Towards providing a priority-based vital sign offloading in healthcare with serverless computing and a fog-cloud architecture

Abstract

Smart cities and healthcare services have been gaining much attention in recent years, as the benefits offered by this field of research are significant and improve quality of life. Systems can proactively detect health problems by monitoring a person’s vital signs and make automated decisions to prevent these problems from worsening. With this in mind, we highlight two essential requirements that smart city architectures should consider to achieve elevated quality of experience in the healthcare domain. The first is to process high-priority vital signs with short response times, so people with comorbidities can have health problems identified as soon as possible. The second is to employ scalability techniques to deal with high usage peaks resulting from people concentrating in specific city neighborhoods. This paper contributes to this field of research by proposing SmartVSO - a computational model of a hierarchic, scalable, tree-based, fog-cloud architecture that executes healthcare services with reduced response time for urgent vital signs. Fog computing is employed to reduce response times, and cloud computing is used to provide virtually infinite computing resources. Serverless computing is the main technology we consider for deploying and running healthcare services because this allows authorized companies to implement their own services in a distributed and pluggable approach, without recompiling the proposed modules and reducing scalability concerns for engineers. An experiment with 80,000 vital signs indicates that our solution processes 60% of the very critical ones in no more than 5.3 s, while an architecture without fog computing and without prioritization takes up to 231 min (around 3 h and 51 min) to process 60% of very critical vital signs.