An anomaly detection parameter optimization algorithm for data center data

The storage and calculation of the larger amount of data in the cloud data center brings more abnormal data. In order to accurately and efficiently find anomalies in the data in the cloud data center, this paper proposes an anomaly detection parameter optimization algorithm for data center data. Methods Fuzzy C-means clustering (FCM) algorithm is used for anomaly detection. At the same time, in order to overcome the problem that the fuzzy clustering algorithm is sensitive to the initial value and easy to fall into the local optimum, the adaptive bat algorithm is used to optimize the FCM algorithm. And add distributed entropy and average distance to the algorithm, adaptively adjust the optimization ability of traditional bat algorithm. Finally, experiments prove the detection accuracy of the algorithm.