基于拓扑门控的数据-机理混合驱动的主动配电网线损计算方法

doi:10.6040/j.issn.1672-3961.0.2024.329

摘要/Abstract

摘要： 传统的配电网线损计算方法不能同时兼顾物理模型的因果逻辑性与数据模型的计算精度优势,无法对不同主体接入下的主动配网线损进行准确计算。因此,本研究提出一种基于拓扑门控的数据-机理混合驱动的主动配电网线损计算方法。基于随机矩阵理论对不同主体接入后的主动配电网线损特征进行相关性分析,得到与线损率相关性最强的线损特征。然后,基于传统线损计算的机理模型与数据模型,利用拓扑门控融合机理模型的因果逻辑性与数据模型的预测精度,建立基于拓扑门控的数据-机理混合驱动的线损计算模型。以分布式电源、储能、电动汽车充电桩接入下的某地区主动配电网为算例进行分析,采用平均绝对误差与均方根误差等评价指标评估模型的计算精度。算例结果表明,本研究所提方法具有较高的计算精度,能够较好地适应不同主体接入后的主动配电网线损计算。

关键词: 配电网线损, 相关性分析, 数据驱动, 拓扑门控

Abstract: Traditional distribution network line loss calculation methods can not simultaneously consider the causal logic of the physical model and the computational accuracy advantage of the data model, and are unable to accurately calculate the active distribution network line loss under the access of different subjects. Therefore, this paper proposed a hybrid data-mechanism driven active distribution network line loss calculation method based on topology gating. Firstly, the correlation analysis of active distribution network line loss features after different subjects' access was performed based on random matrix theory, and the line loss features with the strongest correlation with line loss rate were obtained. Then, based on the mechanism model and data model of traditional line loss calculation, topological gating was used to fuse the causal logic of the mechanism model with the prediction accuracy of the data model to establish a hybrid data-mechanism driven line loss calculation model based on topological gating. The active distribution network in a region with distributed power, energy storage, and electric vehicle charging pile access was taken as an example for analysis, and evaluation indexes such as average absolute error and root mean square error were used to assess the calculation accuracy of the model. The example results showed that the method proposed in this paper had high calculation accuracy and could be well adapted to the calculation of line loss of active distribution network after the access of different subjects.

Key words: power distribution network line loss, correlation analysis, data-driven, topology-gated

中图分类号:

TM732

安海云,周前,刘玉方,黄成,陈哲,吴秋伟. 基于拓扑门控的数据-机理混合驱动的主动配电网线损计算方法[J]. 山东大学学报 (工学版), 2025, 55(5): 51-61.

AN Haiyun, ZHOU Qian, LIU Yufang, HUANG Cheng, CHEN Zhe, WU Qiuwei. A hybrid data-mechanism driven approach to active distribution network line loss calculation[J]. Journal of Shandong University(Engineering Science), 2025, 55(5): 51-61.

