| 引用本文: | 侯 慧,俞菊芳,耿 浩,等.台风灾害下配网用户停电数量预测最优数据驱动模型选择[J].电力系统保护与控制,2021,49(13):114-120.[点击复制] |
| HOU Hui,YU Jufang,GENG Hao,et al.Selection of optimal data-driven model for forecasting outage number of distribution network users under typhoon disaste[J].Power System Protection and Control,2021,49(13):114-120[点击复制] |
|
| 摘要: |
| 严重的台风灾害可能导致配网用户停电，有效的配网用户停电数量预测可为电网应急抢修提供辅助指导。综合考虑气象因素、电网因素及地理因素，提出了基于机器学习回归算法的配网用户停电数量预测方法。分析比较了线性回归、支持向量回归(Support Vector Regression, SVR)、分类回归树(Classification and Regression Tree, CART)、梯度提升树(Gradient Boosting Decision Tree, GBDT)及随机森林(Random Forest, RF)等5种机器学习回归算法对配网用户停电数量预测的应用效果。对比结果表明，LR在进行配网用户停电数量预测时表现较差，SVR及CART模型效果次之，RF及GBDT效果相对较好，其中GBDT算法与RF算法误差较为接近。但考虑到GBDT算法为串行计算，而RF算法为并行计算，使用时RF算法效率更高。因此最终选取了RF进行停电数量预测效果的进一步分析。结果表明其误差在±30%以内的准确率可达70%以上，可为配网用户停电抢修提供有力指导。 |
| 关键词: 台风灾害 停电数量 数据驱动 回归分析 机器学习 |
| DOI：DOI: 10.19783/j.cnki.pspc.201071 |
| 投稿时间：2020-09-01修订日期：2020-11-09 |
| 基金项目:南方电网科技项目资助(GDKJXM20198441)；教育部产学合作协同育人项目资助(201902056044) |
|
| Selection of optimal data-driven model for forecasting outage number of distribution network users under typhoon disaste |
| HOU Hui1,YU Jufang1,GENG Hao1，2,LI Min3,XIE Yufeng3,ZHU Ling3,HUANG Yong4 |
| (1. School of Automation, Wuhan University of Technology, Wuhan 430070, China; 2. Electric Power Research Institute,
Yunnan Power Grid Co., Ltd., Kunming 650200, China; 3. Guangdong Power Grid Co., Ltd., Guangzhou 510000, China;
4. Electric Power Research Institute, Guangdong Power Grid Co., Ltd., Guangzhou 510000, China) |
| Abstract: |
| Severe typhoon disaster may lead to power outage of distribution network users, the effective prediction of the number of outage users in distribution network can provide auxiliary guidance for emergency repair of power grid. Considering meteorological factors, power grid factors and geographical factors, a forecasting method for the outage number of distribution network user based on machine learning regression algorithm is proposed. This paper analyzes and compares the application effects of five machine learning regression algorithms, including Linear Regression (LR), Support Vector Regression (SVR), Classification and Regression Tree (CART), Gradient Boosting Decision Tree (GBDT) and Random Forest (RF) in forecasting the number of power outages of distribution network users. The results show that LR performs poorly in forecasting the number of power outages of distribution network users, followed by SVR and CART, RF and GBDT are relatively good. The error of GBDT is close to RF, but considering that GBDT is serial computing and RF is parallel computing, RF is more efficient when used. Therefore, RF is selected for further analysis of the forecasting effect of outage number. The results show that the accuracy of the method is more than 70% when the error is within ±30%. It can provide powerful guidance for power outage repairs for distribution network users.
This work is supported by the Science and Technology Project of China Southern Power Grid (No. GDKJXM20198441) and the Cooperative Education of Industry-academy Cooperation of Ministry of Education (No. 201902056044). |
| Key words: typhoon disaster outage number data-driven regression analysis machine learning |
