Server Utilization Methodology

My uncle’s company has a huge quantity of servers that are underutilized. His firm has “poked & sniffed” around only to determine that most are being used at 20% or less utilization.

They can save money if they reduce the number of servers needed – and use the freed up machines for new initiatives. If I can, I’d like to get in on the action and “piggyback” more than one application on these machines.

Do you have any idea where I can get some generic background on Server Utilization Methodology?