基于MC-BiLSTM-BDA预测的混合需求响应电动汽车充电策略

钟婷; 王爱娟; 丁雪

doi:doi:10.19912/j.0254-0096.tynxb.2024-1472

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

基于MC-BiLSTM-BDA预测的混合需求响应电动汽车充电策略

更新时间：2026-02-06

- 基于MC-BiLSTM-BDA预测的混合需求响应电动汽车充电策略
- Vol. 47, Issue 1, Pages: 747-755(2026)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：doi:10.19912/j.0254-0096.tynxb.2024-1472
  CLC： TM73
- Online First：05 February 2026，
  
  Published：05 February 2026
- 稿件说明：
移动端阅览
钟婷, 王爱娟, 丁雪. 基于MC-BiLSTM-BDA预测的混合需求响应电动汽车充电策略[J]. 2026, 47(1): 747-755.
DOI：

钟婷, 王爱娟, 丁雪. 基于MC-BiLSTM-BDA预测的混合需求响应电动汽车充电策略[J]. 2026, 47(1): 747-755. DOI： doi:10.19912/j.0254-0096.tynxb.2024-1472.

摘要

提出一种基于MC-BiLSTM-BDA预测的混合需求响应有序充电优化策略。首先

结合马尔科夫链（MC）、双向长短期记忆网络（BiLSTM）和双向注意力机制（BDA）

构建MC-BDA-BiLSTM充电负荷预测模型。其次

依据K均值模糊聚类算法划分的峰、平、谷充电时段

提出基于价格-激励混合的需求响应（PrIncHDR）策略

该策略是在价格需求响应的基础上引入价格补偿激励机制以避免峰谷倒置和促进供需平衡。基于此策略

构建包含可再生能源利用率、用户收益及光伏充电站（PVCS）的电动汽车有序充电优化模型

并采用NSGA-Ⅱ算法进行求解。实验结果表明

MC-BDA-BiLSTM模型的负荷预测精度优于传统BiLSTM模型

决定系数提高11.93%

均方根误差和平均绝对误差分别降低35.06%和37.41%。实验证明：所提的基于MC-BiLSTM-BDA预测的混合需求响应有序充电优化策略可有效降低峰谷差

增加可再生能源消纳

可实现用户和PVCS的双赢。

Abstract

A hybrid demand response orderly charging optimization strategy based on MC-BiLSTM-BDA prediction is proposed. Firstly

a charging load prediction model

named MC-BDA-BiLSTM

is constructed by integrating Markov chains （MC）

Bi-directional long short-term memory （BiLSTM） network

and Bi-directional Attention （BDA）. Secondly

according to the peak

flat

and valley charging periods classified by the K-means fuzzy clustering algorithm

a price-incentive hybrid demand response （PrIncHDR） strategy is presented

which introduces price compensation incentive mechanism on the basis of price based demand response to avoid peak-valley inversion and promote supply and demand balance. Based on this strategy

an EV orderly charging optimization model is constructes

which includes renewable energy utilization rate

user benefits and photovoltaic charging station （PVCS） benefits

and is solved by the NSGA-II algorithm. The experimental results show that compared with BiLSTM model

the MC-BiLSTM-BDA model increases the determination coefficient of the charging load prediction by 11.93%

and reduces the root-mean-square error by 35.06% and the mean absolute error by 37.41%

respectively. The proposed charging optimization strategy based on price-incentive hybrid demand response effectively reduces peak-valley differences

enhances renewable energy consumption

and achieves a win-win for users and photovoltaic charging stations.

关键词

Keywords

references

BARMAN P, DUTTA L, BORDOLOI S, et al.Renewable energy integration with electric vehicle technology: a review of the existing smart charging approaches[J]. Renewable and sustainable energy reviews, 2023, 183: 113518.

PIELTAIN FERNANDEZ L, GOMEZ SAN ROMAN T, COSSENT R, et al. Assessment of the impact of plug-in electric vehicles on distribution networks[J]. IEEE transactions on power systems, 2011, 26(1): 206-213.

