Premium
Virtual machine anomaly detection strategy based on cloud platform operating environment perception
Author(s) -
Miao Xuna,
Wu Xiaobo
Publication year - 2018
Publication title -
concurrency and computation: practice and experience
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.309
H-Index - 67
eISSN - 1532-0634
pISSN - 1532-0626
DOI - 10.1002/cpe.4656
Subject(s) - virtual machine , anomaly detection , computer science , cloud computing , real time computing , anomaly (physics) , maximization , artificial intelligence , operating system , physics , economics , microeconomics , condensed matter physics
Summary In this paper, a variety of anomaly detection strategies are provided with the application of the cloud platform center in view of the processor resources allocation according to the peak load demand, provision of the single anomaly detection strategy, and the problem of the sudden increase of the abnormal rate due to the change of the resource demand. The gray waveform detection algorithm is applied to detect the anomaly arriving at the virtual machine in the future time period, and the abnormal utility function of the virtual machine is given to balance the resource requirements and anomaly detection priority, and all the virtual machines are dynamically configured for each virtual machine with the maximization of the anomaly utility value of the virtual machine as the objective. Through the global load balancing between the same virtual machines and the redistribution of the virtual machines for multiple times, the detection quantity on the virtual machine anomaly with relatively huge increase of anomaly is further increased. Finally, the anomaly detection algorithm based on the gray waveform detection in the cloud platform center ADGWT is given. Simulation experiment results show that the proposed algorithm can effectively improve the abnormal rate of the processors in the cloud platform, and it has practical significance to improve the completion rate of the user requests.