UAV and Fog Computing for IoE-Based Systems: A Case Study on Environment Disasters Prediction and Recovery Plans

Mohammed Al-Khafajiy, Thar Baker, Aseel Hussien, Alison Cotgrave

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNChapterpeer-review

Abstract

In the past few years, an exponential upsurge in the development and use of the Internet of Everything (IoE)-based systems has evolved. IoE-based systems bring together the power of embedded smart things (e.g., sensors and actuators), flying-things (e.g., drones), and machine learning and data processing mediums (e.g., fog and edge computing) to create intelligent and powerful networked systems. These systems benefit various aspects of our modern smart cities—ranging from healthcare and smart homes to smart motorways, for example, via making informed decisions. In IoE-based systems, sensors sense the surrounding environment and return data for processing: Unmanned aerial vehicles (UAVs) survey and scan areas that are difficult to reach by human beings (e.g., oceans and mountains), and machine learning algorithms are used to classify data, interpret and learn from collected data over fog and edge computing nodes. In fact, the integration of UAVs, fog computing and machine learning provides fast, cost-effective and safe deployments for many civil and military applications. While fog computing is a new network paradigm of distributed computing nodes at the edge of the network, fog extends the cloud’s capability to the edge to provide better quality of service (QoS), and it is particularly suitable for applications that have strict requirements on latency and reliability. Also, fog computing has the advantage of providing the support of mobility, location awareness, scalability and efficient integration with other systems such as cloud computing. Fog computing and UAV are an integral part of the future information and communication technologies (ICT) that are able to achieve higher functionality, optimised resources utilisation and better management to improve both quality of service (QoS) and quality of experiences (QoE). Such systems that can combine both these technologies are natural disaster prediction systems, which could use fog-based algorithms to predict and warn for upcoming disaster threats, such as floods. The fog computing algorithms use data to make decisions and predictions from both the embedded-sensors, such as environmental sensors and data from flying-things, such as data from UAV that include live images and videos.

Original languageEnglish
Title of host publicationUnmanned System Technologies
PublisherSpringer
Pages133-152
Number of pages20
DOIs
Publication statusPublished - 21 Apr 2020

Publication series

NameUnmanned System Technologies
ISSN (Print)2523-3734
ISSN (Electronic)2523-3742

Bibliographical note

Publisher Copyright:
© 2020, Springer Nature Switzerland AG.

Cite this