| Popis: |
Considering the advanced nature of computational abilities, task scheduling is a measure of success in any multiprocessing environment performing many different tasks in real-time and effective scheduling process and so on. Cost-effective resource scheduling or CERS algorithm has been a crucial algorithm for many cloud deployments over the years. This algorithm is computationally simple, has minimum overheads, and is based on keeping the cloud utilization to the most optimum level. We analyzed that keeping effective task response time is one of the main drawbacks of the CERS algorithm. In this paper, we propose new machine learning-based optimization algorithm that utilizes the concept as proposed by CERS but in process improves it further using an amalgamation of pre-learning and continuous adaptation techniques in order to reduce the mean response time for a given set of tasks. The proposed algorithm will further be compared with the standard CERS implementation, and the results will be evaluated in terms of resource cost and mean response time. |
