Pasar al contenido principal

NUEVOS ALGORITMOS HIBRIDOS BIO-INSPIRADOS PARA PROBLEMAS DE PREDICCION EN ENERGIAS RENOVABLES

TIN2014-54583-C2-2-R

•
Nombre agencia financiadora Ministerio de Economía y Competitividad
Acrónimo agencia financiadora MINECO
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2014
Plan Estatal 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Unidad de gestión Secretaría de Estado de Educación, Formación Profesional y Universidades
Centro beneficiario UNIVERSIDAD DE ALCALA
Identificador persistente http://dx.doi.org/10.13039/501100003329

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A CRO-species optimization scheme for robust global solar radiation statistical downscaling

  • Salcedo-Sanz, Sancho
  • Jiménez-Fernández, Silvia
  • Aybar-Ruíz, Adrián
  • Casanova-Mateo, Carlos
  • Sanz-Justo, Julia
  • García Herrera, Ricardo
This paper tackles the prediction of the global solar radiation (GSR) at a given point, using as predictive variables the outputs of a numerical weather model (the WRF meso-scale model) obtained at a different grid points. Prediction is obtained in this work using a Multilayer Perceptron (MLP) trained with Extreme Learning Machines (ELMs). Provided that the number of WRF outputs is vast, we propose the use of a Coral Reefs Optimization algorithm with species (CRO-SP) to obtain a reduced number of significant predictive variables, therefore improving the global solar radiation prediction attained without feature selection. The proposed system has been tested on real data from a radiometric station located at Toledo (Spain) and average best results of RMSE of 69.19 have been achieved, resulting in a 21.62% improvement over the average prediction without considering the CRO-SP for the feature selection., This work has been partially supported by the project TIN2014-54583-C2-2-R of the Spanish Ministerial Commission of Science and Technology (MICYT), and by the Comunidad Autónoma de Madrid, under project number S2013ICE-2933_02. We would like to thank as well AEMET for providing the observed atmospherical data used in this work., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Wind power field reconstruction from a reduced set of representative measuring points

  • Salcedo-Sanz, Sancho
  • García Herrera, Ricardo
  • Camacho-Gómez, Carlos
  • Aybar-Ruíz, Adrián
  • Alexandre, Enrique
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., This work has been partially supported by the projects TIN2014-54583-C2-2-R, TIN2017-85887-C2-2-P and PALEOSTRAT (CGL2015-69699-R) of the Spanish Ministerial Commission of Science and Technology (MICYT), and by the Comunidad Autónoma de Madrid, under project number S2013ICE-2933_02., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Feature selection in machine learning prediction systems for renewable energy applications

  • Salcedo-Sanz, Sancho
  • Cornejo-Bueno, Laura
  • Prieto, Luís
  • Paredes, Daniel
  • García Herrera, Ricardo
This paper focuses on feature selection problems that arise in renewable energy applications. Feature selection is an important problem in machine learning, both in classification and regression problems. In renewable energy systems, feature selection appears related to prediction systems in the most important sources such as wind, solar and marine resources. The objective of the paper is twofold: first, a review of the most important prediction systems for renewable energy applications involving feature selection is carried out. Analysis and discussion of different feature selection problems in prediction systems are considered. We show that wrapper FSP approaches are those mostly used due to their higher performance. They include a diversity of algorithms, prevailing fast-training approaches. The lack of an uniform framework for FSP and the diversity of tackled problems impede a systematic assessment of the performance and properties of the applied methods. Thus, the simultaneously use of several global search mechanisms should be the preferred option. In a second part of the paper, we explore this possibility, by introducing a novel approach for feature selection based on a novel meta-heuristic, the Coral Reefs Optimization algorithm with Substrate Layer. This approach is able to combine different search mechanisms into a single algorithm, providing a global search procedure of high quality. We use an Extreme Learning Machine for prediction within this novel approach. The performance of the system is evaluated in a problem of wind speed prediction from numerical models input, using real data from a wind farm in Spain, where comparison with alternative regression algorithms is carried out. Improvements up to 20% in hourly and daily wind speed prediction are obtained with the proposed system versus the algorithms without the feature selection process considered., This work has been partially supported by Comunidad de Madrid, under project number S2013/ICE-2933, and by project TIN2014-54583-C2-2-R of the Spanish Ministerial Commission of Science and Technology (MICYT)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Near-optimal selection of representative measuring points for robust temperature field reconstruction with the CRO-SL and analogue methods

