摘要
广域测量系统WAMS(Wide Area Measure System)的出现,为大电网在线暂稳预测提供了新的实时数据平台。基于WAMS数据,通过CCCOI-RM变换将系统进行简化等值,采用最小二乘支持向量机回归算法LS-SVR(Least Square Support Vector Regression)的出色学习性能和非线性处理能力,对等值系统的功角轨迹进行在线学习和实时预测,并进一步使用极值、阈值双重判据进行暂态稳定性判断。该方法不用考虑系统详细结构,计算速度快,预测时间长,仿真分析表明所提出的方法能够快速准确地预测电力系统的暂态稳定性,并为下一步采取相应的紧急预控制措施提供相对充裕的时间窗口。
Wide Area Measure System provides a new platform for on-line transient stability prediction of bulk power system. A novel time series data based Least Square Support Regression （LS-SVR） transient stability forecasting method is proposed to solve the on-line transient stability problems in the paper. The LS-SVR method has excellent studying and non-linear problems processing abilities, and can provide a comparatively long forecasting time range. Calculation is simplified by CCCOI-RM transform and results stability is enhanced by using of Extremum plus Threshold Double Criterion in the paper. The method is fast and has no direct collection with the system detailed model. Simulation results show that the proposed method yield satisfactory accuracy for real-time transient stability prediction. This project is supported by National Natural Science Foundation of Chongqing Science ＆ Technology Commission （No.2006BB6209）
出处
《电力系统保护与控制》
EI
CSCD
北大核心
2008年第19期9-14,共6页
Power System Protection and Control
基金
重庆市科委自然科学基金资助项目(2006BB6209)~~
