DTTrans: PV Power Forecasting Using Delaunay Triangulation and TransGRU

被引:7
|
作者
Song, Keunju [1 ]
Jeong, Jaeik [1 ]
Moon, Jong-Hee [2 ]
Kwon, Seong-Chul [2 ]
Kim, Hongseok [1 ]
机构
[1] Sogang Univ, Dept Elect Engn, Seoul 04107, South Korea
[2] KEPCO Res Inst, Smart Power Distribut Lab, Daejeon 34056, South Korea
基金
新加坡国家研究基金会;
关键词
Delaunay triangulation; interpretable AI; TransGRU; NEURAL-NETWORK; PREDICTION; MODEL; OUTPUT;
D O I
10.3390/s23010144
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
In an era of high penetration of renewable energy, accurate photovoltaic (PV) power forecasting is crucial for balancing and scheduling power systems. However, PV power output has uncertainty since it depends on stochastic weather conditions. In this paper, we propose a novel short-term PV forecasting technique using Delaunay triangulation, of which the vertices are three weather stations that enclose a target PV site. By leveraging a Transformer encoder and gated recurrent unit (GRU), the proposed TransGRU model is robust against weather forecast error as it learns feature representation from weather data. We construct a framework based on Delaunay triangulation and TransGRU and verify that the proposed framework shows a 7-15% improvement compared to other state-of-the-art methods in terms of the normalized mean absolute error. Moreover, we investigate the effect of PV aggregation for virtual power plants where errors can be compensated across PV sites. Our framework demonstrates 41-60% improvement when PV sites are aggregated and achieves as low as 3-4% of forecasting error on average.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Constrained Delaunay triangulation using Delaunay visibility
    Yang, Yi-Jun
    Zhang, Hui
    Yong, Jun-Hai
    Zeng, Wei
    Paul, Jean-Claude
    Sun, Jiaguang
    ADVANCES IN VISUAL COMPUTING, PT 1, 2006, 4291 : 682 - 691
  • [2] DELAUNAY TRIANGULATION USING A UNIFORM GRID
    FANG, TP
    PIEGL, LA
    IEEE COMPUTER GRAPHICS AND APPLICATIONS, 1993, 13 (03) : 36 - 47
  • [3] Melanoma Detection Using Delaunay Triangulation
    Pennisi, A.
    Bloisi, D. D.
    Nardi, D.
    Giampetruzzi, A. R.
    Mondino, C.
    Facchiano, A.
    2015 IEEE 27TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2015), 2015, : 791 - 798
  • [4] Dynamic pedestrian trajectory forecasting with LSTM-based Delaunay triangulation
    Qiulin Ma
    Qi Zou
    Yaping Huang
    Nan Wang
    Applied Intelligence, 2022, 52 : 3018 - 3028
  • [5] Dynamic pedestrian trajectory forecasting with LSTM-based Delaunay triangulation
    Ma, Qiulin
    Zou, Qi
    Huang, Yaping
    Wang, Nan
    APPLIED INTELLIGENCE, 2022, 52 (03) : 3018 - 3028
  • [6] A method for Delaunay triangulation using a uniform grid
    Hao, YL
    Lu, H
    FOURTH INTERNATIONAL CONFERENCE ON VIRTUAL REALITY AND ITS APPLICATIONS IN INDUSTRY, 2004, 5444 : 60 - 66
  • [7] EFFICIENT DELAUNAY TRIANGULATION USING RATIONAL ARITHMETIC
    KARASICK, M
    LIEBER, D
    NACKMAN, LR
    ACM TRANSACTIONS ON GRAPHICS, 1991, 10 (01): : 71 - 91
  • [8] A TIN compression method using Delaunay triangulation
    Park, D
    Cho, HG
    Kim, Y
    INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE, 2001, 15 (03) : 255 - 269
  • [9] Face recognition using SURF and delaunay triangulation
    Vinay, A.
    Gupta, Abhijay
    Garg, Harsh
    Bhat, Shreyas
    Murthy, K. N. Balasubramanya
    Natarajan, S.
    EMERGING TRENDS IN ENGINEERING, SCIENCE AND TECHNOLOGY FOR SOCIETY, ENERGY AND ENVIRONMENT, 2018, : 865 - 871