Photovoltaic power prediction based on improved grey wolf algorithm optimized back propagation

• Autorzy: He Ping , Dong Jie , Wu Xiaopeng , Yun Lei , Yang Hua

Identyfikatory

DOI

10.24425/aee.2023.146040

• Języki publikacji: EN

Abstrakty

EN

At present, the back-propagation (BP) network algorithm widely used in the short-term output prediction of photovoltaic power stations has the disadvantage of ignoring meteorological factors and weather conditions in the input. The existing traditional BP prediction model lacks a variety of numerical optimization algorithms, such that the prediction error is large. The back-propagation (BP) neural network is easy to fall into local optimization thus reducing the prediction accuracy in photovoltaic power prediction. In order to solve this problem, an improved grey wolf optimization (GWO) algorithm is proposed to optimize the photovoltaic power prediction model of the BP neural network. So, an improved grey wolf optimization algorithm optimized BP neural network for a photovoltaic (PV) power prediction model is proposed. Dynamic weight strategy, tent mapping and particle swarm optimization (PSO) are introduced in the standard grey wolf optimization (GWO) to construct the PSO–GWO model. The relative error of the PSO–GWO–BP model predicted data is less than that of the BP model predicted data. The average relative error of PSO–GWO–BP and GWO–BP models is smaller, the average relative error of PSO–GWO–BP model is the smallest, and the prediction stability of the PSO–GWO–BP model is the best. The model stability and prediction accuracy of PSO–GWO–BP are better than those of GWO–BP and BP.

Słowa kluczowe

EN

BP neural network; photovoltaic power generation; PSO–GWO model; PSO–GWO–BP prediction model; particle swarm optimization; gray wolf optimization; back propagation; standard grey wolf algorithm

• Wydawca: Polish Academy of Sciences, Committee on Electrical Engineering
• Czasopismo: Archives of Electrical Engineering
• Rocznik: 2023
• Tom: Vol. 72, nr 3
• Strony: 613--628
• Opis fizyczny: Bibliogr. 29 poz., fig., tab., wz.

Twórcy

autor

He Ping

• Zhengzhou University of Light Industry, College of Electrical and Information Engineering China

• https://orcid.org/0000-0002-1692-5804

autor

Dong Jie

• Zhengzhou University of Light Industry, College of Electrical and Information Engineering China

• https://orcid.org/0000-0003-2307-4240

autor

Wu Xiaopeng

• Zhengzhou University of Light Industry, College of Electrical and Information Engineering China

• https://orcid.org/0000-0003-2691-4487

autor

Yun Lei

• Zhengzhou University of Light Industry, College of Electrical and Information Engineering China

• https://orcid.org/0000-0002-4277-2178

autor

Yang Hua

• Zhengzhou University of Light Industry, College of Electrical and Information Engineering China

