Search

Deep Learning Convolutional Neural Networks have been successfully used in many applications. Its versatility lies in reducing the number of parameters to train while maintaining or improving the feature representation capabilities offered by other architectures. Due to its success, Convolutional Networks have become the architecture of choice for image and video processing applications. The application of Convolutional Networks to wind time series is still limited, being an area with high potential for developing new approaches. This paper explores several deep learning models and applies them to wind time series for multi-step forecasting. The time series used for the experimentation are multidimensional time-stamped multi-variate meteorological data. We use a large dataset of wind data from the National Renewable Laboratory with 126,692 wind sites, requiring the use of High Performance Computing. The experimentation results show how Convolutional Networks are a valid approach for wind time series forecasting., Peer Reviewed, Postprint (author's final draft)

The application of deep learning to wind time series for multi-step prediction obtains good results at short horizons. The accuracy of a wind forecast is highly dependent on the specific structure of wind in the specific location, as many local features influence wind behaviour. The characterization of the complexity of a site for wind prediction is defined as forecastability or predictability and can be obtained from the inner structure of the meteorological time series observations from a site. We analyze the time series structure searching for properties that have a high correlation with the prediction result, properties that can create measures that have the potential to describe the forecastability of a site. The best measures will show a high correlation with the accuracy of the predictions. In this work, we analyze wind time series from 126,692 wind locations in the US, where we apply several deep learning methods first, and then we verify several forecastability descriptors with the accuracy deep learning results. We require High-Performance Computing (HPC) resources for this task as the deep learning algorithms have sensible resource requirements and are applied to a large set of data. The measures defined and explored in this work are based on several techniques that decompose or transform the wind time-series. By combining several of these measures, we can obtain better predictors of the site complexity, which will allow us to evaluate the future error of a prediction on this site. Forecastability measures can contribute to a wind site multi-dimensional description, becoming a valuable tool for wind resource analysts and wind forecasters., Peer Reviewed, Postprint (published version)

