08-10-2012, 03:12 PM
Measuring Capacity Bandwidth of Targeted Path Segments
Measuring Capacity.doc (Size: 38.5 KB / Downloads: 29)
Abstract
In this project we are going to measure the bandwidth capacity between specified path segments in a distributed network Accurate measurement of network bandwidth is important factor for network management applications as in intranet applications and protocols which are actively manage and dynamically adapt to varying consumption of network resources. The existing work is focused on two approaches to measuring bandwidth capacity of the network are: calculating It by hop-by-hop, and measuring it end-to-end along a specified path of a distributed network. Unfortunately, the existing systems are inefficient and techniques we are going to propose are only able to observe bottlenecks visible at end-to-end scope. In this project, we develop end-to-end probing methods which can measure bottleneck capacity bandwidth along arbitrary, targeted sub paths of a path in the network, including sub paths shared by a set of flows. We are going to calculate the bandwidth capacity through ns simulations, and then provide a comparative Intranet performance evaluation against hop-by-hop and end-to-end techniques.
Existing System
Measurement of network bandwidth is important for many Intranet applications and protocols, especially those involving the transfer of small and large files and those involving the delivery of content with real-time QoS constraints, such as streaming media. Some existing systems can leverage accurate bandwidth estimation include end-system multicast and overlay network configuration protocols, content location and delivery in peer-to-peer (P2P) networks, network-aware cache or replica placement policies , and flow scheduling and admission control policies at massively-accessed content servers. In addition, accurate measurements of network bandwidth are useful to network operators concerned with problems such as capacity provisioning, traffic engineering, network troubleshooting and verification of service level agreements. Accurate measurement of network bandwidth is important for network management applications as well as flexible Intranet applications and protocols which actively manage and dynamically adapt to changing utilization of network resources. Extensive work has focused on two approaches to measuring bandwidth: measuring it hop-by-hop, and measuring it end-to-end along a path. Unfortunately, best-practice techniques for the former are inefficient and techniques for the latter are only able to observe bottlenecks visible at end-to-end scope
Proposed system
We develop end-to-end probing methods which can measure bottleneck capacity bandwidth along arbitrary, targeted sub paths of a path in the network, including sub paths shared by a set of flows. We evaluate our technique through ns simulations, and then provide a comparative Internet performance evaluation against hop-by-hop and end-to-end techniques. We also describe a number of applications which we foresee as standing to benefit from solutions to this problem, ranging from network troubleshooting and capacity provisioning to optimizing the layout of application-level overlay networks, to optimized replica placement. In classifying bandwidth measurement techniques, one can also look at the probing methodology employed—namely, the number and sizes of packets in a probe. Probe structures considered in the literature include: (1) single packet probing (2) packet bunch probing, employing a group of packets sent back-to-back (3) uniform packet-pair probing, employing two back-to-back packets of the same size and (4) non-uniform packet-pair probing, employing two back-to-back packets of different sizes.
Measuring Capacity.doc (Size: 38.5 KB / Downloads: 29)
Abstract
In this project we are going to measure the bandwidth capacity between specified path segments in a distributed network Accurate measurement of network bandwidth is important factor for network management applications as in intranet applications and protocols which are actively manage and dynamically adapt to varying consumption of network resources. The existing work is focused on two approaches to measuring bandwidth capacity of the network are: calculating It by hop-by-hop, and measuring it end-to-end along a specified path of a distributed network. Unfortunately, the existing systems are inefficient and techniques we are going to propose are only able to observe bottlenecks visible at end-to-end scope. In this project, we develop end-to-end probing methods which can measure bottleneck capacity bandwidth along arbitrary, targeted sub paths of a path in the network, including sub paths shared by a set of flows. We are going to calculate the bandwidth capacity through ns simulations, and then provide a comparative Intranet performance evaluation against hop-by-hop and end-to-end techniques.
Existing System
Measurement of network bandwidth is important for many Intranet applications and protocols, especially those involving the transfer of small and large files and those involving the delivery of content with real-time QoS constraints, such as streaming media. Some existing systems can leverage accurate bandwidth estimation include end-system multicast and overlay network configuration protocols, content location and delivery in peer-to-peer (P2P) networks, network-aware cache or replica placement policies , and flow scheduling and admission control policies at massively-accessed content servers. In addition, accurate measurements of network bandwidth are useful to network operators concerned with problems such as capacity provisioning, traffic engineering, network troubleshooting and verification of service level agreements. Accurate measurement of network bandwidth is important for network management applications as well as flexible Intranet applications and protocols which actively manage and dynamically adapt to changing utilization of network resources. Extensive work has focused on two approaches to measuring bandwidth: measuring it hop-by-hop, and measuring it end-to-end along a path. Unfortunately, best-practice techniques for the former are inefficient and techniques for the latter are only able to observe bottlenecks visible at end-to-end scope
Proposed system
We develop end-to-end probing methods which can measure bottleneck capacity bandwidth along arbitrary, targeted sub paths of a path in the network, including sub paths shared by a set of flows. We evaluate our technique through ns simulations, and then provide a comparative Internet performance evaluation against hop-by-hop and end-to-end techniques. We also describe a number of applications which we foresee as standing to benefit from solutions to this problem, ranging from network troubleshooting and capacity provisioning to optimizing the layout of application-level overlay networks, to optimized replica placement. In classifying bandwidth measurement techniques, one can also look at the probing methodology employed—namely, the number and sizes of packets in a probe. Probe structures considered in the literature include: (1) single packet probing (2) packet bunch probing, employing a group of packets sent back-to-back (3) uniform packet-pair probing, employing two back-to-back packets of the same size and (4) non-uniform packet-pair probing, employing two back-to-back packets of different sizes.