Load Forecasting Method for Electric Vehicle Charging Based on FCM Clustering and BiLSTM Network

LIN Xiang; XU Ruilin

doi:10.13882/j.cnki.ncdqh.2024.05.001

RURAL ELECTRIFICATION > 2024 > (5): 1-5. > DOI: 10.13882/j.cnki.ncdqh.2024.05.001 CSTR: 32400.14.ncdqh.2024.05.001

LIN Xiang, XU Ruilin. Load Forecasting Method for Electric Vehicle Charging Based on FCM Clustering and BiLSTM Network[J]. RURAL ELECTRIFICATION, 2024, (5): 1-5. DOI: 10.13882/j.cnki.ncdqh.2024.05.001

Citation:

PDF (1612 KB)

Load Forecasting Method for Electric Vehicle Charging Based on FCM Clustering and BiLSTM Network

LIN Xiang^1, ,,
XU Ruilin²

1.
Nanjing Sanxin Power Supply Service Co., Ltd. Pukou Branch, Jiangsu Nanjing 211899, China
2.
Suzhou Research Institute of Southeast University, Jiangsu Suzhou 215123, China

More Information

Received Date: January 03, 2024
Revised Date: March 04, 2024
Available Online: May 15, 2024

Graphical Abstract

Abstract

Abstract

To address the charging gap issue for electric vehicles in both urban and rural areas of Pukou, and to enhance the intelligence of charging services for an improved user experience, this paper proposes a method for predicting electric vehicle charging loads based on FCM clustering and BiLSTM. Firstly, to identify the internal structure and patterns of charging loads, FCM clustering is applied to the daily charging load dataset, dividing the data into different clusters, with each cluster representing samples with similar charging load characteristics. Subsequently, tailored BiLSTM models are constructed for training and prediction based on the distinct sample features within each cluster. Model parameters are adjusted to enhance prediction accuracy. Through comparative experiments, validating the effectiveness and practicality of the approach.
- electric vehicle,
- FCM,
- BiLSTM,
- load prediction

FullText(HTML)

References (12)

References

[1]	潘越,普美娜,范嘉豪. 基于PSO-LSSVM的新能源汽车充电负荷预测方法研究[J]. 电力与能源,2023,44(4):379−384.
[2]	杨延西,刘丁. 基于小波变换和最小二乘支持向量机的短期电力负荷预测[J]. 电网技术,2005(13):60−64. doi: 10.3321/j.issn:1000-3673.2005.13.012
[3]	董晓红,孔华志,丁飞,等. 考虑电池老化的电动汽车中长期充电负荷预测方法[J/OL]. 电力系统自动化,1-15[2023-12-28]. http://kns.cnki.net/kcms/detail/32.1180.TP.20231009.0751.004.html.
[4]	石立国,李延真,刘继彦,等. 电动汽车充电站超短期充电负荷预测的改进GRU方法[J]. 供用电,2023,40(6):42−47.
[5]	MOHAMMED N S, MOHAMMED H E. Accurate photovoltaic power prediction models based on deep convolutional neural networks and gated recurrent units[J]. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2022, 44(3):6303-6320.
[6]	陈忠华,朱军,王育飞,等. 基于一致性K均值聚类的电动汽车充电负荷建模方法[J]. 现代电力,2022,39(3):338−348.
[7]	周成龙,陈玉明,朱益冬. 粒K均值聚类算法[J]. 计算机工程与应用,2023,59(13):317−324.
[8]	张慧哲,王坚. 基于初始聚类中心选取的改进FCM聚类算法[J]. 计算机科学,2009,36(6):206−209. doi: 10.3969/j.issn.1002-137X.2009.06.055
[9]	关鹏飞,李宝安,吕学强,等. 注意力增强的双向LSTM情感分析[J]. 中文信息学报,2019,33(2):105−111.
[10]	宋军英,何聪,李欣然,等. 基于特征指标降维及熵权法的日负荷曲线聚类方法[J]. 电力系统自动化,2019,43(20):65−72.
[11]	程冬梅. LSTM研究现状综述[J]. 信息系统工程,2022(1):149−152.
[12]	CHAI, Tianfeng, and ROLANG R. Draxler. Root mean square error (RMSE) or mean absolute error (MAE)?–Arguments against avoiding RMSE in the literature. Geoscientific model development, 2014(7): 1247-1250.

