基于高阶马尔可夫链的纯电重卡集群负荷预测

doi:10.11930/j.issn.1004-9649.202306066

中国电力 ›› 2024, Vol. 57 ›› Issue (5): 61-69.DOI: 10.11930/j.issn.1004-9649.202306066

• 新型电力系统源网荷储灵活资源运营及关键技术 • 上一篇下一篇

基于高阶马尔可夫链的纯电重卡集群负荷预测

刘航¹(), 申皓¹, 杨勇¹, 纪陵², 余洋³()

1. 国网邯郸供电公司，河北邯郸　056000
2. 国电南京自动化股份有限公司，江苏南京　210032
3. 新能源电力系统国家重点实验室（华北电力大学（保定）），河北保定　071003

收稿日期:2023-06-19 录用日期:2023-09-17 发布日期:2024-05-23 出版日期:2024-05-28
作者简介:刘航（1986—），男，高级工程师，从事电力系统运行与控制研究，E-mail：286471312@qq.com
余洋（1982—），男，通信作者，博士，教授，博士生导师，从事电力储能技术、柔性负荷建模与调度研究，E-mail：yangyu@ncepu.edu.cn
基金资助:
国家自然科学基金资助项目（52077078）; 国网河北省电力有限公司科技项目（支撑纯电重卡集群与电网友好互动的聚合调控关键技术研究及示范应用，kj2022-050）。

Load Forecast of Electric Trucks Aggregation Based on Higher-order Markov Chains

Hang LIU¹(), Hao SHEN¹, Yong YANG¹, Ling JI², Yang YU³()

1. State Grid Handan Electric Power Supply Company, Handan 056000, China
2. Guodian Nanjing Automation Co., Ltd., Nanjing 210032, China
3. State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources (North China Electric Power University), Baoding 071003, China

Received:2023-06-19 Accepted:2023-09-17 Online:2024-05-23 Published:2024-05-28
Supported by:
This work is supported by National Natural Science Foundation of China (No.52077078), Science and Technology Project of State Grid Hebei Electric Power Co., Ltd. (Research and Demonstration Application of Convergence Regulation Key Technology to Support Friendly Interaction between Pure Electric Heavy Truck Cluster and Grid, No.kj2022-050)

摘要/Abstract

摘要：

相比于普通电动汽车，纯电重卡具有更高的充电功率、更大的电池容量和更可观的调度潜力，同时受货物重量、物流特性及行驶路径等诸多因素影响，其充电负荷呈现更大的随机性，建立准确的纯电重卡集群负荷预测模型有利于掌握其充电规律，降低对电网的冲击。为此，提出了考虑物流特性基于高阶马尔科夫链的纯电重卡集群负荷预测方法。首先，在考虑软时间窗约束实现纯电重卡路径规划的基础上，通过分析纯电重卡行驶特性预测其开始充电时间，以获取各时刻纯电重卡充电数量；其次，对纯电重卡的荷电状态区间进行模糊双层离散化分区处理，将每个大区间进一步细分为n个小区间，提高预测精度；然后，在求取纯电重卡荷电状态多步转移概率基础上，采用高阶马尔可夫链建立集群负荷预测模型，实现更为精确的负荷预测；最后，采用某物流园区实际纯电重卡数据进行仿真验证，结果表明，所构建的负荷预测模型较准确地预测了纯电重卡集群功率，同时减小了普通马尔科夫链方法的预测误差。

关键词: 纯电重卡, 高阶马尔可夫链, 负荷预测, 双层离散化, 物流订单约束

Abstract:

Compared with ordinary electric vehicles, electric trucks have higher charging power, larger battery capacity and more considerable dispatching potential, while their charging load presents greater randomness due to many factors such as cargo weight, logistics characteristics and driving path. To this end, this paper proposes a electric trucks aggregation load prediction method based on higher-order Markov chain considering logistics characteristics. Firstly, on the basis of considering the soft time window constraint to realize the path planning of the electric trucks, the charging time of the electric trucks is predicted by analyzing their driving characteristics to obtain the charging quantity of the electric trucks at each moment. Secondly, the charge state interval of the electric trucks is partitioned with fuzzy two-level discretization, and each large interval is further subdivided into n small intervals so as to improve the prediction accuracy. And then, after obtaining the charge state multi-step transfer probability of the electric trucks, a aggregation load prediction model is established by using high-order Markov chain to achieve more accurate load prediction. Finally, the actual electric truck data of a logistics park is used for simulation verification, and the results show that the proposed load prediction model accurately predicts the aggregation power of electric trucks and reduces the prediction error of the ordinary Markov chain method.

