Prediction of Levelized Cost of Electricity for Solar Photovoltaic Systems by Using Neural Networks
DOI:
https://doi.org/10.24160/1993-6982-2021-4-53-58Keywords:
solar photovoltaic system, levelized cost of energy, artificial neural network, nonlinear autoregressive model, neural network autoregressive model with exogenous inputs, training algorithmAbstract
Elaboration of a new approach to the development of models for predicting the economic indicators of solar photovoltaic systems by using artificial neural network algorithms is becoming of special importance. As is known, the relationships between economic indicators are often difficult to identify. Nonlinear autoregressive models can provide more reliable results than those obtained from predictive linear models based on vector autoregression. The article presents the results from the development of a mathematical model for predicting the levelized cost of energy (LCOE) for solar photovoltaic systems based on a nonlinear autoregressive neural network with exogenous inputs (NARX). A two-layer NARX network with hidden sigmoid neurons and linear output neurons has been developed. The input layer is made up of the following variables: the amount of power consumed from solar photovoltaic systems around the world; the total worldwide energy consumption; domestic consumption of energy, gas, coal, and lignite; the shares of renewable energy, wind and solar energy in electricity generation; carbon dioxide emissions from fuel combustion; the price of Brent oil in US dollars, and the average price for natural gas. The output layer determines the LCOE values for solar photovoltaic systems. The developed NARX network was trained on the basis of retrospective data for 2005-2010 using the Levenberg-Marquardt algorithm. The correlation coefficient value achieved in the course of training made 0.99904, and the mean square error value was in the range from 0.00042 to 0.0029.
References
1. Chang G.W., Lu H.J., Chang Y.R., Lee Y.D. An Improved Neural Network-Based Approach for Short-term wind Speed and Power Forecast // J. Renewable Energy. 2017. V. 105. Pp. 301—311.
2. Ruiz L., Cu′ellar M., Calvo-Flores M., Jim′enez M. An Application of Non-linear Autoregressive Neural Networks to Predict Energy Consumption in Public Buildings // Energies. 2016. V. 9(9). Pp 684—693.
3. Al-Allaf O.N., Abd Al Kader S.A. Nonlinear Autoregressive Neural Network for Estimation Soil Temperature: a Comparison of Diferent Optimization Neural Network Algorithms // UbiCC J. 2011. V. 6. Pp. 43—51.
4. Di Piazza A., Di Piazza M.C., Vitale G. Solar and Wind Forecasting by NARX Neural Networks // Renewable Energy and Environmental Sustainability. 2016. V. 1(36). Pp. 1—5.
5. Lydia M., Kumar S., Selvakumar A.I., Kumar G.E.P. Linear and Non-linear Autoregressive Models for Short-term Wind Speed Forecasting // Energy Conversion and Management. 2016. V. 112. Pp. 115—124.
6. Cadenas E., Rivera W., Campos-Amezcua R., Heard C. Wind Speed Prediction Using a Univariate ARIMA Model and a Multivariate NARX Model // Energies. 2016. V. 9(2). Pp. 109—115.
7. Zhang X., Frey R. Improving ARMA-GARCH Forecasts for High Frequency Data with Regime-switching ARMA-GARCH // J. Computational Analysis and Appl. 2015. V. 18(4). Pp. 727—751.
8. Kambouroudis D.S., McMillan D.G., Tsakou K. Forecasting Stock Return Volatility: a Comparison of GARCH, Implied Volatility, and Realized Volatility Models // J. Futures Markets. 2016. V. 36(12). Pp. 1127—1163.
9. Corrêa J.M., Neto A.C., Júnior L.T., Franco E.M.C., Faria A.E. Time Series Forecasting with the WARIMAX-GARCH Method // Neurocomputing. 2016. V. 9. Pp. 805—815.
10. Chaudhuri T.D., Ghosh I. Artificial Neural Network and Time Series Modeling Based Approach to Forecasting the Exchange Rate in a Multivariate Framework // J. Insurance and Financial Management. 2016. V. 1(5). Pp. 92—123.
