• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
成果搜索

author:

Lin, Peijie (Lin, Peijie.) [1] (Scholars:林培杰) | Zhang, Xiangxin (Zhang, Xiangxin.) [2] | Gong, Longcong (Gong, Longcong.) [3] | Lin, Jingwei (Lin, Jingwei.) [4] | Zhang, Jie (Zhang, Jie.) [5] (Scholars:章杰) | Cheng, Shuying (Cheng, Shuying.) [6] (Scholars:程树英)

Indexed by:

EI Scopus SCIE

Abstract:

Short-term water demand forecasting is essential for ensuring the sustainable use of water resources. The accuracy of water demand forecasting directly impacts the rationality of water resources management and the effectiveness of scheduling. Therefore, it is vital to accurately forecast water demand across various timescales. Based on this motivation, we propose an improved patch time series Transformer (PatchTST) model to forecast the multi-timescale short-term water demand. By introducing relative positional encoding (RPE), the model effectively learns the relationships between tokens. The model combines the global token information capture ability of the self-attention mechanism with the local token information capture ability of the convolutional network to enhance feature extraction abilities. Additionally, the model integrates the advantages of patch-wise and series-wise representation, enabling it to simultaneously capture both local and global dependencies in time series. We utilize historical data collected from district metering area to experimentally validate the effectiveness of the proposed model. Compared with one-dimensional convolutional neural network (1D-CNN), long shortterm memory (LSTM), Transformer, DLinear, and PatchTST models, our model demonstrates superior performance across all five forecasting scales. Finally, the effectiveness of the proposed design is further validated through ablation experiments.

Keyword:

Deep learning Multi-timescale PatchTST Water demand forecasting

Community:

  • [ 1 ] [Lin, Peijie]Fuzhou Univ, Coll Phys & Informat Engn, Fuzhou, Peoples R China
  • [ 2 ] [Zhang, Xiangxin]Fuzhou Univ, Coll Phys & Informat Engn, Fuzhou, Peoples R China
  • [ 3 ] [Zhang, Jie]Fuzhou Univ, Coll Phys & Informat Engn, Fuzhou, Peoples R China
  • [ 4 ] [Cheng, Shuying]Fuzhou Univ, Coll Phys & Informat Engn, Fuzhou, Peoples R China
  • [ 5 ] [Lin, Peijie]Fuzhou Univ, Inst Micronano Devices & Solar Cells, Fuzhou, Peoples R China
  • [ 6 ] [Zhang, Xiangxin]Fuzhou Univ, Inst Micronano Devices & Solar Cells, Fuzhou, Peoples R China
  • [ 7 ] [Zhang, Jie]Fuzhou Univ, Inst Micronano Devices & Solar Cells, Fuzhou, Peoples R China
  • [ 8 ] [Cheng, Shuying]Fuzhou Univ, Inst Micronano Devices & Solar Cells, Fuzhou, Peoples R China
  • [ 9 ] [Gong, Longcong]Fuzhou Water Supply Co Ltd, Fuzhou, Peoples R China
  • [ 10 ] [Lin, Jingwei]Fuzhou Water Supply Co Ltd, Fuzhou, Peoples R China

Reprint 's Address:

  • 章杰 程树英

    [Zhang, Jie]Fuzhou Univ, Coll Phys & Informat Engn, Fuzhou, Peoples R China;;[Cheng, Shuying]Fuzhou Univ, Coll Phys & Informat Engn, Fuzhou, Peoples R China;;[Zhang, Jie]Fuzhou Univ, Inst Micronano Devices & Solar Cells, Fuzhou, Peoples R China;;[Cheng, Shuying]Fuzhou Univ, Inst Micronano Devices & Solar Cells, Fuzhou, Peoples R China

Show more details

Related Keywords:

Source :

JOURNAL OF HYDROLOGY

ISSN: 0022-1694

Year: 2024

Volume: 651

5 . 9 0 0

JCR@2023

Cited Count:

WoS CC Cited Count:

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 3

Online/Total:173/10010756
Address:FZU Library(No.2 Xuyuan Road, Fuzhou, Fujian, PRC Post Code:350116) Contact Us:0591-22865326
Copyright:FZU Library Technical Support:Beijing Aegean Software Co., Ltd. 闽ICP备05005463号-1