Short-term Load Forecasting with Deep Residual Networks

TL;DR

This paper introduces a deep residual network-based model for short-term power load forecasting, combining domain knowledge integration, ensemble strategies, and probabilistic methods to improve accuracy and generalization across multiple datasets.

Contribution

The paper proposes a novel deep residual network architecture with a two-stage ensemble and probabilistic forecasting for improved load prediction.

Findings

Achieves high accuracy in load forecasting across three datasets.

Demonstrates superior generalization compared to existing models.

Effective probabilistic load forecasting using Monte Carlo dropout.

Abstract

We present in this paper a model for forecasting short-term power loads based on deep residual networks. The proposed model is able to integrate domain knowledge and researchers' understanding of the task by virtue of different neural network building blocks. Specifically, a modified deep residual network is formulated to improve the forecast results. Further, a two-stage ensemble strategy is used to enhance the generalization capability of the proposed model. We also apply the proposed model to probabilistic load forecasting using Monte Carlo dropout. Three public datasets are used to prove the effectiveness of the proposed model. Multiple test cases and comparison with existing models show that the proposed model is able to provide accurate load forecasting results and has high generalization capability.