11. Домащенко Д.В., Никулин Э.Е. Прогнозирование рядов динамики рыночных индикаторов на основе нелинейной авторегрессионной нейронной сети // Статистика и экономика. 2017. Т. 14. № 3. C. 4—9.
12. Хайкин C. Нейронные сети: полный курс. М.: Издат. дом «Вильямс», 2006.
13. Executive Summary — Projected Costs of Generating Electricity [Электрон. ресурс] www.oecd-nea.org/jcms/pl_14974/executive-summary-of-projected-costs-of-generating-electricity-2015-edition (дата обращения 08.04.2020).
14. Исследования об энергоэффективности, выбросов СО2, энергопотреблении, прогнозы [Офиц. сайт] www.enerdata.ru. (дата обращения 06.11.2020).
15. График изменения цен на нефть Brent к доллару США [Электрон. ресурс] www.finovosti.ru/quotes/BRENT/USD/chart/total (дата обращения 06.11.2020).
16. Природный газ: цена на бирже и онлайн график – Forex Club [Электрон. ресурс]. www.fxclub.org/markets/neft-gaz/ng (дата обращения 06.11.2020).
17. REN21 — Building the Sustainable Energy Future with Renewable Energy [Офиц. сайт] www.ren21.net. (дата обращения 06.11.2020).
18. Хайкин С. Преимущества и ограничения обучения методом обратного распространения. М.: Издат. дом «Вильямс», 2006.
19. Yousif J.H., Kazem H.A., Alattar N.N., Elhassan I.I. A Comparison Study Based on Artificial Neural Network for Assessing PV/T Solar Energy Production // Case Studies in Thermal Eng. 2019. V. 13. Pp. 1—13.
20. O’Leary D., Kubby J. Feature Selection and ANN Solar Power Prediction // Hindawi. 2017. V. 2017. Pp. 1—7.
---
Для цитирования: Филиппченкова Н.С. Нейросетевое прогнозирование полной приведенной стоимости электроэнергии для солнечных фотоэлектрических систем // Вестник МЭИ. 2021. № 4. С. 53—58. DOI: 10.24160/1993-6982-2021-4-53-58.
#
1. Chang G.W., Lu H.J., Chang Y.R., Lee Y.D. An Improved Neural Network-Based Approach for Short-term wind Speed and Power Forecast. J. Renewable Energy. 2017;105:301—311.
2. Ruiz L., Cu′ellar M., Calvo-Flores M., Jim′enez M. An Application of Non-linear Autoregressive Neural Networks to Predict Energy Consumption in Public Buildings. Energies. 2016;9(9):684—693.
3. Al-Allaf O.N., Abd Al Kader S.A. Nonlinear Autoregressive Neural Network for Estimation Soil Temperature: a Comparison of Diferent Optimization Neural Network Algorithms. UbiCC J. 2011;6:43—51.
4. Di Piazza A., Di Piazza M.C., Vitale G. Solar and Wind Forecasting by NARX Neural Networks. Renewable Energy and Environmental Sustainability. 2016;1(36):1—5.
5. Lydia M., Kumar S., Selvakumar A.I., Kumar G.E.P. Linear and Non-linear Autoregressive Models for Short-term Wind Speed Forecasting. Energy Conversion and Management. 2016;112:115—124.
6. Cadenas E., Rivera W., Campos-Amezcua R., Heard C. Wind Speed Prediction Using a Univariate ARIMA Model and a Multivariate NARX Model. Energies. 2016;9(2):109—115.
7. Zhang X., Frey R. Improving ARMA-GARCH Forecasts for High Frequency Data with Regime-switching ARMA-GARCH. J. Computational Analysis and Appl. 2015;18(4):727—751.
8. Kambouroudis D.S., McMillan D.G., Tsakou K. Forecasting Stock Return Volatility: a Comparison of GARCH, Implied Volatility, and Realized Volatility Models. J. Futures Markets. 2016;36(12):1127—1163.
