Ant MAXMIN Approach of Load Balancing through VMs in Cloud Computing

Load balancing by virtual machine migration is one of the most significant issues in cloud computing research. A basic approach is to use intelligent algorithms such as Ant Colony Optimization (ACO). However, the main issues with traditional ACO is that it dependents on the initial conditions, which affects the convergence speed and final optimal solution. To solve this problem, we propose Max-min Algorithm. Another problem, ACO could arrive at local optimal point, and the convergence speed is typically low. Along this line, we introduce the idea of max-min optimal feature selection to avoid local optimal and accelerate the convergence. Lastly, our experiments show that our improved ACO (Max-min ACO Algorithm) achieves good performance in load balancing. The experimental results show that SLA violations and number of migrations are reduced. The new scheduling strategy was simulated using the Cloud-Sim toolkit package.