Abstract
This work presents a hybrid and hierarchical deep learning model for midterm load forecasting. The model combines exponential smoothing (ETS), advanced long short-term memory (LSTM), and ensembling. ETS extracts dynamically the main components of each individual time series and enables the model to learn their representation. Multilayer LSTM is equipped with dilated recurrent skip connections and a spatial shortcut path from lower layers to allow the model to better capture long-term seasonal relationships and ensure more efficient training. A common learning procedure for LSTM and ETS, with a penalized pinball loss, leads to simultaneous optimization of data representation and forecasting performance. In addition, ensembling at three levels ensures a powerful regularization. A simulation study performed on the monthly electricity demand time series for 35 European countries confirmed the high performance of the proposed model and its competitiveness with classical models such as ARIMA and ETS as well as state-of-the-art models based on machine learning.
Highlights
E LECTRICITY demand forecasting is an essential tool in all sectors in the electric power industry
Due to the stochastic nature of exponential smoothing (ETS)+RD-long short-term memory (LSTM), the results reported in this article take averages over 30 independent trials
The models, k-NNw, FNM, N-WE, and GRNN are known as pattern similarity-based forecasting models (PSFMs) because the forecast is constructed by aggregating the training output patterns using similarity between the query pattern and training input patterns [14]
Summary
E LECTRICITY demand forecasting is an essential tool in all sectors in the electric power industry. Hierarchical structure learning is posed as a residual learning framework to prevent performance degradation problems Another example of using a new deep learning solution for time series forecasting is the N-BEATS model proposed is [22]. We propose a state-ofthe-art forecasting model for MTLF that meets these high requirements It is based on the winning submission to the M4 competition for monthly data. 1) This work empirically demonstrates that the proposed generic hybrid model using specific mechanisms of time series processing and prediction outperforms in MTLF well-established statistical and ML approaches and is on a pair with state-of-the-art domain-adjusted models combining ML and statistical approaches.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
