Resource Provisioning in Heterogeneous Cloud: A Comparison of Nash Auction and Cost-Energy Aware Nash Equilibrium Models

Authors:
K. Chitra, A. Chitra, P. Paramasivan, S. Suman Rajest, M. Mohamed Sameer Ali, M. Rehena Sulthana

Addresses:
Department of Computer Applications, Dayananda Sagar Academy of Technology and Management, Bengaluru, Karnataka, India. Department of Computer Science and Applications, St. Peter's Institute of Higher Education and Research, Chennai, Tamil Nadu, India. Department of Research and Development, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India. School of Information Technology and Engineering, Melbourne Institute of Technology, Melbourne, Victoria, Australia.

Abstract:

Cloud provisioning is the step-by-step provisioning and management of applications in a cloud environment, such as Virtual Machine (VM) provisioning, resource allocation, and application installation. VM provisioning involves provisioning multiple virtual machines based on application requirements, software, and infrastructure. Resource allocation schedules, VM placement on hosts, load balancing, and infrastructure optimisation. Cloud provisioning would be equivalent to a solution of an optimisation problem in which resources ('x') are provisioned to consumers ('y) to form an 'x*y' matrix in the cloud space. With a watchful eye on addressing complexity in this sector, one model based on game-theoretic principles is the Nash Auction Equilibrium (NAE), which is used to predict optimal outcomes in competitive resource allocation. The NAE model uses an ASK-BID-based approach to calculate auction payments, utilisation payments, and reserve prices. Inefficiency and scalability were the primary drivers behind the development of the Cost-Energy-Aware Nash Equilibrium (CEANE) model. CEANE uses the energy consumption and VM load levels of data centres in a cluster to calculate Scheduling Parameter (SP) values. This enables the intelligent scheduling of VMs of the same resource type, thereby optimizing runtime performance, energy efficiency, and system performance compared to traditional provisioning methods.

Keywords: Virtual Machine; Nash Auction Equilibrium; Runtime Optimisation; Energy Efficiency; System Performance; Hosts Balancing; Load Balancing; Optimising Infrastructure.

Received on: 23/10/2024, Revised on: 26/12/2024, Accepted on: 02/02/2025, Published on: 03/06/2025

DOI: 10.69888/FTSCL.2025.000426

FMDB Transactions on Sustainable Computer Letters, 2025 Vol. 3 No. 2, Pages: 105-115

  • Views : 76
  • Downloads : 10
Download PDF