Multiscale-integrated deep learning approaches for short-term load forecasting

被引:2
|
作者
Yang, Yang [1 ]
Gao, Yuchao [1 ]
Wang, Zijin [1 ]
Li, Xi'an [2 ]
Zhou, Hu [1 ]
Wu, Jinran [3 ]
机构
[1] Nanjing Univ Posts & Telecommun, Nanjing 210023, Jiangsu, Peoples R China
[2] Ceyear Technol Co Ltd, Qingdao 266555, Shandong, Peoples R China
[3] Australian Catholic Univ, North Sydney, NSW 2060, Australia
关键词
Deep learning; Time series decomposition; Load forecasting; Outliers; Robust regression; SUPPORT VECTOR REGRESSION; EMPIRICAL MODE DECOMPOSITION; NEURAL-NETWORK; ALGORITHM;
D O I
10.1007/s13042-024-02302-4
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Accurate short-term load forecasting (STLF) is crucial for the power system. Traditional methods generally used signal decomposition techniques for feature extraction. However, these methods are limited in extrapolation performance, and the parameter of decomposition modes needs to be preset. To end this, this paper develops a novel STLF algorithm based on multi-scale perspective decomposition. The proposed algorithm adopts the multi-scale deep neural network (MscaleDNN) to decompose load series into low- and high-frequency components. Considering outliers of load series, this paper introduces the adaptive rescaled lncosh (ARlncosh) loss to fit the distribution of load data and improve the robustness. Furthermore, the attention mechanism (ATTN) extracts the correlations between different moments. In two power load data sets from Portugal and Australia, the proposed model generates competitive forecasting results.
引用
收藏
页码:6061 / 6076
页数:16
相关论文
共 50 条
  • [21] Comparison of different approaches to short-term load forecasting
    Girgis, AA
    Varadan, S
    ElDin, AK
    Zhu, J
    ENGINEERING INTELLIGENT SYSTEMS FOR ELECTRICAL ENGINEERING AND COMMUNICATIONS, 1995, 3 (04): : 205 - 210
  • [22] Comparison of different approaches to short-term load forecasting
    Girgis, Adly A.
    Varadan, Srinivas
    El-Din, A.Karim
    Zhu, Jun
    International Journal of Engineering Intelligent Systems for Electrical Engineering and Communications, 1995, 3 (04): : 205 - 210
  • [23] A Hybrid Deep Learning Model with Evolutionary Algorithm for Short-Term Load Forecasting
    Al Mamun, Abdullah
    Hoq, Muntasir
    Hossain, Eklas
    Bayindir, Ramazan
    2019 8TH INTERNATIONAL CONFERENCE ON RENEWABLE ENERGY RESEARCH AND APPLICATIONS (ICRERA 2019), 2019, : 886 - 891
  • [24] A deep learning model for short-term power load and probability density forecasting
    Guo, Zhifeng
    Zhou, Kaile
    Zhang, Xiaoling
    Yang, Shanlin
    ENERGY, 2018, 160 : 1186 - 1200
  • [25] Short-Term Load Forecasting in Smart Grids Using Hybrid Deep Learning
    Asiri, Mashael M.
    Aldehim, Ghadah
    Alotaibi, Faiz Abdullah
    Alnfiai, Mrim M.
    Assiri, Mohammed
    Mahmud, Ahmed
    IEEE ACCESS, 2024, 12 : 23504 - 23513
  • [26] A Deep Learning Method for Short-Term Residential Load Forecasting in Smart Grid
    Hong, Ye
    Zhou, Yingjie
    Li, Qibin
    Xu, Wenzheng
    Zheng, Xiujuan
    IEEE ACCESS, 2020, 8 (08): : 55785 - 55797
  • [27] An effective deep learning neural network model for short-term load forecasting
    Li, Ning
    Wang, Lu
    Li, Xinquan
    Zhu, Qing
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2020, 32 (07):
  • [28] Research on Short-term Load Forecasting of Power System Based on Deep Learning
    Li, Lei
    Jia, Kunlin
    PROCEEDINGS OF 2024 INTERNATIONAL CONFERENCE ON POWER ELECTRONICS AND ARTIFICIAL INTELLIGENCE, PEAI 2024, 2024, : 251 - 255
  • [29] Short-Term Load Forecasting Based on VMD and Combined Deep Learning Model
    Wang, Nier
    Xue, Sheng
    Li, Zhanming
    IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING, 2023, 18 (07) : 1067 - 1075
  • [30] Application of Deep Learning Method in Short-term Load Forecasting of Characteristic Enterprises
    Dou, Yuchen
    Zhang, Xinman
    Wu, Zhihui
    Zhang, Hang
    PROCEEDINGS OF 2018 ARTIFICIAL INTELLIGENCE AND CLOUD COMPUTING CONFERENCE (AICCC 2018), 2018, : 35 - 40