Real-time server capacity optimization tool using maximum predicted value of resource utilization determined based on historica data and confidence interval

Abstract

A system includes a server associated with a resource utilization, a database storing historical data including resource utilization values over a first time period, and a processor. The processor identifies, from the historical data, a maximum resource utilization value and determines a duration of time for which the resource utilization exceeds a percentage of the maximum. The processor predicts, based on the historical data, a maximum predicted resource utilization value over a second time period, later than the first. The processor also determines, based on the historical data, an upper bound of a resource utilization confidence interval. The processor generates, based on the maximum value over the first time period, the duration of time, the maximum predicted value over the second time period, and the upper bound, a recommendation to consolidate the server with a second server and/or to release computational resources. The processor transmits the recommendation to an administrator.