2020
Cornejo-Bueno, Laura; Camacho-Gómez, C.; Aybar-Ruíz, Adrián; Prieto, Luis; Barea-Ropero, Alberto; Salcedo-Sanz, Sancho
Wind power ramp event detection with a hybrid neuro-evolutionary approach Journal Article
In: Neural Computing and Applications, vol. 32, no. 2, pp. 391-402, 2020.
Links | BibTeX | Tags: Evolutionary Computation, Wind power
@article{nokey,
title = {Wind power ramp event detection with a hybrid neuro-evolutionary approach},
author = {Laura Cornejo-Bueno and C. Camacho-Gómez and Adrián Aybar-Ruíz and Luis Prieto and Alberto Barea-Ropero and Sancho Salcedo-Sanz},
doi = {s00521-018-3707-7},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
journal = {Neural Computing and Applications},
volume = {32},
number = {2},
pages = {391-402},
keywords = {Evolutionary Computation, Wind power},
pubstate = {published},
tppubtype = {article}
}
2018
Salcedo-Sanz, Sancho; García-Herrera, R.; Camacho-Gómez, C.; Aybar-Ruíz, A.; Alexandre, E.
Wind power field reconstruction from a reduced set of representative measuring points Journal Article
In: Applied Energy, vol. 228, pp. 1111-1121, 2018, ISSN: 0306-2619.
Abstract | Links | BibTeX | Tags: Analogue method, Coral Reefs Optimization, Representative points, Wind power, Wind power field reconstruction
@article{SALCEDOSANZ20181111,
title = {Wind power field reconstruction from a reduced set of representative measuring points},
author = {Sancho Salcedo-Sanz and R. García-Herrera and C. Camacho-Gómez and A. Aybar-Ruíz and E. Alexandre},
url = {https://www.sciencedirect.com/science/article/pii/S0306261918310304},
doi = {https://doi.org/10.1016/j.apenergy.2018.07.003},
issn = {0306-2619},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
journal = {Applied Energy},
volume = {228},
pages = {1111-1121},
abstract = {In this paper we deal with a problem of representative measuring points selection for long-term wind power analysis. It has direct applications such as wind farm prospective location or long-term power generation prediction in wind-based energy facilities. The problem’s objective is to select the best set of N measuring points (i.e. N representative points), in such a way that a wind power error reconstruction measure is minimized, considering a monthly average wind power field. In order to solve this problem, we use a novel meta-heuristic algorithm, the Coral Reefs Optimization with Substrate Layer, which is an evolutionary-type method able to combine different search procedures within a single population. The CRO-SL is hybridized with the Analogue Method as wind power reconstruction method, to identify the most representative points for the wind field. The proposed approach has been tested in the reconstruction of monthly average wind power fields in Europe, from reanalysis data (ERA-Interim reanalysis). The method exhibits strong performance as evidenced from the experiments carried out. The solutions obtained show that the more significant measuring points are mainly located over the Atlantic ocean, which is consistent with the wind speed climatology of the Northern hemisphere mid-latitudes. We have also analyzed the set of least representative points to reconstruct the wind power field (less informative points for whole reconstruction of the field), obtaining points mainly located at the North of Scandinavia (which may be associated with the circumpolar circulation), and some points in the Eastern Mediterranean, which seem to be related to the Etesian winds. Reconstructions at seasonal scales show similar results, which provides confidence on the robustness of the proposed method. The proposed methodology can be further applied to alternative energy-related problems, such as the selection of critical energy infra-structures or the selection of critical points for climate change studies, among others.},
keywords = {Analogue method, Coral Reefs Optimization, Representative points, Wind power, Wind power field reconstruction},
pubstate = {published},
tppubtype = {article}
}
In this paper we deal with a problem of representative measuring points selection for long-term wind power analysis. It has direct applications such as wind farm prospective location or long-term power generation prediction in wind-based energy facilities. The problem’s objective is to select the best set of N measuring points (i.e. N representative points), in such a way that a wind power error reconstruction measure is minimized, considering a monthly average wind power field. In order to solve this problem, we use a novel meta-heuristic algorithm, the Coral Reefs Optimization with Substrate Layer, which is an evolutionary-type method able to combine different search procedures within a single population. The CRO-SL is hybridized with the Analogue Method as wind power reconstruction method, to identify the most representative points for the wind field. The proposed approach has been tested in the reconstruction of monthly average wind power fields in Europe, from reanalysis data (ERA-Interim reanalysis). The method exhibits strong performance as evidenced from the experiments carried out. The solutions obtained show that the more significant measuring points are mainly located over the Atlantic ocean, which is consistent with the wind speed climatology of the Northern hemisphere mid-latitudes. We have also analyzed the set of least representative points to reconstruct the wind power field (less informative points for whole reconstruction of the field), obtaining points mainly located at the North of Scandinavia (which may be associated with the circumpolar circulation), and some points in the Eastern Mediterranean, which seem to be related to the Etesian winds. Reconstructions at seasonal scales show similar results, which provides confidence on the robustness of the proposed method. The proposed methodology can be further applied to alternative energy-related problems, such as the selection of critical energy infra-structures or the selection of critical points for climate change studies, among others.