Voltage estimation using ICA on distribution system

This paper presents a method to estimate voltage profiles on source distribution system using Independent Component Analysis (ICA) algorithm. The profiles are estimated for 24- hours with time interval of 1 minute. The objective of this research is to reduce loss by controlling source of voltage per-unit. When voltage source is controlled, the losses occur on the system is reduced drastically. Power System Simulation for Engineering (PSS™E) Software and Python Programming was used in the simulation of IEEE 69 test bus system, while ICA is programmed using MATLAB R2012b version. The losses of simulation results with different tap changer and voltage set are compared and discussed in this paper.

[1]  Zuhaina Zakaria,et al.  Nodal Load Profiles Estimation for Time Series Load Flow Using Independent Component Analysis , 2012 .

[2]  S. P. Chowdhury,et al.  Intelligent algorithm for optimal meter placement and bus voltage estimation in ring main distribution system , 2012 .

[3]  M. M. Hussain,et al.  FastICA techniques for load profiles estimation , 2012, 2012 IEEE Symposium on Industrial Electronics and Applications.

[4]  Jean-Francois Cardoso,et al.  Blind signal separation: statistical principles , 1998, Proc. IEEE.

[5]  Dagmar Niebur,et al.  Exploring independent component analysis for electric load profiling , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[6]  Aapo Hyvärinen,et al.  Gaussian moments for noisy independent component analysis , 1999, IEEE Signal Processing Letters.

[7]  Michel. edited by Michel Crappe. Crappe,et al.  Electric power systems , 2008 .

[8]  Z.I. Choudhry.  Electric power delivery to big cities , 2008, 2008 IEEE/PES Transmission and Distribution Conference and Exposition.

[9]  Jing Liu,et al.  A New Algorithm of Blind Source Separation Based on ICA , 2009, 2009 WRI World Congress on Computer Science and Information Engineering.