A Swarm Intelligence Model for Enhancing Health Care Services in Smart Cities Applications

Abstract

Cloud computing plays a significant role in healthcare services (HCS) within smart cities due to its the ability to retrieve patients’ data, collect big data of patients by sensors, diagnosis of diseases and other medicinal fields in less time and less of cost. However, the task scheduling problem to process the medical requests represents a big challenge in smart cities. The task scheduling performs a significant role for the enhancement of the performance through reducing the execution time of requests (tasks) from stakeholders and utilization of medical resources to help stakeholders for saving time and cost in smart cities. In addition, it helps the stakeholders to reduce their waiting time, turnaround time of medical requests on cloud environment, minimize waste of CPU utilization of VMs, and maximize utilization of resources. For that, this paper proposes an intelligent model for HCS in a cloud environment using two different intelligent optimization algorithms, which are Particle Swarm Optimization (PSO), and Parallel Particle Swarm Optimization (PPSO). In addition, a set of experiments are conducted to provide a competitive study between those two algorithms regarding the execution time, the data processing speed, and the system efficiency. The results showed that PPSO algorithm outperforms on PSO algorithm. In addition, this paper proposes a new PPSO dependent algorithm using CloudSim package to solve task scheduling problem to support healthcare providers in smart cities to reduce execution time of medical requests and maximize utilization of medical resources.