ZHANG Z Y, LYU L J.Status and development of research on orderly charging and discharging of electric vehicles[J]. Electronics, 2023, 12(9): 2041.

ZHANG Z Y, LYU L J, WANG X H.Researh on dynamic time-sharing tariff orderly charging strategy based on NSGA2 in PV-storage-charging stations[J]. Electric power systems research, 2023, 225: 109784.

YANG X D, XU C B, ZHANG Y B, et al.Real-time coordinated scheduling for ADNs with soft open points and charging stations[J]. IEEE transactions on power systems, 2021, 36(6): 5486-5499.

REN L N, YUAN M M, JIAO X H.Electric vehicle charging and discharging scheduling strategy based on dynamic electricity price[J]. Engineering applications of artificial intelligence, 2023, 123: 106320.

WANG W, YANG Y, ZHONG Y L, et al.Bi-level optimal scheduling model of virtual energy storage based on electric vehicles under time-of-use electricity price[C]//2023 5th International Conference on Power and Energy Technology (ICPET), Tianjin, China, 2023.

TIAN J, LYU Y, ZHAO Q, et al.Electric vehicle charging load prediction considering the orderly charging[J]. Energy reports, 2022, 8: 124-134.

LI S W, KONG X Y, YUE L, et al.Short-term electrical load forecasting using hybrid model of manta ray foraging optimization and support vector regression[J]. Journal of cleaner production, 2023, 388: 135856.

LIU Y, LIU W, GAO S, et al.Fast charging demand forecasting based on the intelligent sensing system of dynamic vehicle under EVs-traffic-distribution coupling[J]. Energy reports, 2022, 8: 1218-1226.

YAN Q Y, LIN H Y, LI J M, et al.Many-objective charging optimization for electric vehicles considering demand response and multi-uncertainties based on Markov chain and information gap decision theory[J]. Sustainable Cities and Society, 2022, 78: 103652.

WANG S Y, ZHUGE C X, SHAO C F, et al.Short-term electric vehicle charging demand prediction: a deep learning approach[J]. Applied energy, 2023, 340: 121032.

张程, 林谷青, 匡宇. 基于MEEMD-QUATRE-BILSTM的短期光伏出力区间预测[J]. 太阳能学报, 2023, 44(11): 40-54.ZHANG C, LIN G Q, KUANG Y. Short-term PV output interval prediction based on MEEMD-QUATRE-BILSTM[J]. Acta energiae solaris sinica, 2023, 44(11): 40-54.

焦丕华, 蔡旭, 王乐乐, 等. 考虑数据分解和进化捕食策略的BiLSTM短期光伏发电功率预测[J]. 太阳能学报, 2024, 45(2): 435-442.JIAO P H, CAI X, WANG L L, et al. BiLSTM short-term photovoltaic power prediction considering data decomposition and evolutionary predation strategies[J]. Acta energiae solaris sinica, 2024, 45(2): 435-442.

LIU J Y, WANG L T, HU W, et al.Spatial-temporal feature with dual-attention mechanism for encrypted malicious traffic detection[J]. Security and communication networks, 2023, 2023: 7117863.

LAI S Y, QIU J, TAO Y C, et al.Pricing for electric vehicle charging stations based on the responsiveness of demand[J]. IEEE transactions on smart grid, 2023, 14(1): 530-544.

董海鹰, 贠韫韵, 汪宁渤, 等. 基于双重电价的电动汽车充放电两阶段优化调度策略[J]. 太阳能学报, 2021, 42(4): 115-124.DONG H Y, YUN Y Y, WANG N B, et al. Two-stage dispatch optimization strategy for charging and discharging of electric vehicles based on double electricity price[J]. Acta energiae solaris sinica, 2021, 42(4): 115-124.

CHEN Q, WANG W Q, WANG H Y, et al.Information gap-based coordination scheme for active distribution network considering charging/discharging optimization for electric vehicles and demand response[J]. International journal of electrical power & energy systems, 2023, 145: 108652.

