Masters Thesis

Permanent URI for this collection

https://dspace.nstu.ac.bd/handle/123456789/95

Browse

Browsing Masters Thesis by Author "ISHTIAQ AHAMMAD"

Now showing 1 - 1 of 1
  • No Thumbnail Available
    Item
    COMBINING CLOUD, FOG, ROOF AND DEW COMPUTING WITH SDN TO IMPROVE QoS OF IoT ECOSYSTEM
    (2021-01-20) ISHTIAQ AHAMMAD
    Recently, there's been a growing curiosity in the Internet of Things (IoT), due to the ubiquitous existence of the internet. Such curiosity leads the concept of IoT ecosystem. But contemporary fragmented ecosystem of regulations, technologies, and systems slows IoT deployments. Because they typically concentrate on a particular use case, or are confined to a specific standard. Therefore, an IoT ecosystem which encompasses all the elements (i.e. remote controls, dashboards, communications, access points, analytics, data management, security etc.) to enable companies, governments, and users to seamlessly connect their IoT devices to the existing ecosystem framework to receive services is a necessity. But some concerns in this ubiquitous IoT ecosystem infrastructure may end up making its development a really difficult task. Thus in this paper multi-tiered computational infrastructure is considered which would be feasible to provide services from the nearest possible location of end-user devices and thus fix most of the difficulty issues. However, bringing computational infrastructures to user surroundings doesn't really automatically address all technological challenges. It also generates complications of its own if it is not properly managed. Therefore, this paper takes into account Software-Defined Networking (SDN) as a solution. SDN has shown its utility in lessening the complications of management in today's networks. Now to understand the journey behind SDN-supported multi tier computational infrastructure; elaborate study on cloud, fog, roof, and dew computing and their interaction with SDN is performed in this paper. Then two novel methods are presented to improve QoS in an IoT ecosystem. In “Method I”, a novel architecture is proposed to combine independently researched areas of SDN and Fog Computing to improve QoS. In support of the architecture, there is also a proposed algorithm based on Virtual Partition for optimal access point and optimal place of operation selection. The “Method II” presents SD-DRFC framework architecture for today's IoT ecosystem which combines Cloud, Fog, Roof and Dew computing domains which are managed by SDN. The novelty of this SD-DRFC framework lies in its ability to deliver services from the nearest possible location, manage data routing pathways individually for various types of data, efficiently balance huge data traffic on the network, offer limited services without internet connection, and distribute network and computing resources appropriately. Next simulation setup is performed for both of these proposed methods. For simulation, a use case is defined for each method which is identical to the proposed methods architecture. These simulation setups are performed on iFogSim simulator. The result shows a significant improvement of several QoS parameters in the execution of proposed methods compared to the cloud-only execution. In specific, the simulation result of “Method I” offers much better results for energy consumption, network usage and latency compared with previous similar approaches. The result shows a 275.9% reduction in latency and a 212.21% reduction in network usage. For both “Method I” and “Method II”; the simulation results justify major improvement in some QoS parameter in favor of the proposed methods. Since these parameters are the most significant ones in an IoT ecosystem; hence their improvement indicates overall QoS improvement of IoT ecosystem.