Abstract
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.
Highlights
The development of clean electricity is one pivotal area for the transition to a de-carbonized world, and for this reason, the electricity systems are under a process of transformation from a heavily-centralized network, based on large uranium, coal, gas or gas-oil generation plants, to a new decentralized model with small wind or solar units that require high coordination, accomplished by the intensive use of computer algorithms [1]
Section 3.2.2); Recurrent Networks (RNN) seq2seq and RNN encoder-decoder (ED). With combinations of these components, 4 architectures were developed: a deep Multi-Layer Perceptron Networks (MLP) with fully-connected layers (MLP), a Convolutional Networks (CNN) combined with an MLP to obtain a sequence output
Seq2seq), a RNN combined with an MLP that obtains a sequence and a recurrent neural network
Summary
The development of clean electricity is one pivotal area for the transition to a de-carbonized world, and for this reason, the electricity systems are under a process of transformation from a heavily-centralized network, based on large uranium, coal, gas or gas-oil generation plants, to a new decentralized model with small wind or solar units that require high coordination, accomplished by the intensive use of computer algorithms [1]. Hydro energy is inexpensive and secure, and by adding different versions of pumped-storage technologies, dams can be transformed into electricity storage systems, helping to regulate the electricity systems around the world [2]. This energy depends on water, a resource not always available or scarce, and cannot be ramped up to cover the energy needs of the world, opening the door for other clean sources. Solar and wind show the fastest growth around the globe Both technologies share the intermittency issues inherent to renewables; forecasting becomes a critical process to integrate all Energies 2019, 12, 2385; doi:10.3390/en12122385 www.mdpi.com/journal/energies
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