参考文献

[1] 曹永吉, 张恒旭, 张怡, 等. 基于事件驱动的机组快速频率响应控制方法[J].电力系统自动化, 2021, 45(19): 148-154. CAO Yongji, ZHANG Hengxu, ZHANG Yi, et al. Event-driven fast frequency response control method for generator unit[J]. Automation of Electric Power Systems, 2021, 45(19): 148-154.
[2] 李文升, 刘晓明, 曹永吉, 等. 考虑电力系统灵活性的网-储联合规划[J]. 智慧电力, 2023, 51(4): 30-37. LI Wensheng, LIU Xiaoming, CAO Yongji, et al. Joint planning of energy storage and transmission line considering power system flexibility[J]. Smart Power, 2023, 51(4): 30-37.
[3] 张恒旭, 曹永吉, 张怡, 等. 电力系统频率动态行为衍变与分析方法需求综述[J]. 山东大学学报(工学版), 2021, 51(5): 42-52. ZHANG Hengxu, CAO Yongji, ZHANG Yi, et al. Review of frequency dynamic behavior evolution and analysis method requirements of power system[J]. Journal of Shandong University(Engineering Science), 2021, 51(5): 42-52.
[4] 赵康宁. 基于贝叶斯神经网络的分布式光伏预测及应用[D]. 北京: 中国电力科学研究院, 2020. ZHAO Kangning. Distributed photovoltaic prediction and application based on Bayesian neural network[D]. Beijing: China Electric Power Research Institute, 2020.
[5] RASTGOU A, MOSHTAGH J, BAHRAMARA S. Improved harmony search algorithm for electrical distribution network expansion planning in the presence of distributed generators[J]. Energy, 2018, 151: 178-202.
[6] 孙宏斌, 张伯明. 配电匹配潮流技术及其在配电状态估计中的应用[J]. 电力系统自动化, 1998, 22(7): 18-22. SUN Hongbin, ZHANG Boming. Distribution matching power flow technology and its application to state estimation for distribution systems[J]. Automation of Electric Power Systems, 1998, 22(7): 18-22.
[7] 付学谦. 考虑配电网网损和电能质量的分布式电源优化配置[D]. 广州: 华南理工大学, 2015. FU Xueqian. Optimal allocation of distributed generation considering network loss and power quality of distribution network[D]. Guangzhou: South China University of Technology, 2015.
[8] 霍佳丽. 电力系统理论线损计算实用方法的分析研究[D]. 重庆: 重庆大学, 2009. HUO Jiali. Analysis and research on practical method of theoretical line loss calculation in power system[D]. Chongqing: Chongqing University, 2009.
[9] 董继征, 陈洪云, 何怡刚. 基于负荷分类的台区线损测算方法[J]. 现代电力, 2006, 23(1): 44-48. DONG Jizheng, CHEN Hongyun, HE Yigang. Method for calculating transformer district line loss based on load classification[J]. Modern Electric Power, 2006, 23(1): 44-48.
[10] 黄明欣, 唐酿, 黄辉, 等. 基于统计偏差和技术偏差的低压台区线损率分析方法[J]. 现代电力, 2024, 41(4): 673-679. HUANG Mingxin, TANG Niang, HUANG Hui, et al. A statistical and technical deviations based analysis approach for line loss rate in low-voltage transformer district[J]. Modern Electric Power, 2024, 41(4): 673-679.
[11] BOWDEN G J, BARKER P R, SHESTOPAL V O, et al. The Weibull distribution function and wind power statistics[J]. Wind Engineering, 1983, 7(2): 85-98.
[12] 祖凯涛, 林卓琼. 配电网精细化线损计算及降损分析[J]. 陕西电力, 2016, 44(1): 60-64. ZU Kaitao, LIN Zhuoqiong. Line loss fine calculation and loss-reducing analysis[J]. Shaanxi Electric Power, 2016, 44(1): 60-64.
[13] 王磊, 张建宾, 余昆, 等. 基于典型负荷曲线的配电网线损计算方法研究[J]. 智慧电力, 2020, 48(3): 124-130. WANG Lei, ZHANG Jianbin, YU Kun, et al. Calculation method of distribution line loss based on typical load curve[J]. Smart Power, 2020, 48(3): 124-130.
[14] 徐茹枝, 王宇飞. 粒子群优化的支持向量回归机计算配电网理论线损方法[J]. 电力自动化设备, 2012, 32(5): 86-89. XU Ruzhi, WANG Yufei. Theoretical line loss calculation based on SVR and PSO for distribution system[J]. Electric Power Automation Equipment, 2012, 32(5): 86-89.
[15] 张勇军, 石辉, 翟伟芳, 等. 基于层次分析法-灰色综合关联及多灰色模型组合建模的线损率预测[J]. 电网技术, 2011, 35(6): 71-76. ZHANG Yongjun, SHI Hui, ZHAI Weifang, et al. Line loss rate prediction based on combinatorial modeling by analytic hierarchy process-gray comprehensive relationship and multi grey models[J]. Power System Technology, 2011, 35(6): 71-76.
