基于双层可信联邦学习的电动汽车能量需求预测

岳高峰; 韩迪; 陈嘉鑫; 王莎

doi:null

您当前的位置：

首页 >

文章列表页 >

基于双层可信联邦学习的电动汽车能量需求预测

更新时间：2026-06-15

- 基于双层可信联邦学习的电动汽车能量需求预测
- Electric Vehicle Energy Demand Prediction Based on Double-Layer Credible Federated Learning
- 物联网学报 2026年
- 作者机构：
  
  自动化工程学院，西安航空职业技术学院，西安 710089
- 作者简介：
  
  韩迪（2000-06-30），女，工学硕士学位，西安航空职业技术学院，助教，专任教师，主要研究方向：多传感器融合。
  陈嘉鑫（1995-04-26），女，工学硕士学位，西安航空职业技术学院，讲师，专任教师，主要研究方向：大数据处理技术。
- 基金信息：
  
  校级自然科学基金(25XHZK-13;25XHZQ-054)
- DOI：
  中图分类号：
- 收稿：2026-03-12，
  
  修回：2026-06-11，
  
  录用：2026-06-15，
- 稿件说明：
移动端阅览
岳高峰, 韩迪, 陈嘉鑫, 等. 基于双层可信联邦学习的电动汽车能量需求预测[J/OL]. 物联网学报, 2026.

YUE Gaofeng, Han Di, Chen Jiaxin, et al. Electric Vehicle Energy Demand Prediction Based on Double-Layer Credible Federated Learning[J/OL]. Chinese Journal on Internet of Things, 2026.
岳高峰, 韩迪, 陈嘉鑫, 等. 基于双层可信联邦学习的电动汽车能量需求预测[J/OL]. 物联网学报, 2026. DOI：

YUE Gaofeng, Han Di, Chen Jiaxin, et al. Electric Vehicle Energy Demand Prediction Based on Double-Layer Credible Federated Learning[J/OL]. Chinese Journal on Internet of Things, 2026. DOI：

摘要

电动汽车充电需求的准确预测对缓解电网压力至关重要。针对现有预测方法在处理非独立同分布数据时收敛慢、易受不可靠节点影响的问题，本文提出一种双层可信联邦学习(Double-Layer Credible Federated Learning

DCFL)能量需求预测策略。该方法利用启发式关联规则自动挖掘充电信息，无需额外数据采集；通过权值损失变化筛选良性本地因子以加速收敛并抵御不可靠节点干扰；引入多通道注意力机制设计损失函数与加权聚合方式。实验结果表明，相比传统联邦学习方法，本方法训练时间减少71%，收敛速度提升17.6%，在预测准确度和收敛效率方面均有显著优势。

Abstract

Accurate prediction of electric vehicle charging demand is crucial for alleviating pressure on the power grid. To address the issues of slow convergence and vulnerability to unreliable nodes in existing prediction methods when processing non-independently and identically distributed (non-IID) data

this paper proposes a Double-Layer Credible Federated Learning (DCFL) strategy for energy demand prediction. The proposed method employs heuristic association rules to automatically mine charging information without requiring additional data collection. It selects benign local updates based on weight loss variation to accelerate convergence and resist interference from unreliable nodes. Furthermore

a multi-channel attention mechanism is introduced to design the loss function and the weighted aggregation scheme of federated learning. Experimental results demonstrate that

compared with traditional federated learning methods

the proposed method reduces training time by 71% and increases convergence speed by 17.6%

showing significant advantages in both prediction accuracy and convergence efficiency.

关键词

Keywords

references

Hinov N , Vacheva G , Giles B . Mathematical Model for Determination of Energy Cycles in EVs [C ] . 2020 24th International Conference Electronics , 2020 : 1 - 5 .

Li G , Gorges D . Ecological Adaptive Cruise Control and Energy Management Strategy for Hybrid Electric Vehicles Based on Heuristic Dynamic Programming [J ] . IEEE Transactions on Intelligent Transportation Systems , 2018 , PP:1- 10 .

Elmi S , Tan K L . DeepFEC: Energy Consumption Prediction under Real-World Driving Conditions for Smart Cities [C ] . The Web Conference 2021 . 2021 : 1880 --1890.

Majidpour M , Qiu C , Chu P , et al . Fast Prediction for Sparse Time Series: Demand Forecast of EV Charging Stations for Cell Phone Applications [J ] . IEEE Transactions on Industrial Informatics , 2015 , 11 ( 1 ): 242 - 250 .

Wang Y , Bennani I L , Liu X , et al . Electricity Consumer Characteristics Identification: A Federated Learning Approach [J ] . IEEE Transactions on Smart Grid , 2021 , 12 ( 4 ): 3637 - 3647

Fuli Qiao , Shan Lin . Data-driven prediction of fine-grained EV charging behaviors in public charging stations: Poster [C ] . Proceedings of the Twelfth ACM International Conference on Future Energy Systems (e-Energy '21 ). 2021 , 276 – 277 .

Zhong D , Sun P , Boukerche A . Empirical Study and Analysis of the Impact of Traffic Flow Control at Road Intersections on Vehicle Energy Consumption [C ] . Proceedings of the 18th ACM Symposium on Mobility Management and Wireless Access . 2020 : 21 – 28 .

Chis A , Lunde N J , Koivunen V . Reinforcement Learning-Based Plug-in Electric Vehicle Charging with Forecasted Price [J ] . IEEE Transactions on Vehicular Technology , 2016 , 66 ( 99 ): 1 - 1 .

