当前位置>主页 > 期刊在线 > 信息化应用 >

信息化应用22年13期

基于混合分类的插电式新能源汽车行为需求预测
唐菲¹,郑振²
(1. 武汉船舶职业技术学院,湖北 武汉 430050;2. 武汉软件工程职业学院,湖北 武汉 430205)

摘  要:针对新能源汽车行为和充电需求的不确定性问题,提出了结合无监督聚类和有监督深度学习分类器的混合分类方法,以发掘汽车行驶数据中隐藏的行驶模式;提出基于深度长短期记忆网络的需求预测方法,以预测新能源汽车的需求。基于预测结果,提出了基于成本优化的投标模型,以降低新能源汽车充电成本。结合真实的数据集,使用实验评估所提出方法的有效性。实验结果表明,提出的方法在预测新能源汽车需求方面具有出色的表现。


关键词:深度学习;插电式新能源汽车;分类和预测



DOI:10.19850/j.cnki.2096-4706.2022.013.044


中图分类号:TP18                                        文献标识码:A                                      文章编号:2096-4706(2022)13-0182-03


Prediction of Behavior and Demand for Plug-in New Energy Vehicles Based on Hybrid Classification

TANG Fei 1, ZHENG Zhen2

(1.Wuhan Institute of Shipbuilding Technology, Wuhan 430050, China; 2.Wuhan Vocational College of Software and Engineering, Wuhan 430205, China)

Abstract: Aiming at the uncertainty problem of new energy vehicle behavior and charging demand, a hybrid classification method combined unsupervised clustering with supervised deep learning classifier is proposed to discover hidden driving patterns in vehicle driving data. Then a demand prediction method based on deep long-term and short-term memory network is proposed to predict the demand of new energy vehicles. Based on the prediction results, a bidding model based on cost optimization is proposed to reduce the charging cost of new energy vehicles. Combined with real datasets, experiments are used to evaluate the effectiveness of the proposed method. The experimental results show that the proposed method has excellent performance in predicting the demand of new energy vehicles.

Keywords: deep learning; plug-in new energy vehicle; classification and prediction


参考文献:

[1] YAN L,CHEN X,ZHOU J,e t al . D e e p reinforcement learning for continuous electric vehicles charging control with dynamic user behaviors [J].IEEE Transactions on Smart Grid,2021,12(6):5124-5134.

[2] 隗寒冰,贺少川 . 基于深度强化学习的插电式柴电混合动力汽车多目标优化控制策略 [J]. 重庆交通大学学报(自然科学版),2021,40(1):44-52.

[3] OLANLARI F G,GOUGHERI S S,NIKOOFARD A. A Multi-Objective Generation Expansion Planning with Modeling Load Demand Uncertainty by a Deep LearningBased Approach [C]//2020 10th Smart Grid Conference (SGC). IEEE,2020:1-6.

[4] 姚颖蓓,陆建忠,傅业盛,等 . 华东地区电动汽车发展趋势及用电需求预测 [J]. 电力系统保护与控制,2021,49(4):141-145.

[5] NALMPANTIS C,VRAKAS D. On time series representations for multi-label NILM [J].Neural Computing and Applications,2020,32(23):17275-17290.

[6] 张蕾,章毅 . 大数据分析的无限深度神经网络方法 [J]. 计算机研究与发展,2016,53(1):68-79.


作者简介:唐菲(1985—)女,汉族,湖北十堰人,工程师,硕士,研究方向:汽车设计;郑振(1986—),男,汉族,湖北十堰人,讲师,硕士,研究方向:新能源。