An Ensemble Framework for Short-Term Load Forecasting Based on TimesNet and TCN

被引:18
|
作者
Zuo, Chuanhui [1 ]
Wang, Jialong [1 ]
Liu, Mingping [1 ]
Deng, Suhui [1 ]
Wang, Qingnian [1 ]
机构
[1] Nanchang Univ, Sch Informat Engn, Nanchang 330031, Peoples R China
基金
中国国家自然科学基金;
关键词
short-term power load forecasting; multi-periodicity; TimesNet; temporal convolutional network; NEURAL-NETWORK; ALGORITHM; CNN;
D O I
10.3390/en16145330
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Accurate and efficient short-term power load forecasting is crucial for ensuring the stable operation of power systems and rational planning of electricity resources. However, power load data are often characterized by nonlinearity and instability due to external factors such as meteorological conditions and day types, making accurate load forecasting challenging. While some hybrid models can effectively capture the spatiotemporal features of power load data, they often overlook the multi-periodicity of load data, leading to suboptimal feature extraction and efficiency. In this paper, a novel hybrid framework for short-term load forecasting based on TimesNet and temporal convolutional network (TCN) is proposed. Firstly, the original load data are preprocessed to reconstruct a feature matrix. Secondly, the TimesNet transforms the one-dimensional time series into a set of two-dimensional tensors based on multiple periods, capturing dependencies within different time scales and the relationships between different time scales in power load data. Then, the temporal convolutional network is employed to further extract the temporal features and long-term dependencies of the load data, enabling a more global pattern to be obtained for temporal information. Finally, the results of load forecasting can be achieved from the fully connected layer based on the extracted features. To verify the effectiveness and generalization of the proposed model, experiments have been conducted based on the ISO-NE and Southern China datasets. Experimental results show that the proposed model greatly outperforms the long short-term memory (LSTM), TCN, TimesNet, TCN-LSTM, and TimesNet-LSTM models. The proposed model reduces the mean absolute percentage error by 20% to 43% for the ISO-NE dataset and by 10% to 31% for the Southern China dataset, respectively.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] Short-Term Load Forecasting Based on Improved TCN and DenseNet
    Liu, Mingping
    Qin, Hao
    Cao, Ran
    Deng, Suhui
    IEEE ACCESS, 2022, 10 : 115945 - 115957
  • [2] Ensemble models of TCN-LSTM-LightGBM based on ensemble learning methods for short-term electrical load forecasting
    Gong, Jianqiang
    Qu, Zhiguo
    Zhu, Zhenle
    Xu, Hongtao
    Yang, Qiguo
    ENERGY, 2025, 318
  • [3] Short-Term Load Forecasting for Industrial Customers Based on TCN-LightGBM
    Wang, Yuanyuan
    Chen, Jun
    Chen, Xiaoqiao
    Zeng, Xiangjun
    Kong, Yang
    Sun, Shanfeng
    Guo, Yongsheng
    Liu, Ying
    IEEE TRANSACTIONS ON POWER SYSTEMS, 2021, 36 (03) : 1984 - 1997
  • [4] Multi-Scale Short-Term Load Forecasting Based on VMD and TCN
    Liu J.
    Jin Y.
    Tian M.
    Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China, 2022, 51 (04): : 550 - 557
  • [5] Short-term Load Forecasting with LSTM based Ensemble Learning
    Wang, Lingxiao
    Mao, Shiwen
    Wilamowski, Bogdan
    2019 INTERNATIONAL CONFERENCE ON INTERNET OF THINGS (ITHINGS) AND IEEE GREEN COMPUTING AND COMMUNICATIONS (GREENCOM) AND IEEE CYBER, PHYSICAL AND SOCIAL COMPUTING (CPSCOM) AND IEEE SMART DATA (SMARTDATA), 2019, : 793 - 800
  • [6] An ensemble framework for short-term load forecasting based on parallel CNN and GRU with improved ResNet
    Hua, Heng
    Liu, Mingping
    Li, Yuqin
    Deng, Suhui
    Wang, Qingnian
    ELECTRIC POWER SYSTEMS RESEARCH, 2023, 216
  • [7] Short-term power load forecasting based on the CEEMDAN-TCN-ESN model
    Huang, Jiacheng
    Zhang, Xiaowen
    Jiang, Xuchu
    PLOS ONE, 2023, 18 (10):
  • [8] Short-Term Electric Load Forecasting Based on Signal Decomposition and Improved TCN Algorithm
    Xiang, Xinjian
    Yuan, Tianshun
    Cao, Guangke
    Zheng, Yongping
    ENERGIES, 2024, 17 (08)
  • [9] Enhancing Short-Term Power Load Forecasting With a TimesNet-Crossformer-LSTM Approach
    He, Jun
    Yuan, Kuidong
    Zhong, Zijie
    Sun, Yifan
    IEEE ACCESS, 2024, 12 : 56774 - 56788
  • [10] Ensemble Residual Networks for Short-Term Load Forecasting
    Xu, Qingshan
    Yang, Xiaohui
    Huang, Xin
    IEEE ACCESS, 2020, 8 (64750-64759) : 64750 - 64759