In close collaboration with researchers from MINES ParisTech (France) and University of Patras (Greece), UBITECH co-authors a journal publication entitled “Short-Term Net Load Forecasting with Singular Spectrum Analysis and LSTM Neural Networks” that has been just accepted for publication from MDPI Energies, a peer-reviewed, open access journal of related scientific research, technology development, engineering, and the studies in policy and management and is published semimonthly online by MDPI.
Mr. Athanasios Bachoumis and his co-authors presents a hybrid approach that combines Singular Spectrum Analysis (SSA)-based decomposition and Artificial Neural Networks (ANNs) for day-ahead hourly load forecasting. First, the trajectory matrix of the time series is constructed and decomposed into trend, oscillating, and noise components. Next, the extracted components are employed as exogenous regressors in a global forecasting model, comprising either a Multilayer Perceptron (MLP) or a Long Short-Term Memory (LSTM) predictive layer.
The model is further extended to include exogenous features, e.g., weather forecasts, transformed via parallel dense layers. The predictive performance is evaluated on two real-world datasets, controlling for the effect of exogenous features on predictive accuracy. The results showcase that the decomposition step improves the relative performance for ANN models, with the combination of LSTM and SAA providing the best overall performance.
For more info, please access online our manuscript at https://www.mdpi.com/1996-1073/14/14/4107
