ENERGY EFFICIENT SCHEDULING ALGORITHM FOR CLOUD COMPUTING SYSTEMS BASED ON PREDICTION MODEL

Existing cloud resource scheduling approaches have mainly concentrated on enhancing the reducing power consumption and resource utilization by enhancing the legacy heuristic algorithms. Although, different resourceintensive applications running on cloud data centers in realistic scenarios have significant results on the power consumption and cloud application performance. Furthermore, occurring peak loads may lead to a scheduling error, which can significantly effects on the energy efficiency of scheduling algorithms. At peak loads may lead to scheduling errors because there is no prediction model to predict the coming resource utilization of a data center through the data collected by the monitoring model. Effective scheduling mechanism gives an optimal solutions for complex problems while providing the Quality-of-Service (QoS) and avoiding Service Level Agreement (SLA) violations. To enhance the resource scheduling mechanism in cloud environment, predicting future workload to the each virtual machine pool in different manners like number of physical machines, number of virtual machines, number of requests and resource utilization etc., is an essential step. According to the prediction results, resource scheduling can be done in the right time, while avoiding QoS dropping and SLA violations. To achieve efficient resource scheduling, proposed approach lease advantages of prediction models. The proposed algorithm consists of a prediction model which is based on iterative fractal model and a scheduler which is based on an improved heuristic algorithms. Proposed scheduler algorithm is responsible for scheduling of resources while reducing the energy consumption and giving the guaranteeing the QoS.