Abstract
Load forecasting is a task that gives future load prediction of the power system in order to better arrange the power generation. Similar day selection based short-term load forecasting has been a classic method combined with many newly-introduced machine learning methods which use similar days as input. Traditional similar day method selects historic days simply by human experience or clustering of meteorological and date factors while ignoring the shape information in the load time series. A new similar day selection method based on shape selection is proposed in this paper: Firstly, we cluster the historic days by load series shape using improved K-shape method. Secondly, an XGBoost classifier is developed to classify the shape type using meteorological and date information. Then the classifier is used to predict the shape type of the forecasting day and select the similar days by judging their shape and meteorological factor. Shape-similar days are combined with traditional method-selected days as inputs of forecasting model. The result shows that our method has improved the prediction accuracy.
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
Czernichow, T., et al.: Short term electrical load forecasting with artificial neural networks. Eng. Intell. Syst. 2, 85–89 (1996)
Pandian, S.C., Duraiswamy, K., Asir Rajan, C.C., Kanagaraj, N.: Fuzzy approach for short term load forecasting. Electr. Power Syst. Res. 76, 541–548 (2006)
Mohandes, M.: Support vector machines for short-term electrical load forecasting. Int. J. Energy Res. 26, 335–345 (2002)
Zhang, Y., Qiu, C., He, X., Ling, Z., Shi, X.: Short-term load forecasting based on LSTM neural network. Electr. Power ICT 15(9), 19–25 (2017). (in Chinese)
Tian, C., Ma, J., Zhang, C., Zhan, P.: A deep neural network model for short-term load forecast based on long short-term memory network and convolutional neural network. Energies 11(3493), 1–13 (2018)
Choi, H., Ryu, S., Kim, H.: Short-term load forecasting based on Resnet and LSTM. In: 2018 IEEE Conference on Communications, Control, and Computing Technologies for Smart Grid. IEEE (2018)
Chen, K., Chen, K., Wang, Q., He, Z., Hu, J., He, J.: Short-term load forecasting with deep residual networks. IEEE Trans. Smart Grid 10(4), 3943–3952 (2019)
Park, R., Song, K., Kwon, B.: Short-term load forecasting algorithm using a similar day selection method based on reinforcement learning. Energies 13(2640), 1–19 (2020)
Paparrizos, J., Gravano, L.: k-shape: efficient and accurate clustering of time series. In: Proceeding of SIGMOD, pp. 1855–1870. ACM (2015)
Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceeding of SIGKDD. ACM (2016)
Liu, J.: Short-term power load forecasting based on similar day and support vector machine. In: Dissertation for Master Degree (2010). (in Chinese)
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
Shi, M., He, X. (2022). Shape-Aided Similar Day Selection Method for Short Term Load Forecasting. In: Deng, Z. (eds) Proceedings of 2021 Chinese Intelligent Automation Conference. Lecture Notes in Electrical Engineering, vol 801. Springer, Singapore. https://doi.org/10.1007/978-981-16-6372-7_23
Download citation
DOI: https://doi.org/10.1007/978-981-16-6372-7_23
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6371-0
Online ISBN: 978-981-16-6372-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)