Abstract
Recently, load forecasting based on machine learning and artificial intelligence has shown great promise. As an individual with high power load, the accurate load forecasting of the special transformer users can guide the planning of future power generation and transmission, which is the key to ensuring the safe, stable and efficient running of the power system. However, most forecasting models do not consider the actual power consumption data of users and the power load characteristics of different types of users, and their application practicability and stability are insufficient. In this paper, we present a load forecasting syncretic model based on user unsupervised classification. Firstly, in the unsupervised classification of users, multiple features and similarities are introduced at the same time to realize the primary classification of special users. Secondly, with two time series clustering methods as the core, the secondary classification of special users is realized. Finally, different time series forecasting models are used for the power load curve characteristics of different user categories. Our model has achieved the best results in multiple metrics (RMSE: 0.359, MSE: 0129, MAE: 0.079, CR: 0.881), which can effectively improve the stability and accuracy of the load forecasting of the special transformer users.
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
Sun, Y., Wang, Y., Zhu, W., Li, Y.: Residential daily power load forecasting based on threshold ARMA model considering the influence of temperature. Electr. Power Constr. 43(09), 117–124 (2022)
Liu, J., Zhao, J., Feng, Y., Zhou, C., Jiang, M., Zhang, H.: Power load forecasting in power internet of things based on gradient boosting decision tree. Smart Power 50(08), 46–53 (2022)
Yao, G., Li, T., Liu, L., Zheng, Y.: Residential electricity load forecasting method based on DAE and LSTM. Control Eng. China 29(11), 2048–2053 (2022)
Liu, Y., Ma, Q., Wang, Z., Li, P., Liu, C.: Cogitation on power and electricity balance dispatching in new power system. Proc. CSEE 43(05), 1694–1706 (2023)
Cheng, J., Xie, F., Han, S.-C., Lu, X., Lv, L.: Design of customer real-name information collection and storage model for power marketing system. Tech. Autom. Appl. 41(04), 38–41+62 (2022)
Xu, Y., Zhang, X., Zhou, X., Sun, J., Qiu, X., Xie, L.: The short-term load forecasting method for transformer based on prophet-LightGBM. J. North China Electr. Power Univ. (Nat. Sci. Ed.) 12(29), 1–7 (2022)
Dat, N.Q., Ngoc Anh, N.T., Nhat Anh, N., et al.: Hybrid online model based multi seasonal decompose for short-term electricity load forecasting using ARIMA and online RNN. J. Intell. Fuzzy Syst. 41(5), 5639–5652 (2021)
Wang, Z., et al.: Electric bus charging load forecasting method based on spectral clustering and LSTM neural network. Electr. Power Constr. 58(06), 58–66 (2021)
Li, H., Jia, R., Tan, G.: Fuzzy classification for time series on K-Shape. J. Univ. Electron. Sci. Technol. China 50(06), 899–906 (2021)
Wu, H., Xu, J., Wang, J., et al.: Autoformer: decomposition transformers with auto-correlation for long-term series forecasting. Adv. Neural Inf. Process. Syst. 34, 22419–22430 (2021)
China State Administration for Market Supervision and Regulation, China National Standardisation Administration. GB/T 40607-2021 Technical requirements for dispatching side forecasting system of wind or photovoltaic power. Beijing: Standards Press of China, 2021
Guantong, H., Lanxin, H.: Short-term load forecasting model based on EEMD-LSTS-ARIMA. J. Phys. Conf. Ser. 1684(1), 012045 (2020). IOP Publishing
Zhenyu, C., et al.: Ultra short-term power load forecasting based on combined LSTM-XGBoost model. Power Syst. Technol. 44(02), 614–620 (2020)
