Abstract:Desktop Cloud computing is the idea of benefiting from computing resources around us to build a Cloud system in order to have better usage of these resources instead of them being idle. However, such resources are prone to failure at any given time without prior knowledge. Such failure events have a can negative impact on the outcome of a Desktop Cloud system. This paper proposes metrics that can evaluate the behaviour of Virtual Machine (VM) allocation mechanisms in the presence of node failures. The metrics are throughput, power consumption and availability. Three VM allocation mechanisms (Greedy, FCFS and RoundRobin mechanisms) are evaluated using the given metrics.