ML/SDN-Based MEC Resource Management for QoS Assurances

seyha daily



    Part of the Lecture Notes in Electrical Engineering book series (LNEE,volume 1028)


    Abstract

    Mobile edge computing (MEC) extracts the resource closer to end users; however, resource orchestration and management are still mentioned as the important issues. We propose the software-defined networking (SDN) technique to provide the control management based on the centralized global controller. The benefits of the SDN involvement for flexibility and efficient MEC resources management will be gained. In this paper, the MEC resource will be coordinated by SDN, in order to provide the efficient operation for MEC resources in the network. Moreover, we present the benefits of SDN within the heterogeneous Internet of Things (HetIoTs) in order to provide the effective quality of services (QoS) for massive traffic. With the overview of resourceful HetIoTs data-driven in 5G and the adoption of MEC-SDN benefits, the proposed approach presents the study with K-Mean-based assistance. Since the user traffic will be waiting for serving or disconnecting when there are insufficient resources in the packet data gateway (PGW). In this mentioned issue, priority queuing has been proposed to tackle network congestion problems in IP networking. In this paper, we also propose and employ priority queueing to backhaul network to manage the users’ traffic in PGW. Based on K-Mean clustering algorithm, this approach possibly classifies the communication types and allows priority queue to schedule the traffic effectively. The main goal is to reduce network congestion by improving QoS and 5G network performance.

    Keywords

    • Quality of service
    • Software-defined networking
    • Mobile edge computing
    • K-mean
    • Resource management

    Acknowledgements

    This work was supported by BK21 FOUR (Fostering Outstanding Universities for Research) under Grant 5199990914048.

    Author information

    Authors and Affiliations

    1. Department of Software Convergence, Soonchunhyang University, Asan, Korea

      Seyha Ros, Chanthol Eang, Prohim Tam & Seokhoon Kim

    2. Department of Computer Software Engineering, Soonchunhyang University, Asan, Korea

      Seokhoon Kim

    Corresponding author

    Correspondence to Seokhoon Kim .

    Editor information

    Editors and Affiliations

    1. Department of Computer Science and Engineering, Jeonju University, Jeonju-si, Korea (Republic of)

      Ji Su Park

    2. Department of Computer Science, St. Francis Xavier University, Antigonish, NS, Canada

      Laurence T. Yang

    3. Department of Computer Science, Georgia State University, Atlanta, USA

      Yi Pan

    4. Department of Computer Science and Engineering, Seoul National University of Science and Technology, Seoul, Korea (Republic of)

      Jong Hyuk Park

    Rights and permissions

    Reprints and Permissions

    Copyright information

    © 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

    About this paper

    Check for updates. Verify currency and authenticity via CrossMark

    Cite this paper

    Ros, S., Eang, C., Tam, P., Kim, S. (2023). ML/SDN-Based MEC Resource Management for QoS Assurances. In: Park, J.S., Yang, L.T., Pan, Y., Park, J.H. (eds) Advances in Computer Science and Ubiquitous Computing. CUTECSA 2022. Lecture Notes in Electrical Engineering, vol 1028. Springer, Singapore. https://doi.org/10.1007/978-981-99-1252-0_79

    Download citation

    • DOIhttps://doi.org/10.1007/978-981-99-1252-0_79

    • Published

    • Publisher NameSpringer, Singapore

    • Print ISBN978-981-99-1251-3

    • Online ISBN978-981-99-1252-0

    • eBook PackagesEngineeringEngineering (R0)

    0 Comments