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 40 条
  • [1] A proposed intelligent short-term load forecasting hybrid models of ANN, WNN and KF based on clustering techniques for smart grid
    Aly, Hamed H. H.
    [J]. ELECTRIC POWER SYSTEMS RESEARCH, 2020, 182
  • [2] Statistical Load Forecasting Using Optimal Quantile Regression Random Forest and Risk Assessment Index
    Aprillia, Happy
    Yang, Hong-Tzer
    Huang, Chao-Ming
    [J]. IEEE TRANSACTIONS ON SMART GRID, 2021, 12 (02) : 1467 - 1480
  • [3] Bai SJ, 2018, Arxiv, DOI [arXiv:1803.01271, 10.48550/arXiv.1803.01271]
  • [4] An Optimal Distributed RES Sizing Strategy in Hybrid Low Voltage Networks Focused on EVs' Integration
    Boglou, Vasileios
    Karavas, Christos-Spyridon
    Karlis, Athanasios
    Arvanitis, Konstantinos G.
    Palaiologou, Ilias
    [J]. IEEE ACCESS, 2023, 11 : 16250 - 16270
  • [5] An intelligent decentralized energy management strategy for the optimal electric vehicles' charging in low-voltage islanded microgrids
    Boglou, Vasileios
    Karavas, Christos-Spyridon
    Karlis, Athanasios
    Arvanitis, Konstantinos
    [J]. INTERNATIONAL JOURNAL OF ENERGY RESEARCH, 2022, 46 (03) : 2988 - 3016
  • [6] A hybrid information model based on long short-term memory network for tool condition monitoring
    Cai, Weili
    Zhang, Wenjuan
    Hu, Xiaofeng
    Liu, Yingchao
    [J]. JOURNAL OF INTELLIGENT MANUFACTURING, 2020, 31 (06) : 1497 - 1510
  • [7] Chung JY, 2014, Arxiv, DOI arXiv:1412.3555
  • [8] Deep Learning: Methods and Applications
    Deng, Li
    Yu, Dong
    [J]. FOUNDATIONS AND TRENDS IN SIGNAL PROCESSING, 2013, 7 (3-4): : I - 387
  • [9] Multi-Scale Convolutional Neural Network With Time-Cognition for Multi-Step Short-Term Load Forecasting
    Deng, Zhuofu
    Wang, Binbin
    Xu, Yanlu
    Xu, Tengteng
    Liu, Chenxu
    Zhu, Zhiliang
    [J]. IEEE ACCESS, 2019, 7 : 88058 - 88071
  • [10] Convolutional and recurrent neural network based model for short-term load forecasting
    Eskandari, Hosein
    Imani, Maryam
    Moghaddam, Mohsen Parsa
    [J]. ELECTRIC POWER SYSTEMS RESEARCH, 2021, 195 (195)