Software-Defined Data Center Networks for IoT

Softwarized Data data networks and Fat-Tree Architecture-based data center networks for Internet of Things

Data Center Networks (DCNs) are formed by interconnecting different data centers, which are capable of generating huge amount of data with storage facilities. With the advancement of IoT technologies, different devices are capable of generating and processing huge volume of data and introduce challenges such as — hetergenous network configuration, dynamic application requirements, and mobility of the IoT devices. On the other hand, software-defined networking (SDN) is a promising approach to control the network in a unified manner using rule-based management. The abstractions provided by SDN enable holistic control of the network using high-level policies, without being concerned about low-level configuration. Hence, Software-Defined DCN is envisioned to address the heterogeneity and application-specific requirements of IoT in the context of DCN.

We study the impact on DCNs in the presence of IoT devices from different perspectives such as broadcasting and multicasting while ensuring high network throughput and low network delay. Additionally, we analyze the performance bounds of software-defined DCNs for IoT environments.

 

Data-Transmission in Software-Defined DCNs

Broadcasting

In this work, we study the problem of throughput and delay-optimal dynamic big-data broadcast in fat-tree Data Center Networks (DCNs) in the presence of mobile Internet of Things (IoT) devices, where one of the IoT devices acts as a source node. To address the aforementioned problem, we propose a Dynamic Big-Dat Broadcasting scheme, named D2B, using single-leader-multiple-follower Stackelberg game for solving the aforementioned problem, while presenting bandwidth distribution as a pseudo-Cournot competition.
Keywords: Switches, Broadcasting, Bandwidth, Throughput, Big Data, Delays, Multicast communication, bandwidth allocation, Big Data, computational complexity, computer centres, game theory, Internet of Things, optimisation, telecommunication traffic

Read More PDF Citation

Multicasting

In this work, we study the problem of mobility-aware dynamic data multicasting in software-defined Data Center Networks (DCNs) in the presence of Internet of Things (IoT) devices. To address the aforementioned problem, we propose a Dynamic Data Multicasting scheme, named D2M, using single leader multiple follower Stackelberg game for ensuring high utilization of network capacity and efficient load balancing.

Read More PDF Citation
 

Performance Analysis of Software-Defined DCNs

Buffer Size Evaluation

In this work, we address the problem of minimum buffer size evaluation of an OpenFlow system in software-defined networks (SDNs), while ensuring optimum packet waiting time. To address the aforementioned problem, we propose an analytical scheme for buffer bound evaluation of an OpenFlow system, named OPUS. Additionally, we propose a queuing scheme for an OpenFlow system - C-M/M/1/K/∞ queuing model-based on the OpenFlow specification version 1.5.0. Further, we calculate the minimum buffer size requirement of an OpenFlow switch, theoretically.

Read More PDF Citation

Probabilistic Performance Bounds

In this work, we address the problem of defining probabilistic bounds of packet flow through an OpenFlow switch in software-defined networks (SDNs). To address the aforementioned problem, we propose Markov chain-based analytical model, named AMOPE, for analyzing packet flow through an OpenFlow switch, while defining the probabilistic bounds on performance analysis. Additionally, in AMOPE, we propose a state diagram based on the OpenFlow specification version 1.5.0, and calculate the theoretical probabilities of a packet to be in different states of the OpenFlow switch. Furthermore, AMOPE defines the theoretical bounds of OpenFlow performance measures such as the output action, packet drop, and send to the controller probabilities.

Read More PDF Citation