Short-term power load forecasting method based on CNN-SAEDN-Res

TL;DR

This paper introduces a novel short-term power load forecasting method combining CNN, self-attention encoder-decoder network, and residual refinement to improve prediction accuracy and stability, especially with non-temporal factors.

Contribution

It proposes an integrated deep learning model that effectively captures local and global data correlations for improved load forecasting accuracy.

Findings

Enhanced prediction accuracy over traditional methods

Improved stability in load forecasts

Effective handling of non-temporal factors

Abstract

In deep learning, the load data with non-temporal factors are difficult to process by sequence models. This problem results in insufficient precision of the prediction. Therefore, a short-term load forecasting method based on convolutional neural network (CNN), self-attention encoder-decoder network (SAEDN) and residual-refinement (Res) is proposed. In this method, feature extraction module is composed of a two-dimensional convolutional neural network, which is used to mine the local correlation between data and obtain high-dimensional data features. The initial load fore-casting module consists of a self-attention encoder-decoder network and a feedforward neural network (FFN). The module utilizes self-attention mechanisms to encode high-dimensional features. This operation can obtain the global correlation between data. Therefore, the model is able to retain important information based on the coupling relationship between the data in data mixed with non-time series factors. Then, self-attention decoding is per-formed and the feedforward neural network is used to regression initial load. This paper introduces the residual mechanism to build the load optimization module. The module generates residual load values to optimize the initial load. The simulation results show that the proposed load forecasting method has advantages in terms of prediction accuracy and prediction stability.