摘要
对多用户网络高风险连锁故障区域进行预警,能够确保多用户网络的安全运行。对高风险连锁故障区域进行预警,需要故障数据进行经验模态分解,获取故障信号特征估计结果,完成连锁故障区域的预警。传统方法通过迁移学习模型得到不同故障间差异,获得多网络连锁故障区域风险度,但忽略了对连锁故障信号特征进行估计,导致预警精度偏低。提出基于小波包调频估计的多用户网络高风险连锁故障区域预警方法。建立高风险连锁故障信号采集模型,并对高风险连锁故障信号进行分解滤波处理。对滤波处理信号后的故障数据进行经验模态分解,对分解后的高风险连锁故障信号特征进行估计,实现多用户网络高风险连锁故障区域预警。实验结果表明,所提方法可有效减少多用户网络的连锁故障,预警精度较高,可保障多用户网络的稳定性。
Traditional method ignores the estimation of feature of cascading failure signal, leading to low early warning accuracy. Therefore, an early warning method for high - risk cascading failure area in multi - user network based on wavelet packet frequency modulation estimation was proposed. Firstly, the model of high-risk cascading failure signal acquisition was built, and then high-risk cascading failure signal was decomposed and filtered. Moreover, the fault data processed by the filtering signal were decomposed based on empirical mode. Finally, the feature of high-risk cascading failure signal after decomposition was estimated. Thus, the early warning of high-risk cascading failure area in multi-user network was achieved. Simulation results prove that the proposed method can effectively reduce cascading failure in multi-user network. Meanwhile, the early warning accuracy is high, which can guarantee the stability of multi-user network.
作者
杜涛
DU Tao(Jinzhong University,Jinzhong Shanxi 030600,China)
出处
《计算机仿真》
北大核心
2019年第7期328-330,375,共4页
Computer Simulation
关键词
多用户网络
高风险
连锁故障区域
预警
Multi-user network
High-risk
Cascading failure area
Early warning
