SRAF: Scalable Resource Allocation Framework using Machine Learning in user-Centric Internet of Things

Abstract

Internet of Things (IoT) design focuses on concurrently handling multiple tasks for improving the scalability and robustness of the information sharing platform. Therefore, sophisticated resource allocation and optimization methods are necessary to prevent backlogs in request processing and resource allocation. This paper introduces a scalable resource allocation framework that is designed to maximize the service reliability in IoT because of a large volume of tasks and information. In this process, deep learning is used to assist the effective and scalable framework in allocating the resources to tasks with respective time constraints. The assisted allocation through deep learning balances the density of users, requests, and available resources without replications and overloading. Thus, the proposed deep learning based resource allocation framework helps in reducing the waiting and processing times of the requests under a controlled response time. Besides, the optimal segregation of available resources and request density facilitates failure-less allocation.