[1]	ZHANG Qian, JIANG Yongmei, YU Panfeng. Research on Power Market Strategy Based on Industrial Cluster Load DR Potential Assessment[J]. RURAL ELECTRIFICATION, 2025, (2): 61-66. DOI: 10.13882/j.cnki.ncdqh.2409A006
[2]	CHENG Xiye, MA Xuheng, YANG Fan, ZHAO Yun. Ultra-short-term Power Load Forecasting Based on Multi-head Attention Mechanism and BiLSTM[J]. RURAL ELECTRIFICATION, 2024, (12): 41-45. DOI: 10.13882/j.cnki.ncdqh.2410A032
[3]	Ma Tianyi, Wu Yue. Distribution Network Load Forecasting Based on Grey Correlation Analysis and BP Neural Network[J]. RURAL ELECTRIFICATION, 2021, (12): 17-20. DOI: 10.13882/j.cnki.ncdqh.2021.12.004
[4]	Wu Zhijia, Luo Feng, Liu Yutuo, Li Yanbin. Forecast of Daily Power Generation Load in Multi-hydropower Area[J]. RURAL ELECTRIFICATION, 2021, (7): 64-65. DOI: 10.13882/j.cnki.ncdqh.2021.07.020
[5]	Han Jicheng, Li Yunfei, Chen Shiming, Zhou Yonghan, Yan Yi. Intellectual Load Predication Method Based on Composite Valley Management and Meteorology Management[J]. RURAL ELECTRIFICATION, 2021, (4): 42-43, 73. DOI: 10.13882/j.cnki.ncdqh.2021.04.014
[6]	Zhan Yang. Residential Power Load Forecasting based on Deep Time Convolution Network[J]. RURAL ELECTRIFICATION, 2021, (3): 23-24. DOI: 10.13882/j.cnki.ncdqh.2021.03.007
[7]	He Moling, Chen Ludong. Research and Analysis of Latent Load Prediction in Rural Village Power Network[J]. RURAL ELECTRIFICATION, 2019, (5): 5-9. DOI: 10.13882/j.cnki.ncdqh.2019.05.001
[8]	Xia Wenfang. Electric vehicle load predication and analysis of influence of electric vehicle load on urban power network[J]. RURAL ELECTRIFICATION, 2018, (11): 9-11. DOI: 10.13882/j.cnki.ncdqh.2018.11.002
[9]	Liu Bei. Application of load predication method based on grid in power distribution network[J]. RURAL ELECTRIFICATION, 2018, (11): 5-8. DOI: 10.13882/j.cnki.ncdqh.2018.11.001
[10]	Sun Haimeng, Sun Junru. Electric Power Load Predictor Based on Ant Colony Algorithm[J]. RURAL ELECTRIFICATION, 2018, (10): 9-10. DOI: 10.13882/j.cnki.ncdqh.2018.10.002

Cited By

Cited by

Periodical cited type(2)

1.	王娟，陈明，支刚，王文娟. 电动汽车充电负荷的蒙特卡洛预测方法. 云南电力技术. 2024(04): 10-14 .
2.	耿鹏，杨豪杰，师宗夏，柳艳. 基于时空图卷积网络的电动汽车充电需求预测. 交通工程. 2024(11): 37-45 .

Other cited types(0)

Get Citation

PDF

XML

Article views (22) PDF downloads (4) Cited by(2)

Turn off MathJax

Article Contents

Abstract

References

Load Forecasting Method for Electric Vehicle Charging Based on FCM Clustering and BiLSTM Network