Improved genetic algorithm based on Shapley value for a virtual machine scheduling model in cloud computing

Introduction: In cloud computing, a common idea to reduce operation costs and improve service quality is to study task scheduling algorithms. Methods: To better allocate virtual machine resources, a virtual machine resource scheduling algorithm, Shapley value method-genetic algorithm (SVM-GA) is proposed. This algorithm uses the SVM to obtain the contribution values of each component of the virtual machine, refine the topological network, and achieve the optimal solution of scheduling by the genetic algorithm. Results and Discussion: CloudSim simulation results indicate that SVM-GA has the lowest total task completion time when compared with existing intelligent optimization algorithms (such as the max-min algorithm, logistic regression algorithm, and differential evolution algorithm) with the same number of tasks, and the total task time is 25, 55, 81, 112, 145, and 175 s for 200, 400, 600, 800, 1,000, and 1,200 tasks, respectively. As the number of evolutionary generations increases, the ability of SVM-GA to reach the optimal solution of the model increases. In the simulated light load case, the SVM-GA migration time and Q10 migration count optimal solutions are slightly inferior to those of the logistic regression algorithm (3.02 s > 2.38 s; 1,129 times >999 times), but the migration energy consumption and service level agreement violation rate optimal solutions are superior. The SVM-GAA's performance in the heavy load case is similar to that in the light load case. The experiments show the feasibility of the algorithm proposed in the study.