赵玉, 徐天奇, 李琰, 等. 基于分时电价的电动汽车调度策略研究[J]. 电力系统保护与控制, 2020, 48(11): 92-101.ZHAO Y, XU T Q, LI Y, et al. Research on electric vehicle scheduling strategy based on time-shared electricity price[J]. Power system protection and control, 2020, 48(11): 92-101.

ZHANG L, SUN C L, CAI G W, et al.Charging and discharging optimization strategy for electric vehicles considering elasticity demand response[J]. eTransportation, 2023, 18: 100262.

PANDEY V C, GUPTA N, NIAZI K R, et al.An adaptive demand response framework using price elasticity model in distribution networks[J]. Electric power systems research, 2022, 202: 107597.

王均, 黄琦. 基于优惠券激励的需求响应双层优化机制[J]. 电力系统保护与控制, 2019, 47(1): 108-114.WANG J, HUANG Q. Coupon incentives based customers voluntary demand response program via bilevel optimization mechanism[J]. Power system protection and control, 2019, 47(1): 108-114.

魏震波, 张海涛, 魏平桉, 等. 考虑动态激励型需求响应的微电网两阶段优化调度[J]. 电力系统保护与控制, 2021, 49(19): 1- 10.WEI Z B, ZHANG H T, WEI P A, et al. Two-stage optimal dispatching for microgrid considering dynamic incentive-based demand response[J]. Power system protection and control, 2021, 49(19): 1-10

XIONG H, MAMON R. A higher-order Markov chain-modulated model for electricity spot-price dynamics[J]. Applied energy, 2019, 233/234: 495-515.

GRAVES A, SCHMIDHUBER J.Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural networks, 2005, 18(5/6): 602-610.

SEO M, KEMBHAVI A, FARHADI A, et al. Bidirectional attention flow for machine comprehension[J]. arxiv preprint arxiv:1611.01603, 2016.

LEDMAOUI Y, EL MAGHRAOUI A, EL AROUSSI M, et al.Forecasting solar energy production: a comparative study of machine learning algorithms[J]. Energy reports, 2023, 10: 1004-1012.

ZHONG S W, CHE Y B, ZHANG S Y.Electric vehicle charging load optimization strategy based on dynamic time-of-use tariff[J]. Energy engineering, 2024, 121(3): 603-618.

NASIRI N, ZEYNALI S, RAVADANEGH S N, et al.A convex multi-objective distributionally robust optimization for embedded electricity and natural gas distribution networks under smart electric vehicle fleets[J]. Journal of cleaner production, 2024, 434: 139843.

廖鑫, 李婧, 徐佳, 等. 基于MDP及激励需求响应的电动汽车有序充电控制[J]. 电力科学与技术学报, 2021, 36(5): 79-86.LIAO X, LI J, XU J, et al. Research on coordinated charging control for electric vehicles based on MDP and incentive demand response[J]. Journal of electric power science and technology, 2021, 36(5): 79-86.

SRINIVAS N, DEB K.Muiltiobjective optimization using nondominated sorting in genetic algorithms[J]. Evolutionary computation, 1994, 2(3): 221-248.

BAEK K, LEE E, KIM J.A dataset for multi-faceted analysis of electric vehicle charging transactions[J]. Scientific data, 2024, 11: 262.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

一种基于PatchTST模型的燃料电池老化趋势预测方法

基于SSA-VMD预处理的TCN-Informer短期风速多步预测混合模型

考虑用户随机出行行为的大规模电动汽车集群调度策略

不确定因素下基于主从博弈的电动汽车参与综合能源系统优化调度

基于MFM-CG-DBN模型的高渗透率光伏微电网发电功率短期预测

Related Author

施永

胡芝龙

谢缔

汪亮亮

姚继刚

苏建徽

孔宪正

黄国勇

Related Institution

美国大自然保护协会

农业部农村可再生能源重点开放实验室

中原工学院

School of Electrical Engineering, Shenyang University of Technology

Research Center for Renewable Energy Generation Engineering of Ministry of Education, Hohai University

AI问答

⁰