Location of Fog Nodes for Reduction of Energy Consumption of End-User Devices
Rodrigo A. C. da Silva, Nelson L. S. da Fonseca
Abstract
New applications and the number of mobile devices connected to the Internet have increased considerably. Fog computing has been arising to allow the deployment of latency-sensitive applications which cannot be processed in the cloud. In fog computing, small facilities, known as fog nodes, provide processing, storage, and networking resources to users. A key problem in the design of a fog-cloud infrastructure is the decision about where to locate the fog nodes, since a poorly designed infrastructure may not support the requirements of mobile and latency-sensitive applications. This paper proposes a solution to the fog node location problem which provides support for mobile users with limited battery while being able to process heavy workloads with low latency constraints. This approach favors locations where offloading of workloads to the fog reduces the energy consumed by end-user devices. This paper proposes a multicriteria mixed-integer linear programming (MILP) formulation for the problem, as well as a heuristic solution for solving large-scale problems. The results obtained using a real data set of mobility show that the heuristic solution produces accurate results when compared to those given by the MILP formulation, thus allowing significant energy savings for end-users.