Understanding Infrastructure Edge Computing. Alex Marcham
Читать онлайн книгу.
the Open Glossary of Edge Computing has been adopted by the Linux Foundation’s LF Edge [3] group as an official project and continues to contribute to a shared set of terminology for edge computing to help facilitate clear discussion and shared understanding.
2.3 Where Is the Edge?
As previously described, an edge is itself a contextual entity. By itself, an edge cannot exist; it is the creation of two things at the point at which they interact. This somewhat floaty definition is one part of what has made establishing a concise and clear definition of edge computing difficult, especially when combined with the many different factors and dimensions that edge computing will influence.
This book will focus on the accepted definition from the Open Glossary of Edge Computing which uses the physical and role‐based separation provided by using the last mile network as a line of demarcation between the infrastructure edge and device edge to provide separation and clarity.
2.3.1 A Tale of Many Edges
Although there are many potential edges, for the purposes of this book and to the most general definition of edge computing, the edge that is of the greatest importance is the last mile network.
The last mile network is the clearest point of physical separation between end user devices and the data centre infrastructure which supports them. In this context, the last mile network refers to the transmission medium and communications equipment which connects a user device to the network of a network operator who is providing wide area network (WAN) or metropolitan area network (MAN) service to one or more user devices, whether large or small, fixed position or mobile.
Examples of last mile networks include cellular networks, where the transmission medium is radio spectrum and the communications equipment used includes radio transceiver equipment, towers, and antennas. Wired networks such as those using cable, fibre, or digital subscriber line (DSL) are also examples of last mile networks which use a copper or fibre‐based transmission medium. The specific type of last mile network used is irrelevant here for the terminology of edge computing.
This definition cannot capture all of the potential nuance which may exist; for example, in the case of an on‐premises data centre which is physically located on the device side of the last mile network, the owner of that data centre may regard it as infrastructure rather than as a device itself. However, a different definition and accompanying set of terminology offering equal clarity without introducing unnecessary dimensions into the equation has not been established within the industry, and so this book will continue to use the infrastructure edge and device edge, separated by a last mile network.
Fundamentally, if everything can be recast as an example of edge computing, then nothing is truly an example of edge computing. It is similar to referring to a horse and cart as a car because both of them consist of a place to sit, four wheels, and an entity that pulls the cart forward. This is important to note with both the infrastructure edge and the device edge. In the case of the former, an existing data centre which exists a significant distance away from its end users should not be referred to as an example of edge computing. If, however, that same data centre is located within an acceptable distance from its end users and it satisfies their needs, an argument can be made for it to be so.
Similarly, if a device edge entity, such as a smartphone which already had significant local compute capabilities is now referred to as an edge computing device yet does not participate in any device‐to‐device ad hoc resource allocation and utilisation, this is a somewhat disingenuous application of the term edge computing. However, where there was once a dumb device or no device at all which is now being augmented or replaced with some local compute, storage, and network resources, this can be reasonably argued to be an example of device edge computing, even if limited in capability.
Although “edge washing” of this type is not unique to edge computing as similar processes occur for most technological changes for a period of time, due to the difficulties previously mentioned in the industry arriving at a single set of terminology around edge computing, this can be challenging to identify. This identification challenge can be addressed by using the framework described in the next section.
2.3.2 Infrastructure Edge
The infrastructure edge refers to the collection of edge data centre infrastructure which is located on the infrastructure side of the last mile network. These facilities typically take the form of micro‐modular data centres (MMDCs) which are deployed as close as possible to the last mile network and, therefore, as close as possible to the users of that network who are located on the device edge. Throughout this book, these MMDCs will typically be referred to as infrastructure edge data centres (IEDCs), whereas their larger cousins will be referred to as regional or national data centres (RNDCs).
The primary aim of edge computing is to extend compute resources to locations where they are as close as possible to their end users in order to provide enhanced performance and improvements in economics related to large‐scale data transport. The success of cloud computing in reshaping how compute resources are organised, allocated, and consumed over the past decade has driven the use of infrastructure edge computing as the primary method to achieve this goal; the infrastructure edge is where data centre facilities are located which support this usage model, unlike at the device edge.
Although it is typically deployed in a small number of large data centres today, the cloud itself is not a physical place. It is a logical entity which is able to utilise compute, storage, and network resources that are distributed across a variety of locations as long as those locations are capable of supporting the type of elastic resource allocation as their hyperscale data centre counterparts. The limited scale of an MMDC compared to a traditional hyperscale facility, where the MMDC represents only a small fraction of the total capacity of that larger facility, can be offset by the deployment of several MMDC facilities across an area with the allocation of only a physically local subset of users to each facility (see Figure 2.1).
2.3.3 Device Edge
The device edge refers to the collection of devices which are located on the device side of the last mile network. Common examples of these entities include smartphones, tablets, home computers, and game consoles; it also includes autonomous vehicles, industrial robotics systems, and devices that function as smart locks, water sensors, or connected thermostats or that can provide many other internet of things (IoT) functionalities. Whether or not a device is part of the device edge is not driven by the size, cost, or computational capabilities of that device but on which side of the last mile network that it operates. This functional division clarifies the basic architecture of an edge computing system and allows several more dimensions such as ownership, device capability, or other factors to be built on top.
Figure 2.1 Infrastructure edge computing in context.
These devices may communicate directly with the infrastructure edge using the last mile network or may use an intermediary device on the device edge such as a gateway to do so. An example of each type of device is a smartphone that has an integrated Long‐Term Evolution (LTE) modem and so is able to communicate directly with the LTE last mile network itself, and a device which instead has only local range Wi‐Fi network connectivity that is used to connect to a gateway which itself has last mile network access.
In comparison to infrastructure edge computing, many devices on the device edge are powered by batteries and subject to other power constraints due to their limited size or mobile nature. It would be possible to design cooperative processing scenarios using only device edge resources in which a device can utilise compute, storage, or network resources from