In modern virtualization based compute clouds, applications share the underlying hardware by running in isolated Virtual Machines (VMs). Each VM, during its initial creation, is configured with certain amount of computing resources (such as CPU, memory and I/O). A key factor for achieving economies of scale in a compute cloud is resource provisioning, which refers to allocating resources to VMs to match their workload. Typically, efficient provisioning is achieved by two operations: (1) Static Resource Provisioning: VMs are created with specified size and then consolidated onto a set of physical servers, the VM capacity does not change; and (2) Dynamic Resource Provisioning: VM capacity is dynamically adjusted to match workload fluctuations. In both static and dynamic provisioning, VM sizing is perhaps the most vital step. VM sizing refers to the estimation of the amount of resources that should be allocated to a VM. The objective of VM sizing is to ensure that the VM capacity commensurate with the workload by scheduling. While overbooking wastes costly resources, under-provisioning degrades application performance and may lose customers. In this proposed work, collocated VM provisioning approach is used in which multiple VMs are consolidated and provisioned based on an estimate of their aggregate capacity needs. This work focuses on implementing an autonomic risk-aware overbooking architecture capable of increasing the resource utilization of cloud data centers by accepting more virtual machines than physical available resources. Admission Control and Fuzzy logic functions are used to estimate the associated risk to each overbooking decision.