A Self-Adaptive Multikernel Machine Based on Recursive Least-Squares Applied to Very Short-Term Wind Power Forecasting

• Published in: IEEE access 2021, Vol.9, p.104761-104772
• Main Authors: Bezerra, Erick C., Pinson, Pierre, Leao, Ruth P. S., Braga, Arthur P. S.
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; Autoregressive processes; Decision making; Forecasting; Kernel; Kernels; Least squares; Machine learning; Mathematical models; Multiple kernel learning; online training; Predictive models; renewable energy; Time series; Wind farms; Wind forecasting; Wind power; wind power forecasting; Wind power generation
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2021.3099999

Wind power has contributed significantly to the increase in electricity generation, but a decision-making tool capable of dealing with its variability and limited predictability is necessary. For this purpose, a novel self-adaptive approach for kernel recursive least-squares machines named multiple challengers is introduced in this work, which is successfully used to produce very short-term wind power forecasts at eight wind farms in Australia. The proposed method is based on a competitive tracking method, and the algorithm deals with some common difficulties of kernel methods, e.g., the increasing kernel matrix size associated with time and memory complexities and the overfitting problem. The proposed method always considers the new information received by the model, thus identifying changes in the time series, avoiding abrupt loss of information and maintaining a controlled number of examples since there is an adaptive selection of the active kernel. It works with the smallest dictionary possible, reducing the probability of overfitting. Five minute-ahead wind power forecasts are produced and evaluated in terms of point forecast skill scores and calibration. The results of the proposed method are compared with those provided by other kernel-based versions of the recursive least-squares algorithm, an online version of the extreme learning machine method, and the persistence time series model. An increase in the number of kernels used in the ensemble system can lead to better results when compared with those of single-kernel models.