A new method for task scheduling in fog‐based medical healthcare systems using a hybrid nature‐inspired algorithm

Abstract

Summary The goal of the healthcare system is to offer a dependable and well‐organized solution for improving human's wellbeing. Examining a patient's history can assist clinicians in considering the patient's wants when building a healthcare system and providing service, resulting in increased patient satisfaction. Thus, healthcare is becoming a more competitive sector. Massive data volume, latency, response time, and security susceptibility are all difficulties resulting from this substantial increase in healthcare systems. As a famous distributed structure, fog computing might thus aid in the resolution of such problems. Processing parts are situated among end devices and cloud components in a fog computing infrastructure and run programs. This design is well suited to real‐time and low‐latency applications, like healthcare systems. Because task scheduling is an NP‐hard optimization issue in fog‐based medical healthcare systems, this work proposes a hybrid genetic algorithm and particle swarm optimization (GA‐PSO) strategy. A powerful single‐objective optimization technique is the GA‐PSO. Individuals in a novel generation are formed in GA‐PSO through mutation and crossover operations in GA‐PSO, which uses a redefined local optimization swarm. Hence, it may avoid local minimums and perform well in global searches. The study's goal in fog‐based medical healthcare systems is to lower the makespan and overall response time. The suggested technique is simulated in MATLAB and compared to the GA and PSO methods. The empirical findings confirmed the improved makespan, making the approach appropriate for medical and real‐time systems applications.

Research on Digital Medical Resource Scheduling Method Considering Data Interoperability

“…For digital medical data center, each independent component of data warehouse has its own unique metadata. Among them, for relational digital medical database, digital medical data dictionary, digital medical ETL tool conversion relational database and digital medical multidimensional tool knowledge base all have the above attribute characteristics [13][14] . However, it is worth noting that for some digital medical metadata that reflects the change of relationship, the components of data warehouse cannot contain such data.…”

An Efficient Combination of Genetic Algorithm and Particle Swarm Optimization for Scheduling Data-Intensive Tasks in Heterogeneous Cloud Computing

“…Nwogbaga et al [32] applied PSO after GA for the population evolution. Wang et al [33] applied the evolution strategy of GA first, and then that of PSO in each evolution. These methods tried to combine benefits of two or more algorithms, but they exploited these algorithms sequentially and separately in each iteration or in the whole evolutionary process, which provides inefficient combinations.…”

“…GAPSO first uses GA to evolve its population, and then applies PSO on the evolution, in each iteration [33].…”

An Energy‐Aware Technique for Task Allocation in the Internet of Things using Krill Herd Algorithm

“…IoT task allocation is a common NP-hard problem. Solving this problem requires a meta-heuristic algorithm [17].…”