  • Salcedo-Sanz, Sancho
  • García Herrera, Ricardo
  • Camacho-Gómez, Carlos
  • Alexandre, Enrique
  • Carro-Calvo, Leopoldo
  • Jaume-Santero, Fernando
In this paper we tackle a problem of representative measuring points selection for temperature field reconstruction. This problem is a version of the more general Representative Selection (RS) problem, well-known in computer and data science. In this particular case, the objective is to select the best set of N measuring points (i.e. N representative points), in such a way that a reconstruction error is minimized when reconstructing the monthly average temperature field. We use a novel meta-heuristic algorithm, the Coral Reefs Optimization with Substrate Layer (CRO-SL), which is an evolutionary-type method able to combine several different search procedures within a single population. The CRO-SL is combined with the Analogue Method (AM) to identify the most representative points. This approach exhibits strong performance from experiments with gridded and un-gridded temperature field datasets (European Climate Assessment & Dataset (ECA) and ERA-Interim reanalysis (ERA)). Different aspects such as the error assessment and the comparison with alternative approaches, are discussed in the experimental analysis of this article. We show that the algorithm performs better than a greedy approach, i.e. the best solution for N points is different from the N best individual predictors. The solutions obtained with the proposed methodology are climatologically consistent and include points from Scandinavia, Central and Southern Europe, the Black Sea and Central and South Western Asia as the more representative in the case of the ECA dataset; similar areas are selected for ERA. We have found out that once the number of stations/points goes over a threshold, the improvement in the model is obtained by increasing the density of data in the given zones, instead of adding data from different zones to the algorithm. The method proposed may have direct application in Palaeoclimalogy, where there are a large amount of distributed proxies with scarce information, so the proposed approach could be useful to select the most important ones to reconstruct a desired field., This work has been partially supported by the projects TIN2014-54583-C2-2-R, TIN2017-85887-C2-2-P and PALEOSTRAT (CGL2015-69699-R) of the Spanish Ministerial Commission of Science and Technology (MICYT), and by the Comunidad Autónoma de Madrid, under project number S2013ICE-2933_02., Peer reviewed
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Artículo científico (JournalArticle)

Optimal design of a planar textile antenna for Industrial Scientific Medical (ISM) 2.4GHz Wireless Body Area Networks (WBAN) with CRO-SL algorithm

  • Sánchez Montero, Rocío|||0000-0002-3135-8828
  • Camacho Gómez, Carlos
  • López Espí, Pablo Luis|||0000-0003-3750-255X
  • Salcedo Sanz, Sancho|||0000-0002-4048-1676
This paper proposes a low-profile textile-modified meander line Inverted-F Antenna (IFA) with variable width and spacing meanders, for Industrial Scientific Medical (ISM) 2.4-GHz Wireless Body Area Networks (WBAN), optimized with a novel metaheuristic algorithm. Specifically, a metaheuristic known as Coral Reefs Optimization with Substrate Layer (CRO-SL) is used to obtain an optimal antenna for sensor systems, which allows covering properly and resiliently the 2.4&-2.45-GHz industrial scientific medical bandwidth. Flexible pad foam has been used to make the designed prototype with a 1.1-mm thickness. We have used a version of the algorithm that is able to combine different searching operators within a single population of solutions. This approach is ideal to deal with hard optimization problems, such as the design of the proposed meander line IFA. During the optimization phase with the CRO-SL, the proposed antenna has been simulated using CST Microwave Studio software, linked to the CRO-SL by means of MATLAB implementation and Visual Basic Applications (VBA) code. We fully describe the antenna design process, the adaptation of the CRO-SL approach to this problem and several practical aspects of the optimization and details on the algorithm's performance. To validate the simulation results, we have constructed and measured two prototypes of the antenna, designed with the proposed algorithm. Several practical aspects such as sensitivity during the antenna manufacturing or the agreement between the simulated and constructed antenna are also detailed in the paper., Ministerio de Ciencia y Tecnología, Ministerio de Educación, Cultura y Deporte
e_Buah Biblioteca Digital Universidad de Alcalá
Publicación Artículo científico (JournalArticle)

A Coral Reefs Optimization algorithm with substrate layer for robust Wi-Fi channel assignment

  • Camacho Gómez, Carlos
  • Marsá Maestre, Iván|||0000-0002-5529-2851
  • Giménez Guzmán, José Manuel|||0000-0002-1645-8476
  • Salcedo Sanz, Sancho|||0000-0002-4048-1676
In this paper, we tackle a problem of frequency assignment in Wi-Fi networks with a novel evolutionary-type algorithm. In this version of the problem, we consider the interferences originated by the access points, and also by the clients and all the 11 available channels in the 2.4 GHz Wi-Fi frequency band. The proposed evolutionary-type algorithm is the Coral Reefs Optimization approach with substrate layer (CRO-SL). It is a recently proposed algorithm, which simulates the processes which occur in real coral reefs, including the reproduction and fight for the space of living corals. This version of the algorithm includes a layer of “substrates” which allows using different search patterns jointly in the algorithm. This way, the CRO-SL is able to apply search patterns such as harmony search, differential evolution, Gaussian-based mutations and other traditional and novel search procedures, including local search algorithms, within a single population of solutions. We show the good performance of the proposed approach in a real case study of Wi-Fi frequency assignment, in the Polytechnic School building of the Universidad de Alcalá (Spain), where different realistic scenarios of the problem have been simulated and successfully solved with the CRO-SL algorithm., Ministerio de Economía y Competitividad, Comunidad de Madrid