Motivated by these two trends, a plethora of research has been conducted to support mobile cloud computing, which bridges the Cloud and mobile devices by leveraging both the powerful computing capability of the Cloud and the mobility support of mobile devices. Much of the work has been focused on how to effectively offload the computation-intensive tasks to the cloud and gets the results back promptly. In this way, the battery of mobile devices can be effectively preserved. However, due to the often unpredictable network latency, expensive bandwidth, and privacy concerns, especially in a mobile environment, cloud computing often cannot meet the stringent requirements of applications, for example latency-sensitive, security/privacy-sensitive, or geographically constrained applications. The growing amount of data generated by end devices and systems can often times become impractical or resource-prohibitive to transport over networks to remote clouds. To this end, "Edge computing" is new paradigm in which the resources for communication, computation, control and storage are placed at the edge of the Internet, in close proximity to mobile devices, sensors, and end users, and the emerging Internet of Things. Terms such as "cloudlets" and "micro data centers" have been used in the literature to refer to these small, edge-located data centers, while "fog" has been used to denote architectures that use a collaborative multitude of client or edge devices to carry out storage, communication and management. They all represent counterpoints to the theme of massive data centers and core networks that has dominated discourse in cloud and mobile computing.
The edge of the Internet is a unique place. For example, located often just one wireless hop away from associated mobile devices, it offers ideal placement for low-latency offload infrastructure to support emerging applications such as augmented reality, wearable cognitive assistance and cyber physical systems. It can be an optimal site for aggregating, analyzing and distilling bandwidth-hungry sensor data from devices such as video cameras. In the Internet of Things, it offers a natural vantage point for organizational access control, privacy, administrative autonomy and responsive analytics. In vehicular systems, it marks the junction between the well-connected inner world of a moving vehicle and its tenuous reach into the cloud.
New challenges and opportunities arise as the consolidation of cloud computing meets the dispersion of edge computing. On both data plane and control plane, the benefits of real-time capabilities, device-to-device and device-for-device communication, edge caching, client-centric control, and agile development need to be realized through evolving interfaces between the edge and the core. The challenges of security, trust and incentivization, of potential instability and inconsistency due to autonomous agents, and of the tradeoff between local and global control must also be addressed.
In this workshop, we intend to bring together industry practitioners and academic researchers to build the community and discuss the vision, challenges, and opportunities for Edge Computing research for the next decade. More specifically, the objectives of the workshop include:
- Foster the Edge Computing community, to increase interaction between academia and industry.
- Set the vision and identify grand challenges and open problems.
- Identify collaboration mechanisms among academia, industry and government.