Forecasting is a critical task for the integration of wind-generated energy into electricity grids. Numerical weather models applied to wind prediction, work with grid sizes too large to reproduce all the local features that influence wind, thus making the use of time series with past observations a necessary tool for wind forecasting. This research work is about the application of deep neural networks to multi-step forecasting using multivariate time series as an input, to forecast wind speed at 12 hours ahead. Wind time series are sequences of meteorological observations like wind speed, temperature, pressure, humidity, and direction. Wind series have two statistically relevant properties; non-linearity and non-stationarity, which makes the modelling with traditional statistical tools very inaccurate. In this thesis we design, test and validate novel deep learning models for the wind energy prediction task, applying new deep architectures to the largest open wind data repository available from the National Renewable Laboratory of the US (NREL) with 126,692 wind sites evenly distributed on the US geography. The heterogeneity of the series, obtained from several data origins, allows us to obtain conclusions about the level of fitness of each model to time series that range from highly stationary locations to variable sites from complex areas. We propose Multi-Layer, Convolutional and recurrent Networks as basic building blocks, and then combined into heterogeneous architectures with different variants, trained with optimisation strategies like drop and skip connections, early stopping, adaptive learning rates, filters and kernels of different sizes, between others. The architectures are optimised by the use of structured hyper-parameter setting strategies to obtain the best performing model across the whole dataset. The learning capabilities of the architectures applied to the various sites find relationships between the site characteristics (terrain complexity, win, La predicció de vent és clau per a la integració de l'energia eòlica en els sistemes elèctrics. Els models meteorològics es fan servir per predicció, però tenen unes graelles geogràfiques massa grans per a reproduir totes les característiques locals que influencien la formació de vent, fent necessària la predicció d'acord amb les sèries temporals de mesures passades d'una localització concreta. L'objectiu d'aquest treball d'investigació és l'aplicació de xarxes neuronals profundes a la predicció \textit{multi-step} utilitzant com a entrada series temporals de múltiples variables meteorològiques, per a fer prediccions de vent d'ací a 12 hores. Les sèries temporals de vent són seqüències d'observacions meteorològiques tals com, velocitat del vent, temperatura, humitat, pressió baromètrica o direcció. Les sèries temporals de vent tenen dues propietats estadístiques rellevants, que són la no linearitat i la no estacionalitat, que fan que la modelització amb eines estadístiques sigui poc precisa. En aquesta tesi es validen i proven models de deep learning per la predicció de vent, aquests models d'arquitectures d'autoaprenentatge s'apliquen al conjunt de dades de vent més gran del món, que ha produït el National Renewable Laboratory dels Estats Units (NREL) i que té 126,692 ubicacions físiques de vent distribuïdes per total la geografia de nord Amèrica. L'heterogeneïtat d'aquestes sèries de dades permet establir conclusions fermes en la precisió de cada mètode aplicat a sèries temporals generades en llocs geogràficament molt diversos. Proposem xarxes neuronals profundes de tipus multi-capa, convolucionals i recurrents com a blocs bàsics sobre els quals es fan combinacions en arquitectures heterogènies amb variants, que s'entrenen amb estratègies d'optimització com drops, connexions skip, estratègies de parada, filtres i kernels de diferents mides entre altres. Les arquitectures s'optimitzen amb algorismes de selecció de paràmetres que permeten obtenir el model amb el mil, Arquitecturas de aprendizaje profundo aplicadas a la predición en múltiple escalón de series temporales de viento. La predicción de viento es clave para la integración de esta energía eólica en los sistemas eléctricos. Los modelos meteorológicos tienen una resolución geográfica demasiado amplia que no reproduce todas las características locales que influencian en la formación del viento, haciendo necesaria la predicción en base a series temporales de cada ubicación concreta. El objetivo de este trabajo de investigación es la aplicación de redes neuronales profundas a la predicción multi-step usando como entrada series temporales de múltiples variables meteorológicas, para realizar predicciones de viento a 12 horas. Las series temporales de viento son secuencias de observaciones meteorológicas tales como, velocidad de viento, temperatura, humedad, presión barométrica o dirección. Las series temporales de viento tienen dos propiedades estadísticas relevantes, que son la no linealidad y la no estacionalidad, lo que implica que su modelización con herramientas estadísticas sea poco precisa. En esta tesis se validan y verifican modelos de aprendizaje profundo para la predicción de viento, estos modelos de arquitecturas de aprendizaje automático se aplican al conjunto de datos de viento más grande del mundo, que ha sido generado por el National Renewable Laboratory de los Estados Unidos (NREL) y que tiene 126,682 ubicaciones físicas de viento distribuidas por toda la geografía de Estados Unidos. La heterogeneidad de estas series de datos permite establecer conclusiones válidas sobre la validez de cada método al ser aplicado en series temporales generadas en ubicaciones físicas muy diversas. Proponemos redes neuronales profundas de tipo multi capa, convolucionales y recurrentes como tipos básicos, sobre los que se han construido combinaciones en arquitecturas heterogéneas con variantes de entrenamiento como drops, conexiones skip, estrategias de parada, filtros y kernels d, Postprint (published version)

Wind Energy generation depends on the existence of wind, a meteorological phenomena intermittent by nature, with the consequence of generating uncertainty on the availability of wind energy in the future. The grid stability processes require continuous forecasting of wind energy generated. Forecasting wind energy can be performed either by using weather forecast data or by projecting (or regressing) the past time-series data observations into the future. This last method is the statistical or time series approach. Wind Time Series show non-linearity and non-stationarity properties, and these two properties increase the complexity of the forecasting task using statistical methodologies. In this paper we explore the use of deep learning techniques, which can represent non-linearity, to the wind speed prediction using the largest public wind dataset available, the Wind Toolkit from the National Renewable Laboratory of the US. Several deep network architectures like Multi Layer Perceptrons, Convolutional Networks or Recurrent Networks have been tested on the 126,692 wind-sites and with the results obtained valuable comparisons and conclusions have been obtained. The distribution of the wind sites across the North American Geography has allowed to include in the analysis relationships between terrain, wind forecast complexity and deep methods. With the developed testing workbench and with the availability of the Barcelona Supercomputing Center new architectures are being developed. This work concludes with the feasibility of deep learning architectures for the wind and energy forecasting., Peer Reviewed, Postprint (published version)

