面向低尺度特征约束的虚拟现实异常检测模型

The Anomaly Detection Model for Virtual Reality Based on Low-scale Feature Constraint

针对虚拟现实平台按负载峰值需求配置处理机资源、提供单一的异常检测策略导致异常率剧增的问题,采用虚拟现实平台中心来提供异常检测策略.利用低尺度特征约束算法对未来时间段内到达虚拟现实的异常进行检测,以最大化虚拟现实的异常效用值为目标,给出兼顾资源需求和异常检测优先等级的虚拟现实异常效用函数.模拟实验表明所提算法能够有效提高虚拟现实平台中处理机的异常率,对提高用户请求完成率具有实际意义.

In this paper,aiming at the problem that the virtual reality platform can configure the processor resources according to the peak load demand and provide a single anomaly detection strategy,which leads to the increase of the abnormal rate,the virtual reality platform is used to provide the anomaly detection strategy.The low-scale feature constraint detection algorithm is applied to detect the anomaly arriving at the virtual reality in the future time,aiming at maximizing the abnormal utility value of virtual reality,the utility function of virtual reality is given,which takes into account the resource requirement and the priority level of anomaly detection.The simulation experiment results show that the proposed algorithm can effectively improve the abnormal rate of the processors in the virtual reality platform,and it has practical significance to improve the completion rate of the user requests.