• https://orcid.org/0000-0003-1129-019X

Bibliografia

• [1] Wang W.B., Zheng S.J., Chen W., Performance evaluation index and method of microgrid distributed electric energy trading under the background of “carbon peaking and carbon neutrality”, Journal of Shanghai Jiaotong University, vol. 55, no. 3, pp. 312–324 (2022), DOI: 10.16183/j.cnki.jsjtu.2021.391.
• [2] Zhang K., Miao M., Zhang L.Q., Carbon Peaking and Carbon Neutrality Goals and Reflections on China’s Energy Transition Part I, Sino-global Energy, vol. 27, no. 3 (2022).
• [3] Xin B.A., Shan B.G., Li Q.H., Rethinking of the “Three Elements of Energy” Toward Carbon Peak and Carbon Neutrality, Proceedings of the CSEE, vol. 42, no. 9, pp. 3117–3126 (2022), DOI:10.13334/j.0258-8013.pcsee.212780.
• [4] Wei L.M., Li K.K., Research on the output characteristics of photovoltaic arrays under partial shading conditions based on peak point approximate calculation method, Archives of Electrical Engineering, vol. 71, no. 2, pp. 409–424 (2022), DOI: 10.24425/aee.2022.140719.
• [5] Ke B., Ku T., Ke Y., Sizing the Battery Energy Storage System on a University Campus with Prediction of Load and Photovoltaic Generation, IEEE Transactions on Industry Applications, vol. 52, no. 2, pp. 1136–1147 (2016), DOI: 10.1109/TIA.2015.2483583.
• [6] Zhang J.P., Wang B.N., Huang R., Survey on frequency regulation technology of power grid by high penetration photovoltaic, Power System Protection and Control, vol. 47, no. 15, pp. 179–186 (2019), DOI: 10.19783/j.cnki.pspc.181042.
• [7] Zhang F., Zhang F., Power Load Forecasting in the Time Series Analysis Method Based on Lifting Wavelet, Power System Automation, vol. 39, no. 3, pp. 72–76 (2017), DOI: 10.7500/AEPS20180603002.
• [8] Li M.K., Wang Y., Sun G., Research on fault location method of UHVDC grounding pole line based on regression analysis, Electrical Measurement Instrumentation, vol. 58, no. 9, pp. 129–134 (2021), DOI: 10.19753/j.issn1001-1390.2021.09.019.
• [9] Abedinia O., Amjady N., Ghadimi N., Solar energy forecasting based on hybrid neural network and improved metaheuristic algorithm, Computational Intelligence, vol. 34, no. 1, pp. 241–260 (2018), DOI: org/10.1111/coin.12145.
• [10] Zhu H., Wang Y., Intelligent Prediction of Prestressed Steel Structure Construction Safety Based on BP Neural Network, Applied Sciences, vol. 12, no. 1, pp. 1442 (2022), DOI: 10.3390/app12031442.
• [11] Al-Dahidi S., Ayadi O., Alrbai M., Adeeb J., Ensemble Approach of Optimized Artificial Neural Networks for Solar Photovoltaic Power Prediction, IEEE Access, vol. 7, pp. 81741–81758 (2019), DOI: 10.1109/ACCESS.2019.2923905.
• [12] Yuan X.L., Shi J.H., Xu J.Y., Short-term power forecast for photovoltaic generation based on BP neutral network, Renewable Energy Resources, vol. 31, no. 7, pp. 11–16 (2013), DOI: 10.13941/j.cnki.21-1469/tk.2013.07.019.
• [13] Ding M., Wang L., Bi R., A short-term prediction model to forecast output power of photovoltaic system based on improved BP neural network, Power System Protection and Control, vol. 40, no. 11, pp. 93–99+148 (2012), DOI: 10.13941/j.cnki.21-1469/tk.2013.07.019.
• [14] Chui X., Fang J.L., Qu L., Photovoltaic power prediction based on PSO-BP algorithm, Heilongjiang Electric Power, vol. 43, no. 2, pp. 109–112+117 (2021), DOI: 10.13625/j.cnki.hljep.2021.02.004.
• [15] Tang X., Dai Y., Wang T., Short-term power load forecasting based on multi-layer bidirectional recurrent neural network, IET Generation, Transmission & Distribution, vol. 13, no. 17, pp. 3847–3854 (2019), DOI: 10.1049/iet-gtd.2018.6687.
• [16] Li Y.C., Ma L.Q., Fault diagnosis of power transformer based on improved particle swarm optimization OS-ELM, Archives of Electrical Engineering, vol. 68, no. 1, pp. 161–172 (2019), DOI:10.24425/aee.2019.125987.
• [17] Ahmed A. Shehata, Ahmed Refaat, Mamdouh K. Ahmed, Nikolay V. Korovkin, Optimal placement and sizing of FACTS devices based on Autonomous Groups Particle Swarm Optimization technique, Archives of Electrical Engineering, vol. 70, no. 1, pp. 161–172(2021), DOI:10.24425/aee.2021.136059.
• [18] Cao Y., Gao B.P., Zhang Z.H., A fault diagnosis method for power grid based on PSO–GWO, Electrical Measurement and Instrumentation, vol. 58, no. 9, pp. 35–40 (2021), DOI: 10.19753/j.issn1001-1390.2021.09.006.
• [19] Dhal Pradip, Azad Chandrashekhar, A multi-objective feature selection method using Newton’s law based PSO with GWO, Applied Soft Computing Journal, vol. 107, pp. 107394 (2021), DOI:10.1016/j.asoc.2021.107394.
• [20] Gao X., Liu C.L., Cao M., Load forecasting based on VMD and Support Vector Machine Optimized by Hybrid PSO–GWO, Mathematics in Practice and Theory, vol. 51, no. 19, pp. 235–242 (2021).
• [21] He S.M., Yuan Z.Y., Optimal setting method of inverse time over-current protection for a distribution network based on the improved grey wolf optimization, Power System Protection and Control, vol. 49, no. 18, pp. 173–181 (2021), DOI: 10.19783/j.cnki.pspc.201351.
• [22] Wu Y.X., Gao C., Cao H.Z., Clustering analysis of daily load curves based on GWO algorithm, Power System Protection and Control, vol. 48, no. 6, pp. 68–76 (2020), DOI: 10.19783/j.cnki.pspc.190486.
• [23] Tian S.X., Liu L., Wei S.R., Dynamic reconfiguration of a distribution network based on an improved grey wolf optimization algorithm, Power System Protection and Control, vol. 49, no. 16, pp. 1–111(2021), DOI: 10.19783/j.cnki.pspc.201356.
• [24] Zhang W.T., Zhang D.P., Soft Sensor Model of SCR Denitration Efficiency Based on IGWO–BP, Computer Measurement and Control, vol. 29, no. 10, pp. 66–70+76 (2021), DOI: 10.16526/j.cnki.11-4762/tp.2021.10.012.
• [25] Li X.W., Chen C., Tao Y.G., Comprehensive evaluation of distribution network connection mode based on IGWO–BP, Electronic Measurement Technology, vol. 43, no. 3, pp. 71–76 (2020), DOI:10.19651/j.cnki.emt.1903358.
• [26] Liang E.H., Sun J.W., Wang Y.F., Wind and solar complementary grid-connected power generation prediction based on BP optimized by a swarm intelligence algorithm, Power System Protection and Control, vol. 49, no. 24, pp. 114–120 (2021), DOI: 10.19783/j.cnki.pspc.210059.
• [27] Teng Y.J., Lv J.L., Guo L.W., An improved hybrid grey wolf optimization algorithm based on Tent mapping, Journal of Harbin Institute of Technology, vol. 50, no. 11, pp. 40–49 (2018), DOI:1011918/jissn0367-6234201806096.
• [28] Hu Y., Wei Y., Zhang H., Using machine learning to predict two-phase flow regimes in horizontal pipes, International Journal of Heat and Mass Transfer, vol. 120, pp. 1043–1053 (2018), DOI:10.1016/j.ijheatmasstransfer.2017.12.110.
• [29] Kailkhura B., Chakraborty T., A systematic study of the effect of feature normalization on the performance of machine learning models in classifying medical images, Journal of Medical Systems, vol. 43,no. 6, pp. 137 (2019), DOI: 10.1007/s10916-019-1297-8.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).