Learning-Based QoS Control Algorithms for Next Generation Internet of Things

Abstract

The Internet has become an evolving entity, growing in importance and creating new value through its expansion and added utilization. The Internet of Things (IoT) is a new concept associated with the future Internet and has recently become popular in a dynamic and global network infrastructure. However, in an IoT implementation, it is difficult to satisfy different Quality of Service (QoS) requirements and achieve rapid service composition and deployment. In this paper, we propose a new QoS control scheme for IoT systems. Based on the Markov game model, the proposed scheme can effectively allocate IoT resources while maximizing system performance. In multiagent environments, a game theory approach can provide an effective decision-making framework for resource allocation problems. To verify the results of our study, we perform a simulation and confirm that the proposed scheme can achieve considerably improved system performance compared to existing schemes.

An Autonomic Management System for IoT Platforms based on Data Analysis Tasks

“…Table 5. Data analysis tasks in the second case study Works Criteria C1 C2 C3 C4 [5,6,9] x [7,11] x x Our AMS x x x x…”

“…In general, there are some IoT AMS that use the data of the context in order to make decisions about the QoS mechanisms to deploy in a system [3,11]. Also, some works consider the idea of an autonomous self-configuration [5,6,7,11].…”

“…In general, there are some IoT AMS that use the data of the context in order to make decisions about the QoS mechanisms to deploy in a system [3,11]. Also, some works consider the idea of an autonomous self-configuration [5,6,7,11]. However, our paper is the only one where is used the AMS in different contexts, additionally, to reach QoE / QoS requirements.…”

“…P ✓ ✓ X [11] It proposes a QoS control scheme for IoT systems, based on the Markov game model, to allocate IoT resources while maximizing QoS performance. S ✓ X ✓ [12] It proposes IoT-MP (Internet of Things Management Platform), which considers the low-cost and low-power requirements of things, and the heterogeneity, scalability, and autonomy of the communications supported in the IoT.…”

“…Finally, they present a redirection mechanism evaluated in a case study related to vehicular transportation. Also, in [11] proposes a QoS control scheme for IoT systems, based on the Markov game model. The QoS scheme can effectively allocate IoT resources while maximizing QoS performance.…”