针对特征选择问题的改进蚁群算法及其在电力系统安全评估中的应用

摘要
图/表
参考文献
相关文章 (4)

全文: PDF (571 KB)
输出: BibTeX | EndNote (RIS)

摘要提出基于改进蚁群优化算法和k近邻算法相结合的特征选择算法。利用k近邻分类器的分类精度和特征子集维数加权构造了综合适应度指标, 利用改进蚁群算法的全局寻优和多次优解搜索能力实现特征子集搜索。针对传统蚁群算法在特征选择中可能含有冗余特征的问题, 设计了局部细化搜索方式, 使得特征选择结果不含冗余特征的同时提高了算法的收敛性。通过测试数据验证了算法的有效性和快速性后, 将所提算法应用于10机39节点电力系统的安全评估问题, 获得了良好的特征选择和稳定预测性能。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	章小强
	管霖
	王同文

关键词 ：特征选择, 蚁群优化算法, k-近邻分类器, 电力系统安全评估

Abstract：A novel embedded feature selection method based on improved ant colony optimization algorithm combined with the k-nearest neighbor (k-NN) classifier is proposed to tackle the feature selection problem. A weighted sum of the k-NN classification accuracy and the selected feature dimension form the fitness function. The improved ant colony optimization algorithm provides good global searching capability and multiple sub-optimal solutions. A local refinement searching scheme is designed to exclude the redundant features and improves the convergence rate. The feasibility and effectiveness of the proposed algorithm is first verified by a set of artificial test data and then applied to the power system security analysis problem. In the IEEE 10-unit-39-bus system, the proposed scheme obtains well-behaved security-related kernel features and provides good transient stability assessment performance.

Key words： Feature selection ant colony optimization algorithm k-nearest neighbor classifier power system security analysis

收稿日期: 2009-01-14 出版日期: 2014-03-04

PACS:

TM712

基金资助:国家自然科学基金资助项目(50407014)

作者简介: 章小强男, 1984年生, 硕士研究生, 研究方向为电力系统安全稳定分析。管霖女, 1970年生, 教授, 博士生导师, 主要研究方向包括电力系统稳定与控制、电网可靠性与规划以及人工智能技术在电力系统中的应用。

引用本文:

章小强, 管霖, 王同文. 针对特征选择问题的改进蚁群算法及其在电力系统安全评估中的应用[J]. 电工技术学报, 2010, 25(12): 154-160. Zhang Xiaoqiang, Guan Lin, Wang Tongwen. Kernel Feature Identification Based on Improved Ant Colony Optimization Algorithm for Transient Stability Assessment. Transactions of China Electrotechnical Society, 2010, 25(12): 154-160.

链接本文:

http://dgjsxb.ces-transaction.com/CN/Y2010/V25/I12/154

[1] 李大虎, 江全元, 曹一家. 基于聚类的支持向量回归模型在电力系统暂态稳定预测中的应用[J]. 电工技术学报, 2006, 21(7): 75-80.
Li Dahu, Jiang Quanyuan, Cao Yijia. Clustering based on support vector regression model and its application in power system transient stability prediction[J]. Transactions of China Electrotechnical Society, 2006, 21(7): 75-80.
[2] 卢锦玲, 朱永利, 赵洪山, 等. 提升型贝叶斯分类器在电力系统暂态稳定评估中的应用[J]. 电工技术学报, 2009, 24(5): 178-182.
Lu Jinling, Zhu Yongli, Zhao Hongshan, et al. Power system transient stability assessment based on boosting Bayesian classifier[J]. Transactions of China Electrotechnical Society, 2009, 24(5): 178-182.
[3] 王同文, 管霖. 基于模式发现的电力系统稳定评估和规则提取[J]. 中国电机工程学报, 2007, 27(19): 25-31.
Wang Tongwen, Guan Lin. Power system stability assessment and rule extraction based on pattern discovery[J]. Proceedings of the CSEE, 2007, 27(19): 25-31.
[4] 于之虹, 郭志忠. 基于数据挖掘理论的电力系统暂态稳定评估[J]. 电力系统自动化, 2003, 27(8): 45-48.
Yu Zhihong, Guo Zhizhong. A novel approach for transient stability assessment based on data mining theory[J]. Automation of Electric Power Systems, 2003, 27(8): 45-48.
[5] 顾雪平, 张文朝. 基于Tabu搜索技术的暂态稳定分类神经网络的输入特征选择[J]. 中国电机工程学报, 2002, 22(7): 66-70.
Gu Xueping, Zhang Wenchao. Feature selection by Tabu search for neural-network based transient stability classification[J]. Proceedings of the CSEE, 2002, 22(7): 66-70.
[6] 管霖, 王同文, 唐宗顺. 电网安全监测的智能化关键特征识别及稳定分区算法[J]. 电力系统自动化, 2006, 30(21): 22-27.
Guan Lin, Wang Tongwen, Tang Zongshun. Intelligent algorithm for Kernel feature identification and stability-based system decision in power grid security monitoring[J]. Automation of Electric Power Systems, 2006, 30(21): 22-27.
[7] Marco Dorigo, Vittorio Maniezzo, Alberto Colorni. Ant system: optimization by a colony of cooperating agents[J]. IEEE Transaction on System, Man, and Cybernetics-Part B: Cybernetics, 1996, 26(1): 29-41.
[8] Helmi Md Rais, Zulaiha Ali Othman, Abdul Razak Hamdan. Improved dynamic ant colony system (DACS) on symmetric traveling salesman problem (TSP)[C]. International Conference on Intelligent and Advanced Systems, 2007: 43-48.
[9] Montemanni R, Smith DH, Gambardella LM. Ant colony systems for large sequential ordering problems[C]. Proceedings of the 2007 IEEE Swarm Intelligence Symposium, 2007: 478-482.
[10] 吕勇, 赵光宙. 蚁群优化算法及其在电力系统中的应用[J]. 电工技术学报, 2003, 18(4)：70-74.
Lv Yong, Zhao Guangzhou. Ant colony optimization algorithm and its applications in power system[J]. Transactions of China Electrotechnical Society, 2003, 18(4)：70-74.
[11] 彭春华, 徐雪松. 基于蚁群算法的电力网络节点编号多方案优化[J]. 电力系统自动化学报, 2007, 19(2): 60-65.
Peng Chunhua, Xu Xuesong. Electric power network node numbering multi-scheme optimization based on ant colony algorithm[J]. Proceedings of the CSU- EPSA, 2007, 19(2): 60-65.
[12] 翟海保, 程浩忠, 吕干云, 等. 基于模式记忆并行蚁群算法的输电网规划[J]. 中国电机工程学报, 2005, 25(9): 17-22.
[13] 王元崑, 王锦彪, 郑芸. 蚂蚁算法的收敛性分析及其改进[J]. 计算机工程, 2005, 31(增): 106-109.
Wang Yuankun, Wang Jinbiao, Zheng Yun. Research on convergence of ant algorithm and its improvement [J]. Computer Engineering, 2005, 31 (Sup): 106-109.
[14] 涂亚平, 刘萍, 谢宝陵, 等. 基本蚂蚁算法中算法参数的优化[J]. 小型微型计算机系统, 2007, 28(11): 1985-1987.
Tu Yaping, Liu Ping, Xie Baoling, et al. Improvement for parameters of ant algorithm[J]. Journal of Chinese Computer Systems, 2007, 28(11): 1985-1987.