Satish Raghunath

Resource Management for Virtual Private Networks

Virtual private networks (VPNs) have rapidly emerged as a leading solution for multi-site enterprise communication needs. Provider-managed solutions modeled on RFC 2547 serve as a popular choice for layer 3 VPNs, and the hose model has emerged as a common and simple service specification. It offers a hose of a certain contracted bandwidth to customers. With the growth in size and number of VPNs and the uncertainties in the traffic patterns of customers, providers are faced with new challenges in efficient provisioning and capacity planning for these networks and satisfying customer service level agreements (SLA). We suggest that a set of techniques can be used to help the provider build an adaptively provisioned network. These techniques involve continually processing measurement information, building inferences regarding VPN characteristics, and leveraging them for adaptive resource provisioning. We developed scalable techniques to infer VPN characteristics that are important for provisioning tasks. We demonstrated the feasibility of such provisioning techniques with existing measurement obtained using SNMP infrastructure from a large IP/VPN service provider. Our examination of measurement data yielded interesting new insights into VPN structure and properties. Building on our experience with analyzing VPN characteristics, we articulate an adaptive provisioning architecture that enables providers to effectively deal with the dynamic nature of customer traffic

Measurement-based characterization of IP VPNs

Virtual private networks (VPNs) provide secure and reliable communication between customer sites. With the increase in number and size of VPNs, providers need efficient provisioning techniques that adapt to customer demand by leveraging a good understanding of VPN properties. In this paper, we analyze two important properties of VPNs that impact provisioning: (1) structure of customer endpoint (CE) interactions and (2) temporal characteristics of CE-CE traffic. We deduce these properties by computing traffic matrices from SNMP measurements. We find that existing traffic matrix estimation techniques are not readily applicable to the VPN scenario due to the scale of the problem and limited measurement information. We begin by formulating a scalable technique that makes the most out of existing measurement information and provides good estimates for common VPN structures. We then use this technique to analyze SNMP measurement information from a large IP VPN service provider. We find that even with limited measurement information (no per-VPN data for the core) we can estimate traffic matrices for a significant fraction of VPNs, namely, those constituting the ldquoHub-and-Spokerdquo category. In addition, the ability to infer the structure of VPNs holds special significance for provisioning tasks arising from topology changes, link failures and maintenance. We are able to provide a classification of VPNs by structure and identify CEs that act as hubs of communication and hence require prioritized treatment during restoration and provisioning.

Quantifying trade-offs in resource allocation for VPNs

Virtual Private Networks (VPNs) feature notable characteristics in structure and traffic patterns that allow for efficient resource allocation. A strategy that exploits the underlying characteristics of a VPN can result in significant capacity savings to the service provider.There are a number of admission control and bandwidth provisioning strategies to choose from. We examine trade-offs in design choices in the context of distinctive characteristics of VPNs. We examine the value of signaling-based mechanisms, traffic matrix information and structural characteristics of VPNs in the way they impact resource utilization and service quality. We arrive at important conclusions which could have an impact on the way VPNs are architected. We show that the structure of VPNs profoundly influences achievable resource utilization gains with various admission control and provisioning schemes.