Edge computing (EC) – and there are several different versions/approaches – emerged on the wireless industry stage several years ago. It has the potential to be as disruptive a technology as anything that is being discussed today – 5G New Radio, NFV/SDN, C-RAN, etc. In fact, EC is quite likely to help realize the promise of 5G particularly since the new 5G system architecture is designed to capitalize on virtualization.
Defining the edge
Before we discuss where the edge actually is, we should first agree on a definition of edge computing. iGR defines an edge computing hardware platform as a secure, virtualized platform which can be “opened up” to third parties – content providers, application developers, etc. That platform might incorporate an LTE radio, Wi-Fi, 5G NR or some combination of them. Today, most edge compute implementations use Ethernet and/or Wi-Fi and not cellular. Over time, iGR believes that will change as private LTE networks get deployed and 4G/5G-based IoT devices are brought to market.
It could be argued that mobile edge computing is a subset of the mobile cloud computing concept in which user equipment takes advantage of “distant” storage and compute resources, along with the transport provided by the RAN, to:
- Introduce new applications that could not have run on the UE
- Extend the battery life of the UE by “offloading” compute to the cloud
- Increased storage via the cloud and/or obviating the need for storage (e.g., streaming music, video, etc.).
Edge computing essentially moves the cloud servers closer to the UE so it helps mitigate the downsides of mobile cloud computing – increased mobile data usage and higher latency.
Network operators also benefit from edge computing since they are able to:
- Offload traffic from their networks at earlier point thereby reducing the burden on their RAN and backhaul
- Use edge computing to improve the efficiencies of their network operations, which ties into the NFV/SDN trend as well as the evolution of their networks from LTE and the EPC to 5G NR and the next-gen core.
- Potentially offer new services to enterprises via the edge computing platforms.
Locating the ‘edge’
You could say that the edge is located where, if you take one more step, you fall of the cliff!
In networking terms, the ‘edge’ typically means a location that is very close to the end consumer of the content. This can mean different locations for an operator versus an enterprise. And depending on the type of content, the type of end user and the specific needs of the application, the edge could be in very different places. There are essentially multiple ‘edges’ depending on need.
Some considerations in deciding where to locate the edge computing server include:
- How much latency can the given function tolerate?
- Mobility of the user equipment through the mobile network
- What are the benefits of doing the computation at the edge versus somewhere else? How does the storage location of the data itself impact this cost/benefit analysis?
- How is backhaul impacted? What else is going on in the network?
- How inter-dependent is the given application with other applications and/or network functions?
- Does the end user have a say in where the processing is done? Perhaps the answer is different for enterprise and consumer users.
- How scalable are the edge compute resources are available at the edge to handle additional offloading?
- If the edge computing platform is hosting packet core components for 4G LTE and 5G, as well as third-party applications, what measure are in place to prevent those third-party application from hogging resources the network needs? Alternatively, are multiple edge compute platforms required to prevent this type of situation?
- Are there security concerns regarding where the processing is done? Could the 4G or 5G packet core get hacked by exploiting a weakness in the EC?
These and many other questions have to be answered on an application-by-application, company-by-company and/or operator-by-operator basis. The goal here is simply to show that there is a lot more to edge computing than simply stating that edge compute enables AR/VR in a potentially more robust fashion than running all of that on the user equipment. And none of the above really dives into the business case conflicts that will certainly arise among all the various companies that are trying to provide their product/service to their (mobile) customer in the least expensive, most value-added fashion.
At a high level, the edge computing answer to these questions involve providing “general purpose” computing hardware in a secure form factor on which secure, virtualized software can be run. These edge nodes can emulate parts of the core network, serve as reliable caching units and/or run virtualized applications from any number of an operator’s developer partners.
The answer to this question is easy: anywhere and everywhere!
Edge compute servers by definition need to be close to the end user, have a reliable source of power and backhaul, be in a secure location (both physically and from a network perspective), and be accessible for maintenance, etc. Some typical locations for EC therefore include:
- On a truck or vehicle – for example, a small server can be placed on a refrigerated truck to monitor the various sensors for the cargo, engine and other systems. The various inputs are processed locally so that only important alerts are sent up to the cloud. This type of architecture can easily be applied to an aircraft, train or ship.
- Cellular base stations for both 4G LTE and 5G – a wide range of applications, including public cloud environments, can be supported at the edge of the mobile network, thereby reducing latency and backhaul and providing capabilities such as local breakout.
- Cell aggregation sites, where multiple small cells are aggregated before backhauling the traffic back to the packet core – the edge server in this example is one step removed from the radio but will be able to support a wider number of users.
- Edge of the operator’s core network – this could be for the mobile operator, telco or ISP.
- In the enterprise – obviously, this includes a wide range of possible locations from the enterprise main data center to retail and manufacturing locations, depending on the application.
- In a home or multiple-dwelling unit, for example to cache high-definition movies locally or enable AR/VR gaming.
- At the side of the road to support smart traffic and transportation applications, as well as smart city. Just as the controls for stop and traffic lights are located in secure boxes near the intersection, edge compute servers could also be location in the same place.
To summarize, virtualized applications from vendors, service providers, and third-parties would be deployed and executed within virtual machines that run on edge compute platforms located in a range of different places. A single edge compute platform can run multiple VMs; which lets the hardware resources be leveraged across multiple applications and perhaps even service providers in a controlled, efficient, scalable and flexible manner.
The location for edge computing servers is limited only by the availability of secure power and backhaul, a secure location and imagination. While this article outlined some typical EC locations, the reality is that new locations are being defined every day to meet specific content and application needs, with many more to come.
iGR is a market strategy consultancy focused on the wireless and mobile communications industry. Founded by Iain Gillott, one of the wireless industry’s leading analysts, we research and analyze the impact new wireless and mobile technologies will have on the industry, on vendors’ competitive positioning, and on our clients’ strategic business plans.
A more complete profile of the company can be found at http://www.iGR -inc.com/.