Short term load forecasting in Greek interconnected power system using ANN: A study for output variables

Tsekouras, GJ; Kanellos, FD; Elias, ChN; Kontargyri, VT; Tsirekis, CD; Karanasiou, IS; Salis, AD; Contaxis, PA; Gialketsi, AA; Mastorakis, NE

dc.contributor.author	Tsekouras, GJ	en
dc.contributor.author	Kanellos, FD	en
dc.contributor.author	Elias, ChN	en
dc.contributor.author	Kontargyri, VT	en
dc.contributor.author	Tsirekis, CD	en
dc.contributor.author	Karanasiou, IS	en
dc.contributor.author	Salis, AD	en
dc.contributor.author	Contaxis, PA	en
dc.contributor.author	Gialketsi, AA	en
dc.contributor.author	Mastorakis, NE	en
dc.date.accessioned	2014-03-01T02:53:28Z
dc.date.available	2014-03-01T02:53:28Z
dc.date.issued	2011	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/36341
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-82955164951&partnerID=40&md5=2c5c9f97f4b1079fae00af599490449e	en
dc.subject	ANN training scaled conjugate gradient algorithm	en
dc.subject	Artificial neural networks	en
dc.subject	Output variables' analysis	en
dc.subject	Short-term load forecasting	en
dc.subject.other	Activation functions	en
dc.subject.other	Artificial Neural Network	en
dc.subject.other	Calibration process	en
dc.subject.other	Crucial parameters	en
dc.subject.other	Different structure	en
dc.subject.other	Experimental measurements	en
dc.subject.other	Historical data	en
dc.subject.other	Hourly load	en
dc.subject.other	Input variables	en
dc.subject.other	Load demand	en
dc.subject.other	Load predictions	en
dc.subject.other	Mean absolute percentage error	en
dc.subject.other	Output variables	en
dc.subject.other	Scaled conjugate gradient algorithm	en
dc.subject.other	Scaled conjugate gradients	en
dc.subject.other	Short term load forecasting	en
dc.subject.other	Short-term forecasting	en
dc.subject.other	Test sets	en
dc.subject.other	Training algorithms	en
dc.subject.other	Algorithms	en
dc.subject.other	Conjugate gradient method	en
dc.subject.other	Forecasting	en
dc.subject.other	Neural networks	en
dc.subject.other	Power transmission	en
dc.subject.other	Systems science	en
dc.subject.other	Electric load forecasting	en
dc.title	Short term load forecasting in Greek interconnected power system using ANN: A study for output variables	en
heal.type	conferenceItem	en
heal.publicationDate	2011	en
heal.abstract	The purpose of this paper is to compare the performance of different structures of Artificial Neural Networks (ANNs) regarding the output variables used for short term forecasting of the next day load of the interconnected Greek power system. In all cases the output variables are the hourly actual loads of the next day. The classical ANN design adopts an ANN model with 24 output variables. Alternatively, 24 different ANN models can be implemented for each hour of the day. This solution can affect the selection of input variables indirectly. In this paper, various scenarios of the solution of 24 different ANN models are going to be studied with different sets of input variables using the scaled conjugate gradient training algorithm, for which a calibration process is conducted regarding the crucial parameters values, such as the number of neurons, the type of activation functions, etc. The performance of each structure is evaluated by the Mean Absolute Percentage Error (MAPE) between the experimental measurements and estimated values of the hourly load demand of the next day for the evaluation set in order to specify the optimal ANN. Next, the load demand for the next day of the test set (with the historical data of the current year) is estimated using the best ANN structure, to verify the behaviour of ANN load prediction techniques. Finally the classical design and different proposed structures are compared.	en
heal.journalName	Recent Researches in System Science - Proceedings of the 15th WSEAS International Conference on Systems, Part of the 15th WSEAS CSCC Multiconference	en
dc.identifier.spage	440	en
dc.identifier.epage	445	en