“Edge” Movement as a Paradigm Shift in Computing, Networking and Storage
In the evolution of computing, networking, and storage architectures, the edge of the network has always played an important architectural and functional role. Computing resources have been located in homes, in factories, along roads and highways, in cities and their shopping centers. The idea of pervasive or ubiquitous computing has been active for a long time. With the advent of the internet and streaming services, caching media and data at the edge have been fundamental to the evolution of Web services and video delivery. So why does anyone need to claim that we are witnessing a new technology trend let alone invent new and often conflicting terms to describe it?
First, many of the still maturing breakthroughs in Cloud infrastructure and services are needed also at the edge, features such as virtualization, data analytics, software defined networking, and modern resource management. However, the classic Cloud model does not work well for a variety of reasons in cases where faster response times are needed or the sheer volume of data transmitted would overwhelm the network. Complementing the swarm of Endpoints and the Cloud, the new “Edge” will enable the seamless deployment of distributed applications, responding to the needs of critical use cases in a broad array of verticals. With appropriate adaptations, Cloud-like innovations applied to localized domains that have been untouched by the IT evolution will be revolutionary.
Furthermore, this new trend is tightly connected with the growing focus on the Industrial Internet of Things (IIoT), where these innovations provide a key element of the end-to-end infrastructure required to support IIoT applications, even as it has deep relevance in traditional IT and in the Mobile Internet. Industrial and manufacturing applications often have strict timing and safety requirements, such as time-sensitive and deterministic behaviors in networking, computing and storage, sensor and actuator support, and aggregation. The very nature of these applications precludes the notion that Cloud-based services can provide a complete solution. Adapting the Cloud-model to the industrial world is the natural thing to do.
One Movement, under Many Names
It is unfortunate that for a number of reasons, perhaps related to marketing battles across industrial giants (e.g., Cisco, HPE, Huawei, Amazon, Microsoft, etc.), this common movement to the edge has been associated with many confusing and/or conflicting names, such as: Fog Computing, Edge Computing, Edge Cloud, Mobile Edge Computing, Real-time Advanced Computing, and so on.
To highlight a bit of the history behind the “Edge” and “Fog” technology trend, starting in 2009, the Advanced Architecture and Research team at Cisco Systems did much of the early exploration, prototyping, and evangelization for the deployment of modern edge computing. The main inspiration for this work came from focusing on Connected Vehicles and Intelligent Transportation.
Flavio Bonomi’s team started using the term “Fog Computing” on September 16th, 2010, at a meeting at the Monterey Bay Aquarium Research Institute (MBARI) in Moss landing, California. During Flavio’s presentation, Ginny Nichols, formerly at AT&T and Cisco, said: “Flavio, why don’t you call what you are talking about Fog Computing, which is Cloud Computing close to the ground.” Flavio adopted the idea and the broad concept got a name.
Flavio and his team continued to explore and evangelize the Fog paradigm over the next few years, and their work appeared outside Cisco, starting in 2011 , , , , , .
After leaving Cisco, Flavio Bonomi founded Nebbiolo Technologies which built the Fog Computing Platform to support the many applications in Industrial Automation. Rather than trying to make sense of all these terms or identify boundaries across them, it is more important to recognize the broad and common characteristics of this technology trend at the edge and to develop it for its powerful consequences.
- F. Bonomi, “Cloud and Fog Computing: Trade-Offs and Applications”, EON-2011 Workshop, at the International Symposium on Computer Architecture (ISCA 2011), San Jose’, USA, (2011).
- F. Bonomi, “Connected Vehicles, the Internet of Things, and Fog Computing”, The Eighth ACM International Workshop on Vehicular Inter-Networking (VANET), Las Vegas, USA, (2011).
- F. Bonomi, R. Milito, J. Zhu, and S. Addepalli, “Fog Computing and its role in the Internet of Things,” in Proceedings of the First Edition of the MCC”12, ACM, (2012), pp. 13-16. (Already in the list for the introduction)
- F. Bonomi, R. Milito, P. Natarajan and J. Zhu, N. Bessis and C. Dobre (eds.), “Fog Computing: A Platform for Internet of Things and Analytics”, Big Data and Internet of Things: 169 A Roadmap for Smart Environments, Studies in Computational Intelligence 546, DOI: 10.1007/978-3-319-05029-4_7, © Springer International Publishing Switzerland, 2014
- J. Zhu, D. Chan, M. Prabhu, P. Natarajan, H. Hu, and F. Bonomi, “Improving web sites performance using edge servers in Fog Computing architecture,” in Service Oriented System Engineering (SOSE), 2013 IEEE 7th International Symposium on, March 2013, pp. 320–323.
- X. Zhu, D. Chan, H. Hu, M. Prabhu, E. Ganesan, F. Bonomi, “Improving Video Performance with Edge Servers in the Fog Computing Architecture” Intel Technology Journal . Apr2015, Vol. 19 Issue 1, p202-224. 23p.