Abstract
In this paper, we propose a new ensemble residual network model for short-term load forecasting (STLF). This model improves the accuracy of short-term load forecasting (24 hours in advance). The model has a two-stage network structure. First, the different fully-connected layers are combined, and the combined structure is similar to a recurrent neural network (RNN). Features obtained from historical load data are input to the first stage of the model to get preliminary prediction results. The second stage of the model is a modified residual network, and the final predictions are output from here. We use the ensemble snapshot model with learning rate decay to improve the generalization capability of the model. The model proposed in this paper was trained and tested on two public datasets. Numerical testing shows that the proposed model can get better forecasting results in comparison with other methods, and the ensemble method adopted effectively improves the generalization ability of the model.
Highlights
Load forecasting is a critical task in the energy field
We proposed an short-term load forecasting (STLF) model based on ensemble residual network
ENSEMBLE RESIDUAL NETWORK In this paper, we propose a short-term load forecast based on an ensemble residual network
Summary
Load forecasting is a critical task in the energy field. Accurate forecasting results enables useful support for the optimal pricing strategies, seamless integration of renewables, and reduce the maintenance costs of power systems. Reference [15] proposed a non-residential load prediction framework based on a multi-sequence LSTM recurrent neural network. Two deep learning methods were proposed for electric load forecasting in [17]. Reference [21] proposed a residual network This method makes the application of deep neural networks a reality. To improve the robustness of the prediction model and overfitting, we adopted an ensemble model of neural networks. We proposed an STLF model based on ensemble residual network. To improve the robustness of the proposed model, the snapshot ensemble with learning rate decay is used This ensemble method effectively enhances the prediction accuracy and generalization ability of the proposed model without spending extra computing power.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have