This flows across available paths using flow hashing

Published by admin on

article discusses the best in class in traffic engineering for SDN with
attention to four cores including flow management, fault tolerance, topology
update, and traffic analysis. The challenging issues for SDN traffic
engineering solutions are talked about in detail. SDN is a developing
networking administration that isolates the network control plane from the data
sending plane with the guarantee to significantly enhance organize asset usage,
streamline network management, reduce working expenses, and promote development
and advancement. For network performance optimization by dynamically analyzing,
predicting, and regulating the behavior of the transmitted data, traffic
engineering is an important subject. Over the last two decades traffic
engineering has been exploited in asynchronous transfer mode(ATM) and
IP/multiprotocol label switching(MPLS). The existing traffic engineering
technologies rely on closed and firm architectural design, where the control
and data planes are firmly coupled and coordinated. The inflexibility and the
closed nature of the architecture prevents the existing traffic engineering
technologies to provide differentiated services that would adapt to
increasingly growing uneven and highly variable traffic patterns. Coming back
to the four cores flow management, fault tolerance, topology update, and
traffic analysis: Starting of with the flow management, in SDN the significant
overhead at both control and data planes caused when an OF switch receives a
new flow that doesn’t match any rule in its flow entry. To overcome the bottle
neck in SDN solution are discussed in the paper, by considering the balance
between latency and load balancing at the data plane and control plane. In load
balancing for the data plane, two methods are followed: Hash-Based ECMP Flow
Forwarding and Wildcard Rule Flow Forwarding. The hash-based Equal-Cost
Multi-Path(ECMP) is a load balancing scheme to distribute flows across
available paths using flow hashing methods. This solution can improve the band
width and processing overhead at the switches. In wildcard rule flow forwarding
to aggregate traffic flows, OF switches use flow match wild cards. In load
balancing for the control plane SDN may cause the network controller to become
a potential performance bottleneck, to overcome this controller load balancing
schemes have been used. They are logically centralized and physically
distributed controller, physically distributed controller, hierarchical
controller, hybrid controller, multithread controllers and generalized
controllers. The multithread controllers are developed to improve the request
processing throughput. The parallelism architecture of servers is used to
provide high throughput with scalability at the controllers in multithread
multicore SDN controllers. The research challenges in flow management are dynamic
load balancing scheme for the data plane and dynamic load balancing scheme for
the control plane. Now coming to the second core i.e. fault tolerance: for
ensuring the reliability of the network, SDN must be able to perform the
failure recovery straight forwardly and effortlessly when a failure occurs in
the network. Even though a switch could be used in such a failure, it has
neither the insight nor the information to make new route. For this it has to
depend on the controller. In this manner, we discuss the research efforts on
fast failure recovery in SDN networks. For fault tolerance in the data plane we
have two failure recovery mechanisms, which are restoration and protection. In restoration,
the recovery path can be pre-planned or dynamically designated. Whereas in
protection the recovery path must be pre-planned and reserved before the
failure occurs. Taking the bandwidth and latency factors into consideration,
for larger SDN systems the protection solution is used for faster failure

the control plane the fault tolerance is an important factor to maintain the
efficiency of the network. A single point failure can cause an entire network
to degrade. The primary-backup replication method is the most fundamental
method used in the recovery process of the control plane. The OF protocol do
not have any coordination mechanisms for the primary and backup controllers to
use. For this reason, the coordination protocols are wanted. In the deployment
of the backup controller, properly placing the backup controllers in the SDN we
can increase the network reliability. There are mainly two research challenges in the
fault tolerance, they are cost-efficient and fast failure recovery for the data
plane and primary-backup replication with the traffic adaptivity for the
control plane. Now coming to the third core i.e. topology update. In the
topology update pre-planned changes like network policy rules change. When
these changes occur, each flow is identified and then it is guaranteed to be
managed by either the old or the new policy. There are two types of consistency:
per-packet consistency and per-flow consistency, which have a common update
operation that is the switches process the packet by following the old or new
policies until the old configuration rules are deleted by the controller. For
the problem which is caused by the duplicate policy scheme we require more efficient
update algorithm for implementing consistent update. The research challenges
that arises during the topology update are a single controller in a large scale
SDN network and multiple controllers in multi-domain SDN networks. Now talking
about the fourth or the last core i.e. traffic analysis. In traffic analysis monitoring
the network is significant for the network management. When it comes to SDN
networks, the existing monitoring solutions become less efficient due to the
large-scale nature of the network which effects the central controller.
Query-base and Push-based monitoring are the current solutions available. The
Query-based solution is based on the request or response paradigm, whereas the
Push-based solution is based on publish or subscribe or distribute paradigm. The research challenges
that come up during the traffic analysis are traffic analysis, traffic monitoring
and network checking and programming debugging methods. In this paper, the
investigation is done on the SDN traffic engineering solutions form the various
aspects of flow management, load balancing, fault tolerance, topology update
and traffic analysis. The current state and research difficulties of SDN
traffic engineering are exhibited by the addressing the key SDN execution
measurements as far as scalability, availability, reliability, consistency and

Categories: Management


I'm Iren!

Would you like to get a custom essay? How about receiving a customized one?

Check it out