9. Corrêa J.M., Neto A.C., Júnior L.T., Franco E.M.C., Faria A.E. Time Series Forecasting with the WARIMAX-GARCH Method. Neurocomputing. 2016;9:805—815.
10. Chaudhuri T.D., Ghosh I. Artificial Neural Network and Time Series Modeling Based Approach to Forecasting the Exchange Rate in a Multivariate Framework. J. Insurance and Financial Management. 2016;1(5):92—123.
11. Domashchenko D.V., Nikulin E.E. Prognozirovanie Ryadov Dinamiki Rynochnyh Indikatorov na Osnove Nelinejnoj Avtoregressionnoj Nejronnoj Seti. Statistika i Ekonomika. 2017;14;3:4—9. (in Russian).
12. Hajkin C. Nejronnye Seti: Polnyj Kurs. M.: Izdat. Dom «Vil'yams», 2006. (in Russian).
13. Executive Summary — Projected Costs of Generating Electricity [Elektron. Resurs] www.oecd-nea.org/jcms/pl_14974/executive-summary-of-projected-costs-of-generating-electricity-2015-edition (Data Obrashcheniya 08.04.2020).
14. Issledovaniya ob Energoeffektivnosti, Vybrosov SO2, Energopotreblenii, Prognozy [Ofitc. Sayt] www.enerdata.ru. (Data Obrashcheniya 06.11.2020). (in Russian).
15. Grafik Izmeneniya Cen na Neft' Brent k Dollaru SSHA [Elektron. Resurs] www.finovosti.ru/quotes/BRENT/USD/chart/total (Data Obrashcheniya 06.11.2020). (in Russian).
16. Prirodnyj Gaz: Cena na Birzhe i Onlajn Grafik – Forex Club [Elektron. Resurs]. www.fxclub.org/markets/neft-gaz/ng (Data Obrashcheniya 06.11.2020). (in Russian).
17. REN21 — Building the Sustainable Energy Future with Renewable Energy [Ofitc. Sayt] www.ren21.net. (Data Obrashcheniya 06.11.2020).
18. Khaykin S. Preimushchestva i Ogranicheniya Obucheniya Metodom Obratnogo Rasprostraneniya. M.: Izdat. Dom «Vil'yams», 2006. (in Russian).
19. Yousif J.H., Kazem H.A., Alattar N.N., Elhassan I.I. A Comparison Study Based on Artificial Neural Network for Assessing PV/T Solar Energy Production. Case Studies in Thermal Eng. 2019;13:1—13.
20. O’Leary D., Kubby J. Feature Selection and ANN Solar Power Prediction. Hindawi. 2017;2017:1—7.
---
For citation: Filippchenkova N.S. Prediction of Levelized Cost of Electricity for Solar Photovoltaic Systems by Using Neural Networks. Bulletin of MPEI. 2021;4:53—58. (in Russian). DOI: 10.24160/1993-6982-2021-4-53-58.
2. Ruiz L., Cu′ellar M., Calvo-Flores M., Jim′enez M. An Application of Non-linear Autoregressive Neural Networks to Predict Energy Consumption in Public Buildings // Energies. 2016. V. 9(9). Pp 684—693.
3. Al-Allaf O.N., Abd Al Kader S.A. Nonlinear Autoregressive Neural Network for Estimation Soil Temperature: a Comparison of Diferent Optimization Neural Network Algorithms // UbiCC J. 2011. V. 6. Pp. 43—51.
4. Di Piazza A., Di Piazza M.C., Vitale G. Solar and Wind Forecasting by NARX Neural Networks // Renewable Energy and Environmental Sustainability. 2016. V. 1(36). Pp. 1—5.
5. Lydia M., Kumar S., Selvakumar A.I., Kumar G.E.P. Linear and Non-linear Autoregressive Models for Short-term Wind Speed Forecasting // Energy Conversion and Management. 2016. V. 112. Pp. 115—124.
6. Cadenas E., Rivera W., Campos-Amezcua R., Heard C. Wind Speed Prediction Using a Univariate ARIMA Model and a Multivariate NARX Model // Energies. 2016. V. 9(2). Pp. 109—115.
