Application of Neuro-Fuzzy Dynamic Programming to Improve the Reactive Power and Voltage Profile of a Distribution Substation

Improving the reactive power and voltage profile of a distribution substation is investigated in this paper. The purpose is to properly determination of the shunt capacitors on/off status and suitable tap changer (TC) position of a substation transformer. In addition, the limitation of secondary bus voltage, the maximum allowable number of switching operation in a day for on load tap changer and on/off status of capacitors are taken into account. To achieve these goals, an artificial neural network (ANN) is designed to provide preliminary scheduling. Input of ANN is active and reactive powers of transformer and its primary and secondary bus voltages. The output of ANN is capacitors on/off status and TC position. The preliminary schedule is further refined by fuzzy dynamic programming in order to reach the final schedule. The operation of proposed method in Q/V improving is compared with the results obtained by operator operation in a distribution substation.




References:
[1] Feng - Chang Lu , Yuan - Yih Hsu , " Fuzzy Dynamic PROGRAMMING
Approach to Reactive Power/Voltage Control in a Distribution
Substation " IEEE Trans. on Power System , Vol. 12, No. 2, May 1997,
pp. 681 - 688.
[2] Yuan - Yih Hsu , Fen - Chang Lu, " A Combined Artificial Neural
Network - Fuzzy Dynamic Programming Approach to Reactive
Power/Voltage Control in a Distribution Substation ", IEEE Trans. on
Power systems, Vol.13, No. 4, November 1998, pp.1265-1271.
[3] F. C. LU, Y. Y. HSU, "Reactive Power/Voltage Control in a Distribution
Substation Using Dynamic Programming" IEE Proc. Generation
Transmission and Distribution, Vol. 142, No. 6. November 1995, pp. 639
- 645.
[4] K. Warwick, A. Ekwure, R. Aggarwal, "Artificial Intelligence
Techniques in Power Systems", IEE Power Engineering Series 22,
Bookcratt Printed, pp. 17-19, 1997.
[5] K. Tomosovic, "A Fuzzy Linear Programming Approach to the Reactive
Power/Voltage Control Problem", IEEE Trans. Power Systems, 1992,
pp. 87-293.