To balance electricity production and demand, it is required to use different prediction techniques extensively. Renewable energy, due to its intermittency, increases the complexity and uncertainty of forecasting, and the resulting accuracy impacts all the different players acting around the electricity systems around the world like generators, distributors, retailers, or consumers. Wind forecasting can be done under two major approaches, using meteorological numerical prediction models or based on pure time series input. Deep learning is appearing as a new method that can be used for wind energy prediction. This work develops several deep learning architectures and shows their performance when applied to wind time series. The models have been tested with the most extensive wind dataset available, the National Renewable Laboratory Wind Toolkit, a dataset with 126,692 wind points in North America. The architectures designed are based on different approaches, Multi-Layer Perceptron Networks (MLP), Convolutional Networks (CNN), and Recurrent Networks (RNN). These deep learning architectures have been tested to obtain predictions in a 12-h ahead horizon, and the accuracy is measured with the coefficient of determination, the R² method. The application of the models to wind sites evenly distributed in the North America geography allows us to infer several conclusions on the relationships between methods, terrain, and forecasting complexity. The results show differences between the models and confirm the superior capabilities on the use of deep learning techniques for wind speed forecasting from wind time series data., Peer Reviewed, Postprint (published version)

Decarbonizing the energy supply requires extensive use of renewable generation. Their intermittent nature requires to obtain accurate forecasts of future generation, at short, mid and long term. Wind Energy generation prediction is based on the ability to forecast wind intensity. This problem has been approached using two families of methods one based on weather forecasting input (Numerical Weather Model Prediction) and the other based on past observations (time series forecasting). This work deals with the application of Deep Learning to wind time series. Wind Time series are non-linear and non-stationary, making their forecasting very challenging. Deep neural networks have shown their success recently for problems involving sequences with non-linear behavior. In this work, we perform experiments comparing the capability of different neural network architectures for multi-step forecasting in a 12 h ahead prediction. For the Time Series input we used the US National Renewable Energy Laboratory’s WIND Dataset [3], (the largest available wind and energy dataset with over 120,000 physical wind sites), this dataset is evenly spread across all the North America geography which has allowed us to obtain conclusions on the relationship between physical site complexity and forecast accuracy. In the preliminary results of this work it can be seen a relationship between the error (measured as R2R2 ) and the complexity of the terrain, and a better accuracy score by some Recurrent Neural Network Architectures., Peer Reviewed, Postprint (author's final draft)

One of the ways of reducing the effects of Climate Change is to rely on renewable energy sources. Their intermittent nature makes necessary to obtain a mid-long term accurate forecasting. Wind Energy prediction is based on the ability to forecast wind speed. This has been a problem approached using different methods based on the statistical properties of the wind time series. Wind Time series are non-linear and non-stationary, making their forecasting very challenging. Deep neural networks have shown their success recently for problems involving sequences with non-linear behavior. In this work, we perform experiments comparing the capability of different neural network architectures for multi-step forecasting obtaining a 12 hours ahead prediction using data from the National Renewable Energy Laboratory's WIND dataset, Peer Reviewed, Postprint (published version)

Retrieval sobre un fichero de información bibliográfica mediante expresiones booleanas entre descriptores (campos de información). Basado en un análisis sintáctico SLR sobre una gramática que utiliza como operadores relacionales el AND y el OR. El objetivo es dotar de una herramienta informática de búsqueda al usuario de una Biblioteca., Postprint (published version)