Cognitive machine learning refers to the combination of machine learning and brain cognitive mechanism, specifically, combining machine learning with mind model CAM. Three research directions are proposed in this pape...Cognitive machine learning refers to the combination of machine learning and brain cognitive mechanism, specifically, combining machine learning with mind model CAM. Three research directions are proposed in this paper, that is, emergency of learning, complementary learning system and evolution of learning.展开更多
风电集中接入使得传统方式有效计算极限传输容量存在困难。为此,提出一种基于差分进化极限学习机的含风电系统输电断面极限传输功率(Total Transfer Capability, TTC)运行规则提取方法。首先基于K-medoids聚类方法提取以"风功率-负...风电集中接入使得传统方式有效计算极限传输容量存在困难。为此,提出一种基于差分进化极限学习机的含风电系统输电断面极限传输功率(Total Transfer Capability, TTC)运行规则提取方法。首先基于K-medoids聚类方法提取以"风功率-负荷"二维特征表征的典型运行场景,然后通过随机采样和重复潮流方法生成用于TTC运行规则挖掘的知识库。接着采用RELIEF-F算法筛除冗余特征并辨识与输电断面TTC存在强关联的特征属性,以削减运行特征的高维度。最终通过将训练数据输入差分进化极限学习机,从知识库中提取TTC运行规则。算例验证表明,所提方法能够以较高的计算精度及较强的泛化能力实现TTC的快速估计。展开更多
文摘Cognitive machine learning refers to the combination of machine learning and brain cognitive mechanism, specifically, combining machine learning with mind model CAM. Three research directions are proposed in this paper, that is, emergency of learning, complementary learning system and evolution of learning.
文摘风电集中接入使得传统方式有效计算极限传输容量存在困难。为此,提出一种基于差分进化极限学习机的含风电系统输电断面极限传输功率(Total Transfer Capability, TTC)运行规则提取方法。首先基于K-medoids聚类方法提取以"风功率-负荷"二维特征表征的典型运行场景,然后通过随机采样和重复潮流方法生成用于TTC运行规则挖掘的知识库。接着采用RELIEF-F算法筛除冗余特征并辨识与输电断面TTC存在强关联的特征属性,以削减运行特征的高维度。最终通过将训练数据输入差分进化极限学习机,从知识库中提取TTC运行规则。算例验证表明,所提方法能够以较高的计算精度及较强的泛化能力实现TTC的快速估计。
