Abstract
Cluster analysis of power loads can not only accurately extract the commonalities and characteristics of the loads, but also help to understand the users’ habits and patterns of electricity consumption, so as to optimize the power dispatching and regulate the operation of the entire power grid. Based on the traditional clustering methods, this paper proposes a clustering algorithm that can automatically determine the optimal cluster number. Firstly, Fast-DTW algorithm is used as the similarity measuring function to calculate the similar matrix between two time series, and then Spectral Clustering and Affinity Propagation (AP) algorithm are used for clustering. It is combined with Euclidean distance, DTW and Fast-DTW algorithms to evaluate the algorithm effect. By analyzing the actual power data, our results show that the improved external performance evaluation index ARI, AMI and internal performance evaluation index SSE are significantly improved and have better time series similarity and accuracy. Applying the algorithm to more than six thousands of users, twelve kinds of typical power load patterns can be obtained. For any other load curve, it can be mapped to a standard load by feature extraction. The corresponding prediction model is adopted, which is of great significance to reduce the peak power consumption, adjust the electricity price appropriately and solve the problem of system balance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Panapakidis, I.P., Christoforidis, G.C.: Implementation of modified versions of the K-means algorithm in power load curves profiling. Sustain. Cities Soc. 35, 83–93 (2017)
Gao, Z., Li, Z., Bao, S.: Short term prediction of photovoltaic power based on FCM and CG DBN combination. J. Electr. Eng. Technol. 15, 333–341 (2020)
Fu, X., Zeng, X.J., Feng, P., Cai, X.: Clustering-based short-term load forecasting for residential electricity under the increasing-block pricing tariffs in China. Energy 165, 76–89 (2018)
Khan, Z.A., Jayaweera, D., Alvarez-Alvarado, M.S.: A novel approach for load profiling in smart power grids using smart meter data. Electr. Power Syst. Res. 165, 191–198 (2018)
Rajabi, A., Eskandari, M., Ghadi, M.J., Li, L., Zhang, J., Siano, P.: A comparative study of clustering techniques for electrical load pattern segmentation. Renew. Sustain. Energy Rev. 120, 109628 (2019)
Charwand, M., Gitizadeh, M., Siano, P., Chicco, G., Moshavash, Z.: Clustering of electrical load patterns and time periods using uncertainty-based multi-level amplitude thresholding. Int. J. Electr. Power Energy Syst. 117, 105624 (2020)
Motlagh, O., Berry, A., O’Neil, L.: Clustering of residential electricity customers using load time series. Energy 237, 11–24 (2019)
Janani, R., Vijayarani, S.: Text document clustering using spectral clustering algorithm with particle swarm optimization. Expert Syst. Appl. 134, 192–200 (2019)
Zhao, Y., Yuan, Y., Nie, F., Wang, Q.: Spectral clustering based on iterative optimization for large-scale and high-dimensional data. Neurocomputing 318, 227–235 (2018)
Wan, Y., Chen, X.-L., Shi, Y.: Adaptive cost dynamic time warping distance in time series analysis for classification. J. Comput. Appl. Math. 319, 514–520 (2017)
Han, T., Peng, Q., Zhu, Z., Shen, Y., Huang, H., Abid, N.N.: A pattern representation of stock time series based on DTW. Phys. A Stat. Mech. Appl. 550, 124161 (2020)
Kang, Z., et al.: Multi-graph fusion for multi-view spectral clustering. Knowl.-Based Syst. 189, 105102 (2019)
Salvadora, S., Chan, P.: Toward accurate dynamic time warping in linear time and space. Intell. Data Anal. 11, 561–580 (2007)
Cao, Y., Rakhilin, N., Gordon, P.H., Shen, X., Kan, E.C.: A real-time spike classification method based on dynamic time warping for extracellular enteric neural recording with large waveform variability. J. Neurosci. Methods 261, 97–109 (2016)
Han, Y., Wu, H., Jia, M., Geng, Z., Zhong, Y.: Production capacity analysis and energy optimization of complex petrochemical industries using novel extreme learning machine integrating affinity propagation. Energy Convers. Manag. 180, 240–249 (2019)
Alcock, R.: Synthetic control chart time series data set (1999). http://archive.ics.uci.edu/ml/machine-learning-databases/synthetic_control-mld/. Accessed via UCI
CER smart metering project-electricity customer behaviour trial (2017). http://www.ucd.ie/issda/data/commissionforenergyregulationcer/. Accessed via the Irish Social Science Data Archive
Xie, J., Gao, H., Xie, W.: Robust clustering by detecting density peaks and assigning points based on fuzzy weighted K-nearest neighbors. Inf. Sci. 354, 19–40 (2016)
Xie, J., Zhou, Y., Ding, L.: Local standard deviation spectral clustering. In: IEEE International Conference on Big Data and Smart Computing, vol. 143, pp. 242–250 (2018)
Martiniano, A., Ferreira, R.P., Sassi, R.J.: Absenteeism at work Data Set (2010). http://archive.ics.uci.edu/ml/datasets/Absenteeismatwork/. Accessed via UCI
Acknowledgment
This work is supported by the National Nature Science Foundation of China (No. 61972357, No. 61672337).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Bi, Z., Leng, Y., Liu, Z., Li, Y., Fuentes, S. (2020). An Improved Spectral Clustering Algorithm Using Fast Dynamic Time Warping for Power Load Curve Analysis. In: Liu, J., Gao, H., Yin, Y., Bi, Z. (eds) Mobile Computing, Applications, and Services. MobiCASE 2020. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 341. Springer, Cham. https://doi.org/10.1007/978-3-030-64214-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-64214-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-64213-6
Online ISBN: 978-3-030-64214-3
eBook Packages: Computer ScienceComputer Science (R0)