Optimized Multitask Scheduling in Cloud Computing Using Advanced Machine Learning Techniques

The delivery of computing services over the internet is known as cloud computing. One of most important problem in the cloud computing environment task scheduling, which has a direct affect on the platform's overall performance. Tasks are scheduled for specific resources at specific times based on user requests. It mainly focuses maximize resource utilization, minimize make span. Task scheduling in cloud is still a problem even if there are several ways to improve it. One important step in effectively harnessing cloud computing potential is scheduling tasks efficiently. In this work, machine learning technique is presented for improved multitask scheduling in cloud computing. For efficient task scheduling, we propose ML feature-based heuristic task scheduling (MLF-H). Instead of randomly assigning a scheduling algorithm, ML techniques are used to incoming task requests to classify best suitable algorithm for task. Simulations results show that MLF-H task scheduling approach has shortest make span and rapid generalization capabilities when compared to traditional methods. This proves the availability of the approach and the efficiency of the MLF-H scheduling algorithm.