物联网环境下Web数据库异常数据检测方法研究

Under the environment of Internet Web database abnormal data detection method research

摘要:

物联网环境下web数据库网络承载着不同的网络载体和网络信道,web数据库通过云储存的形式来实现资源共享,云储存产生的异常数据会给网络信息web数据库空间带来一种危机感和存储数据容量空间的不足,所以对物联网环境下web数据库异常数据的检测要求更精准。传统的异常数据检测方法采用简化梯度方法进行web数据库异常数据检测,对含有干扰频率成份的web异常数据不能准确的去除,检测性能低。为此,提出一种基于时空关联的分布式的web数据库异常数据检测方法,通过与集中式算法的精度和消耗量进行对比,仿真实验表明,所提方法进行异常数据检测,减少了web数据的能量消耗,信号幅值大于干扰噪声数据幅值,具有较好的抗干扰性能。

Abstract:

Web database network networking environment carrying network carrier and network channel is different, web database through the cloud storage form to realize the sharing of resources, abnormal data cloud storage to network information generated by the web database space to bring a sense of crisis and the data storage space is insufficient, so the network environment to detect abnormal data web the database requires more accurate to. The traditional outlier detection method uses the simplified gradient method to detect the abnormal data of Web database, which can not remove the abnormal web data with the interference frequency components, and has low detection performance. To this end, we propose a web distributed database abnormal data detection method based on spatial-temporal correlation, compared with the centralized algorithm accuracy and consumption, simulation results show that the proposed method of outlier detection, reduce the energy consumption of the web data, the amplitude of the signal is greater than the amplitude of noise data, has good anti-jamming performance.