A Novel Application for Optimization Utility in Smart Grid using Machine Learning Technique

5 Pages Posted: 11 Apr 2019

See all articles by Ravindra Kumar Chahar

Ravindra Kumar Chahar

Galgotias University

S.V.A.V. Prasad

Lingaya's University

Rafeeq Ahmad

Jamia Millia Islamia

Date Written: March 11, 2019


The use of machine learning techniques in an optimization utility is described in the paper. Earlier systems which use classical approaches for optimization lack inclusion of risk analysis, whereas recently the different approaches stress on the need for its inclusion. The proposed approach is based on using Taguchi’s Loss function as a factor for risk parameter. The risk parameter is computed using two factors, the analysis of these factors which is based on a simple machine learning classification is presented here. Lastly, risk computation using a deep learning method is discussed. The scheme dis-cussed here could prove beneficial for a designer who wants to include risk contribution accounting for uncertainties in system modeling. Such a scheme would be helpful in minimizing the overall cost comprising of operation cost and risk, whereas this utility is not desired to minimize the cost alone.

Keywords: Optimization, Machine Learning, Deep Learning, Big Data, Risk

Suggested Citation

Chahar, Ravindra Kumar and Prasad, S.V.A.V. and Ahmad, Rafeeq, A Novel Application for Optimization Utility in Smart Grid using Machine Learning Technique (March 11, 2019). Proceedings of 2nd International Conference on Advanced Computing and Software Engineering (ICACSE) 2019. Available at SSRN: https://ssrn.com/abstract=3350302 or http://dx.doi.org/10.2139/ssrn.3350302

Ravindra Kumar Chahar (Contact Author)

Galgotias University ( email )

Plot No.2, Sector 17-A
Yamuna Expressway
Greater Noida, UT Uttar Pradesh 201306

S.V.A.V. Prasad

Lingaya's University ( email )


Rafeeq Ahmad

Jamia Millia Islamia ( email )

New Delhi 110025

Here is the Coronavirus
related research on SSRN

Paper statistics

Abstract Views
PlumX Metrics