Key words: electric truck, higher-order Markov chains, load forecasting, two-level discretization, logistics order constraints

刘航, 申皓, 杨勇, 纪陵, 余洋. 基于高阶马尔可夫链的纯电重卡集群负荷预测[J]. 中国电力, 2024, 57(5): 61-69.

Hang LIU, Hao SHEN, Yong YANG, Ling JI, Yang YU. Load Forecast of Electric Trucks Aggregation Based on Higher-order Markov Chains[J]. Electric Power, 2024, 57(5): 61-69.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202306066

https://www.electricpower.com.cn/CN/Y2024/V57/I5/61

图/表 11

图 1 ETA配送网络

Fig.1 ETA distribution network

表 1 道路拓扑图涉及的自适应系数取值

Table 1 The adaptive coefficients involved in the road topology map

道路等级	c₁	c₂	c₃	c₄	p₁	p₂	p₃	p₄
快速	0.9526	1	3	3	0.0405	500	3	3
普通	0.9526	1	2	2	0.0405	500	2	2

图 2 动态转移示意

Fig.2 Dynamic transfer schematic

图 3 SOC双层离散化

Fig.3 SOC two-level discretization

表 2 参数设置

Table 2 Parameter Setting

参数名称		参数值
ET电池容量/(kW·h)		300
计划充放电功率/kW		200
充放电效率/%		94

图 4 配送网络拓扑

Fig.4 Distribution network topology

图 5 ETA充电开始时间分布

Fig.5 ETA charging start time distribution

图 6 ETA充电数量预测及比较

Fig.6 ETA charging quantity forecast and comparison

图 7 有后续订单的ETA

Fig.7 ETA with follow-up orders

图 8 ETA充电负荷

Fig.8 ETA charging load

图 9 不同规模ETA充电负荷比较

Fig.9 Comparison of different sizes of ETA charging loads

参考文献 22

1	彭云, 李相达, 王文渊, 等. 绿色集装箱港口节能减排策略综述[J]. 交通运输工程学报, 2022, 22 (4): 28- 46.
	PENG Yun, LI Xiangda, WANG Wenyuan, et al. Review on energy saving and emission reduction strategies of green container ports[J]. Journal of Traffic and Transportation Engineering, 2022, 22 (4): 28- 46.
2	DUAN X Y, HU Z C, SONG Y H. Bidding strategies in energy and reserve markets for an aggregator of multiple EV fast charging stations with battery storage[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22 (1): 471- 482. DOI
3	LOPEZ K L, GAGNE C, GARDNER M A. Demand-side management using deep learning for smart charging of electric vehicles[J]. IEEE Transactions on Smart Grid, 2019, 10 (3): 2683- 2691. DOI
4	文家燕, 闻海潮, 程洋, 等. 基于GWO-NSGA-Ⅱ混合算法的露天矿低碳运输调度[J]. 工矿自动化, 2023, 49 (2): 94- 101.
	WEN Jiayan, WEN Haichao, CHENG Yang, et al. Low-carbon transportation scheduling of open-pit mine based on GWO-NSGA-Ⅱ hybrid algorithm[J]. Journal of Mine Automation, 2023, 49 (2): 94- 101.
5	陈蓉珺, 何永秀, 陈奋开, 等. 基于系统动力学和蒙特卡洛模拟的电动汽车日负荷远期预测[J]. 中国电力, 2018, 51 (9): 126- 134.
	CHEN Rongjun, HE Yongxiu, CHEN Fenkai, et al. Long-term daily load forecast of electric vehicle based on system dynamics and Monte Carlo simulation[J]. Electric Power, 2018, 51 (9): 126- 134.
6	余军伟, 孙云莲, 张笑迪. 考虑发展不均衡的电动汽车充电负荷预测[J]. 电测与仪表, 2019, 56 (5): 43- 50.
	YU Junwei, SUN Yunlian, ZHANG Xiaodi. Charging load forecasting considering the unbalanced development of EV[J]. Electrical Measurement & Instrumentation, 2019, 56 (5): 43- 50.
7	赵书强, 周靖仁, 李志伟, 等. 基于出行链理论的电动汽车充电需求分析方法[J]. 电力自动化设备, 2017, 37 (8): 105- 112.
	ZHAO Shuqiang, ZHOU Jingren, LI Zhiwei, et al. EV charging demand analysis based on trip chain theory[J]. Electric Power Automation Equipment, 2017, 37 (8): 105- 112.
8	锁军, 李龙, 贺瀚青, 等. 考虑交通路况的电动汽车充电负荷预测[J]. 电网与清洁能源, 2022, 38 (10): 141- 147.
	SUO Jun, LI Long, HE Hanqing, et al. Load forecasting of electric vehicle charging considering traffic conditions[J]. Power System and Clean Energy, 2022, 38 (10): 141- 147.
9	蒋怡静, 于艾清, 黄敏丽. 考虑用户满意度的电动汽车时空双尺度有序充电引导策略[J]. 中国电力, 2020, 53 (4): 122- 130.
