JultikaUniversity of Oulu repository

Abstract

Internet of Things (IoT) has become a backbone technology that connects together various devices with diverse capabilities. It is a technology, which enables ubiquitously available digital services for end-users. IoT applications for mission-critical scenarios need strict performance indicators such as of latency, scalability, security and privacy. To fulfil these requirements, IoT also requires support from relevant enabling technologies, such as cloud, edge, virtualization and fifth generation mobile communication (5G) technologies. For Latency-critical applications and services, long routes between the traditional cloud server and end-devices (sensors /actuators) is not a feasible approach for computing at these data centres, although these traditional clouds provide very high computational and storage for current IoT system. MEC model can be used to overcome this challenge, which brings the CC computational capacity within or next on the access network base stations.

However, the capacity to perform the most critical processes at the local network layer is often necessary to cope with the access network issues. Therefore, this thesis compares the two existing IoT models such as traditional cloud-IoT model, a MEC-based edge-cloud-IoT model, with proposed local edge-cloud-IoT model with respect to their performance and efficiency, using iFogSim simulator. The results consolidate our research team’s previous findings that utilizing the three-tier edge-IoT architecture, capable of optimally utilizing the computational capacity of each of the three tiers, is an effective measure to reduce energy consumption, improve end-to-end latency and minimize operational costs in latency-critical It applications.