Coherent Hierarchical Probabilistic Forecasting of Electric Vehicle Charging Demand

被引:3
作者
Zheng, Kedi [1 ]
Xu, Hanwei [2 ]
Long, Zeyang [3 ]
Wang, Yi [4 ]
Chen, Qixin [1 ]
机构
[1] Tsinghua Univ, Dept Elect Engn, State Key Lab Power Syst, Beijing 100084, Peoples R China
[2] Beijing Deepseek Artificial Intelligence Fundament, Beijing 100094, Peoples R China
[3] Huazhong Univ Sci & Technol, Sch Elect & Elect Engn, Wuhan 430074, Peoples R China
[4] Univ Hong Kong, Dept Elect & Elect Engn, Hong Kong 999077, Peoples R China
基金
中国国家自然科学基金;
关键词
Forecasting; Probabilistic logic; Predictive models; Load modeling; Electric vehicle charging; Time series analysis; Demand forecasting; Probabilistic forecasting; electric vehicle; deep learning; hierarchical forecasting; convex learning; PREDICTION; ENERGY;
D O I
10.1109/TIA.2023.3344544
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
The growing penetration of electric vehicles (EVs) significantly changes typical load curves in smart grids. With the development of fast charging technology, the volatility of EV charging demand is increasing, which requires additional flexibility for real-time power balance. The forecasting of EV charging demand involves probabilistic modeling of high dimensional time series dynamics across diverse electric vehicle charging stations (EVCSs). This article studies the forecasting problem of multiple EVCS in a hierarchical probabilistic manner. For each charging station, a deep learning model based on a partial input convex neural network (PICNN) is trained to predict the day-ahead charging demand's conditional distribution, preventing the common quantile crossing problem in traditional quantile regression models. Then, differentiable convex optimization layers (DCLs) are used to reconcile the scenarios sampled from the distributions to yield coherent scenarios that satisfy the hierarchical constraint. It learns a better weight matrix for adjusting the forecasting results of different targets in a machine-learning approach compared to traditional optimization-based hierarchical reconciling methods. Numerical experiments based on real-world EV charging data are conducted to demonstrate the efficacy of the proposed method.
引用
收藏
页码:1329 / 1340
页数:12
相关论文
共 50 条
[41]   An efficient hierarchical electric vehicle charging control strategy [J].
He, Chenyuan ;
Zhang, Zhouyu .
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2023,
[42]   Energy Demand Load Forecasting for Electric Vehicle Charging Stations Network Based on ConvLSTM and BiConvLSTM Architectures [J].
Mohammad, Faisal ;
Kang, Dong-Ki ;
Ahmed, Mohamed A. ;
Kim, Young-Chon .
IEEE ACCESS, 2023, 11 :67350-67369
[43]   Hierarchical Distributed Frequency Regulation Strategy of Electric Vehicle Cluster Considering Demand Charging Load Optimization [J].
Deng, Xiaosong ;
Zhang, Qian ;
Li, Yan ;
Sun, Tao ;
Yue, Huanzhan .
2020 IEEE STUDENT CONFERENCE ON ELECTRIC MACHINES AND SYSTEMS (SCEMS 2020), 2020, :959-969
[44]   A Meta-Learning Approach for Electric Vehicles' Charging Load Demand Forecasting [J].
Kambale, Witesyavwirwa Vianney ;
D'Ambrosi, Denis ;
El Bahnasawi, Mohamed ;
Kayisu, Antoine K. ;
Fasouli, Paraskevi ;
Kyamakya, Kyandoghere .
2024 31ST IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS AND SYSTEMS, ICECS, 2024,
[45]   Forecasting Charging Demand of Electric Vehicles Using Time-Series Models [J].
Kim, Yunsun ;
Kim, Sahm .
ENERGIES, 2021, 14 (05)
[46]   A Hierarchical Approach to Probabilistic Wind Power Forecasting [J].
Gilbert, Ciaran ;
Browell, Jethro ;
McMillan, David .
2018 IEEE INTERNATIONAL CONFERENCE ON PROBABILISTIC METHODS APPLIED TO POWER SYSTEMS (PMAPS), 2018,
[47]   Flexibility of Electric Vehicle Charging With Demand Response and Vehicle-to-Grid for Power System Benefit [J].
Jokinen, Ilkka ;
Lehtonen, Matti .
IEEE ACCESS, 2024, 12 :131419-131441
[48]   An Optimised Deep Learning Model for Load Forecasting in Electric Vehicle Charging Stations [J].
Buvanesan, Vasanthan ;
Venugopal, Manikandan ;
Murugan, Kabil ;
Senthilkumar, Venbha V. E. L. U. M. A. N., I .
ECONOMIC COMPUTATION AND ECONOMIC CYBERNETICS STUDIES AND RESEARCH, 2025, 59 (01) :324-340
[49]   Enabling Optimal Control Under Demand Elasticity for Electric Vehicle Charging Systems [J].
Fan, Guiyun ;
Yang, Zhaoxing ;
Jin, Haiming ;
Gan, Xiaoying ;
Wang, Xinbing .
IEEE TRANSACTIONS ON MOBILE COMPUTING, 2022, 21 (03) :955-970
[50]   Multi-Objective Planning Optimization of Electric Vehicle Charging Stations With Coordinated Spatiotemporal Charging Demand [J].
Zhu, Jiawei ;
Chen, Fei ;
Liu, Shumei ;
An, Yisheng ;
Wu, Naiqi ;
Zhao, Xiangmo .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2025, 26 (02) :1754-1768