Search

Showing total 4 results
4 results

1. Photovoltaic power electricity generation nowcasting combining sky camera images and learning supervised algorithms in the Southern Spain.

Author

Trigo-González, Mauricio, Cortés-Carmona, Marcelo, Marzo, Aitor, Alonso-Montesinos, Joaquín, Martínez-Durbán, Mercedes, López, Gabriel, Portillo, Carlos, and Batlles, Francisco Javier

Subjects
*MACHINE learning, *PHOTOVOLTAIC power generation, *SUPERVISED learning, *ELECTRIC power distribution, *SUPPORT vector machines, *ARTIFICIAL intelligence, *CAMERAS
Abstract

The alternation between cloudy and clear skies alters the photovoltaic production. This makes it necessary to anticipate these disturbances hours in advance for the correct operation of the electricity distribution plants and networks. In this paper, two short-term forecasting models (3 h) are developed to forecast the photovoltaic production in an integrated plant in the CIESOL building of the University of Almería. The methodology used is based on sky camera images and Artificial Intelligence techniques. Two models have been developed and compared applying artificial neural network (ANN) and support vector machine (SVM) techniques. The global irradiance predicted using sky camera images is used as an input variable in both models. In addition, the operational status of the plants has been included as an input parameter through the performance ratio. The results have shown that the errors made by ANN and SVM are very similar. For all sky conditions, the uncertainty of the production forecast differs by less than 2% from the uncertainty of the solar resource, which is the main source of error in the production models developed. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

2. Multi-surrogate assisted multi-objective evolutionary algorithms for feature selection in regression and classification problems with time series data.

Author

Espinosa, Raquel, Jiménez, Fernando, and Palma, José

Subjects
*FEATURE selection, *EVOLUTIONARY algorithms, *MACHINE learning, *TIME series analysis, *SUPPORT vector machines, *CLASSIFICATION, *SHORT-term memory
Abstract

Feature selection wrapper methods are powerful mechanisms for reducing the complexity of prediction models while preserving and even improving their precision. Meta-heuristic methods, such as multi-objective evolutionary algorithms, are commonly used as search strategies in feature selection wrapper methods since they allow minimizing the cardinality of the attribute subset and simultaneously maximizing the predictive capacity of the model. However, in high-dimensional problems, multi-objective evolutionary algorithms for wrapper-type feature selection may require excessive computational time, sometimes impractical, especially when the learning algorithm has a high computational cost, such as deep learning. To address this drawback, in this paper we propose a multi-surrogate assisted multi-objective evolutionary algorithm for feature selection, specially designed to improve generalization error. The proposed method has been compared with conventional feature selection wrapper methods that use random forest, support vector machine and long short-term memory learning algorithms to evaluate subsets of attributes. The experiments have been carried out with regression and classification problems with time series data for air quality forecasting in the south-east of Spain and for indoor temperature forecasting in a domotic house. The results demonstrate the superiority of the proposed multi-surrogate assisted method over conventional wrapper methods using the same run times. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

3. Multi-surrogate assisted multi-objective evolutionary algorithms for feature selection in regression and classification problems with time series data.

Author

Espinosa, Raquel, Jiménez, Fernando, and Palma, José

Subjects
*FEATURE selection, *EVOLUTIONARY algorithms, *MACHINE learning, *TIME series analysis, *SUPPORT vector machines, *CLASSIFICATION, *SHORT-term memory
Abstract

Feature selection wrapper methods are powerful mechanisms for reducing the complexity of prediction models while preserving and even improving their precision. Meta-heuristic methods, such as multi-objective evolutionary algorithms, are commonly used as search strategies in feature selection wrapper methods since they allow minimizing the cardinality of the attribute subset and simultaneously maximizing the predictive capacity of the model. However, in high-dimensional problems, multi-objective evolutionary algorithms for wrapper-type feature selection may require excessive computational time, sometimes impractical, especially when the learning algorithm has a high computational cost, such as deep learning. To address this drawback, in this paper we propose a multi-surrogate assisted multi-objective evolutionary algorithm for feature selection, specially designed to improve generalization error. The proposed method has been compared with conventional feature selection wrapper methods that use random forest, support vector machine and long short-term memory learning algorithms to evaluate subsets of attributes. The experiments have been carried out with regression and classification problems with time series data for air quality forecasting in the south-east of Spain and for indoor temperature forecasting in a domotic house. The results demonstrate the superiority of the proposed multi-surrogate assisted method over conventional wrapper methods using the same run times. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

4. Mapping groundwater-dependent ecosystems by means of multi-layer supervised classification.

Author

Martínez-Santos, P., Díaz-Alcaide, S., De la Hera-Portillo, A., and Gómez-Escalonilla, Víctor

Subjects
*ENDANGERED ecosystems, *WETLAND management, *ECOSYSTEMS, *BIOSPHERE reserves, *SUPPORT vector machines, *LAND management
Abstract

• Groundwater-dependent wetlands rank among the world's most endangered ecosystems. • A novel machine learning approach to map groundwater-dependent ecosystems is presented. • Multi-parametric supervised classification rendered test scores over 96%. • Support vector machines, tree-based classifiers and logistic regression proved suitable. • Results could be used to inform wetland management and land use policy. Identifying groundwater-dependent ecosystems is the first step towards their protection. This paper presents a machine learning approach that maps groundwater-dependent ecosystems by extrapolating from the characteristics of a small sample of known wetland and non-wetland areas to find other areas with similar geological, hydrological and biotic markers. Explanatory variables for wetland occurrence include topographic elevation, lithology, vegetation vigor, and slope-related variables, among others. Supervised classification algorithms are trained based on the ground truth sample, and their outcomes are checked against an official inventory of groundwater-dependent ecosystems for calibration. This method is illustrated through its application to a UNESCO Biosphere Reserve in central Spain. Support vector machines, tree-based classifiers, logistic regression and k-neighbors classification predicted the presence of groundwater-dependent ecosystems adequately (>96% test and AUC scores). The ensemble mean of the best five classifiers rendered a 90% success rate when computed per surface area. This method can optimize fieldwork during the characterization stage of groundwater-dependent ecosystems, thus contributing to integrate wetland protection in land use planning. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF