Education, Science, Technology, Innovation and Life
Open Access
Sign In

Motor Group Aggregation of Refinery and Chemical Enterprises Based on Hierarchical Clustering Algorithm

Download as PDF

DOI: 10.23977/jaip.2020.040102 | Downloads: 15 | Views: 1262


Qi Qi 1,2, Yi Wang 2


1 China Electric Power Research Institute, Beijing 100192, China
2 Sinopec Luoyang Branch, Luoyang 471012, Henan, China

Corresponding Author

Qi Qi


The electric load of the refinery and chemical enterprises is mainly induction motors. When the statistical synthesis method is used to establish the load model, it is an important research content to improve the aggregation accuracy of the motor group. The clustering feature is determined by analyzing the sensitivity of each parameter of the motor model to the power trajectory. The hierarchical clustering algorithm in machine learning is applied to the classification of the motor group, and the motor aggregation is carried out according to the classification result. Through an example, the simulation results show that, compared with the equivalent of one motor group, the hierarchical clustering algorithm can improve the accuracy of motor group aggregation. 


Motor group aggregation; Hierarchical clustering; Load modeling


Qi Qi, Yi Wang. Motor Group Aggregation of Refinery and Chemical Enterprises Based on Hierarchical Clustering Algorithm. Journal of Artificial Intelligence Practice (2021) Vol. 4: 13-22. DOI:


[1] CIGRE Task Force. Load modeling and dynamics [J]. Electra, 1990(130): 124-141.
[2] Pereira L, Kosterev D, Mackin P, et al. An interim dynamic induction motor model for stability studies in the WSCC [J]. IEEE
[3] IEEE Task Force. Load representation for dynamic performance analysis [J]. IEEE Transaction on Power Systems, 1993, 8(2): 472-482.
[4] IEEE Task Force. Standard load models for power flow and dynamic performance simulation [J]. IEEE Transaction on Power Systems, 1995, 10(3) :1302-1313.
[5] Bing Zhao, Yong Tang, Wenchao Zhang. Study on single- unit equivalent algorithm of induction motor group [J]. Proceedings of the CSEE, 2009, 29(19) :43-49.
[6 ]Hou J X, Tang Y, Zhang H B, “Study on Integration Method for Induction Motor”, Power System Technology, vol. 45, no. 18, pp. 2546–2554, 2007.
[7] NOZA RI F , KANHAM M D, PRICE W W . Aggregation of induction motors for transient stability load modeling .IEEE Trans on Power Systems, 1987, 2(4):1096-1103.
[8] T ALEB M , AKBABA M , ABDU LLAH E A .Aggregation of induction machines for power system dynamic studies . IEEE Trans on Power Systems , 1994 , 9(4):2042-2048 .
[9] AHMED-ZAID S , TALEBM .Structural modeling of small and large induction machines using integral manifolds. IEEE Trans on Energy Conversion, 1991 , 6(3):529-535.
[10] FRANKLIN D C , MORE LATO A. Improving dynamic aggregation of induction mot or models. IEEE Trans on Power Systems, 1994 , 9(4):1934-1941 .
[11] KUNDUR P. Power system stability and control [M]. New York, USA :McGraw-Hill, 1994.
[12] Hiskens I A, Pai M A. Trajectory sensitivity analysis of hybrid systems. IEEE Transactions on Circuits and Systems Part I: Regular Papers, 2000,47(2): 204-220.
[13] China Electric Power Research Institute, et al. One of the Special Issues on Power System Model Parameters Research. Power System Technology, 2007, 31 (4): 1-78.
[14] Leskovec J, Rajaraman A, Ullman J David, Wang Bin, et al. Translation. Big Data: Large-scale Internet Data Mining and Distributed Processing[M]. Beijing: People's Posts and Telecommunications Publishing House, 2015.

Downloads: 6668
Visits: 189590

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.