Kademlia hash snow ablation resource optimized stride scheduling for mobile computing services in healthcare sector.

Healthcare plays an essential role in every individual’s life. Smart healthcare employs a new generation of information technologies like Internet of Things (IoT), Mobile Computing (MC), and Artificial Intelligence (AI) to transform the conventional medical system into a modernized one. Many researchers have reached better healthcare solutions by ensuring robust and versatile accessibility to the people. Healthcare applications on mobile devices exchange data through communication interfaces between patients and healthcare service providers. However, every patient’s data possess a significant amount of computing resources like Central Processing Unit (CPU), network bandwidth, and memory, and hence cannot be processed and validated at the same time. In order to overcome resource limitations and make scheduling efficient, mobile devices contain patient data that is integrated with the scheduling process to provide the resource efficient mobile computing services in the healthcare sector. Kademlia HashSnow Ablation Resource Optimized Stride Scheduling (KHSAROSS) is proposed in mobile computing. The novelty of the proposed KHSAROSS method is designed to build mobile phone based remote healthcare monitoring to identify the resource optimized virtual machine and balance the overloaded virtual machine. The key advantage of the proposed KHSAROSS method is to enhance the mobile computing services in the healthcare sector while increasing makespan. The KHSAROSS method involves three distinct processes, namely the patient data collection task, optimization and scheduling. Sensors with a data acquisition unit are used to acquire patients’ physiological states like temperature, heart rate, and Electroencephalography (EEG) data to perform mobile phone based remote healthcare monitoring. The Kademlia Hash Function here generates a hash value for each patient’s collected data. Following this, Snow Ablation Optimization is carried out to identify resource optimized (i.e., CPU, network bandwidth, and memory) virtual machines (i.e., healthcare service providers) for performing scheduling of stored patient data. Finally, Stride Scheduling is used to balance overloaded virtual machines with less loaded virtual machines. This, in turn, ensures efficient resource allocation and scheduling in mobile computing. The effectiveness of the proposed and existing methods is assessed using metrics for scheduling accuracy, scheduling time, throughput and makespan.