Load Balancing Using Artificial Intelligence for Cloud-Enabled Internet of Everything in Healthcare Domain

Abstract

The emergence of the Internet of Things (IoT) and its subsequent evolution into the Internet of Everything (IoE) is a result of the rapid growth of information and communication technologies (ICT). However, implementing these technologies comes with certain obstacles, such as the limited availability of energy resources and processing power. Consequently, there is a need for energy-efficient and intelligent load-balancing models, particularly in healthcare, where real-time applications generate large volumes of data. This paper proposes a novel, energy-aware artificial intelligence (AI)-based load balancing model that employs the Chaotic Horse Ride Optimization Algorithm (CHROA) and big data analytics (BDA) for cloud-enabled IoT environments. The CHROA technique enhances the optimization capacity of the Horse Ride Optimization Algorithm (HROA) using chaotic principles. The proposed CHROA model balances the load, optimizes available energy resources using AI techniques, and is evaluated using various metrics. Experimental results show that the CHROA model outperforms existing models. For instance, while the Artificial Bee Colony (ABC), Gravitational Search Algorithm (GSA), and Whale Defense Algorithm with Firefly Algorithm (WD-FA) techniques attain average throughputs of 58.247 Kbps, 59.957 Kbps, and 60.819 Kbps, respectively, the CHROA model achieves an average throughput of 70.122 Kbps. The proposed CHROA-based model presents an innovative approach to intelligent load balancing and energy optimization in cloud-enabled IoT environments. The results highlight its potential to address critical challenges and contribute to developing efficient and sustainable IoT/IoE solutions.

An effective hotspot mitigation system for Wireless Sensor Networks using hybridized prairie dog with Genetic Algorithm

“…TSA optimises cluster-based routing by considering factors such as the network’s average energy, the distances between nodes and the sink, load balancing, and each node’s energy condition [ 26 ]. This results in effective CH selection, which is critical for improving energy efficiency and load balancing across the network [ 27 , 28 ]. The proposed approach examines two network scenarios: one where the sink is absent, requiring an alternative data aggregation point, and another representing an ideal condition with the sink present to provide optimal solutions for each WSN context.…”

Optimising barrier placement for intrusion detection and prevention in WSNs

“…The computational load primarily stems from the training phase of the SVR model and the optimisation process of the ACO algorithm. The model has been designed to operate on standard sensor nodes commonly found in WSNs, ensuring compatibility with existing hardware infrastructure [ 24 ].…”

Comprehensive review of load balancing in cloud computing system

“…Virtualization, availability and scalability of cloud computing are the distinct attributes that differentiate it from cluster and grid computing. Whereby, availability, accessibility, resource sharing, elasticity and Pay-As-You-Go are the major characteristic of cloud computing [6], [7]. a.…”

“…Independent and dependent scheduling methods are considered as the key approach in terms of load management. Dependent scheduling, however, is attracting more attentions [6]. Dependent scheduling is suitable for those types of tasks with dependent structured patterns.…”

“…The goal of the best effort algorithms is to reduce the execution time. However, they do not work with the pay-as-you-go charging model [6]. On the other hand, QOS-based approaches are regarded to be advantageous for high-quality applications.…”