Research Papers - Dept of Computer Systems Engineering

Permanent URI for this collection https://rda.sliit.lk/handle/123456789/1253

Browse

Filters

2018 - 201932020 - 20213

Advanced Search

Filter by

Settings

Has files: YesSubject: search.filters.subject.Platform

Search Results

Now showing 1 - 6 of 6
  • Thumbnail Image
    PublicationEmbargo
    Traffic Monitoring Related Experimental Study for a Software-Defined Network Based Virtualized Security Functions Platform
    (IEEE, 2021-12-01) Gamage, T. C. T.; Rankothge, W. H.; Gamage, N. D. U.; Jayasinghe, D; Uwanpriya, S. D. L. S.; Amarasinghe, D. A.
    Cloud computing and virtualization technologies are rapidly evolving with new capabilities being added all the time. Security Functions Virtualization (SFV) is the latest addition to cloud services, where Virtualized Security Functions (VSFs) are offered as services by Cloud Service Providers (CSPs). CSPs are focusing more on implementing effective resource management approaches for the cloud infrastructure, considering specific requirements of VSFs. Network traffic monitoring is one of the most crucial aspects of cloud resource management, as monitoring helps CSPs to have a global view of the resource utilization and take necessary proactive management actions, specifically for VSFs.This experimental study focuses on exploring network traffic and resource monitoring for the traffic traverse via a cloud platform where VSFs are offered as a service. We have considered two approaches: periodic monitoring and continuous monitoring. The network traffic is monitored continuously, and resource utilization is monitored periodically. With the implemented monitored framework, CSPs are able to take proactive decisions on resource management, specially towards scale-out/in decisions and security management.
  • Thumbnail Image
    PublicationEmbargo
    NetEye: Network Monitoring for a Software Defined Network based Virtualized Network Functions Platform
    (IEEE, 2021-12-01) Rankothge, W. H; Gamage, N. D. U; Ariyawansa, M. M. T. R; Suhail, S. A. A; Dewwiman, H. G. H.; Senevirathne, M. D. B. P
    With the introduction of Virtualized Network Functions Virtualization (VNFs), Cloud Service Providers (CSPs) allocate resources and deploy network functions as virtualized entities in the cloud. With the dynamic changes in the traffic and workload, initially allocated resources have to be increased or decreased to maintain the Service Level Agreement (SLA). Therefore, CSPs rely on network monitoring approaches to maintain an effective and efficient resource management process. However, the monitoring process itself creates an overhead to the performance of the network. Monitoring algorithms consume the CPU and memory resources of the cloud infrastructure during their execution. Therefore, selecting an appropriate monitoring approach is important, especially in a resource-constrained network. In this research, we have explored two monitoring approaches: continuous and periodic, and compared their performances in terms of memory and CPU utilization.
  • Thumbnail Image
    PublicationEmbargo
    Network Traffic Prediction for a Software Defined Network Based Virtualized Security Functions Platform
    (IEEE, 2021-12-06) Jayasinghe, D; Rankothge, W. H; Gamage, N. D. U; Gamage, T. C. T; Amarasinghe, D. A. H. M; Uwanpriya, S. D. L. S
    Software-Defined Networking (SDN) has become a popular and widely used approach with Cloud Service Providers (CSPs). With the introduction of Virtualized Security Functions (VSFs), and offering them as a service, CSPs are exploring effective and efficient approaches for resource management in the cloud infrastructure, considering specific requirements of VSFs. Network traffic prediction is an important component of cloud resource management, as prediction helps CSPs to take necessary proactive management actions, specifically for VSFs. This research focuses on introducing an algorithm to predict the network traffic traverse via a cloud platform where VSFs are offered as a service, by using the Auto-Regressive Integrated Moving Average (ARIMA) model. In this paper, the implementation and performance of the traffic prediction algorithm are presented. The results show that the network traffic in cloud environments can be effectively predicted by using the introduced algorithm with an accuracy of 96.49%.
  • Thumbnail Image
    PublicationEmbargo
    Lighthouse-Smart Virtual Learning Platform
    (IEEE, 2018-10-02) Abeyrathne, P. K. R. R. I; Sarathchandra, B. R. I. D; Hewavitharana, D. T. R; Perera, L. M. D; Wijesundara, M