Banda P , Bhuiyan M A , Hasan K N , et al . Timeseries Based Deep Hybrid Transfer Learning Frameworks: A Case Study of Electric Vehicle Energy Prediction [C ] . ICCS2021 - 21st International Conference , 2021 : 259 - 272 .

Afiya Ayman , Amutheezan Sivagnanam , Michael Wilbur , Philip Pugliese , Abhishek Dubey , and Aron Laszka . Data-Driven Prediction and Optimization of Energy Use for Transit FleEVs of Electric and ICE Vehicles [J ] . ACM Transactions on Internet Technology , 2022 , 22 ( 01 ): 1 - 29 .

Naoya Yoshida , Takayuki Nishio , Masahiro Morikura , Koji Yamamoto and Ryo Yonetani . Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data [C ] . 2020 IEEE International Conference on Communications (ICC) , 2020 : 1 - 7 .

Grubwinkler S , Lienkamp M . Energy Prediction for EVs Using Support Vector Regression Methods [J ] . Springer International Publishing , 2015 ( 323 ): 769 --780.

Zhou J , Xiang Y , Zhang X , et al . Optimal self-consumption scheduling of highway electric vehicle charging station based on multi-agent deep reinforcement learning [J ] . Renewable Energy , 2025 , 238121982 - 121982 .

Yadav K , Singh M . A novel energy management of public charging stations using attention-based deep learning model [J ] . Electric Power Systems Research , 2025 , 238111090 - 111090 .

McMahan B , Moore E , Ramage D , et al . Communication-efficient learning of deep networks from decentralized data [C ] . Artificial intelligence and statistics. PMLR , 2017 : 1273 - 1282 .

Chen N , Li M , Wang M , et al . Compensation of Charging Station Overload via On-road Mobile Energy Storage Scheduling [C ] . 2019 : 1 - 6 .

He C , Annavaram M , Avestimehr S . Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge [J ] . 2020 , 33 : 14068 - 14080 .

Wang X H , Zheng X K , Liang X . Charging Station Recommendation for Electric Vehicle Based on Federated Learning [J ] . Journal of Physics: Conference Series , 2021 , 1792 : 12055 .

Saputra Y M , Hoang D T , Nguyen D N , et al . Energy Demand Prediction with Federated Learning for Electric Vehicle Networks [C ] . IEEE Global Communications Conference (2019). 2019 : 1 - 6 .

Tun Y L , Thar K , Thwal C M , and Hong C S . Federated learning-based energy demand prediction with clustered aggregation [C ] . IEEE International Conference on Big Data and Smart Computing(Big Comp )( 2021 ). 2021 : 164 – 167 .

Christopher Briggs , Zhong Fan , and Peter Andras . Federated Learning for Short-term Residential Energy Demand Forecasting [C ] . 2021 : 2105 .

Li T ， Sahu A K ， Zaheer M ， et al . Federated Optimization in Heterogeneous Networks [C ] . Proceedings of Machine Learning and Systems ， 2020 ， 2 : 429 - 450 .

Karimireddy S P ， Kale S ， Mohri M ， et al . SCAFFOLD: Stochastic Controlled Averaging for Federated Learning [C ] . International Conference on Machine Learning. PMLR ， 2020 : 5132 - 5143 .

Sattler F ， Müller K R ， Samek W . Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints [J ] . IEEE Transactions on Neural Networks and Learning Systems ， 2020 ， 32 ( 8 ): 3710 - 3722 .

Zhu Y , Luo H , Chen R , et al . DenseNetX and GRU for the Sussex-Huawei Locomotion-transportation Recognition Challenge [C ] . UbiComp/ISWC 20 , 2020 : 373 - 377 .

Mills , Jed and Hu , Jia and Min , Geyong . Multi-Task Federated Learning for Personalized Deep Neural Networks in Edge Computing [J ] . IEEE Transactions on Parallel and Distributed Systems , 2022 , 33 ( 3 ): 630 - 641 .

Bonawitz Keith , Ivanov Vladimir , Kreuter Ben , et al . Practical Secure Aggregation for Privacy-Preserving Machine Learning [J ] . Association for Computing Machinery . 2017 , 17 : 1175 - 1191 .

Luo Y , Liu X , Xiu J . Energy-efficient Clustering to Address Data Heterogeneity in Federated Learning [C ] . IEEE International Conference on Communications (2021). 2021 : 1 - 6 .

Li A , Zhang L , Tan J , Qin Y , Wang J , et al . Sample-lETel Data Selection for Federated Learning [C ] . IEEE Conference on Computer Communications (2021). 2021 : 1 - 10 .

Jonatan Reyes , Lisa DiJorio , Low Kam , Marta Kersten . Precision-Weighted Federated Learning [C ] . 2021 : 2107 .09627.

Beibei Li , Yuqing Guo , Qingyun Du , Ziqing Zhu , Xiaohui Li , Rongxing Lu . P3: Privacy-Preserving Prediction of Real-time Energy Demands in EV Charging Networks [J ] . IEEE Transactions on Industrial Informatics , 2023 , 19 ( 3 ): 029 - 3038 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于迁移自编码器与多模态数据的智能手机隐式身份认证

一种基于雾计算思想的私密性云存储方案

大模型数据安全与隐私保护研究综述

基于UWB融合定位的室内自动泊车系统设计与国产化验证

任务驱动的立体无线Mesh网络多维资源智能协同算法研究