	JIANG Yijing, YU Aiqing, HUANG Minli. Coordinated charging guiding strategy for electric vehicles in temporalspatial dimension considering user satisfaction degree[J]. Electric Power, 2020, 53 (4): 122- 130.
10	刘志强, 张谦, 朱熠, 等. 计及车-路-站-网融合的电动汽车充电负荷时空分布预测[J]. 电力系统自动化, 2022, 46 (12): 36- 45.
	LIU Zhiqiang, ZHANG Qian, ZHU Yi, et al. Spatial-temporal distribution prediction of charging loads for electric vehicles considering vehicle-road-station-grid integration[J]. Automation of Electric Power Systems, 2022, 46 (12): 36- 45.
11	PERTL M, CARDUCCI F, TABONE M, et al. An equivalent time-variant storage model to harness EV flexibility: forecast and aggregation[J]. IEEE Transactions on Industrial Informatics, 2019, 15 (4): 1899- 1910. DOI
12	JIN Y W, YU B, SEO M, et al. Optimal aggregation design for massive V2G participation in energy market[J]. IEEE Access, 2020, 8, 211794- 211808. DOI
13	DABBAGHJAMANESH M, MOEINI A, KAVOUSI-FARD A. Reinforcement learning-based load forecasting of electric vehicle charging station using Q-learning technique[J]. IEEE Transactions on Industrial Informatics, 2021, 17 (6): 4229- 4237. DOI
14	ZHANG X, CHAN K W, LI H, et al. Deep-learning-based probabilistic forecasting of electric vehicle charging load with a novel queuing model[J]. IEEE Trans Cybern, 2021, 51 (6): 3157- 3170. DOI
15	郄朝辉, 李威, 崔晓丹, 等. 基于分层马尔可夫的可修复稳定控制系统可靠性分析[J]. 中国电力, 2020, 53 (3): 101- 109.
	QIE Zhaohui, LI Wei, CUI Xiaodan, et al. Reliability analysis of repairable stability control system based on hierarchical Markov[J]. Electric Power, 2020, 53 (3): 101- 109.
16	ZHANG Q, CHEN X, LIAO S Y. Energy management control strategy for hybrid energy storage systems in electric vehicles[J]. International Journal of Electrochemical Science, 2022, 17 (1): 220121. DOI
17	KIANI S, SHESHYEKANI K, DAGDOUGUI H. An extended state space model for aggregation of large-scale EVs considering fast charging[J]. IEEE Transactions on Transportation Electrification, 2023, 9 (1): 1238- 1251. DOI
18	LIN X Y, ZHANG G J, WEI S S. Velocity prediction using Markov Chain combined with driving pattern recognition and applied to Dual-Motor Electric Vehicle energy consumption evaluation[J]. Applied Soft Computing, 2021, 101, 106998. DOI
19	ALJOHANI TAWFIQ M, AHMED E, OSAMA M. Real-Time metadata-driven routing optimization for electric vehicle energy consumption minimization using deep reinforcement learning and Markov chain model[J]. Electric Power Systems Research, 2021, 192, 106962. DOI
20	SHEN H R, WANG Z J, ZHOU X Y, et al. Electric vehicle velocity and energy consumption predictions using transformer and markov-chain Monte Carlo[J]. IEEE Transactions on Transportation Electrification, 2022, 8 (3): 3836- 3847. DOI
21	DING T, ZENG Z Y, BAI J W, et al. Optimal electric vehicle charging strategy with Markov decision process and reinforcement learning technique[J]. IEEE Transactions on Industry Applications, 2020, 56 (5): 5811- 5823. DOI
22	董锴, 蔡新雷, 崔艳林, 等. 基于马尔科夫链的电动汽车聚合建模及多模式调频控制策略[J]. 电网技术, 2022, 46 (2): 622- 634.
	DONG Kai, CAI Xinlei, CUI Yanlin, et al. Aggregation modeling based on Markov chain and multi-mode control strategies of aggregated electric vehicles for frequency regulation[J]. Power System Technology, 2022, 46 (2): 622- 634.

