Dynamic Load Modeling Based on Extreme Learning Machine

Abstract:

The dynamic load characteristics have significant impact on the power flow, transient stability computation, voltage stability calculation of the power system, and so on. Noticing that traditional mechanism loads model has difficulty in precisely describing the dynamic characteristics of synthetic load, this paper presents a non-mechanism dynamic load model based on Extreme Learning Machine (ELM). The Power Fault Recorder and Measurement System (PFRMS) is used to obtain data for load modeling. Take voltage and real/reactive power with different time delay as inputs, and take real/reactive power as output, train the ELM using the samples formed by fault data, the real power model and reactive power model are established respectively. The number of hidden layer nodes which has impact on the ELM model is also discussed. Dynamic simulation experiment is conducted at power system dynamic simulation laboratory. The simulation result shows that the ELM load model is simple and flexible, its parameters are easy to be identified. The ELM load model can describe the dynamic load characteristics accurately.

• Periodical: Applied Mechanics and Materials (Volumes 195-196)
• Pages: 1043-1048
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.195-196.1043
• Online since: August 2012
• Authors: Zhong Hui Liu, Zhen Shu Wang, Mei Hua Su
• Keywords: Dynamic Load Modelling, Extreme Learning Machine, Measurement System, Parameter Identification, Power Fault Recorder

References

[1] IEEE task Force. Bibliography on load models for power flow and dynamic performance simulation, IEEE Transactions on Power System, vol. 9, no. 4, pp.1868-1874, (1999).

[2] X. Fang, N. Yang, et al. Application of load model to transient stability calculation of electric power system, Automation of Electric Power Systems, vol. 23, no. 19, pp.48-50, 1999. (in Chinese).

[3] D. Hang, R. He, et al. Effect of Uncertainty in Load Model on Power System Dynamic Simulation, Proceedings of the CSEE, vol. 28, no. 12, pp.69-74, 2008. (in Chinese).

[4] D. Zhang, Y. Tang, et al. A Survey Paper of Application and Research of Power System Load Model in Power Utilities, Power System Technology, vol. 31, no. 4, pp.16-23, 2007. (in Chinese).

[5] P. Ju, D. Ma, et al. Power System Load Modeling, 2rd ed., Beijing，CEPP Press，2008. (in Chinese).

[6] Hiyama T, Tokieda M. Artificial neural network based dynamic load modelling, IEEE Trans on Power Systems, vol. 12, no. 4, pp.1576-1582, (1997).

DOI: 10.1109/59.627861

[7] S. Shen, S. Zhu, et al. Application of fast back propagation neural networks in power system dynamic load modeling, Automation of Electric Power Systems, vol. 23, no. 19, pp.8-11, 33, 2009. (in Chinese).

[8] Mahinda D, Vilathgamuwa, Wijekoon H.M. Representation of power system load dynamics with ANN for real-time application, Power Engineering Society General Meeting, Singapore, pp.91-96, (2003).

DOI: 10.1109/pes.2003.1267406

[9] Z. Wang, L. Li, L. Niu. Load Modeling Based on Support Vector Machine Based on Bayesian Evidence Framework, Transactions of China Electrotechnical Society, vol. 24, no. 8, pp.127-134, 140, 2009. (in Chinese).

[10] G. Huang, Q. Zhu, et al. Extreme Learning Machine: Theory and applications, NEUROCOMPUTER, vol. 71, no. 13, pp.489-501, (2006).

[11] Y. Chang, F. Wang, et al. Soft Sensing Modeling Based on Extreme Learning Machine for Biochemical Processes, Journal of System Simulation, vol. 19, no. 23, pp.5587-5590, 2007. (in Chinese).

[12] Z. Zhu, F. Han, et al. The Comparative Study between ELM and SVM on Predicting the Postoperative Survival Time of NSCLC Patients, Pattern Recognition and Artificial Intelligence, vol. 18, no. 5, pp.636-640, 2007. (in Chinese).

[13] D. Zhang, Y. Tang, et al. Power Utility Non-technical Loss Analysis with Extreme Learning Machine Method, IEEE TRANSACTION ON POWER SYSTEM, vol. 23, no. 3, pp.946-955, 2008. (in Chinese).

DOI: 10.1109/tpwrs.2008.926431

[14] Z. Wang, B. Zhang, X. Li. A Novel Type of Power Fault Recording and Monitoring System, Automation of Electric Power Systems, vol. 31, no. 10, pp.92-96, 101, 2007. (in Chinese).