AI-based Online VoI-Aware Healthcare and Medical Monitoring Task Computing

Abstract—In recent years, there has been a significant advancementin the field of healthcare systems with the introductionof fifth generation cellular communications and beyond (5GB).This development has paved the way for the utilization oftelecommunications technologies in healthcare systems with anlevel of certainty, reaching up to 99.999 percent. In this paper,we present a novel task computing framework that can addressthe requirements of healthcare systems, such as reliability. Inthis regard, we assume that IoT devices that are applied in theconsidered healthcare have tasks with uncertain requirements.On the other hand, we have uncertainty in the computingresources in the healthcare servers. To address these uncertaintiesthat we obtain closed-form formulas. Furthermore, we adopt apartial offloading approach to address the task of IoT devices.Our goal in the proposed framework is to maximize the totaldate rate of the healthcare system. To achieve this, we formulatean optimization problem that considers a novel constraint thatguarantees the minimum value of information (VoI), minimumdata rate, and computational capacity constraints. To solve theproposed optimization problem, we adapt a deep reinforcementlearning (DRL) based solution to effectively solve it, compared tothe other baselines. In this regard, we propose a soft actor critic(SAC)-based algorithm, entitled SAC-based VoI-aware healthcarenetworks (SACVAHC), that can address uncertainties exist in theconsidered healthcare network. The results obtained show thatthe proposed method can improve the total sum rate up to 20%,compared to the other baselines.