针对分布式光伏接入后,异常线损率的判定阈值不合理导致漏检率较高的问题,提出考虑光伏波动性的10 kV配电网线损率波动阈值评估方法。首先,分析分布式光伏电量的并网形式以及可能存在的电量异常情况;其次,采用长短时记忆网络（LSTM）拟合输入特征与线损率之间的非线性关系预测线损率的方法,取代基于量测数据的潮流计算线损率的方法;然后,基于天气类型SCF指数,采用Monte Carol模拟体现光伏发电量的波动性,求得考虑光伏发电随机性的配电网线损率概率密度函数,并以此划定线损率的异常判定阈值。最后以IEEE 37节点配电系统为例,实际评估光伏接入后在考虑气象因素条件下配电线路日线损率的概率密度分布,并与电网的传统判定阈值进行对比分析。
Abstract
An evaluation method for the fluctuation threshold of 10 kV distribution network line loss rate is proposed in this article, which takes into account the fluctuation of photovoltaics, to address the issue of high leakage rate caused by the unreasonable judgment threshold of abnormal line loss rate after distributed photovoltaic access. Firstly, the grid connection form of distributed photovoltaic electricity and possible abnormal electricity situation are analyzed. Secondly, the long short term memory （LSTM） network is used to fit the nonlinear relationship between input features and line loss rate to predict line loss rate, replacing the method of calculating line loss rate based on measured data in power flow. Then, based on the weather type SCF index, Monte Carlo simulation is used to reflect the volatility of photovoltaic power generation,to obtain the probability density function of distribution network line loss rate considering the randomness of photovoltaic power generation, and use this to determine the abnormal judgment threshold of line loss rate. Finally, taking IEEE 37 bus distribution system as an example, the probability density distribution of daily line loss rate of distribution lines afterphotovoltaic access is actually evaluated under the condition of considering meteorological factors, and is compared with the traditional determination threshold of the grid.
关键词
分布式光伏 /
线损 /
配电网 /
长短时记忆网络 /
异常光伏计量点 /
SCF指数
Key words
distributed photovoltaic /
line loss /
distributed network /
long short-term memory network /
abnormal photovoltaic metering points /
SCF index
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 杨婧, 辛明勇, 欧家祥, 等. 基于大数据的配电网线损定位与评估方法研究[J]. 中国测试, 2019, 45(7): 19-24.
YANG J, XIN M Y, OU J X, et al.Distribution network line loss location and evaluation method study based on big data[J]. China measurement & test, 2019, 45(7): 19-24.
[2] 陈锦铭, 陈烨, 焦昊, 等. 基于多源数据融合的配电网分时分段线损诊断方法研究与应用[J]. 电力信息与通信技术, 2022, 20(7): 50-57.
CHEN J M, CHEN Y, JIAO H, et al.Research and application of time and section division line loss diagnosis method of distribution network based on multi-source data fusion[J]. Electric power information and communication technology, 2022, 20(7): 50-57.
[3] 郭庆伟, 黄珊, 郭秀娟, 等. 等值电阻法在配电线路线损计算中的应用[J]. 吉林大学学报(信息科学版), 2022, 40(5): 856-861.
GUO Q W, HUANG S, GUO X J, et al.Application of equivalent resistance method in line loss calculation for distribution lines[J]. Journal of Jilin University (information science edition), 2022, 40(5): 856-861.
[4] 刘慧慧. 配电网理论线损计算及降损策略研究[D]. 青岛: 青岛大学, 2018.
LIU H H.Study on theoretical line loss calculation and loss reduction strategy of distribution network[D]. Qingdao: Qingdao University, 2018.
[5] 谢荣燕, 赵明. 基于支持向量机的企业生产设备采购预测模型研究[J]. 计算技术与自动化, 2018, 37(4): 139-142.
XIE R Y, ZHAO M.Study on enterprise production equipment purchasing prediction model based on SVM[J]. Computing technology and automation, 2018, 37(4): 139-142.
[6] 高小芹, 王梓玮, 卢晨, 等. 基于最小二乘支持向量机的配电网故障量预测模型[J]. 武汉理工大学学报(信息与管理工程版), 2020, 42(1): 23-29.
GAO X Q, WANG Z W, LU C, et al.Prediction model of distribution network fault based on least squares support vector machine[J]. Journal of Wuhan University of Technology (information & management engineering), 2020, 42(1): 23-29.
[7] 李畸勇, 班斓. 基于长短记忆神经网络的短期光伏发电预测技术研究[J]. 华北电力大学学报(自然科学版), 2020, 47(4): 46-52.
LI J Y, BAN L.Research on short-term photovoltaic power forecasting technology based on LSTM[J]. Journal of North China Electric Power University (natural science edition), 2020, 47(4): 46-52.
[8] 郑若楠, 李国杰, 韩蓓, 等. 基于加权扩展日特征矩阵的分布式光伏发电日前功率预测[J]. 电力自动化设备, 2022, 42(2): 99-105.
ZHENG R N, LI G J, HAN B, et al.Day-ahead power forecasting of distributed photovoltaic generation based on weighted expanded daily feature matrix[J]. Electric power automation equipment, 2022, 42(2): 99-105.
[9] 张世丰. 影响太阳能光伏发电的气象因子分析[J]. 农业与技术, 2014, 34(7): 194.
ZHANG S F.Analysis of meteorological factors affecting solar photovoltaic power generation[J]. Agriculture and technology, 2014, 34(7): 194.
[10] 李薇, 王鑫鹏, 许野, 等. 基于传递闭包的光伏短期功率组合预测方法研究[J]. 太阳能学报, 2023, 44(6): 265-274.
LI W, WANG X P, XU Y, et al.Research of combined forecasting method of short-term photovoltaic power based on transitive closure[J]. Acta energiae solaris sinica, 2023, 44(6): 265-274.
[11] 王晓霞, 俞敏, 冀明, 等. 基于气候相似性与SSA-CNN-LSTM的光伏功率组合预测[J]. 太阳能学报, 2023, 44(6): 275-283.
WANG X X, YU M, JI M, et al.Photovoltaic power combination forecasting based on climate similarity and SSA-CNN-LSTM[J]. Acta energiae solaris sinica, 2023, 44(6): 275-283.
[12] 李芬, 周尔畅, 孙改平, 等. 一种新型天气分型方法及其在光伏功率预测中的应用[J]. 上海交通大学学报, 2021, 55(12): 1510-1519.
LI F, ZHOU E C, SUN G P, et al.A novel weather classification method and its application in photovoltaic power prediction[J]. Journal of Shanghai Jiao Tong University, 2021, 55(12): 1510-1519.
[13] 李争, 罗晓瑞, 张杰, 等. 基于改进麻雀搜索算法的光伏功率短期预测[J]. 太阳能学报, 2023, 44(6): 284-289.
LI Z, LUO X R, ZHANG J, et al.Short term prediction of photovoltaic power based on improved sparrow search algorithm[J]. Acta energiae solaris sinica, 2023, 44(6): 284-289.
[14] 李明, 来国红, 常晏鸣, 等. 深度学习算法中不同优化器的性能分析[J]. 信息技术与信息化, 2022(3): 206-209.
LI M, LAI G H, CHANG Y M, et al.Performance analysis of different optimizers in deep learning algorithm[J]. Information technology and informatization, 2022(3): 206-209.
PDF(1137 KB)
