Hybrid genetic algorithms for forecasting power systems state variables

Author

Kurbatsky, Victor ; Tomin, Nikita ; Sidorov, Denis ; Spiryaev, Vadim

Author_Institution

Electr. Power Syst., Energy Syst. Inst., Irkutsk, Russia

fYear

2013

fDate

16-20 June 2013

Firstpage

1

Lastpage

6

Abstract

A problem of forecasting state variables of electric power system is studied. The paper suggests data-driven adaptive approach based on hybrid-genetic algorithm which combines the advantages of genetic algorithm and simulated annealing algorithm. The input signal is decomposed into orthogonal basis functions using the Hilbert-Huang transform. The hybrid-genetic algorithm is applied to optimal training of the support vector machine and artificial neural network. The results of applying the developed approach for the short-term forecasts of active power flows in the electric networks are presented. The best efficiency of proposed approach is demonstrated on real retrospective data of active power flow forecast using the hybrid-genetic support vector machine algorithm empowered with the Hilbert-Huang transform.

Keywords

Hilbert transforms; genetic algorithms; load flow; load forecasting; neural nets; power engineering computing; simulated annealing; support vector machines; Hilbert-Huang transform; active power flows short-term forecasts; artificial neural network; data-driven adaptive approach; hybrid genetic algorithms; hybrid-genetic algorithm; orthogonal basis functions; power systems state variables forecasting; simulated annealing algorithm; support vector machine; Artificial neural networks; Forecasting; Genetic algorithms; Load flow; Predictive models; Support vector machines; ANN; Hilbert-Huang transform; active power flow; forecast; genetic algorithm; support vector machine;

fLanguage

English

Publisher

ieee

Conference_Titel

PowerTech (POWERTECH), 2013 IEEE Grenoble

Conference_Location

Grenoble

Type

conf

DOI

10.1109/PTC.2013.6652215

Filename

6652215