Xie, M., Chai, C., Guo, H., Wang, M.: Household electricity load forecasting based on pearson correlation coefficient clustering and convolutional neural network. In: Proceedings of 2020 4th International Conference on Electrical, Mechanical and Computer Engineering (ICEMCE 2020), vol. 1 (2020)
Deng, Z., Wang, B., Guo, H., et al.: Unified quantile regression deep neural network with time-cognition for probabilistic residential load forecasting. Complexity 2020, 1–18 (2020)
Chen, M., Liu, Q., Chen, S., et al.: XGBoost-based algorithm interpretation and application on post-fault transient stability status prediction of power system. IEEE Access 7, 13149–13158 (2019)
Bao, W.-Q., Chen, J., Xiong, T.: Research on short-term power load forecasting based on evolving neural network. Electr. Eng. (11), 46–49 (2019)
Ju, Y., Sun, G., Chen, Q., et al.: A model combining convolutional neural network and LightGBM algorithm for ultra-short-term wind power forecasting. IEEE Access 7, 28309–28318 (2019)
Meiying, Q., Yuxiang, L., Hui, T.: A similarity metric algorithm for multivariate based on information entropy and DTW. Acta Sci. Natur. Univ. Sunyatseni 58(02), 1–8 (2019)
Zhuo, C., Longxiang, S.: Short-term electrical load forecasting based on deep learning LSTM network. Electron. Technol. 47(01), 39–41 (2018)
Shi, H., Xu, M., Li, R.: Deep learning for household load forecasting—a novel pooling deep RNN. IEEE Trans. Smart Grid 9(5), 5271–5280 (2017)
Kumar, J., Goomer, R., Singh, A.K.: Long short term memory recurrent neural network (LSTM-RNN) based workload forecasting model for cloud datacenters. Procedia Comput. Sci. 125, 676–682 (2018)
Tan, F., Zhang, Z., Zhu, C., Zhang, J.: Optimized exponential smoothing foe load forecast. Power Demand Side Manag. 18(06), 22–26 (2016)
Al-Otaibi, R., Jin, N., Wilcox, T., et al.: Feature construction and calibration for clustering daily load curves from smart-meter data. IEEE Trans. Ind. Inform. 12(2), 645–654 (2016)
Computer Science Research; Studies from University of Padua Update Current Data on Computer Science Research (Sequence similarity measures based on bounded hamming distance). Computer Weekly News, 2016: 359
Cui, H., Peng, X.: Summer short-term load forecasting based on ARIMAX model. Power Syst. Prot. Control 43(04), 108–114 (2015)
Wang, X., Meng, L.: Ultra-short-term load forecasting based on EEMD-LSSVM. Power Syst. Prot. Control 43(1), 61–65 (2015)
Yu, Y., Mu, Y.: Research on interpolation algorithm. Mod. Comput. 1(05), 32–35 (2014)
Wei, R.R., Wei, Z.Z., Rong, R., et al.: Short term load forecasting based on PCA and LS-SVM. Adv. Mater. Res. 756, 4193–4197 (2013)
Bandyopadhyay, S., Saha, S.: Unsupervised Classification: Similarity Measures, Classical and Metaheuristic Approaches, and Applications. Springer, Berlin, Heidelberg (2013). https://doi.org/10.1007/978-3-642-32451-2
Wang, W.: Coefficient of variation - a simple and useful statistical indicator to measure the degree of dispersion. China Stati. 306(06), 41–42 (2007)
Chen, Y., Wang, L., Long, H.: Short-term load forecasting with model neural network. Proc. CSEE 04(18), 79–82 (2001)
Xu, D.: A further study on the exponential smoothing estimation method for parameters of forecasting model and its application. Syst. Eng. Theory Pract. 19(2), 25–30 (1999)
McLeod, I.: Derivation of the theoretical autocovariance function of autoregressive-moving average time series. Appl. Stat. 24(2), 255–256 (1975)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Tang, Y. et al. (2023). The Load Forecasting of Special Transformer Users Based on Unsupervised Fusion Model. In: Yang, Y., Wang, X., Zhang, LJ. (eds) Artificial Intelligence and Mobile Services – AIMS 2023 . AIMS 2023. Lecture Notes in Computer Science, vol 14202. Springer, Cham. https://doi.org/10.1007/978-3-031-45140-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-45140-9_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45139-3
Online ISBN: 978-3-031-45140-9
eBook Packages: Computer ScienceComputer Science (R0)