in the tropics. Energy Conversion and Management, 79:66–73, 2014.
  12. Zibo Dong, Dazhi Yang, Thomas Reindl, and Wilfred M Walsh. A novel hybrid approach based on self-organizing maps, support vector regression and particle swarm optimization to forecast solar irradiance. Energy, 82:570–577, 2015.
  13. Jia-Hua Wei Fang-Fang Li, Si-Ya Wang. Long term rolling prediction model for solar radiation combining empirical mode decomposition (emd) and artificial neural network (ann)techniques. Renewable and Sustainable Energy, 10, 2018.
  14. Mahmoud Ghofrani, Mohadeseh Ghayekhloo, and Rasool Azimi. A novel soft computing framework for solar radiation forecasting. Applied Soft Computing, 48:207–216, 2016.
  15. X. Huang, J. Shi, B. Gao, Y. Tai, Z. Chen, and J. Zhang. Forecasting hourly solar irradiance using hybrid wavelet transformation and elman model in smart grid. IEEE Access, 7:139909–139923, 2019.
  16. Wu Ji and Keong Chan Chee. Prediction of hourly solar radiation using a novel hybrid model of arma and tdnn. Solar Energy, 85(5):808–817, 2011.
  17. Pedro F Jim´enez-P´erez and Llanos Mora-L´opez. Modeling and forecasting hourly global solar radiation using clustering and classification techniques. Solar Energy, 135:682–691, 2016.
  18. Amanpreet Kaur, Lukas Nonnenmacher, Hugo TC Pedro, and Carlos FM Coimbra. Benefits of solar forecasting for energy imbalance markets. Renewable Energy, 86:819–830, 2016.
  19. Stephane G Mallat. A theory for multiresolution signal decomposition: the wavelet representation. IEEE transactions on pattern analysis and machine intelligence, 11(7):674–693, 1989.
  20. Ricardo Marquez and Carlos FM Coimbra. Proposed metric for evaluation of solar forecasting models. Journal of solar energy engineering, 135(1):011016, 2013.
  21. Kasra Mohammadi, Shahaboddin Shamshirband, ChongWen Tong, Muhammad Arif, Dalibor Petkovi´c, and Sudheer Ch. A new hybrid support vector machine–wavelet transform approach for estimation of horizontal global solar radiation. Energy Conversion and Management, 92:162–171, 2015.
  22. St´ephanie Monjoly, Ma¨ına Andr´e, Rudy Calif, and Ted Soubdhan. Hourly forecasting of global solar radiation based on multiscale decomposition methods: A hybrid approach. Energy, 119:288–298, 2017.
  23. David Opitz and Richard Maclin. Popular ensemble methods: An empirical study. Journal of Artificial Intelligence Research, 11:169–198, 1999.
  24. Marius Paulescu, Eugenia Paulescu, Paul Gravila, and Viorel Badescu. Weather modeling and forecasting of PV systems operation. Springer Science & Business Media, 2012.
  25. Ye Ren, PN Suganthan, and N Srikanth. Ensemble methods for wind and solar power forecasting—a state-of-the-art review. Renewable and Sustainable Energy Reviews, 50:82–91, 2015.
Index Terms

Computer Science
Information Sciences

Keywords

Forecasting Ensemble Forecast renewable energy wavelet transform