文献类型： 外文期刊

作者： Jin, Xue-Bo ¹ ; Zheng, Wei-Zhen ¹ ; Kong, Jian-Lei ¹ ; Wang, Xiao-Yi ¹ ; Bai, Yu-Ting ¹ ; Su, Ting-Li ¹ ; Lin, Seng ³ ;

作者机构： 1.Beijing Technol & Business Univ, Sch Artificial Intelligence, Beijing 100048, Peoples R China

2.Natl Key Lab Environm Protect Food Chain Pollut P, Beijing 100048, Peoples R China

3.Beijing Res Ctr Intelligent Equipment Agr, Beijing 100097, Peoples R China

关键词： electric power load prediction; deep-learning encoder-decoder framework; gated recurrent neural units; temporal attention; Bayesian optimization

期刊名称：ENERGIES （ 影响因子：2.702； 五年影响因子：2.822 ）

ISSN：

年卷期： 2021 年 14 卷 6 期

页码：

收录情况： SCI

摘要： Short-term electrical load forecasting plays an important role in the safety, stability, and sustainability of the power production and scheduling process. An accurate prediction of power load can provide a reliable decision for power system management. To solve the limitation of the existing load forecasting methods in dealing with time-series data, causing the poor stability and non-ideal forecasting accuracy, this paper proposed an attention-based encoder-decoder network with Bayesian optimization to do the accurate short-term power load forecasting. Proposed model is based on an encoder-decoder architecture with a gated recurrent units (GRU) recurrent neural network with high robustness on time-series data modeling. The temporal attention layer focuses on the key features of input data that play a vital role in promoting the prediction accuracy for load forecasting. Finally, the Bayesian optimization method is used to confirm the model's hyperparameters to achieve optimal predictions. The verification experiments of 24 h load forecasting with real power load data from American Electric Power (AEP) show that the proposed model outperforms other models in terms of prediction accuracy and algorithm stability, providing an effective approach for migrating time-serial power load prediction by deep-learning technology.