Wavelet CNN-LSTM time series forecasting of electricity power generation considering biomass thermal systems

Abstract

The use of biomass as a renewable energy source for electricity generation has gained attention due to its sustainability and environmental benefits. However, the intermittent electricity demand poses challenges for optimizing electricity generation in thermal systems. Time series forecasting techniques are crucial in addressing these challenges by providing accurate predictions of biomass availability and electricity generation. Here, wavelet transform is applied for denoising, convolutional neural networks (CNN) are used to extract features of the time series, and long short-term memory (LSTM) is applied to perform the predictions. The result of the mean absolute percentage error equal to 0.0148 shows that the wavelet CNN-LSTM is a promising machine-learning methodology for electricity generation forecasting. Additionally, this paper discusses the importance of model evaluation techniques and validation strategies to assess the performance of forecasting models in real-world applications. The major contribution of this paper is related to improving forecasting using a hybrid method that outperforms other models based on deep learning. Finally, future research directions and potential advancements in time series forecasting for biomass thermal systems are outlined to foster continued innovation in sustainable energy generation.