An Effective Approach for Load Balancing and Resource Scheduling in Cloud-Based Healthcare Communication

Abstract

Abstract Cloud computing is frequently utilized in distributed environments to handle user demands for resources and services. In order to respond to user requests for resources within a specific time window, resource scheduling is utilized. Healthcare management and systems rely on internet-connected smart gadgets in today's environment. These devices manage the enormous volumes of data that smart medical sensors process and collect while maintaining performance parameters like throughput and latency. To avoid any insensitivity, load balancing amongst the smart operating devices has become necessary. Both a distributed and centralized approach to managing massive amounts of data is achieved through load balancing (LB). LB architecture for scheduling in resource deployment in cloud-based healthcare terms is elaborated in this study. Authors use various reinforcement learning algorithms and Q-learning techniques for resource scheduling. These algorithms are used in cloud-based healthcare systems to forecast the best method to manage demand. The recommended system offers a short fabrication time, low energy consumption, and reduced latency time. Utilizing performance measurements for throughput, time of make-span, and latency rate, the suggested approaches performance is examined using MATLAB. The make span in this work is smaller than in the current process, and the proposed mechanism has a higher throughput.