欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
暂态稳定评估的特征选择是一个典型的组合优化问题。针对该问题解的离散性特点，提出基于蚁群优化算法的特征选择方法。该方法以最小二乘支持向量机作为暂态稳定评估分类器，以分类错误率最低和特征选择比率最小为优化目标，通过二进制编码形式的蚁群优化算法实现特征的选择。这样能选择出计及分类器特性的最优特征子集，减少了特征维教，提高了分类正确率。通过对综合程序EPRI-36节点系统的仿真计算，验证了该方法的有效性。
英文摘要：
Feature selection of transient stability assessment（TSA） is a typical combinatorial optimization problem. To handle the discrete character of the problem, a method based on ant colony optimization（ACO） is presented to solve the feature selection problem of transient stability assessment. In this paper, least square support vector machine（ LS-SVM ） is used as transient stability assessment classifier, the lowest classification error rate and feature selection rate are defined as optimization objectives. By using the binary code forms of ACO to complete the feature selection, it can select the optimal subset of features considering classifier characteristic, which decreases the dimensions, of input features EPRI-36 bus model of PSAPS is tested to demonstrate the validity and increases the correct classification percentage as well. The of this proposed approach.
同期刊论文项目
同项目期刊论文
位置：