    This paper presents the design, development and performance evaluation of a new virtual learning platform. The novel features in this platform include real-time transcribing of live lectures conducted in English and the ability to search recorded lectures based on keywords mentioned during the lectures. This is in addition to real-time streaming and archiving of nine channels of information namely; audio, subtitles, video, slide synchronization, code editor, whiteboard, chat, polls and emotion. The system provides a number of novel features to ease the lecturer's workload. These include one touch recording, real-time polling, real-time emotion detection of students, and cloud based lecture editor allowing editing of each of the nine channels. From an operational perspective, the system requires no additional or special hardware other than a laptop, and it uses cloud based streaming and storage, eliminating the need for a dedicated infrastructure.
  • Thumbnail Image
    PublicationEmbargo
    Policies Based Container Migration Using Cross-Cloud Management Platform
    (IEEE, 2018-12-21) Janarthanan, K; Peramune, P. R. L. C; Ranaweera, A. T; Krishnamohan, T; Rupasinghe, L; Sampath, K. K; Liyanapathirana, C
    Over the last decade, cloud computing has helped in variety of ways to humanity. Mainly in the ways of, achieving Disaster Recovery (DR) and in protecting the end users' data and Anywhere, Any device, Anytime access to the users' data. This research further helps people and organization to overcome common problems related to clouds such as, vendor-lock in and legal regulation. In today's world, more and more organizations are adopting the cloud services mainly because of the reliability and affordability provided by them. However, there are several drawbacks faced by the cloud users and cloud service providers. Apart from the security perspective, the cloud users are facing challenges in control and visibility, lack of standard service interfaces, difficulty in deploying applications across multiple clouds and vendor lock-in. Also, cloud service providers are facing challenges in degradation of the quality of service provided because of the distance between cloud data center and the end user and unexpected interruption of services etc. The above problems can be reduced to a greater extent or mitigated by adopting Multi Cross Cloud Infrastructure. This benefits the cloud users to receive the best quality services to increase their productivity. Hence, the main aim of this research is to build a common platform to manage the cross-cloud environment particularly Microsoft AZURE cloud and Amazon Web Services (AWS) with multiple features such as policies based container migration among the clouds and finding the best virtual machines (VM) across the clouds to deploy new containers. Cross-cloud management platform can be implemented within an organization or Enterprise and is used by the 3rd level support team such as Infrastructure team to provide multiple services (E.g. - Delivering application containers, Migration of containers on request) to end users based on some service level agreements (SLA) with more control and visibility.
  • Thumbnail Image
    PublicationEmbargo
    Policies based container migration using cross-cloud management platform
    (IEEE, 2018-12-21) Janarthanan, K; Peramune, P. R. L. C; Ranaweera, A. T; Krishnamohan, T; Rupasinghe, L; Sampath, K. K; Liyanapathirana, C
    Over the last decade, cloud computing has helped in variety of ways to humanity. Mainly in the ways of, achieving Disaster Recovery (DR) and in protecting the end users' data and Anywhere, Any device, Anytime access to the users' data. This research further helps people and organization to overcome common problems related to clouds such as, vendor-lock in and legal regulation. In today's world, more and more organizations are adopting the cloud services mainly because of the reliability and affordability provided by them. However, there are several drawbacks faced by the cloud users and cloud service providers. Apart from the security perspective, the cloud users are facing challenges in control and visibility, lack of standard service interfaces, difficulty in deploying applications across multiple clouds and vendor lock-in. Also, cloud service providers are facing challenges in degradation of the quality of service provided because of the distance between cloud data center and the end user and unexpected interruption of services etc. The above problems can be reduced to a greater extent or mitigated by adopting Multi Cross Cloud Infrastructure. This benefits the cloud users to receive the best quality services to increase their productivity. Hence, the main aim of this research is to build a common platform to manage the cross-cloud environment particularly Microsoft AZURE cloud and Amazon Web Services (AWS) with multiple features such as policies based container migration among the clouds and finding the best virtual machines (VM) across the clouds to deploy new containers. Cross-cloud management platform can be implemented within an organization or Enterprise and is used by the 3rd level support team such as Infrastructure team to provide multiple services (E.g. - Delivering application containers, Migration of containers on request) to end users based on some service level agreements (SLA) with more control and visibility.