A Multidimensional Virtual Resource Allocation Framework With Energy-Aware Physical Resource Mapping for Green Cloud Computing

Uslu A., ÖZER A. H.

Concurrency and Computation: Practice and Experience, vol.37, no.4-5, 2025 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 37 Issue: 4-5
  • Publication Date: 2025
  • Doi Number: 10.1002/cpe.70039
  • Journal Name: Concurrency and Computation: Practice and Experience
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Applied Science & Technology Source, Communication Abstracts, Compendex, Computer & Applied Sciences, INSPEC, Metadex, zbMATH, Civil Engineering Abstracts
  • Keywords: ant colony optimization, cloud computing, combinatorial auction, energy-aware resource allocation, genetic algorithm, virtual machine placement
  • Marmara University Affiliated: Yes

Abstract

Cloud computing has seen a surge in demand, driven by its scalability and cost efficiency. However, the growing energy consumption of data centers poses significant environmental challenges. This study introduces a multidimensional resource allocation model designed to allocate and place virtual resources in an energy-efficient manner using a combinatorial auction approach. Unlike current approaches, which rely on predefined virtual resources, this model allows users to request virtual resources with specific features and capacities tailored to their workflows. Furthermore, it incorporates a flexible bidding language that supports simultaneous requests for multiple resources using logical AND/OR relations. The model accommodates various data centers, allowing users to indicate their preferred locations. Through a combinatorial optimization problem, the model identifies the most resource-efficient allocations and the most energy-efficient placements. This study provides the mathematical definition of the model and the formulation of its optimization problem. Given the complexity of this problem, it explores several heuristic methods, including ant colony optimization and genetic algorithms. A test case generator is developed to simulate real-life scenarios. The effectiveness of the model and the proposed heuristic solutions is assessed through various experiments, demonstrating that these methods can achieve near-optimal solutions within reasonable timeframes.