Situation-aware Edge Computing
Future wireless networks must cope with an increasing amount of data that needs to be transmitted to or from mobile devices. Furthermore, novel applications, e.g., augmented reality games or autonomous driving, require low latency and high bandwidth at the same time. To address these challenges, the...
|Online Access:||PDF Full Text|
No Tags, Be the first to tag this record!
|Summary:||Future wireless networks must cope with an increasing amount of data that needs to be transmitted to or from mobile devices. Furthermore, novel applications, e.g., augmented reality games or autonomous driving, require low latency and high bandwidth at the same time. To address these challenges, the paradigm of edge computing has been proposed. It brings computing closer to the users and takes advantage of the capabilities of telecommunication infrastructures, e.g., cellular base stations or wireless access points, but also of end user devices such as smartphones, wearables, and embedded systems. However, edge computing introduces its own challenges, e.g., economic and business-related questions or device mobility. Being aware of the current situation, i.e., the domain-specific interpretation of environmental information, makes it possible to develop approaches targeting these challenges.
In this thesis, the novel concept of situation-aware edge computing is presented. It is divided into three areas: situation-aware infrastructure edge computing, situation-aware device edge computing, and situation-aware embedded edge computing. Therefore, the concepts of situation and situation-awareness are introduced. Furthermore, challenges are identified for each area, and corresponding solutions are presented. In the area of situation-aware infrastructure edge computing, economic and business-related challenges are addressed, since companies offering services and infrastructure edge computing facilities have to find agreements regarding the prices for allowing others to use them. In the area of situation-aware device edge computing, the main challenge is to find suitable nodes that can execute a service and to predict a node’s connection in the near future. Finally, to enable situation-aware embedded edge computing, two novel programming and data analysis approaches are presented that allow programmers to develop situation-aware applications.
To show the feasibility, applicability, and importance of situation-aware edge computing, two case studies are presented. The first case study shows how situation-aware edge computing can provide services for emergency response applications, while the second case study presents an approach where network transitions can be implemented in a situation-aware manner.|
|Physical Description:||241 Pages|