7. Zhang X., Frey R. Improving ARMA-GARCH Forecasts for High Frequency Data with Regime-switching ARMA-GARCH // J. Computational Analysis and Appl. 2015. V. 18(4). Pp. 727—751.
8. Kambouroudis D.S., McMillan D.G., Tsakou K. Forecasting Stock Return Volatility: a Comparison of GARCH, Implied Volatility, and Realized Volatility Models // J. Futures Markets. 2016. V. 36(12). Pp. 1127—1163.
9. Corrêa J.M., Neto A.C., Júnior L.T., Franco E.M.C., Faria A.E. Time Series Forecasting with the WARIMAX-GARCH Method // Neurocomputing. 2016. V. 9. Pp. 805—815.
10. Chaudhuri T.D., Ghosh I. Artificial Neural Network and Time Series Modeling Based Approach to Forecasting the Exchange Rate in a Multivariate Framework // J. Insurance and Financial Management. 2016. V. 1(5). Pp. 92—123.
11. Домащенко Д.В., Никулин Э.Е. Прогнозирование рядов динамики рыночных индикаторов на основе нелинейной авторегрессионной нейронной сети // Статистика и экономика. 2017. Т. 14. № 3. C. 4—9.
12. Хайкин C. Нейронные сети: полный курс. М.: Издат. дом «Вильямс», 2006.
13. Executive Summary — Projected Costs of Generating Electricity [Электрон. ресурс] www.oecd-nea.org/jcms/pl_14974/executive-summary-of-projected-costs-of-generating-electricity-2015-edition (дата обращения 08.04.2020).
14. Исследования об энергоэффективности, выбросов СО2, энергопотреблении, прогнозы [Офиц. сайт] www.enerdata.ru. (дата обращения 06.11.2020).
15. График изменения цен на нефть Brent к доллару США [Электрон. ресурс] www.finovosti.ru/quotes/BRENT/USD/chart/total (дата обращения 06.11.2020).
16. Природный газ: цена на бирже и онлайн график – Forex Club [Электрон. ресурс]. www.fxclub.org/markets/neft-gaz/ng (дата обращения 06.11.2020).
17. REN21 — Building the Sustainable Energy Future with Renewable Energy [Офиц. сайт] www.ren21.net. (дата обращения 06.11.2020).
18. Хайкин С. Преимущества и ограничения обучения методом обратного распространения. М.: Издат. дом «Вильямс», 2006.
19. Yousif J.H., Kazem H.A., Alattar N.N., Elhassan I.I. A Comparison Study Based on Artificial Neural Network for Assessing PV/T Solar Energy Production // Case Studies in Thermal Eng. 2019. V. 13. Pp. 1—13.
20. O’Leary D., Kubby J. Feature Selection and ANN Solar Power Prediction // Hindawi. 2017. V. 2017. Pp. 1—7.
---
Для цитирования: Филиппченкова Н.С. Нейросетевое прогнозирование полной приведенной стоимости электроэнергии для солнечных фотоэлектрических систем // Вестник МЭИ. 2021. № 4. С. 53—58. DOI: 10.24160/1993-6982-2021-4-53-58.
#
1. Chang G.W., Lu H.J., Chang Y.R., Lee Y.D. An Improved Neural Network-Based Approach for Short-term wind Speed and Power Forecast. J. Renewable Energy. 2017;105:301—311.
2. Ruiz L., Cu′ellar M., Calvo-Flores M., Jim′enez M. An Application of Non-linear Autoregressive Neural Networks to Predict Energy Consumption in Public Buildings. Energies. 2016;9(9):684—693.
3. Al-Allaf O.N., Abd Al Kader S.A. Nonlinear Autoregressive Neural Network for Estimation Soil Temperature: a Comparison of Diferent Optimization Neural Network Algorithms. UbiCC J. 2011;6:43—51.
4. Di Piazza A., Di Piazza M.C., Vitale G. Solar and Wind Forecasting by NARX Neural Networks. Renewable Energy and Environmental Sustainability. 2016;1(36):1—5.
