Voltage Coordination of FACTS Devices in Power Systems Using RL-Based Multi-Agent Systems

Tousii, M. R.; Hosseinianii, S. H.; Menhaji, Mohammad B

doi:10.22060/eej.2009.283

دانشگاه صنعتی امیرکبیر

تعداد نشریات	4
تعداد شماره‌ها	157
تعداد مقالات	1,845
تعداد مشاهده مقاله	1,007,722
تعداد دریافت فایل اصل مقاله	784,090

Voltage Coordination of FACTS Devices in Power Systems Using RL-Based Multi-Agent Systems

AUT Journal of Electrical Engineering

مقاله 5، دوره 41، شماره 2، زمستان 2009، صفحه 39-49 اصل مقاله (253 K)

نوع مقاله: Research Paper

شناسه دیجیتال (DOI): 10.22060/eej.2009.283

نویسندگان

M. R. Tousii^* ¹؛ S. H. Hosseinianii²؛ Mohammad B Menhaji³

¹Corresponding Author, M. R. Tousi is PhD student in Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran (e-mail: smr_tousi@yahoo.com).

²S. H. Hosseininan is with the Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran (e-mail: Hosseininan@aut.ac.ir).

³M. B. Menhaj is with the Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran (e-mail: tmenhaj@ieee.org).

چکیده

This paper describes how multi-agent system technology can be used as the underpinning platform for voltage control in power systems. In this study, some FACTS (flexible AC transmission systems) devices are properly designed to coordinate their decisions and actions in order to provide a coordinated secondary voltage control mechanism based on multi-agent theory. Each device here is modeled as an agent being able to cooperate and communicate with other devices. In this system, individual autonomous agents and intelligent decision makers learn to perform optimal actions through proper interactions with their environments. The SARSA Q-learning, which is an on-policy algorithm in reinforcement learning (RL) is then used and tested successfully in voltage control problem. In this research, the Java Agent DEvelopment (JADE) platform is used to implement the agents and to simulate their communications. The power system is also fully implemented in Java. The proposed intelligent MA based method is finally applied to IEEE 39-buses New England power system. The results of simulation better highlight the merit of the method and its ability in coordinating FACTS devices for removing voltage disturbances.

کلیدواژه ها

Multi-Agent Systems (MAS)؛ Secondary Voltage Control؛ Voltage Coordination؛ Reinforcement Learning؛ Java Agent Development (JADE) Framework

عنوان مقاله [English]

Voltage Coordination of FACTS Devices in Power Systems Using RL-Based Multi-Agent Systems

نویسندگان [English]

چکیده [English]

کلیدواژه ها [English]

Multi-Agent Systems (MAS), Secondary Voltage Control, Voltage Coordination, Reinforcement Learning, Java Agent Development (JADE) Framework

مراجع

[1] H. Lefebvre, D. Fragnier, and J. Y. Boussion, “Secondary coordinated voltage control system: Feedback of EDF”, in Proc. IEEE/PES Summer Meeting, Seattle, USA, July, 2000, pp. 291-295.

[2] H. F. Wang, “Multi-agent co-ordination for the secondary voltage control in power system contingencies,” in Proc. Inst. Elect. Eng. C, 2001, pp. 61–66.

[3] Hai Feng Wang,, H. Li, and H. Chen “Coordinated Secondary Voltage Control to Eliminate Voltage Violations in Power System Contingencies,” IEEE Trans. on Power Systems, Vol. 18, No. 2, May 2003.

[4] J. P. Paul, J. Y. Leost, and J. M. Tesseron, “Survey of the secondary voltage control in France: present realization and investigation”, IEEE Trans. on Power System, 2 (2), 1987, pp. 505-511.

[5] J. P. Paul and J. Y. Leost, “Improvements of the secondary voltage control in France,” in IFAC Symp. on Power Syst. Power Plants Control, Beijing, China, 1986.

[6] Mats Larsson, “Coordinated Voltage Control in Electric Power Systems,” Doctoral Dissertation, Lund University, Sweden, 2000, pp55-60.

[7] Sheng Gehao, Jiang Xiuceng, and Zeng Yi , “Optimal Coordination For Multi-Agent Based Secondary Voltage Control in Power System,” IEEE/PES Transmission and Distribution Conference & Exhibition: Asia and Pacific, Dalian, China, 2005.

[8] JADE – Java Agent DEvelopment Framework, see: http://jade.tilab.com/

[9] Foundation for Intelligent Physical Agents (FIPA), see: http://www.fipa.org/.

[10] D. P. Bertsekas and J. N. Tsitsiklis, Neuro-Dynamic Programming. Belmont, MA: Athena Scientific, 1996.

[11] L. P. Kaelbling, M. L. Littman, and A. W. Moore, “Reinforcement learning: A survey,” J. Artif. Intell. Res., vol. 4, pp. 237–285, Jan.–June 1996.

[12] R. S. Sutton and A. G. Barto, “Reinforcement learning: An introduction,” Adaptive Computations and Machine Learning, 1998.

[13] J. G. Vlachogiannis and N. D. Hatziargyriou, “Reinforcement Learning for Reactive Power Control,” IEEE Trans on Power System, Vol. 19, No. 3, August 2004.

[14] C.Rehtanz, “Autonomous Systems and Intelligent Agents in Power System Control and Operation” , Springer , ISBN 3-540-40202-0.

[15] Russell, S. J. and Norvig, “Artificial Intelligence: a Modern Approach”, Prentice Hall, 2nd edition, 2003.

[16] M.Wooldridge, “An Introduction to Multi-agent Systems”, Wiley Press, May 2002

[17] KAI HUANG, “Shipboard Power System Reconfiguration Using Multi-Agent System”, Ph.D. dissertation, Dept. Elec. Eng., The Florida State University, summer 2007.

[18] J. M. Solanki,N. N. Schulz, “Using Intelligent Multi-agent System for Shipboard Power Systems Reconfiguration”, Proceedings of the 13th International Intelligent Systems Application to Power Systems, Nov. 2005.

[19] D.P. Buse , Q.H.Wu, “ " IP network-based multi-agent systems for industrial automation : information management, condition monitoring and control of power systems”, SPRINGER, 2007, ISBN 978-1-84628-646-9.

[20] InterPSS Power System Simulation Project, see: http://www.interpss.org

[21] Marek Zima, Damien Ernst, “On multi-area control in electric power systems”, Proc. 15th Power System Computation Conference, Liege (Belgium), 2005.

آمار

تعداد مشاهده مقاله: 1,455

تعداد دریافت فایل اصل مقاله: 1,046

Journal Management System. Designed by sinaweb.