Forecasting Photovoltaic Power Production using a Deep Learning Sequence to Sequence Model with Attention

被引:11
|
作者
Kharlova, Elizaveta [1 ]
May, Daniel [1 ]
Musilek, Petr [1 ]
机构
[1] Univ Alberta, Elect & Comp Engn, Edmonton, AB, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
photovoltaic power; PV; forecasting; probabilistic forecasting; time-series; deep learning; sequence to sequence; attention; encoder-decoder; GENERATION;
D O I
10.1109/ijcnn48605.2020.9207573
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Rising penetration levels of (residential) photovoltaic (PV) power as distributed energy resource pose a number of challenges to the electricity infrastructure. High quality, general tools to provide accurate forecasts of power production are urgently needed. In this article, we propose a supervised deep learning model for end-to-end forecasting of PV power production. The proposed model is based on two seminal concepts that led to significant performance improvements of deep learning approaches in other sequence-related fields, but not yet in the area of time series prediction: the sequence to sequence architecture and attention mechanism as a context generator. The proposed model leverages numerical weather predictions and high-resolution historical measurements to forecast a binned probability distribution over the prognostic time intervals, rather than the expected values of the prognostic variable. This design offers significant performance improvements compared to common baseline approaches, such as fully connected neural networks and one-block long short-term memory architectures. Using normalized root mean square error based forecast skill score as a performance indicator, the proposed approach is compared to other models. The results show that the new design performs at or above the current state of the art of PV power forecasting.
引用
收藏
页数:7
相关论文
共 50 条
  • [1] Deep Learning for Load Forecasting: Sequence to Sequence Recurrent Neural Networks With Attention
    Sehovac, Ljubisa
    Grolinger, Katarina
    IEEE ACCESS, 2020, 8 : 36411 - 36426
  • [2] Time Series Forecasting using Sequence-to-Sequence Deep Learning Framework
    Du, Shengdong
    Li, Tianrui
    Horng, Shi-Jinn
    2018 9TH INTERNATIONAL CONFERENCE ON PARALLEL ARCHITECTURES, ALGORITHMS AND PROGRAMMING (PAAP 2018), 2018, : 171 - 176
  • [3] A Novel Sequence-to-Sequence-Based Deep Learning Model for Multistep Load Forecasting
    Lu, Renzhi
    Bai, Ruichang
    Li, Ruidong
    Zhu, Lijun
    Sun, Mingyang
    Xiao, Feng
    Wang, Dong
    Wu, Huaming
    Ding, Yuemin
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, : 1 - 15
  • [4] Sequence to sequence deep learning models for solar irradiation forecasting
    Mukhoty, Bhaskar Pratim
    Maurya, Vikas
    Shukla, Sandeep Kumar
    2019 IEEE MILAN POWERTECH, 2019,
  • [5] A deep learning sequence model based on self-attention and convolution for wind power prediction
    Liu, Chien-Liang
    Chang, Tzu-Yu
    Yang, Jie-Si
    Huang, Kai-Bin
    RENEWABLE ENERGY, 2023, 219
  • [6] A Novel Deep Learning Attention Based Sequence to Sequence Model for Automatic Abstractive Text Summarization
    Abd Algani Y.M.
    International Journal of Information Technology, 2024, 16 (6) : 3597 - 3603
  • [7] Forecasting Building Energy Consumption with Deep Learning: A Sequence to Sequence Approach
    Sehovac, Ljubisa
    Nesen, Cornelius
    Grolinger, Katarina
    2019 IEEE INTERNATIONAL CONGRESS ON INTERNET OF THINGS (IEEE ICIOT 2019), 2019, : 108 - 116
  • [8] A hybrid deep learning model with error correction for photovoltaic power forecasting
    Zhang, Rongquan
    Li, Gangqiang
    Bu, Siqi
    Kuang, Guowen
    He, Wei
    Zhu, Yuxiang
    Aziz, Saddam
    FRONTIERS IN ENERGY RESEARCH, 2022, 10
  • [9] Forecasting of Patient-Specific Kidney Transplant Function With a Sequence-to-Sequence Deep Learning Model
    Van Loon, Elisabet
    Zhang, Wanqiu
    Coemans, Maarten
    De Vos, Maarten
    Emonds, Marie-Paule
    Scheffner, Irina
    Gwinner, Wilfried
    Kuypers, Dirk
    Senev, Aleksandar
    Tinel, Claire
    Van Craenenbroeck, Amaryllis H.
    De Moor, Bart
    Naesens, Maarten
    JAMA NETWORK OPEN, 2021, 4 (12)
  • [10] Photovoltaic power forecasting: A hybrid deep learning model incorporating transfer learning strategy
    Tang, Yugui
    Yang, Kuo
    Zhang, Shujing
    Zhang, Zhen
    RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2022, 162