[16] 张力. 配电网理论线损计算分析与研究[D]. 兰州: 兰州理工大学, 2013. ZHANG Li. Analysis and research on theoretical line loss calculation of distribution network[D]. Lanzhou: Lanzhou University of Technology, 2013.
[17] 吴丽珍, 秦文彬, 赵一凡, 等. 基于TASSA-Mg LSTM的配电网线损预测方法[J]. 电力系统及其自动化学报, 2023, 35(12): 40-49. WU Lizhen, QIN Wenbin, ZHAO Yifan, et al. Prediction method for distribution network line loss based on TASSA-Mg LSTM[J]. Proceedings of the CSU-EPSA, 2023, 35(12): 40-4
[18] 张勤, 周步祥, 林楠, 等. 基于灰色模型与神经网络组合的线损率预测[J]. 电力系统及其自动化学报, 2013, 25(5): 162-166. ZHANG Qin, ZHOU Buxiang, LIN Nan, et al. Line loss rate forecasting based on combination of grey model and neural network[J]. Proceedings of the Chinese Society of Universities for Electric Power System and Its Automation, 2013, 25(5): 162-166.
[19] 史佳琪, 张建华. 基于多模型融合Stacking集成学习方式的负荷预测方法[J]. 中国电机工程学报, 2019, 39(14): 4032-4042. SHI Jiaqi, ZHANG Jianhua. Load forecasting based on multi-model by Stacking ensemble learning[J]. Proceedings of the CSEE, 2019, 39(14): 4032-4042.
[20] 王彪, 吕洋, 陈中, 等. 考虑信息时移的分布式光伏机理-数据混合驱动短期功率预测[J]. 电力系统自动化, 2022, 46(11): 67-74. WANG Biao, LYU Yang, CHEN Zhong, et al. Hybrid mechanism-data-driven short-term power forecasting of distributed photovoltaic considering information time shift[J]. Automation of Electric Power Systems, 2022, 46(11): 67-74.
[21] 尚宇炜, 郭剑波, 吴文传, 等. 数据-知识融合的机器学习(1): 模型分析[J]. 中国电机工程学报, 2019, 39(15): 4406-4416. SHANG Yuwei, GUO Jianbo, WU Wenchuan, et al. Machine learning methods embedded with domain knowledge(part Ⅰ): model analysis[J]. Proceedings of the CSEE, 2019, 39(15): 4406-4416.
[22] 尚宇炜, 郭剑波, 吴文传, 等. 数据-知识融合的机器学习(2):泛化风险[J].中国电机工程学报, 2019, 39(16): 4641-4649. SHANG Yuwei, GUO Jianbo, WU Wenchuan, et al. Machine learning methods embedded with domain knowledge(part II): generalization risk[J].Proceedings of the CSEE, 2019, 39(16): 4641-4649.
[23] 庄远灿. 基于过程状态特征化的10 kV配电网线损计算及相关性分析[D]. 广州: 华南理工大学, 2018. ZHUANG Yuancan. Line loss calculation and correlation analysis of 10 kV distribution network based on process state characterization[D]. Guangzhou: South China University of Technology, 2018.
[24] 马丽叶, 刘建恒, 卢志刚, 等. 基于深度置信网络的低压台区理论线损计算方法[J]. 电力自动化设备, 2020, 40(8): 140-146. MA Liye, LIU Jianheng, LU Zhigang, et al. Theoretical line loss calculation method of low voltage transform district based on deep belief network[J]. Electric Power Automation Equipment, 2020, 40(8): 140-146.
[25] 张一彦, 陆嘉铭, 贺静, 等. 基于改进随机森林算法的线损率预测研究[J].电力大数据, 2025, 28(3): 19-26. ZHANG Yiyan, LU Jiaming, HE Jing, et al. A Study on line loss rate prediction based on an improved random forest algorithm[J]. Power Big Data, 2025, 28(3): 19-26.
[26] 李子龙, 刘亚东, 王耀东, 等. 基于大维随机矩阵的电网异常快速检测方法[J]. 陕西电力, 2017, 45(3): 77-81. LI Zilong, LIU Yadong, WANG Yaodong, et al. Abnormal situation detection in power grid with large-dimensional random matrix spectral distribution[J]. Shaanxi Electric Power, 2017, 45(3): 77-81.
[27] XU X Y, HE X, AI Q, et al. A correlation analysis method for power systems based on random matrix theory[J]. IEEE Transactions on Smart Grid, 2017, 8(4): 1811-1820.
[28] 黎静华, 黄乾, 韦善阳, 等. 基于S-BGD和梯度累积策略的改进深度学习方法及其在光伏出力预测中的应用[J]. 电网技术, 2017(10):3292-3299. LI Jinghua, HUANG Qian, WEI Shanyang, et al. Improved deep learning algorithm based on S-BGD and gradient pile strategy and its application in PV power forecasting[J]. Power System Technology, 2017(10): 3292-3299.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed