inis 18: e1

Research Article

Optimisation of Server Selection for Maximising Utility in Erlang-Loss Systems

Download72 downloads
  • @ARTICLE{10.4108/eai.24-10-2019.161367,
        author={Maciej  Pietowski and Quoc-Tuan  Vien and Truong  Khoa  Phan},
        title={Optimisation of Server Selection for Maximising Utility in Erlang-Loss Systems},
        journal={EAI Endorsed Transactions on Industrial Networks and Intelligent Systems: Online First},
        volume={},
        number={},
        publisher={EAI},
        journal_a={INIS},
        year={2019},
        month={11},
        keywords={Utility function, Erlang-Loss System (ELS), Server Selection},
        doi={10.4108/eai.24-10-2019.161367}
    }
    
  • Maciej Pietowski
    Quoc-Tuan Vien
    Truong Khoa Phan
    Year: 2019
    Optimisation of Server Selection for Maximising Utility in Erlang-Loss Systems
    INIS
    EAI
    DOI: 10.4108/eai.24-10-2019.161367
Maciej Pietowski1,*, Quoc-Tuan Vien2, Truong Khoa Phan3
  • 1: Research Computing Services, University of Cambridge, UK
  • 2: Faculty of Science and Technology, Middlesex University, UK
  • 3: Department of Electronic and Electrical Engineering, University College London, UK
*Contact email: Mp929@cam.ac.uk

Abstract

This paper undertakes the challenge of server selection problem in Erlang-loss system (ELS). We propose a novel approach to the server selection problem in the ELS taking into account probabilistic modelling to reflect a practical scenario when user arrivals vary over time. The proposed framework is divided into three stages, including i) developing a new method for server selection based on the M/M/n/n queuing model with probabilistic arrivals; ii) combining server allocation results with further research on utility-maximising server selection to optimise system performance; and iii) designing a heuristic approach to efficiently solve the developed optimisation problem. Simulation results show that by using this framework, Internet Service Providers (ISPs) can significantly improve QoS for better revenue with optimal server allocation in their data centre networks.