Abstract
As a clean and renewable energy source, solar energy makes photovoltaic (PV) generation become one of the most viablepower generation resources. However, photovoltaic power generation is greatly affected by weather changes and random changes, which limits the development of photovoltaic grid-connected systems. To timely control the impact and fluctuation brought by photovoltaic grid connection, it is very necessary to establish a reliable photovoltaic power generation forecasting model. This paper utilizes the Gated Recurrent Unit (GRU) neural network to predict the photovoltaic power generation in ultra-short time. The proposed method is applied to the DC competition dataset and a smart microgrid photovoltaic dataset. After the data set is analyzed and preprocessed, different loss functions are used to train the GRU model. The comparison analysis with the Deep Neural Network (DNN) model and the Support Vector Machine (SVR) model shows that the proposed method exhibits high performance in forecasting accuracy method achieve more accurate prediction result. In addition, experiment under different weather conditions shows that the GRU network model could adapt to weather changes.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
China’s installed renewable energy power generation capacity reaches 948 million kilowatts. Electr. Power Surv. Des. (05), 29 (2021). (in Chinese)
Zhang, H., Shan, L., Ren, J., et al.: Study on photovoltaic grid-connected inverter control system, pp. 210–212. IEEE (2009)
Kim, J., Song, S., Kim, Y.: A basic study on anti-reflection coating PV technology for reducing reflected sunlight on the building skin. Asia-Pac. J. Converg. Res. Interchange 5(2), 23–30 (2019)
Araki, K., Algora, C., Siefer, G., et al.: Standardization of the CPV and car-roof PV technology in 2018 – Where are we going to go? In: AIP Conference Proceedings 2012(1) (2018)
Abdin, Z.U., Rachid, A.: Survey on applications of hybrid PV/T panels. Energies 14(4), 1205 (2021)
Ahmed, R., Sreeram, V., Mishra, Y., et al.: A review and evaluation of the state-of-the-art in PV solar power forecasting: techniques and optimization. Renew. Sustain. Energy Rev. 12s4 (2020)
Li, L., Wen, S., Tseng, M., et al.: Renewable energy prediction: a novel short-term prediction model of photovoltaic output power. J. Clean. Prod. 228, 359–375 (2019)
Ma, W.X., Chen, Z.M., Zhu, Q.: Ultra-short-term forecasting of photo-voltaic power via RBF neural network. Electronics 9(10), 1717 (2020)
Wang, J., Li, P., Ran, R., et al.: A short-term photovoltaic power prediction model based on the gradient boost decision tree. Appl. Sci. 8(5), 689 (2018)
Liu, Z.F., Luo, S.F., Tseng, M.L., et al.: Short-term photovoltaic power prediction on modal reconstruction: a novel hybrid model approach. Sustain. Energy Technol. Assess. 45, 101048 (2021)
Mellit, A., Pavan, A.M., Ogliari, E., et al.: Advanced methods for photovoltaic output power forecasting: a review. Appl. Sci. 10(2), 487 (2020)
Yingfei, G., Zongxiang, L., Ying, Q., Qiang, W.: Automation of Electric Power Systems 40(04), 140–151 (2016). (in Chinese)
Fachini, F., Fully, B.I.L.: A comparison of machine learning regression models for critical bus voltage and load mapping with regards to max reactive power in PV buses. Electr. Power Syst. Res. 191, 106883 (2021)
Anbo, M., Jiaming, C., Zhanlian, L., et al.: Short-Term photovoltaic power generation prediction based on similar day theory and CSO-WGPR. High Voltage Eng. 47(4), 1176–1184 (2021)
Cheng, Z., Jianbo, B., Kang, L., Xinxin, H., Chen, F., Xia, X.: Power generation forecast of photovoltaic power station based on data mining and genetic wavelet neural network. Acta Energia Sinica 42(03), 375–382 (2021). (in Chinese)
Mahendran, K., Prabha, S.U.: Optimal control strategies for a hybrid renewable energy system: an ALANN/RNN technique. Soft. Comput. 23(24), 13459–13475 (2019). https://doi.org/10.1007/s00500-019-03885-9
Juntian, L., Ling, S., Quan, S.: Prediction of bus arrival time based on gated recurrent unit neural network. J. Nantong Univ. (Nat. Sci. Edn.) 19(02), 43–49 (2020). (in Chinese)
Zheng, D.Y., Li, J.: Short-term photovoltaic power prediction based on sparse representation method. J. Phys: Conf. Ser. 1757(1), 5 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Tian, F., Fan, X., Fan, Y., Wang, R., Lian, C. (2022). Ultra-short-Term PV Power Generation Prediction Based on Gated Recurrent Unit Neural Network. In: He, J., Li, Y., Yang, Q., Liang, X. (eds) The proceedings of the 16th Annual Conference of China Electrotechnical Society. Lecture Notes in Electrical Engineering, vol 891. Springer, Singapore. https://doi.org/10.1007/978-981-19-1532-1_8
Download citation
DOI: https://doi.org/10.1007/978-981-19-1532-1_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-1531-4
Online ISBN: 978-981-19-1532-1
eBook Packages: EngineeringEngineering (R0)