THESIS
2019
xiii, 100 pages : illustrations ; 30 cm
Abstract
Accurate traffic and latency measurements are the foundation of many network management
tasks, including traffic engineering and network provision, network diagnosis and fault
recovery. However, SNMP-based traffic measurement techniques in traditional IP networks
only provide measurements for link loads, which cannot lead to accurate measurements. For
link latency measurement, it has been shown that a traditional IP network needs to deploy a
large number of monitors to achieve accurate measurements.
The software-defined network (SDN) architecture opens up new opportunities to tackle
the traffic matrix estimation and latency measurement problems. For the traffic estimation
problem, the counter in a flow table entry of an SDN switch can directly measure the size of
a matched flow...[
Read more ]
Accurate traffic and latency measurements are the foundation of many network management
tasks, including traffic engineering and network provision, network diagnosis and fault
recovery. However, SNMP-based traffic measurement techniques in traditional IP networks
only provide measurements for link loads, which cannot lead to accurate measurements. For
link latency measurement, it has been shown that a traditional IP network needs to deploy a
large number of monitors to achieve accurate measurements.
The software-defined network (SDN) architecture opens up new opportunities to tackle
the traffic matrix estimation and latency measurement problems. For the traffic estimation
problem, the counter in a flow table entry of an SDN switch can directly measure the size of
a matched flow. This dramatically increases the number and type of flows that can be
measured accurately. For link latency measurement, SDN switches provide flexible routing
and hence allow even non-shortest paths to be measured in the network. This routing
flexibility can reduce the number of monitors deployed in the network to achieve a complete
measurement of all the link latencies.
But the additional measurement capabilities of SDNs also have limitations: the flow table
entries added for measurements must be limited due to the high cost of ternary content-addressable
memory (TCAM), and the amount of additional traffic for measurement should
also be confined. Under these constraints, this research investigates the traffic matrix estimation and link latency measurement problems for a pure SDN network and a hybrid SDN
network. A hybrid network, which consists of SDN switches and conventional routers, will
exist for some time to come since it is economically impossible to replace every conventional
router overnight. For the traffic matrix estimation problem, we propose a new estimation
framework, which can be used in both SDNs and hybrid SDNs. Performance evaluation
results show that the new framework can achieve highly accurate traffic measurement with a
small number of TCAM entries. For the link latency measurement problem, we first present
minimum monitor placement schemes in hybrid SDNs. It has been shown that our schemes
not only reduce the number of required monitors but also guarantee full link measurements
even when link weights change. We then present two time-stamp-based link latency
measurement schemes for pure SDNs and show that the proposed schemes can minimize the
number of consumed TCAM entries and the amount of traffic generated for measurement.
Post a Comment