Title :
A comparative analysis of SVM and ANN based hybrid model for short term load forecasting
Author :
Selakov, A. ; Ilic, Slobodan ; Vukmirovic, Srdan ; Kulic, Filip ; Erdeljan, A. ; Gorecan, Z.
Author_Institution :
Telvent DMS, Serbia
Abstract :
This paper represents comparison of two artificial intelligence based hybrid models for short term load forecasting (STLF). Models have the same input/output architecture and are built on SVM and ANN technologies, respectively. Algorithm consists of two modules connected in a sequence, and output from first module is connected as additional input to second module. First module acts as a predictor of maximal load of forecasting day and second acts as hourly load predictor. Models are part of large STLF solution and in respect to computational and memory limitations simple input space is designed. This architecture enables short training time which is targeted for frequent re-training needs in modern utilities due to frequent change in customer number and behavior.
Keywords :
artificial intelligence; load forecasting; neural nets; power engineering computing; support vector machines; ANN technology; STLF solution; SVM technology; artificial intelligence based hybrid models; artificial neural networks; computational limitations; forecasting day maximal load; hourly load predictor; memory limitations; short term load forecasting; support vector machines; Artificial neural networks; Forecasting; Load forecasting; Load modeling; Predictive models; Support vector machines; Training; Artificial neural networks; demand forecasting; support vector machines;
Conference_Titel :
Transmission and Distribution Conference and Exposition (T&D), 2012 IEEE PES
Conference_Location :
Orlando, FL
Print_ISBN :
978-1-4673-1934-8
Electronic_ISBN :
2160-8555
DOI :
10.1109/TDC.2012.6281502
