Ibnu Febry Kurniawan, A. Taufiq Asyhari, Fei He, Ye Liu
The importance of an optimal solution for disaster evacuation has recently raised attention from researchers across multiple disciplines. This is not only a serious, but also a challenging task due to the complexities of the evacuees’ behaviors, route planning, and demanding coordination services. Although existing studies have addressed these challenges to some extent, mass evacuation in natural disasters tends to be difficult to predict and manage due to the limitation of the underlying models to capture realistic situations. It is therefore desirable to have on-demand mechanisms of locally-driven computing and data exchange services in order to enable near real-time capture of the disaster area during the evacuation. For this purpose, this paper comprehensively surveys recent advances in information and communication technology-enabled disaster evacuations, with the focus on fog computation and communication services to support a massive evacuation process. A numerous variety of tools and techniques are encapsulated within a coordinated on-demand strategy of an evacuation platform, which is aimed to provide a situational awareness and response. Herein fog services appear to be one of the viable options for responsive mass evacuation because they enable low latency data processing and dissemination. They can additionally provide data analytics support for autonomous learning for both the short-term guidance supports and long-term usages. This work extends the existing data-oriented framework by outlining comprehensive functionalities and providing seamless integration. We review the principles, challenges, and future direction of the state-of-the-art strategies proposed to sit within each functionality. Taken together, this survey highlights the importance of adaptive coordination and reconfiguration within the fog services to facilitate responsive mass evacuations as well as open up new research challenges associated with analytics-embedding network and computation, which is critical for any disaster recovery activities. © 2021 Elsevier B.V.
Centre for Computational Science and Mathematical Modelling, Coventry University, Coventry, CV1 2JH, United Kingdom; School of Computing and Digital Technology, Birmingham City University, Birmingham, B4 7XG, United Kingdom; School of Computing, Electronics and Mathematics, Coventry University, Coventry, CV1 5FB, United Kingdom; Department of Informatics, Universitas Negeri Surabaya, Surabaya, 60231, Indonesia; Department of Communications and Networking, School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, 215123, China
