Short-term load forecasting of Australian National Electricity Market by an ensemble model of extreme learning machine

Artificial Neural Network (ANN) has been recognized as a powerful method for short-term load forecasting (STLF) of power systems. However, traditional ANNs are mostly trained by gradient-based learning algorithms which usually suffer from excessive training and tuning burden as well as unsatisfactor...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IET generation, transmission & distribution Jg. 7; H. 4; S. 391 - 397
Hauptverfasser:	Zhang, Rui, Dong, Zhao Yang, Xu, Yan, Meng, Ke, Wong, Kit Po
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Stevenage The Institution of Engineering and Technology 01.04.2013 Institution of Engineering and Technology The Institution of Engineering & Technology
Schlagworte:	Algorithms ANN Applied sciences artificial neural network Australian National Electricity Market Australian NEM Electrical engineering. Electrical power engineering Electrical power engineering Electricity electricity load variation Elm ELM learning technique ensemble model Exact sciences and technology extreme learning machine Forecasting forecasting accuracy gradient methods gradient‐based learning algorithm Learning learning (artificial intelligence) load forecasting Mathematical models Miscellaneous NEM historical load data neural nets Neural networks Operation. Load control. Reliability power engineering computing power markets Power networks and lines power system operations pre‐defined range short‐term load forecasting stability problem STLF problem Training training speed training‐tuning speed artificial neural network ANN training-tuning speed ensemble model forecasting accuracy STLF problem stability problem ELM learning technique electricity load variation power engineering computing Australian National Electricity Market gradient-based learning algorithm pre-defined range NEM historical load data Australian NEM extreme learning machine load forecasting power system operations power markets learning (artificial intelligence) gradient methods training speed neural nets short-term load forecasting Short term Performance evaluation State of the art Demand forecasting Power system economics Updating Neural network Tuning Forecasting management Learning Electrical network On line processing Load management Power markets Open market Learning algorithm Gradient method Comparative study
ISSN:	1751-8687, 1751-8695
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Artificial Neural Network (ANN) has been recognized as a powerful method for short-term load forecasting (STLF) of power systems. However, traditional ANNs are mostly trained by gradient-based learning algorithms which usually suffer from excessive training and tuning burden as well as unsatisfactory generalization performance. Based on the ensemble learning strategy, this paper develops an ensemble model of a promising novel learning technology called extreme learning machine (ELM) for high-quality STLF of Australian National Electricity Market (NEM). The model consists of a series of single ELMs. During the training, the ensemble model generalizes the randomness of single ELMs by selecting not only random input parameters but also random hidden nodes within a pre-defined range. The forecast result is taken as the median value the single ELM outputs. Owing to the very fast training/tuning speed of ELM, the model can be efficiently updated to on-line track the variation trend of the electricity load and maintain the accuracy. The developed model is tested with the NEM historical load data and its performance is compared with some state-of-the-art learning algorithms. The results show that the training efficiency and the forecasting accuracy of the developed model are superior over the competitive algorithms.
Bibliographie:	SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 14 ObjectType-Article-2 content type line 23 ObjectType-Article-1 ObjectType-Feature-2
ISSN:	1751-8687 1751-8695
DOI:	10.1049/iet-gtd.2012.0541