CURATE: On-Demand Orchestration of Services for Health Emergencies Prediction and Mitigation

Abstract

Telemedicine, or the ability granted to doctors to remotely assist patients has been greatly benefited by advances in IoT, network communications, Machine Learning and Edge/Cloud computing. With the impeding arrival of 5G, virtualized infrastructures and cloud-native approaches enable the execution of unprecedented procedures during such patient/doctor interactions, allowing medical professionals to e.g. request higher granularity metrics from patients' telemetry equipment, or perform on-demand data mining/processing of patient's stored data in order to provide a more educated diagnostic or prediction.In this work we coalesce the virtues of virtualized infrastructures and IoT into a solution able to satisfy increasing data processing demands for eHealth, e.g. for telemedicine applications, remote assistance or patient pre-screening procedures. The proposed platform, CURATE, leverages Network Functions Virtualisation Management and Orchestration (NFV MANO) for the on-demand instantiation of the required virtual resources on the operator's infrastructure, as well as the concept of 5G Network Slices to guarantee e cient resource allocation and tenant isolation. Results show the proposed platform is able to e ciently make use of the available hardware resources via Network Slices, as well as provide cost-e ective service guarantees employing dynamic scaling operations.

Emerging Technologies for Next Generation Remote Health Care and Assisted Living

“…Furthermore, the novel technologies used by 5G such as the integration of the concepts of cloud computing like edge and fog computing have provided opportunities to locate privacy and latencysensitive services in the health care vicinity. Similarly, softwarized and virtualized network functions and services have simplified mobility of sensitive services into and [187] between health care environments [188]. For example, the CURATE platform proposed in [188] uses cloud platforms to instantiate new services in the health care location to meet the latency and privacy requirements, and uses virtualization and slicing for resource isolation.…”

“…Similarly, softwarized and virtualized network functions and services have simplified mobility of sensitive services into and [187] between health care environments [188]. For example, the CURATE platform proposed in [188] uses cloud platforms to instantiate new services in the health care location to meet the latency and privacy requirements, and uses virtualization and slicing for resource isolation. Such techniques can also be used in remote home care to provide latency sensitive services being isolated from each other, yet on the same infrastructure.…”

Optimizing Traffic Engineering for Resilient Services in NFV-Based Connected Autonomous Vehicles

“…The challenge of developing a solution for resilient services in an NFV-based IoT system is to find the optimal resource allocation for data routing and processing when a failure occurs in a distributed system. So far, a few studies have considered the design of a resilient NFV-based IoT system [17][18][19][20]. Huang et al devised a proactive fail-over mechanism based on failure prediction to enhance the resilience of NFV services deployed in a distributed edge network [17].…”

“…Bakhshi et al proposed a mathematical model for an SDN-based fault-tolerant architecture in an IoT environment [19]. Sanabria et al used machine learning techniques to provide prediction and alert capabilities for telemedicine applications [20]. They proposed a hybrid Edge/Cloud architecture training of the deep learning prediction model.…”

“…In the inner loop, if the objective value of a neighborhood solution is less than that of a current solution, the iteration continues with the neighborhood solution as TERH is moving towards a better solution (i.e., lines [16][17][18][19][20][21][22]. Otherwise, TERH randomly accepts the neighborhood solution with a probability in order to overcome local optimization (i.e., lines [24][25][26][27][28].…”