Novel Resource Allocation Model and Algorithms for Cloud Computing

Resource scheduling is one of the most important problems in cloud computing. However, it is a big challenge for efficient resource scheduling algorithm design and implementation (since general scheduling problem is NP-complete). Most existing resource scheduling methods of cloud computing only consider task resource requirements for CPU and memory, without considering bandwidth requirements. In this paper, we model the optimization of the resource allocation as a CSP considering three type resources (RAM, CPU and Bandwidth) and design a Choco-Based algorithm (CB) for VM resource allocation in virtualized cloud data centers. Moreover, we propose an improved FFD (IFFD) and an improved BFD (IBFD) and conduct performance evaluation experiments using Choco and Java. The experimental results show that the proposed algorithms are effective and outperform existing resource allocation algorithms.