Short term load forecasting in Greek interconnected power system using ANN

dc.contributor.author	Τσεκούρας, Γιώργος	el
dc.contributor.author	Κανέλλος, Φ.	el
dc.contributor.author	Ηλίας, Χρήστος	el
dc.contributor.author	Κονταργύρη, Βασιλική	el
dc.contributor.author	Τσιρέκης, Κωνσταντίνος	el
dc.date.accessioned	2015-05-25T18:28:45Z
dc.date.available	2015-05-25T18:28:45Z
dc.date.issued	2015-05-25
dc.identifier.uri	http://hdl.handle.net/11400/11143
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/us/	*
dc.source	http://www.wseas.org	en
dc.subject	Artificial neural networks
dc.subject	Output variables
dc.subject	Short-term load forecasting
dc.subject	Τεχνητά δίκτυα νεύρων
dc.subject	Μεταβλητές εξόδου
dc.subject	Βραχυπρόθεσμη πρόβλεψη φορτίου
dc.title	Short term load forecasting in Greek interconnected power system using ANN	en
heal.type	conferenceItem
heal.secondaryTitle	a study for output variables	en
heal.classification	Technology
heal.classification	Energy
heal.classification	Τεχνολογία
heal.classification	Ενέργεια
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh85133147
heal.classificationURI	http://id.loc.gov/authorities/names/n42028321
heal.classificationURI	N/A-Τεχνολογία
heal.classificationURI	N/A-Ενέργεια
heal.contributorName	Καρανάσιου, Ι.	el
heal.contributorName	Σαλής, Α.	el
heal.contributorName	Κονταξής, Παναγιώτης	el
heal.contributorName	Γιαλκέτση, Α.	el
heal.contributorName	Μαστοράκης, Ν.	el
heal.language	en
heal.access	campus
heal.publicationDate	2011-07-14
heal.bibliographicCitation	Tsekouras, G., Kanellos, F., Elias, C., Kontargyri, V., Tsirekis, C. et al. (2011) Short term load forecasting in Greek interconnected power system using ANN: A study for output variables. In 15th WSEAS International Conference on Systems. 14th to 16th July 2011. Corfu	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.fullTextAvailability	true
heal.conferenceName	15th WSEAS International Conference on Systems	en
heal.conferenceItemType	poster