Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (1): 311-317.DOI: 10.11772/j.issn.1001-9081.2023010078

• Frontier and comprehensive applications • Previous Articles    

Short-term power load forecasting by graph convolutional network combining LSTM and self-attention mechanism

Hanxiao SHI, Leichun WANG()   

  1. School of Computer Science and Information Engineering,Hubei University,Wuhan Hubei 430062,China
  • Received:2023-01-31 Revised:2023-03-31 Accepted:2023-04-03 Online:2023-06-06 Published:2024-01-10
  • Contact: Leichun WANG
  • About author:SHI Hanxiao, born in 1998, M. S. candidate. His research interests include power load forecasting, deep learning.
  • Supported by:
    National Natural Science Foundation of China(62106069)

结合LSTM和自注意力机制的图卷积网络短期电力负荷预测

史含笑, 王雷春()   

  1. 湖北大学 计算机与信息工程学院,武汉 430062
  • 通讯作者: 王雷春
  • 作者简介:史含笑(1998—),男,河南商丘人,硕士研究生,主要研究方向:电力负荷预测、深度学习;
    第一联系人:王雷春(1974—),男,湖北武汉人,副教授,博士,主要研究方向:深度学习、大数据分析。
  • 基金资助:
    国家自然科学基金资助项目(62106069)

Abstract:

Aiming at the problems of the existing power load forecasting models such as heavy modeling workload, insufficient spatiotemporal joint representation, and low forecasting accuracy, a Short-Term power Load Forecasting model based on Graph Convolutional Network (GCN) combining Long Short-Term Memory (LSTM) network and Self-attention mechanism (GCNLS-STLF) was proposed. Firstly, original multi-dimensional time series data was transformed into a power load graph containing the correlation between series by using LSTM and self-attention mechanism. Then, the features were extracted from the power load graph by GCN, LSTM and Graph Fourier Transform (GFT). Finally, a full connection layer was used to reconstruct features, and the residual was used to forecast the power load for multiple times to enhance the expression ability of the original power load data. The short-term power load forecasting experimental results on real historical power load data of power stations in Morocco and Panama showed that compared with Support Vector Machine (SVM), LSTM, mixed model CNN-LSTM and CNN-LSTM based on attention (CNN-LSTM-attention), the Mean Absolute Percentage Error (MAPE) of GCNLS-STLF was reduced by 1.94, 0.90, 0.49 and 0.37 percentage points, respectively, on the entire Morocco power load test set; the MAPE of GCNLS-STLF on the Panama power load test dataset decreased by 1.39, 0.94, 0.38 and 0.29 percentage points respectively in March and 1.40, 0.99, 0.35 and 0.28 percentage points respectively in June. Experimental results show that GCNLS-STLF can effectively extract key features of power load, and forecasting effects are satisfactory.

Key words: short-term power load forecasting, Graph Convolutional Network (GCN), Graph Fourier Transform (GFT), Long Short-Term Memory (LSTM) network, self-attention mechanism

摘要:

针对现有电力负荷预测模型建模工作量大、时空联合表征不足、预测精度低等问题,提出了一种结合长短期记忆(LSTM)网络和自注意力机制的图卷积网络(GCN)的短期电力负荷预测模型GCNLS-STLF。首先,利用LSTM和自注意力机制将原始多维时间序列数据转化为包含序列间关联关系的电力负荷图;然后,通过GCN、LSTM和图傅里叶变换(GFT)对电力负荷图进行特征提取;最后,使用全连接层对特征进行重构,并利用残差进行多次预测,以增强原始电力负荷数据的表达能力。在摩洛哥与巴拿马某电站的真实历史电力负荷数据上进行的短期电力负荷预测实验结果显示,与支持向量机(SVM)、LSTM、混合模型CNN-LSTM和基于注意力的CNN-LSTM(CNN-LSTM-attention)等预测模型相比,GCNLS-STLF在摩洛哥全部电力负荷测试集上的平均绝对百分比误差(MAPE)分别降低1.94、0.90、0.49和0.37个百分点;在巴拿马电力负荷测试集上的3月份MAPE分别降低1.39、0.94、0.38和0.29个百分点,6月份MAPE分别降低1.40、0.99、0.35和0.28个百分点。实验结果表明,GCNLS-STLF能有效提取电力负荷的关键特征,预测效果较好。

关键词: 短期电力负荷预测, 图卷积网络, 图傅里叶变换, 长短期记忆网络, 自注意力机制

CLC Number: