Optimization of Metascheduler for Cloud Machine Learning Services

Cloud meta scheduler act as a global resource manager that discover the resource mapping, job submission and monitoring services in a distributed environment. Machine learning services are offered as pay-per-use by the leading cloud providers such as Amazon, Microsoft and IBM etc., Most of the cloud machine learning service architecture had a constraint that cloud users are allowed to choose the predefined listed algorithms for their experimentation and architecture like Amazon uses a single classification or regression algorithm irrespective of the input dataset. The resource utilization by cloud service user (CSU) is too low with respect to time. Here we proposed and construct the economic metascheduler in cloud machine learning architecture using a decision tree algorithm that selects the suitable classification or prediction algorithm based on the users need and achieve maximum profit for both cloud machine learning service providers (CMLSP) and cloud service user (CSU). The experimentation is carried out using Amazon AWS, Microsoft Azure, WEKA and the number results show that the proposed metascheduler architecture is superior to the real time CMLSP.