A bat optimized neural network and wavelet transform approach for short-term price forecasting

• Published in: Applied energy Vol. 210; pp. 88 - 97
• Main Authors: Bento, P.M.R., Pombo, J.A.N., Calado, M.R.A., Mariano, S.J.P.S.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.01.2018
• Subjects: Artificial neural networks; Bat algorithm; Scaled conjugate gradient; Short-term price forecasting; Similar day selection; Wavelet transform; Bat algorithm; Wavelet transform; Short-term price forecasting; Scaled conjugate gradient; Artificial neural networks; Similar day selection
• ISSN: 0306-2619; 1872-9118
• DOI: 10.1016/j.apenergy.2017.10.058

[Display omitted] •We propose a new method for short-term price forecasting (STPF).•The new method is based on Bat Algorithm, Wavelet Transform and Artificial Neural Networks.•The method has the capability to auto-tune the best simulation parameters.•We compare the proposed method in Spanish and Pennsylvania-New Jersey-Maryland (PJM) electricity markets.•The proposed approach exhibits a better forecasting accuracy. In the competitive power industry environment, electricity price forecasting is a fundamental task when market participants decide upon bidding strategies. This has led researchers in the last years to intensely search for accurate forecasting methods, contributing to better risk assessment, with significant financial repercussions. This paper presents a hybrid method that combines similar and recent day-based selection, correlation and wavelet analysis in a pre-processing stage. Afterwards a feedforward neural network is used alongside Bat and Scaled Conjugate Gradient Algorithms to improve the traditional neural network learning capability. Another feature is the method’s capacity to fine-tune neural network architecture and wavelet decomposition, for which there is no optimal paradigm. Numerical testing was applied in a day-ahead framework to historical data pertaining to Spanish and Pennsylvania-New Jersey-Maryland (PJM) electricity markets, revealing positive forecasting results in comparison with other state-of-the-art methods.