PriorHealth: A Priority-Aware Task Scheduling Framework for Managing Healthcare Data in Fog Computing Applications

The advent of wearable sensor technology, like oximeters, accelerometers, and gyroscope-based monitoring devices, are being widely used to address the important problem of health monitoring for mobility patients. Unusual patient data prompts healthcare facilities to take immediate action by sending out alerts. The major goal of this paper is to investigate the field of fog computing-assisted healthcare service with regard to priority-aware healthcare task offloading. When it comes to providing end users with extra processing power for time-sensitive tasks, the fog server is essential. But this ever-changing environment is really hard when some jobs demand a far slower response time than others. This problem is solved by introducing a priority-aware scheduling and task offloading technique that prioritizes high-priority jobs, especially those with strict deadlines, when allocating CPU resources. Any CPU resources that are left over are then carefully allocated to provide for a longer average response time for the low priority tasks, which are lower on the task hierarchy. Furthermore, a basic lower-bound is obtained for the mean response time of assignments with hard and soft deadlines. This study demonstrates the effectiveness of the proposed task scheduling strategy with a wide range of simulations, skillfully allocating resources for end users and edge servers by giving hard-deadline tasks top priority and carefully scheduling lower priority soft-deadline tasks.