Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Filters

2020 - 20212

Settings

Author: search.filters.author.Kandasamy, A.Subject: search.filters.subject.Prediction

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    A Conceptual Framework for Intelligent Management of Workloads in Cloud Environment
    (Institute of Electrical and Electronics Engineers Inc., 2020) Shishira, S.R.; Kandasamy, A.
    Cloud computing is an important paradigm for processing, computation, storage, and network bandwidth. Workloads are the amount of data given to the hardware resource for processing. Its behavior and properties play a major role in the efficient scheduling of requests to given resources. Also, it is very difficult to predict workloads nature if they are changing excessively. To address this issue, we propose a conceptual framework which can be used for efficient prediction and optimization of workloads in a cloud environment. Classification of optimization metrics based on the provider and consumer constraints are presented. In addition to this, some of the research gaps found during the study has been highlighted and also provided possible solutions in the cloud research domain. © 2020 IEEE.
  • No Thumbnail Available
    Item
    A Novel Feature Extraction Model for Large-Scale Workload Prediction in Cloud Environment
    (Springer, 2021) Shishira, S.R.; Kandasamy, A.
    In an enterprise cloud environment, it is difficult to handle an extensive number of loads. Serving the request in very less time leads to resource allocation problem. It is better to have prior knowledge of the incoming loads to auto-scale the resources. A novel architecture is proposed for the better prediction of workloads in the cloud environment. The proposed feature extraction model considers three essentials for managing cloud resources, i.e., CPU, Disk, and Memory. The model with the very nominal error achieved an accuracy of 98.72%. The proposed model is contrasted with other conventional predictive models for validation. © 2021, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.