International Business Machines Corporation

Harish Nayak

Ankur Tagra

Rajat R Verma

An approach is provided in which an information handling system uses historical time durations of deprecated resources to compute an increased probability window. The increased probability window corresponds to an increase in probability that a currently active resource is likely to be active at a future point in time. Next, the information handling system identifies a set of active resources that have active time durations within the increased probability window and, in turn, marks the set of resources as a set of forecasted active resources. In turn, the information handling system generates a resource cost forecast based on the set of forecasted active resources.

Cognitive detection of cloud service forecast

A method for detecting cloud service uptime for a cloud service on a cloud service provider, by means of a cognitive agent. The method includes receiving, by the cognitive agent, a cloud service request from a client, and determining the cloud service uptime based on a cloud service uptime model. The method further includes preventing the cloud service request from the client if it is determined that the cloud service uptime exceeds a given threshold, and transmitting, by the cognitive agent, cloud service uptime details to the client. The method further includes requesting a provisioning of a cloud service if it is determined that the cloud service uptime does not exceed the given threshold. The method further includes training, by the cognitive agent, the cloud service uptime model based on a dynamic polling of the cloud service, wherein the cloud service uptime model provides an optimal response to the client.

Growing community of inventors

Bengaluru, India

Harish Nayak