Open Collections

An industrial internet architecture based on SDN and fog computing

University of British Columbia

In traditional industrial networks, conventional distributed switches adopt traditional optimization algorithms to equally share bandwidth among contending flows, such as transmission control protocol (TCP) congestion control algorithm. However, a large number of machines, goods, control systems and information systems will be interconnected in industrial Internet. As a result, when an emergency occurs, traffic will increase considerably and network congestion will occur. In the worst-case scenario, the machines may not function properly (e.g. some robot-arms cannot respond fast enough to complete the intended tasks). In this thesis, based on the features of software defined network (SDN), network status information of each SDN switch is extracted by an SDN controller through a centralized control architecture. The information is also processed by a fog computing server through network utility maximization fabric (NUMFabric) using the weight max-min fairness algorithm. Our testbed results show that when an emergency occurs, the new architecture can reduce the bandwidth allocation recovery time by more than 350 times that of the traditional TCP. Moreover, by identifying the requirement of industrial Internet and the features of Internet of Things (IoT), an integrated architecture can be designed based on SDN, fog computing, cloud computing, object linking and embedding for process control unified architecture (OPC UA) standard. This thesis includes key aspects of analysis, design and implementation for industrial Internet architecture with short recovery time. It is demonstrated that network entities such as the fog computing server, the SDN Ryu controller, SDN OpenFlow switches and optical sensors can function together. The centralized parameter acquiring method for NUMFabric using the weight max-min fairness algorithm can also perform bandwidth allocation through OPC UA standard and OpenFlow protocol on our testbed.

Text

2018-01-24

Attribution-NonCommercial-NoDerivatives 4.0 International

http://hdl.handle.net/2429/64456

Electrical Engineering

University of British Columbia

UBCO

http://creativecommons.org/licenses/by-nc-nd/4.0/