为充分利用电网中潜在关联的多组特征和高维多源异构数据,提出一种基于多变量合作学习、最小绝对收缩和选择算法(leastabsolute shrinkage and selection operator,LASSO)的电压稳定裕度在线评估方法。首先,利用合作学习算法在无功储备...为充分利用电网中潜在关联的多组特征和高维多源异构数据,提出一种基于多变量合作学习、最小绝对收缩和选择算法(leastabsolute shrinkage and selection operator,LASSO)的电压稳定裕度在线评估方法。首先,利用合作学习算法在无功储备、节点电压等系统异质运行参数之间形成最佳融合模式,并通过局部加权LASSO回归工具建立评估模型。然后,设计数据库自动更新系统,实现模型对运行工况的检测与自动更新。最后,采用IEEE30节点和1951节点系统对所提方法进行验证。结果表明该方法在功率增长方向、运行方式等变化情况下,具有良好的准确性及泛化性。展开更多
As a new type of learning machine developed on the basis of statistics learning theory, support vector machine （SVM） plays an important role in knowledge discovering and knowledge updating by constructing non-linear...As a new type of learning machine developed on the basis of statistics learning theory, support vector machine （SVM） plays an important role in knowledge discovering and knowledge updating by constructing non-linear optimal classifter. However, realizing SVM requires resolving quadratic programming under constraints of inequality, which results in calculation difficulty while learning samples gets larger. Besides, standard SVM is incapable of tackling multi-classification. To overcome the bottleneck of populating SVM, with training algorithm presented, the problem of quadratic programming is converted into that of resolving a linear system of equations composed of a group of equation constraints by adopting the least square SVM（LS-SVM） and introducing a modifying variable which can change inequality constraints into equation constraints, which simplifies the calculation. With regard to multi-classification, an LS-SVM applicable in multi-dassiftcation is deduced. Finally, efficiency of the algorithm is checked by using universal Circle in square and twospirals to measure the performance of the classifier.展开更多
文摘为充分利用电网中潜在关联的多组特征和高维多源异构数据,提出一种基于多变量合作学习、最小绝对收缩和选择算法(leastabsolute shrinkage and selection operator,LASSO)的电压稳定裕度在线评估方法。首先,利用合作学习算法在无功储备、节点电压等系统异质运行参数之间形成最佳融合模式,并通过局部加权LASSO回归工具建立评估模型。然后,设计数据库自动更新系统,实现模型对运行工况的检测与自动更新。最后,采用IEEE30节点和1951节点系统对所提方法进行验证。结果表明该方法在功率增长方向、运行方式等变化情况下,具有良好的准确性及泛化性。
文摘As a new type of learning machine developed on the basis of statistics learning theory, support vector machine （SVM） plays an important role in knowledge discovering and knowledge updating by constructing non-linear optimal classifter. However, realizing SVM requires resolving quadratic programming under constraints of inequality, which results in calculation difficulty while learning samples gets larger. Besides, standard SVM is incapable of tackling multi-classification. To overcome the bottleneck of populating SVM, with training algorithm presented, the problem of quadratic programming is converted into that of resolving a linear system of equations composed of a group of equation constraints by adopting the least square SVM（LS-SVM） and introducing a modifying variable which can change inequality constraints into equation constraints, which simplifies the calculation. With regard to multi-classification, an LS-SVM applicable in multi-dassiftcation is deduced. Finally, efficiency of the algorithm is checked by using universal Circle in square and twospirals to measure the performance of the classifier.
