Preprint Article Version 1 This version is not peer-reviewed

Hybrid GA-PSO Optimization of Artificial Neural Network for Forecasting Electricity Demand

Version 1 : Received: 28 November 2017 / Approved: 29 November 2017 / Online: 29 November 2017 (12:39:09 CET)
Version 2 : Received: 15 January 2018 / Approved: 16 January 2018 / Online: 16 January 2018 (07:44:04 CET)

How to cite: Anand, A.; Suganthi, L. Hybrid GA-PSO Optimization of Artificial Neural Network for Forecasting Electricity Demand. Preprints 2017, 2017110190 (doi: 10.20944/preprints201711.0190.v1). Anand, A.; Suganthi, L. Hybrid GA-PSO Optimization of Artificial Neural Network for Forecasting Electricity Demand. Preprints 2017, 2017110190 (doi: 10.20944/preprints201711.0190.v1).

Abstract

In  the present study, a hybrid  optimizing algorithm has been proposed using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) for Artificial Neural Network (ANN) to improve the estimation of  electricity demand of  the state of Tamil Nadu in India. The GA-PSO model optimizes  the coefficients of factors of  gross state domestic product (GSDP), per capita demand, income and  consumer price index (CPI) that affect the electricity demand. Based on historical data of 25 years from 1991 till 2015 , the simulation results of GA-PSO models  are having greater accuracy and reliability than single optimization methods based on either PSO or GA. The forecasting results of ANN-GA-PSO are better than models based on single optimization such as  ANN-BP, ANN-GA, ANN-PSO models. Further  the paper also forecasts the electricity demand of Tamil Nadu  based on two scenarios. First scenario is the "as-it-is" scenario , the second scenario  is based on milestones set for achieving goals of "Vision 2023" document for the state. The present research also explores the causality between the economic growth and electricity demand in case of Tamil Nadu. The research indicates that the direct causality exists between  GSDP and the electricity demand of the state.

Subject Areas

Electricity Demand; ANN; PSO; GA; Hybrid Optimization; Quadratic; Gross State Domestic Product; Forecasting.

Readers' Comments and Ratings (4)

Importance: How significant is the paper to the field?
Outstanding/highlight paper
0%
Significant contribution
100%
Incremental contribution
0%
No contribution
0%
Soundness of evidence/arguments presented:
Conclusions well supported
100%
Most conclusions supported (minor revision needed)
0%
Incomplete evidence (major revision needed)
0%
Hypothesis, unsupported conclusions, or proof-of-principle
0%
Comment 1
Received: 30 November 2017
The commenter has declared there is no conflict of interests.
Comment: The article integrates genetic algorithm and particle swarm optimization for the artificial neural network which gives better forecasting results. This research gives researchers a better way to think a step ahead in the area of forecasting the electricity and energy demand.
+ Respond to this comment
Comment 2
Received: 30 November 2017
The commenter has declared there is no conflict of interests.
Comment: The article is well written and gives a clear vision for the readers and focusses the key point
+ Respond to this comment
Comment 3
Received: 3 December 2017
Commenter: Navneet garg
The commenter has declared there is no conflict of interests.
Comment: Article is futuristic and gives defibining arguments for policy work for the government..accurate forecasting is the need for the govt to budget their future capex and optimising current op-ex..
+ Respond to this comment
Comment 4
Received: 4 December 2017
The commenter has declared there is no conflict of interests.
Comment: The paper is well structured and written and the conclusions are supported by the analysis of the data presented.
+ Respond to this comment
Leave a public comment
Send a private comment to the author(s)
Rate this article
Views 0
Downloads 0
Comments 4
Metrics 0
Leave a public comment

×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.