A New Hybrid Wavelet-Neural Network Approach for Forecasting Electricity

Abstract

This study investigates the performance of a novel neural network technique in the problem of price forecasting. To improve the prediction accuracy using each model’s unique features, this research proposes a hybrid approach that combines the -factor GARMA process, empirical wavelet transform and the local linear wavelet neural network (LLWNN) methods, to form the GARMA-WLLWNN process. In order to verify the validity of the model and the algorithm, the performance of the proposed model is evaluated using data from Polish electricity markets, and it is compared with the dual generalized long memory -factor GARMA-G-GARCH model and the individual WLLWNN. The empirical results demonstrated the proposed hybrid model can achieve a better predicting performance and prove that is the most suitable electricity market forecasting technique.

Modelling Risk for Commodities in Brazil: An Application for Live Cattle Spot and Futures Prices

“…It allows time series modelling for non-Gaussian time series data. In this sense, we can highlight some recent works focusing on predicting commodity prices based on GARMA models (see, e.g., [12,13]).…”

“…In line with the increased adoption of the GARMA model for predicting commodity prices, recent endeavours such as those by [12] and a significant study by [13] have further showcased its utility in this domain.…”

“…The body of work in the domain of forecasting using GARMA models, especially with commodity prices, has recently been enriched with studies exploring novel hybrid techniques. A pivotal study by [12] brought forward the GARMAWLLWNN process, a hybrid model that synthesises the k-factor GARMA process, empirical wavelet transform and the local linear wavelet neural network (LLWNN) methods. When evaluated using data from the Polish electricity markets, their hybrid model showed enhanced predicting performance, outdoing both the dual generalised long-memory k-factor GARMA-G-GARCH model and the individual WLLWNN.…”

Coupling the Empirical Wavelet and the Neural Network Methods in Order to Forecast Electricity Price

“…Initially, the historical data have been decomposed into wavelet-domain constitutive subseries using wavelet area and then using the local linear wavelet neural network (LLWNN) to form the WLLWNN forecasting model. The reader should consult Ben Amor et al (2018) and Boubaker et al (2020) for further details.…”

“…The PSO algorithm escapes from convergence toward a local minimum, because it is not based on gradient information contrary to the BP case (Abbass et al 2001;Boubaker et al 2020). The objective of the PSO is to produce the best set of weights (particle position) where numerous particles are moving to obtain the best solution, where the total number of weights characterizes the dimension of the search space.…”