Mr. Mohammed Sadhik Shaik

Efficient Scheduling Mechanism to Allocate the Resource Effectively with Enhanced QoS in Distributed Cloud Environment

Abstract of talk: 

By leveraging virtualization technology to separate the physical infrastructure, cloud service providers can make resources available for users to use. This allows public cloud to provide services that are second to none and tailored to the unique needs of each user. Everything that can be accessible online can be considered a cloud-based system. Distributing computer resources and workloads in the cloud is known as cloud load balancing. Load balancing allows businesses to distribute computing resources among several computers, networks, or servers to handle varying workloads. It is more difficult to manage resource utilization and keep expenditures in check while dealing with the resource allocation problem, also known as the resource overfitting problem, because user needs are dynamic and constantly evolving. Striking a balance between the velocity, variety, authenticity, volume, and pace of enormous data streams is an important problem in a real-time distributed context. You can use the resource scheduler to find the best way to distribute your resources based on observable criteria like demand statistics, resource use and monitoring, and more. This study presents an Efficient Scheduling Mechanism for Distributed Clouds that Improves Resource Allocation and Quality of Service. A scheduling strategy is suggested for allocating resources in a distributed QoS environment that takes resource weight into account for efficient utilization of such resources. Allotting resources to some cloud apps entails distributing available internet resources. In order to improve the cloud's performance, the proposed model does a good job of balancing workloads and completing jobs with the available resources. The utilization of balanced metadata predictions derived by Weather Data Stream Processing allows for efficient resource allocation. Cloud computing features, such as the internet of things, can also benefit from the optimization approach. In a cloud setting, efficient work scheduling is carried out and optimized by activating resources with enhanced energy. Allocating resources to process weather streaming data with metadata in a fair and practical way based on predictions. The load on the cloud system is reduced by efficient scheduling of the resources. Possible future consideration of power consumption as a variable to be decreased in a cloud environment for the purpose of increasing system efficiency. Various performance indicators are investigated for the proposed current methods based on overall performance analysis. Research shows that the suggested approach makes good use of resources during virtual machine migration while simultaneously decreasing execution time and power consumption.