Performance Sensitivity of a Wind Farm Power Curve Model to Different Signals of the Input Layer of ANNs: Case Studies in the Canary Islands

Improving the estimation of the power output of a wind farm enables greater integration of this type of energy source in electrical systems. The development of accurate models that represent the real operation of a wind farm is one way to attain this objective. A wind farm power curve model is propo...

Full description

Saved in:
Bibliographic Details
Main Authors: Sergio Velázquez Medina, José A. Carta, Ulises Portero Ajenjo
Format: Article
Language:English
Published: Wiley 2019-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2019/2869149
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832551485345366016
author Sergio Velázquez Medina
José A. Carta
Ulises Portero Ajenjo
author_facet Sergio Velázquez Medina
José A. Carta
Ulises Portero Ajenjo
author_sort Sergio Velázquez Medina
collection DOAJ
description Improving the estimation of the power output of a wind farm enables greater integration of this type of energy source in electrical systems. The development of accurate models that represent the real operation of a wind farm is one way to attain this objective. A wind farm power curve model is proposed in this paper which is developed using artificial neural networks, and a study is undertaken of the influence on model performance when parameters such as the meteorological conditions (wind speed and direction) of areas other than the wind farm location are added as signals of the input layer of the neural network. Using such information could be of interest, either to study possible improvements that could be obtained in the performance of the original model, which uses exclusively the meteorological conditions of the area where the wind farm is located, or simply because no reliable meteorological data for the area of the wind farm are available. In the study developed it is deduced that the incorporation of meteorological data from an additional weather station other than that of the wind farm site can improve by up to 17.6% the performance of the original model.
format Article
id doaj-art-b3eac7739c864369858cab96194f9717
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2019-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-b3eac7739c864369858cab96194f97172025-02-03T06:01:28ZengWileyComplexity1076-27871099-05262019-01-01201910.1155/2019/28691492869149Performance Sensitivity of a Wind Farm Power Curve Model to Different Signals of the Input Layer of ANNs: Case Studies in the Canary IslandsSergio Velázquez Medina0José A. Carta1Ulises Portero Ajenjo2Department of Electronics and Automatics Engineering, Universidad de Las Palmas de Gran Canaria, Campus de Tafira s/n, 35017 Las Palmas de Gran Canaria, Canary Islands, SpainDepartment of Mechanical Engineering, University of Las Palmas de Gran Canaria, Campus de Tafira s/n, 35017 Las Palmas de Gran Canaria, Canary Islands, SpainSchool of Industrial and Civil Engineering, University of Las Palmas de Gran Canaria, Campus de Tafira s/n, 35017 Las Palmas de Gran Canaria, Canary Islands, SpainImproving the estimation of the power output of a wind farm enables greater integration of this type of energy source in electrical systems. The development of accurate models that represent the real operation of a wind farm is one way to attain this objective. A wind farm power curve model is proposed in this paper which is developed using artificial neural networks, and a study is undertaken of the influence on model performance when parameters such as the meteorological conditions (wind speed and direction) of areas other than the wind farm location are added as signals of the input layer of the neural network. Using such information could be of interest, either to study possible improvements that could be obtained in the performance of the original model, which uses exclusively the meteorological conditions of the area where the wind farm is located, or simply because no reliable meteorological data for the area of the wind farm are available. In the study developed it is deduced that the incorporation of meteorological data from an additional weather station other than that of the wind farm site can improve by up to 17.6% the performance of the original model.http://dx.doi.org/10.1155/2019/2869149
spellingShingle Sergio Velázquez Medina
José A. Carta
Ulises Portero Ajenjo
Performance Sensitivity of a Wind Farm Power Curve Model to Different Signals of the Input Layer of ANNs: Case Studies in the Canary Islands
Complexity
title Performance Sensitivity of a Wind Farm Power Curve Model to Different Signals of the Input Layer of ANNs: Case Studies in the Canary Islands
title_full Performance Sensitivity of a Wind Farm Power Curve Model to Different Signals of the Input Layer of ANNs: Case Studies in the Canary Islands
title_fullStr Performance Sensitivity of a Wind Farm Power Curve Model to Different Signals of the Input Layer of ANNs: Case Studies in the Canary Islands
title_full_unstemmed Performance Sensitivity of a Wind Farm Power Curve Model to Different Signals of the Input Layer of ANNs: Case Studies in the Canary Islands
title_short Performance Sensitivity of a Wind Farm Power Curve Model to Different Signals of the Input Layer of ANNs: Case Studies in the Canary Islands
title_sort performance sensitivity of a wind farm power curve model to different signals of the input layer of anns case studies in the canary islands
url http://dx.doi.org/10.1155/2019/2869149
work_keys_str_mv AT sergiovelazquezmedina performancesensitivityofawindfarmpowercurvemodeltodifferentsignalsoftheinputlayerofannscasestudiesinthecanaryislands
AT joseacarta performancesensitivityofawindfarmpowercurvemodeltodifferentsignalsoftheinputlayerofannscasestudiesinthecanaryislands
AT ulisesporteroajenjo performancesensitivityofawindfarmpowercurvemodeltodifferentsignalsoftheinputlayerofannscasestudiesinthecanaryislands