A QoS-Aware Service Composition Mechanism in the Internet of Things Using a Hidden-Markov-Model-Based Optimization Algorithm

Recently, a new technology topic has been known as the Internet of Things (IoT), where all devices like smartphones, smart TVs, medical and healthcare ones, and home appliances have been applied for data generating. Due to the variety of services, the numerous service composition problems, mostly related to the Quality-of-Service (QoS) parameters, are recognized in the IoT domain. Since this issue is an NP-hard obstacle, different metaheuristic approaches have been utilized up until now to solve it. Many varieties of services can be brought into the IoT, depending on users’ demands. In this research, we have proposed an effective way based on a hidden Markov model (HMM) and an ant colony optimization (ACO) to answer the service composition issue by enhancing the QoS. The HMM has been trained to predict QoS. The emission and transition matrices have been improved using the Viterbi algorithm. We have executed the QoS estimation using the ACO algorithm and found a suitable path. The outcomes have illustrated the efficacy of the introduced method regarding availability, response time, cost, reliability, and energy consumption compared to the previous methods.

I. Introduction

Internet of Things (IoT) explains a network of linked individuals, tools, and services [1], [2]. It is a combined network, including different technologies such as large-scale wireless networks according to the interaction and linking (provided by the Internet) among individuals and things, all the time and everywhere [3]. IoT is an essential technology because of its capacity to montage, test, and distribute the data that can be turned into crucial information and knowledge [4]. Low-capacity batteries typically motorize the gadgets in the IoT, so increasing the lifetime of enduring applications like constant ecological checking is necessary [5]. In the IoT and other distributed services, service composition and allocation organize-related services to solve complex problems [6]. The IoT delivers smart objects employing its underlying technologies, such as pervasive computing, sensor networks, Internet protocols, and communication technologies [7]. The outcome is defined by the Quality-of-Service (QoS) criteria, benefiting the customers in assessing the QoS arrangement [8]. QoS can include service response time, energy, availability, reliability, credibility, etc. As an NP-hard problem, service composition has emerged as a wide-ranging technology for integrating several services into one service over the Internet to combine the required applications [5].