Abstract As the number of running tasks increases dramatically on a cloud platform , the probability of task failure increases. Among the many reasons affecting task failure, the lack of information is straightforward and fatal. Suppose we can predict whether a task will generate missing information and take measures in advance. In that case, we can effectively reduce the probability of task failure and also avoid ineffective use of resources. This paper investigates the missing information of tasks and proposes a missing prediction algorithm based on an improved Mixture of Gaussian (GMM) algorithm. Specifically, we deeply analyze and process the cloud task information based on the latest cloud platform data released by Google Inc in 2019. Several clustering algorithms are used to make experimental comparisons to determine their suitability for prediction. Finally, we developed an optimized GMM algorithm to build the prediction model. The experiments show the model is fast and accurate and can significantly save system time and resource utilization.
原文链接
分享
引用
