Substation Bus Reactive Load Forecasting in Large Iron and Steel Enterprise

Abstract:

Impact loads in large iron and steel enterprise bring the power system reactive power impact, which makes the fluctuation of the system voltage, power factor and other parameters are out of the limitation of the national standard. Substation bus reactive load forecasting in large iron and steel enterprise can be introduced to determine reactive power optimization strategy and the switching of capacitors. In this paper, a combination forecasting model of quadratic self-adaptive exponential smoothing (QSES) model and converse exponential (CE) model has been proposed for substation bus reactive load forecasting. The numerical results in Jinan iron and steel Group show the application of this model is encouraging. Introduction

• Periodical: Advanced Materials Research (Volumes 433-440)
• Pages: 6168-6174
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.433-440.6168
• Online since: January 2012
• Authors: Li Mu, Jia Chuan Shi, Xian Quan Li
• Keywords: Combination Forecasting Model, Iron and Steel Enterprises, Quadratic Self-Adaptive Exponential Smoothing Model, Ultra-Short Time Reactive Load Forecasting

References

[1] Dongxiao Niu, Shuhua Cao, Lei Zhao ect., The technology of electric power forecasting and its application, Beijing: China Electric Power Press, (1998).

[2] Xinqi Shi, Xiuhua Du, Research on short term load forecasting in steel enterprise, Proceedings of the 4th World Congress on Intelligent Control and Automation, 10-14 June 2002, pp.1097-1100.

DOI: 10.1109/wcica.2002.1020747

[3] Swiatek Boguslaw, Klempka Ryszard, Dzieza Jerzy, Artificial neural network in day-ahead electricity load forecasting for large steel factory, CIRED 18th international Conference and Exhibition on Electricity Distribution, 6-9 June 2005, pp.1-4.

DOI: 10.1049/cp:20051387

[4] Escobar A. M., Pere L. P., Application of support vector machines and ANFIS to the short-term load forecasting, Transmission and Distribution Conference and Exposition: latin America, 2008 IEEE/PES, 13-15 Aug. 2008, pp.1-5.

DOI: 10.1109/tdc-la.2008.4641839

[5] S.J. Huang and K. R. Shih, short-term load forecasting via ARMA model identification in cluding non Gaussian process considerations, IEEE Trans. Power Syst., vol. 18, no. 2, pp.673-679, May. (2003).

DOI: 10.1109/tpwrs.2003.811010

[6] L. Mohan Saini and M. Kumar Soni, Artificial neural network-based peak load forecasting using conjugate gradient methods, IEEE Trans. Power Syst., vol, 17, no. 3, pp.907-912, Aug. (2002).

DOI: 10.1109/tpwrs.2002.800992

[7] Donghong Zhao, Wenying Liu, New Combined Load Forecasting Method Based on Model Characteristics, Modern electric power, 2008, 25(6): 21-26.