Application of Augmented Echo State Networks and Genetic Algorithm to Improve Short-Term Wind Speed Forecasting

• Published in: Energies (Basel) Vol. 16; no. 6; p. 2635
• Main Authors: Gouveia, Hugo T. V., Souza, Murilo A., Ferreira, Aida A., de Albuquerque, Jonata C., Nóbrega Neto, Otoni, da Silva Lira, Milde Maria, de Aquino, Ronaldo R. B.
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.03.2023
• Subjects: Algorithms; Alternative energy sources; Artificial intelligence; artificial neural networks; Buildings and facilities; Computational neuroscience; Eigenvalues; Evolutionary algorithms; Forecasting; Genetic algorithms; Genetic research; Linear equations; Machine learning; Methods; Network topologies; Neural networks; Neurons; Power plants; Recurrent neural networks; Regression analysis; Reservoirs; Time series; time series analysis; Topology; wind energy; Wind power; Wind speed; Brazil
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en16062635

The large-scale integration into electrical systems of intermittent power-generation sources, such as wind power plants, requires greater efforts and knowledge from operators to keep these systems operating efficiently. These sources require reliable output power forecasts to set up the optimal operating point of the electrical system. In previous research, the authors developed an evolutionary approach algorithm called RCDESIGN to optimize the hyperparameters and topology of Echo State Networks (ESN), and applied the model in different time series forecasting, including wind speed. In this paper, RCDESIGN was modified in some aspects of the genetic algorithm, and now it optimizes an ESN with augmented states (ESN-AS) and has been called RCDESIGN-AS. The evolutionary algorithm allows the search for the best parameters and topology of the recurrent neural network to be performed simultaneously. In addition, RCDESIGN-AS has the important characteristic of requiring little computational effort and processing time since it is not necessary for the eigenvalues of the reservoir weight matrix to be reduced and also due to the fact that the augmented states make it possible to reduce the number of neurons in the reservoir. The method was applied for wind speed forecasting with a 24-h ahead horizon using real data of wind speed from five cities in the Northeast Region of Brazil. All results obtained with the proposed method overcame forecasting performed by the persistence method, obtaining prediction gains ranging from 60% to 80% in relation to this reference method. In some datasets, the proposed method also yielded better results than the traditional ESN, showing that RCDESIGN-AS can be a powerful tool for wind-speed forecasting and possibly for other types of time series.