Improving Agent Quality in Dynamic Smart Cities by Implementing an Agent Quality Management Framework

Najwa Abu Bakar,Ali Selamat,Ondrej Krejcar

doi:10.3390/app9235111

Abstract

It is critical for quality requirements, such as trust, privacy, and confidentiality, to be fulfilled during the execution of smart city applications. In this study, smart city applications were modeled as agent systems composed of many agents, each with its own privacy and confidentiality properties. Violations of those properties may occur during execution due to the dynamic of agent behavior, decision-making capabilities, and social activities. In this research, a framework called Agent Quality Management was proposed and implemented to manage agent quality in agent systems. This paper demonstrates the effectiveness of the approach by applying it toward a smart city application called a crowdsourced navigation system to verify and assess agent data confidentiality. The AnyLogic Agent-Based Modeling tool was used to model and conduct the experiments. The experiments showed that the framework helped to improve the detection of agent quality violations in a dynamic smart city application. The results can be further analyzed using advanced data analytic approach to reduce future violations and improve data confidentiality in a smart city environment.

Highlights

Cloud-based smart city technologies in the form of smart applications are currently used in many cities around the world
The result shows that the implementation of the Agent Quality Management (AQM) framework and the Run-Time Verification and Quality Assessment (RVQA) process helped to detect about 70% more agent quality violations that occur during the execution of Crowdsourced Navigation System (CNS) as compared to the detection performed using the CNS
Result that the implementation of framework and the process helped to detect about more agent quality violations that the AQM framework and the RVQA process helped to detect about 70% more agent quality violations occur during the execution of CNSofasCNS

Summary

Introduction

Cloud-based smart city technologies in the form of smart applications are currently used in many cities around the world. Fulfilling privacy and confidentiality requirements of smart city applications has been a challenge due to this massive amount of data collected and processed during execution. These data are collected from individual citizens via smart phones, smart cards, smart vehicles, and other Internet of Things (IoT) and wearable devices applications with built-in sensors and data capturing capabilities. These data, combined with data from other facilities in smart cities, such as smart buildings and smart transportation services, are highly interconnected with third party applications and city departments to improve the efficiency of smart city services. The correlation between the large amounts of data increases the risk for privacy and data confidentiality violations, such as the exposure of personal information, locations, and social activities [1]

Methods

Results

Conclusion