Dynamic Route Computation for Big Data using SDN

In current scenario, the world is connected by different heterogeneous links such as Ethernet, WAN and InfiniBand etc. transferring billions of packets. The path of a data packet from the source to destination is usually based on shortest path irrespective of connection speeds. And in real world, th

Project Title

Dynamic Route Computation for Big Data using SDN

Project Area of Specialization

Cloud Infrastructure,

Project Summary

In current scenario, the world is connected by different heterogeneous links such as Ethernet, WAN and InfiniBand etc. transferring billions of packets. The path of a data packet from the source to destination is usually based on shortest path irrespective of connection speeds. And in real world, there exists some application specific critical data which need to be transmitted using high speed links to be completed as soon as possible. Hence, the objective of this research project is to help large organizations which analyze Big Data, so that they can route application specific data in least possible time using high speed links.

In order to achieve the above-mentioned objective, we are developing an intelligent networking environment that is smart enough to route the incoming packets based on their priorities in heterogeneous environment of InfiniBand and Ethernet using SDN considering response time as metric for packet's transmission. In our project, we will deploy a Software Defined Network (SDN) with heterogeneous connections such as Ethernet and InfiniBand having different speed. The SDN controller can be deployed on cloud as well. InfiniBand will give us the speed of 56 Gbps, which is capable to meet requirements for large data centers and cloud infrastructure. We are implementing the routing framework algorithm that tries to find the route with high speed connection considering the priority of a packet. Our focus is to minimize the response time for packet transmission in Big Data.

Project Objectives

Data centers and large organizations usually consist of different heterogeneous network connections, so this research will help the high priority packets to be transferred in minimum amount of time regardless of the connection type when analyzing Big Data. Hence, the objective of this research project is to help large organizations to route application specific data in least possible time using high speed links.

Secondly, this project will help the Service Level Agreement (SLA) applications where a service provider can help its customers to give priority to their application’s data.

And finally when we talk about the concept of smart city, where there is Big Data and whole implementation is based on cloud infrastructure, then there are different priority applications and each of them requires different bandwidth and speed, then this research will help these applications to solve their path selection problem.  

Project Implementation Method

To solve the problem of critical high priority applications to be transferred first when analyzing Big Data, we will propose and implement the forwarding algorithm but in addition to this, we will deploy a software defined network (SDN) with a centralized controller having heterogeneous links (InfiniBand and Ethernet) which will examine every incoming packet into the network and tries to find out its importance and priority. Based on result, it will calculate suitable route for the packet.

The system consists of SDN controller which in future can be deployed on cloud, OpenFlow switches, InfiniBand links, Ethernet links and packet generator. The packet generator will generate different packet of different priorities and send them to the OpenFlow switch. The OpenFlow switch than ask the SDN controller from where to forward the incoming packets. The controller will evaluate the path using Protocol and send the instruction to the OpenFlow switch. The packet will be then transferred to the specified route based on their priority. The packet with the higher priorities will reach the destination first. All switches will be OpenFlow switches and they will be connected to the controller for the instruction.

Benefits of the Project

Firstly, this project will benefit the application of Service Level Agreement (SLA) where a service provider can help its customers to give priority to their application’s data. In today’s era, most of the applications are following cloud infrastructure.

Secondly, this project will help the large organizations and data centers to route application specific data in least possible time using high speed links when forwarding their Big Data.

Thirdly, this project is a research approach for smart city applications where we can route data based on their priority. The smart city concept is totally based on Big Data and cloud infrastructure.

And finally, when there is requirement to route data based on application priority, then this project will be of great benefit.

Technical Details of Final Deliverable

The final deliverable of our project would be a Research Paper/Report that will contain the system architecture, pseudo-code of our forwarding algorithm and the results of our intelligent networking routing environment setup conducted through our proposed forwarding alogorithm.

Final Deliverable of the Project

HW/SW integrated system

Type of Industry

IT

Technologies

Cloud Infrastructure, Big Data

Sustainable Development Goals

Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com