Energy Efficient Fog based Healthcare Monitoring Infrastructure

TL;DR

This paper introduces an energy-efficient fog computing architecture for healthcare monitoring that reduces power consumption and latency by processing health data at the network edge, using MILP optimization and heuristics.

Contribution

It proposes a novel fog computing architecture based on GPON, along with an MILP model and a heuristic for optimizing energy efficiency in health monitoring systems.

Findings

Achieves 36% energy savings at low data rates.

Achieves 52% energy savings at high data rates.

Heuristic performance approaches the MILP model.

Abstract

Recent advances in mobile technologies and cloud computing services have inspired the development of cloud-based real-time health monitoring systems. However, the transfer of health-related data to the cloud contributes to the burden on the networking infrastructures, leading to high latency and increased power consumption. Fog computing is introduced to relieve this burden by bringing services to the users proximity. This study proposes a new fog computing architecture for health monitoring applications based on a Gigabit Passive Optical Network (GPON) access network. An Energy-Efficient Fog Computing (EEFC) model is developed using Mixed Integer Linear Programming (MILP) to optimize the number and location of fog devices at the network edge to process and analyze the health data for energy-efficient fog computing. The performance of the EEFC model at low data rates and high data rates health applications is studied. The outcome of the study reveals that a total energy saving of 36% and 52% are attained via processing and analysis the health data at the fog in comparison to conventional processing and analysis at the central cloud for low data rate application and high data rate application, respectively. We also developed a real-time heuristic; Energy Optimized Fog Computing (EOFC) heuristic, with energy consumption performance approaching the EEFC model. Furthermore, we examined the energy efficiency improvements under different scenarios of devices idle power consumption and traffic volume.