5. Lydia M., Kumar S., Selvakumar A.I., Kumar G.E.P. Linear and Non-linear Autoregressive Models for Short-term Wind Speed Forecasting. Energy Conversion and Management. 2016;112:115—124.
6. Cadenas E., Rivera W., Campos-Amezcua R., Heard C. Wind Speed Prediction Using a Univariate ARIMA Model and a Multivariate NARX Model. Energies. 2016;9(2):109—115.
7. Zhang X., Frey R. Improving ARMA-GARCH Forecasts for High Frequency Data with Regime-switching ARMA-GARCH. J. Computational Analysis and Appl. 2015;18(4):727—751.
8. Kambouroudis D.S., McMillan D.G., Tsakou K. Forecasting Stock Return Volatility: a Comparison of GARCH, Implied Volatility, and Realized Volatility Models. J. Futures Markets. 2016;36(12):1127—1163.
9. Corrêa J.M., Neto A.C., Júnior L.T., Franco E.M.C., Faria A.E. Time Series Forecasting with the WARIMAX-GARCH Method. Neurocomputing. 2016;9:805—815.
10. Chaudhuri T.D., Ghosh I. Artificial Neural Network and Time Series Modeling Based Approach to Forecasting the Exchange Rate in a Multivariate Framework. J. Insurance and Financial Management. 2016;1(5):92—123.
11. Domashchenko D.V., Nikulin E.E. Prognozirovanie Ryadov Dinamiki Rynochnyh Indikatorov na Osnove Nelinejnoj Avtoregressionnoj Nejronnoj Seti. Statistika i Ekonomika. 2017;14;3:4—9. (in Russian).
12. Hajkin C. Nejronnye Seti: Polnyj Kurs. M.: Izdat. Dom «Vil'yams», 2006. (in Russian).
13. Executive Summary — Projected Costs of Generating Electricity [Elektron. Resurs] www.oecd-nea.org/jcms/pl_14974/executive-summary-of-projected-costs-of-generating-electricity-2015-edition (Data Obrashcheniya 08.04.2020).
14. Issledovaniya ob Energoeffektivnosti, Vybrosov SO2, Energopotreblenii, Prognozy [Ofitc. Sayt] www.enerdata.ru. (Data Obrashcheniya 06.11.2020). (in Russian).
15. Grafik Izmeneniya Cen na Neft' Brent k Dollaru SSHA [Elektron. Resurs] www.finovosti.ru/quotes/BRENT/USD/chart/total (Data Obrashcheniya 06.11.2020). (in Russian).
16. Prirodnyj Gaz: Cena na Birzhe i Onlajn Grafik – Forex Club [Elektron. Resurs]. www.fxclub.org/markets/neft-gaz/ng (Data Obrashcheniya 06.11.2020). (in Russian).
17. REN21 — Building the Sustainable Energy Future with Renewable Energy [Ofitc. Sayt] www.ren21.net. (Data Obrashcheniya 06.11.2020).
18. Khaykin S. Preimushchestva i Ogranicheniya Obucheniya Metodom Obratnogo Rasprostraneniya. M.: Izdat. Dom «Vil'yams», 2006. (in Russian).
19. Yousif J.H., Kazem H.A., Alattar N.N., Elhassan I.I. A Comparison Study Based on Artificial Neural Network for Assessing PV/T Solar Energy Production. Case Studies in Thermal Eng. 2019;13:1—13.
20. O’Leary D., Kubby J. Feature Selection and ANN Solar Power Prediction. Hindawi. 2017;2017:1—7.
---
For citation: Filippchenkova N.S. Prediction of Levelized Cost of Electricity for Solar Photovoltaic Systems by Using Neural Networks. Bulletin of MPEI. 2021;4:53—58. (in Russian). DOI: 10.24160/1993-6982-2021-4-53-58.
Downloads
Published
2020-11-13
Issue
Section
Renewable Energy Installations (05.14.08)
