| 基于CNN的配电网快速重构方法 |
| |
| 引用本文： | 张玉敏,孙鹏凯,叶平峰,吉兴全,王志豪,公政.基于CNN的配电网快速重构方法[J].陕西电力,2022,0(11):112-118. |
| |
| 作者姓名： | 张玉敏 孙鹏凯 叶平峰 吉兴全 王志豪 公政 |
| |
| 作者单位： | （1.山东科技大学电气与自动化工程学院，山东青岛 266590；2.山东科技大学储能技术学院，山东青岛 266590；3.国网山东烟台供电公司，山东烟台 264000；4.国网山东潍坊供电公司，山东潍坊 261000） |
| |
| 摘 要： | 针对现有配电网重构算法求解速度慢的问题，提出基于卷积神经网络(CNN）的配电网快速重构方法。首先，搭建基于配电网环路结构的多分支CNN模型，减少建模过程对配电网具体结构的依赖；其次，利用混合训练方法训练CNN模型，使模型具备对不同负载模式的配网进行快速重构的能力；最后，以IEEE33节点测试系统为例，验证所提方法的有效性。
|
| 关 键 词： | 卷积神经网络 配电网快速重构 负载模式 混合训练 数据驱动 |
Fast Reconfiguration Method of Distribution Network of Based on Convolutional Neural Network |
| |
| ZHANG Yumin,SUN Pengkai,YE Pingfeng,JI Xingquan,WANG Zhihao,GONG Zheng.Fast Reconfiguration Method of Distribution Network of Based on Convolutional Neural Network[J].Shanxi Electric Power,2022,0(11):112-118. |
| |
| Authors: | ZHANG Yumin SUN Pengkai YE Pingfeng JI Xingquan WANG Zhihao GONG Zheng |
| |
| Affiliation: | （1. College of Electrical Engineering and Automation，Shandong University of Science and Technology，Qingdao 266590，China；2. College of Energy Storage Technology，Shandong University of Science and Technology，Qingdao 266590，China；3. State Grid Shandong Yantai Power Supply Company，Yantai 264000，China；4. State Grid Shandong Weifang Power Supply Company，Weifang 261000，China） |
| |
| Abstract: | Aiming at the problem of slow solving speed of existing distribution network （DN） reconstruction algorithm，a fast distribution network reconfiguration method based on convolutional neural network （CNN） is proposed.Firstly，a multi-branch CNN model based on the loop structure of DN is established，which can reduce the dependence on the concrete structure of DN in the process of modeling. Secondly，the CNN model is trained based on the hybrid training method，so that the model has the ability to quickly reconfigure the DN with different load modes. Finally，the performance of the model is analyzed in IEEE 33-bus system to verify the effectiveness of the proposed method. |
| |
| Keywords: | convolutional neural network fast reconfiguration of distribution network load mode hybrid training data-driven |
|
| 点击此处可从《陕西电力》浏览原始摘要信息 |
|
点击此处可从《陕西电力》下载全文 |
