Reinforced Ant Colony Optimization for Fault Tolerant Task Allocation in Cloud Environments

Cloud computing is the most emerging technology in distributed systems which provides users flexibility of storing data and sharing of computing resources by making use of the concept of virtualization. Large amount of data processing is required in developing cloud application services which increases the bandwidth. To avoid this, proper scheduling of tasks is required. Task scheduling is a combinatorial optimization problem and is one of the critical issues to be solved in cloud computing. Proper task scheduling not only reduces the make span but also hikes the system performance. In this research work, a novel strategy is proposed to solve task scheduling using Ant Colony Optimization (ACO) by adapting Reinforcement learning (RL) along with fault tolerance to make the scheduling process fault resistant, and to achieve the objective of minimum make-span. The proposed algorithm, Reinforced-Ant Colony Optimization (RACO) yields about 60% of better performance than sole implementation of ACO.