Interval-based Probabilistic Load Forecasting for Individual Households: Clustering Approach

被引:0
|
作者
Kaur, Devinder [1 ]
Islam, Shama Naz [1 ]
Mahmud, Md Apel [2 ]
Haque, Md Enamul [1 ]
机构
[1] Deakin Univ, Geelong, Vic, Australia
[2] Northumbria Univ, Fac Engn & Environm, Newcastle Upon Tyne, Tyne & Wear, England
来源
2022 IEEE PES 14TH ASIA-PACIFIC POWER AND ENERGY ENGINEERING CONFERENCE, APPEEC | 2022年
关键词
Bayesian deep learning; load forecasting; clustering; machine learning; uncertainty; METHODOLOGIES; UNCERTAINTY;
D O I
10.1109/APPEEC53445.2022.10072082
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
With the widespread use of smart meters, it has become easier to manage demand side at the individual household level by employing applications such as load forecasting. However, uncertainty in the load consumption profiles is a major challenge for individual load forecasting methods caused by the key factors such as variation in user behavior, and weather variables. Therefore, the load profiles first need to be modeled systematically in order to achieve effective forecasting results. This paper presents a holistic load forecasting framework by first modeling the temporal features of load consumption profiles using Gaussian mixture model clustering. The extracted information is then fed to the Bayesian Bidirectional long short-term memory (LSTM) method to generate probabilistic forecasts. The proposed framework is implemented on real-life energy consumption data and compared against benchmark machine learning methods using forecasting evaluation metrics at 90%, 50%, and 10% quantiles.
引用
收藏
页数:6
相关论文
共 50 条
  • [21] A Multivariate Approach to Probabilistic Industrial Load Forecasting
    Bracale, Antonio
    Caramia, Pierluigi
    De Falco, Pasquale
    Hong, Tao
    ELECTRIC POWER SYSTEMS RESEARCH, 2020, 187
  • [22] Probabilistic load forecasting considering temporal correlation: Online models for the prediction of households' electrical load
    Lemos-Vinasco, Julian
    Bacher, Peder
    Moller, Jan Kloppenborg
    APPLIED ENERGY, 2021, 303
  • [23] Forecasting of Wind Speed Using an Interval-Based Least Square Method
    Aslam, Muhammad
    Albassam, Mohammed
    FRONTIERS IN ENERGY RESEARCH, 2022, 10
  • [24] Interval-based, nonparametric approach for resampling of fuzzy numbers
    Romaniuk, Maciej
    Hryniewicz, Olgierd
    SOFT COMPUTING, 2019, 23 (14) : 5883 - 5903
  • [25] An interval-based contingency selection approach considering uncertainty
    Xu, Chao
    Gu, Wei
    Luo, Lizi
    Yao, Jianguo
    Yang, Shengchun
    Wang, Ke
    Zeng, Dan
    Fan, Miao
    TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2016, 24 (06) : 4682 - 4692
  • [26] Availability with Input Uncertainties Using an Interval-Based Approach
    Galdino, Sergio
    Maciel, Paulo
    2010 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC 2010), 2010,
  • [27] Interval-based, nonparametric approach for resampling of fuzzy numbers
    Maciej Romaniuk
    Olgierd Hryniewicz
    Soft Computing, 2019, 23 : 5883 - 5903
  • [28] Interval-Based Approach for Uncertainty Propagation in Inverse Problems
    Fedele, Francesco
    Muhanna, Rafi L.
    Xiao, Naijia
    Mullen, Robert L.
    JOURNAL OF ENGINEERING MECHANICS, 2015, 141 (01)
  • [29] Probabilistic short-term load forecasting models based on a parametric approach
    Fernández-Jiménez, L.A.
    Terreros-Olarte, S.
    Capellán-Villacián, C.
    Falces, A.
    García-Garrido, E.
    Lara-Santillán, P.M.
    Mendoza-Villena, M.
    Zorzano-Alba, E.
    Zorzano-Santamaría, P.J.
    Renewable Energy and Power Quality Journal, 2024, 22 (05): : 101 - 106
  • [30] Probabilistic prediction approach of heat load based on support vector interval regression
    Zhang, Yong-Ming
    Chen, Lie
    Qi, Wei-Gui
    Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition), 2010, 40 (06): : 1693 - 1697