AT&T Intellectual Property I, LP

Imad Ahmad

Raghvendra Savoor

Frederick Armanino

A cloud oversubscription system including one or more processors and a memory coupled with the one or more processors. The one or more processors effectuate operations including obtaining a list of service level agreement (SLA) availability values for each of one or more virtual machines (VMs) of a host. The one or more processors further effectuate operations including analyzing the list to determine a maximum availability number for the host. The one or more processors further effectuate operations including identifying a probable overload condition value based on the SLA availability values. The one or more processors further effectuate operations including performing at least one recommended action when the probable overload condition value exceeds an SLA before an occurrence of an overload condition.

Cloud oversubscription system

A cloud oversubscription system comprising an overload detector configured to model a time series of data of at least one virtual machine on a host as a vector-valued stochastic process including at least one model parameter, the overload detector communicating with an inventory database, the overload detector configured to obtain an availability requirement for each of the at least one virtual machine; a model parameter estimator communicating with the overload detector, the model parameter estimator communicating with a database containing resource measurement data for at least one virtual machine on a host at a selected time interval, the model parameter estimator is configured to estimate the at least one model parameter from the resource measurement data; a loading assessment module communicating with the model parameter module to obtain the at least one model parameter for each of the at least one host running at least one virtual machine and determine a probability of overload based on the at least one model parameter, wherein the loading assessment module communicates the probability of overload to the overload detector; wherein the overload detector compares the probability of overload to the availability requirement to identify a probable overload condition value; and wherein the overload detector communicates the probable overload condition value to a recommender, wherein the recommender generates an alert when the overload condition value exceeds the service level agreement requirements for any of the at least one virtual machine.

Growing community of inventors

San Ramon, CA, United States of America

Imad Ahmad