Optimization of Service Placement with Fairness
Noé Godinho, Marília Curado, Luís Paquete · 2019
Due to the large increase of Internet of Things (IoT) devices in the last years, the cloud has been proved unsuitable to deal with the high demand of requests generated by them. To deal with this, fog computing was proposed in order to provide closer computing services in a distributed manner, acting as a middle layer between IoT devices and the cloud. However, these devices have low energy and low computational power. Therefore, strategies to distribute requested services, bundled in a set of applications, are of particular interest. Furthermore, these applications have deadlines that may be short, which have to be met. Hence, models and algorithms are needed to place the requested services in order to meet the deadlines while using the fog as distributed as possible. In this paper, we present a Mixed Integer Linear Programming (MILP) formulation with two main objectives: maximize the fog usage and maximize the fairness throughout the system (fog and cloud). We also propose an heuristic that obtains approximate solutions as fast as possible. We compare both approaches using a set of randomly generated applications composed by different deadlines and services.