[1]	孙庆超, 李嘉靓, 江万里, 王若愚, 李植鹏, 胡亚荣, 朱健斌. 基于数据驱动时空网络的城市中长期电力负荷预测[J]. 中国电力, 2025, 58(3): 168-174.
[2]	王宇飞, 杜桐, 边伟国, 张钊, 刘慧婷, 杨丽君. 基于DTW K-medoids与VMD-多分支神经网络的多用户短期负荷预测[J]. 中国电力, 2024, 57(6): 121-130.
[3]	吴军英, 路欣, 刘宏, 张彬, 柴守亮, 刘蕴春, 王佳楠. 基于Spearman-GCN-GRU模型的超短期多区域电力负荷预测[J]. 中国电力, 2024, 57(6): 131-140.
[4]	陈中飞, 赵越, 蔡秋娜, 张乔榆, 王泽林, 戴晓娟, 陈雨果. 基于净负荷预测误差统计的电力系统爬坡能力充裕度评估[J]. 中国电力, 2024, 57(5): 50-60.
[5]	李丹, 贺帅, 颜伟, 胡越, 方泽仁, 梁云嫣. 考虑动态时间锚点和典型特征约束的年日均负荷曲线预测[J]. 中国电力, 2024, 57(11): 36-47.
[6]	周颖, 白雪峰, 王阳, 邱敏, 孙冲, 武亚杰, 李彬. 面向虚拟电厂运营的温度敏感负荷分析与演变趋势研判[J]. 中国电力, 2024, 57(1): 9-17.
[7]	唐旭辰, 潮铸, 段秦尉, 苏炳洪, 陈卉灿. 基于分层测量数据的高压变电站概率负荷预测方法[J]. 中国电力, 2023, 56(8): 143-150.
[8]	贾巍, 黄裕春. 基于小样本数据差分扩容的微电网负荷预测方法[J]. 中国电力, 2023, 56(8): 151-156,165.
[9]	彭生江, 杨德州, 孙传帅, 袁铁江, 刘永成. 基于氢负荷需求的氢能系统容量规划[J]. 中国电力, 2023, 56(7): 13-20,32.
[10]	杨喜行, 黄纯, 申亚涛, 胡念恩, 万子恒. 基于损失功率匹配的配电线路故障定位方法[J]. 中国电力, 2022, 55(8): 113-120.
[11]	李文武, 石强, 李丹, 胡群勇, 唐芸, 梅锦超. 基于VMD和PSO-SVR的短期电力负荷多阶段优化预测[J]. 中国电力, 2022, 55(8): 171-177.
[12]	徐宇颂, 邹山花, 卢先领. 基于特征选择和组合模型的短期电力负荷预测[J]. 中国电力, 2022, 55(7): 121-127.
[13]	李丹, 张远航, 李黄强, 童华敏, 王凌云. 基于精准气象数据的地区电网短期负荷智能预测系统设计[J]. 中国电力, 2022, 55(7): 128-133.
[14]	郑豪丰, 杨国华, 康文军, 刘志远, 刘世涛, 伍弘, 张鸿皓. 基于多负荷特征和TCN-GRU神经网络的负荷预测[J]. 中国电力, 2022, 55(11): 142-148.
[15]	樊江川, 于昊正, 刘慧婷, 杨丽君, 安佳坤. 基于多分支门控残差卷积神经网络的短期电力负荷预测[J]. 中国电力, 2022, 55(11): 155-162,174.

基于高阶马尔可夫链的纯电重卡集群负荷预测

Load Forecast of Electric Trucks Aggregation Based on Higher-order Markov Chains

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 22

相关文章 15

编辑推荐

Metrics

模态框（Modal）标题

基于高阶马尔可夫链的纯电重卡集群负荷预测

Load Forecast of Electric Trucks Aggregation Based on Higher-order Markov Chains

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 22

相关文章 15

编辑推荐

Metrics