基于改进决策树的安全约束经济调度的冗余约束识别方法

夏卓延<sup>1</sup>; 张大海<sup>1</sup>; 严嘉豪<sup>2</sup>; 李振宇<sup>3</sup>; 毛文博<sup>2</sup>; 杨大坤<sup>1</sup>

引用本文:	夏卓延,张大海,严嘉豪,等.基于改进决策树的安全约束经济调度的冗余约束识别方法[J].电力系统保护与控制,2026,54(05):61-75.
	XIA Zhuoyan,ZHANG Dahai,YAN Jiahao,et al.An identification method for redundant constraints in safety-constrained economic dispatch based on improved decision tree[J].Power System Protection and Control,2026,54(05):61-75

【打印本页】【下载PDF全文】【查看/发表评论】【EndNote】【RefMan】【BibTex】

←前一篇|后一篇→

过刊浏览高级检索

本文已被：浏览 435次下载 740次	码上扫一扫！
分享到：微信更多字体:加大+\|默认\|缩小-
基于改进决策树的安全约束经济调度的冗余约束识别方法
夏卓延,张大海,严嘉豪,等
1.北京交通大学电气工程学院，北京 100044；2.中国电力科学研究院有限公司(南京)，江苏南京 210003；3.国网甘肃省电力公司, 甘肃兰州 730046

摘要:

针对安全约束经济调度(security-constrained economic dispatch, SCED)中冗余约束的识别目前尚缺乏快速有效的识别方法。同时，数据驱动方法容易产生假正例(false positive, FP)误判，从而影响系统安全性。为此，提出了一种改进的决策树(decision tree, DT)算法，即改进的分类回归树(classification and regression tree, CART)算法，以及改进的错误率降低剪枝(reduced error pruning, REP)算法，以实现对冗余约束的快速识别。首先，阐述SCED模型与CART原理。其次，构建了冗余约束识别的特征工程及数据预处理方法。然后，提出了融合FP惩罚机制的改进CART算法及基于FP比的REP剪枝策略。最后，通过SG-126系统验证了所提改进算法在较好地适应极端FP敏感场景的同时，能够快速、准确地识别冗余约束。冗余约束识别准确率达到95.13%，FP误判率为0，在削减冗余约束后系统调度时间减少了88.22%。

关键词: 安全约束经济调度冗余约束识别分类回归树错误率降低剪枝

DOI：10.19783/j.cnki.pspc.250534

分类号:

基金项目:国家重点研发计划项目资助(2022YFB2403400)

An identification method for redundant constraints in safety-constrained economic dispatch based on improved decision tree

XIA Zhuoyan1, ZHANG Dahai1, YAN Jiahao2, LI Zhenyu3, MAO Wenbo2, YANG Dakun1

1. Department of Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China;2. China Electric Power Research Institute (Nanjing), Nanjing 210003, China;3. State Grid Gansu Electric Power Company, Lanzhou 730046, China

Abstract:

Currently, there is a lack of fast and effective methods for identifying redundant constraints in security- constrained economic dispatch (SCED). Moreover, data-driven approaches are prone to false positive (FP) misclassification, which may compromise system security. To address these issues, an improved decision tree (DT) algorithm, namely, an improved classification and regression tree (CART) algorithm combined with an enhanced reduced error pruning (REP) strategy, is proposed for rapid redundant constraints identification. First, the SCED model and the principles of CART are introduced. Second, feature engineering and data preprocessing methods for redundant constraint identification are constructed. Then, an improved CART algorithm incorporating a FP penalty mechanism and a REP strategy based on the FP ratio are proposed. Finally, case studies on the SG-126 system demonstrate that the proposed algorithm can quickly and accurately identify redundant constraints while effectively adapting to extreme FP-sensitive scenarios. The accuracy rate of redundant constraint identification reaches 95.13%, with a FP misclassification rate of zero, and system dispatch time is reduced by 88.22% after eliminating redundant constraints.

Key words: security-constrained economic dispatch (SCED) redundant constraint identification classification and regression tree (CART) reduced error pruning (REP)

X关闭