基于投影能量函数和Pin-SVM的电力系统暂态稳定评估

发布时间：2018-03-20 21:02

本文选题：投影能量函数　切入点：Pin-SVM　出处：《电工技术学报》2017年11期 　论文类型：期刊论文

【摘要】：提出一种基于Pin-SVM的电力系统暂态稳定评估方法。首先,采用系统指标(如平均机械功率、初始加速度和系统冲击等)和投影能量函数指标(如投影角速度、投影角加速度和投影动能PKE)构建暂态稳定指标的原始特征集,通过最大相关最小冗余特征选择方法对暂态指标集进行特征压缩,寻找对电网暂态变化敏感度高的特征子集;然后,基于Pin-SVM思想将特征子集映射到高维空间,实现非线性暂态稳定评估问题的线性转换,进而引入分位数改变系统稳定类与不稳定类之间的最近点位置,将暂态稳定分类问题转换为在Pin-SVM中寻找最优分位数距离问题,以减小边界干扰样本的影响,提高电力系统暂态评估方法的评估准确率和稳定性。最后,以IEEE-39节点系统、IEEE-145节点系统和某实际算例进行仿真计算,计算结果验证了该方法的有效性和准确性。
[Abstract]:A power system transient stability evaluation method based on Pin-SVM is proposed. Firstly, the system indexes (such as average mechanical power, initial acceleration and system impact) and projection energy function (such as projective angular velocity) are used. Projection angular acceleration and projection kinetic energy PKE) are used to construct the original feature set of transient stability index. The feature set is compressed by the method of maximum correlation and minimum redundancy feature selection to find the feature subset with high sensitivity to the transient change of power network. Then, based on the idea of Pin-SVM, the feature subset is mapped to high dimensional space to realize the linear transformation of nonlinear transient stability assessment problem, and the quantile is introduced to change the position of the nearest point between the stability class and the unstable class of the system. In order to reduce the influence of boundary interference samples and improve the accuracy and stability of power system transient evaluation methods, the transient stability classification problem is transformed into the problem of finding the optimal quantile distance in Pin-SVM. The effectiveness and accuracy of this method are verified by the simulation of IEEE-39 node system and a practical example.
【作者单位】：东北电力大学电气工程学院;
【基金】：国家重点研发计划(2016YFB0900903) 国家自然科学基金(51477027,51677022,51607033,51607034) 东北电力大学博士科研启动基金(BSJXM-201501)资助项目
【分类号】：TM712

【相似文献】