Integrating Gradient Search, Logistic Regression and Artificial Neural Network for Profit Based Unit Commitment

DOI

10.1080/18756891.2013.862355How to use a DOI?

Keywords

Artificial neural network, Competitive environment, Deregulation, Gradient search, Logistic Regression, Profit Based Unit Commitment, Restructured system

Abstract

As the electrical industry restructures many of the traditional algorithms for controlling generating units, they need either modification or replacement. In the past, utilities had to produce power to satisfy their customers with the objective to minimize costs and actual demand/reserve were met. But it is not necessary in a restructured system. The main objective of restructured system is to maximize its own profit without the responsibility of satisfying the forecasted demand. The Profit Based Unit Commitment (PBUC) is a highly dimensional mixed-integer optimization problem, which might be very difficult to solve. Hence integrating Optimization Technique Gradient Search (GS), Logistic Regression (LR) and Artificial Neural Network (ANN) approach is introduced in this paper considering power and reserve generating in order to receive the maximum profit in three and ten unit system by considering the softer demand. Also this method gives an idea regarding how much power and reserve should be sold in markets. The proposed approach has been tested on a power system with 3 and 10 generating units. Simulation results of the proposed approach have been compared with the existing methods. It is observed that the proposed algorithm provides maximum profit compared to existing methods.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - JOUR
AU  - A. Amudha
AU  - C. Christober Asir Rajan
PY  - 2014
DA  - 2014/02/03
TI  - Integrating Gradient Search, Logistic Regression and Artificial Neural Network for Profit Based Unit Commitment
JO  - International Journal of Computational Intelligence Systems
SP  - 90
EP  - 104
VL  - 7
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.1080/18756891.2013.862355
DO  - 10.1080/18756891.2013.862355
ID  - Amudha2014
ER  -