We have covered edge computing in various posts in 2020. The power of the edge is its ability to decentralize and distribute compute power closest to the customer. Edge enables a range of applications, data processing and interactivity that was very hard to achieve at a high degree of performance due to data locality.
Amazon Web Services (AWS) has been at the forefront of edge computing innovation in two very specific ways – enabling Regions and Points of Presence (PoPs). With edge computing in mind, AWS released AWS Wavelength which has strong applicability to 5G. Wavelength allows you to deploy applications and services at the edge of a mobile carrier’s 5G network. By combining the benefits of 5G, such as high bandwidth and low latency, with the ability to use AWS tools and services customers can build next generation edge applications.
High bandwidth and the lowest possible latency is the key requirement imposed by end user devices from 5G networks ( described below). Edge nodes are utilized especially to control service delivery to specific regions and they can be customized to that region. However, the main issue remains as one follows the movement of application traffic towards application servers hosted in cloud. That application traffic uses the internet to reach out to subsequent servers. This journey adds more latency that hampers the purpose of 5G to deliver single digit latency for use cases like gaming, autonomous cars or industrial robots, etc.
AWS has resolved this bottleneck with a new offering – Wavelength. AWS wavelength brings AWS services to the edge of the 5G network – in areas called Wavelength zones. In a nutshell, Wavelength Zones are AWS infrastructure deployments that embed AWS compute and storage services within telecommunications providers’ datacenters at the edge of the 5G network. Because of Wavelength zones application traffic from mobile end users can reach servers running in wavelength zones without leaving the communication service provider’s network. In other words, the application becomes part of the 5G network and that drastically reduces latency.
As AWS describes it:
AWS Wavelength is an AWS Infrastructure offering optimized for mobile edge computing applications. Wavelength Zones are AWS infrastructure deployments that embed AWS compute and storage services within communications service providers’ (CSP) datacenters at the edge of the 5G network, so application traffic from 5G devices can reach application servers running in Wavelength Zones without leaving the telecommunications network. This avoids the latency that would result from application traffic having to traverse multiple hops across the Internet to reach their destination, enabling customers to take full advantage of the latency and bandwidth benefits offered by modern 5G networks.
If one catalogues the areas ITU-R categorized as key usages scenarios for 5G, the below three main categories can be identified and all of them have a strong applicability to Edge computing.
- Enhanced Mobile Broadband (eMBB): The Enhanced Mobile Broadband category of use cases include areas such as mobile hotspots where high data transfer rates are needed across wide geographical areas. The eMBB area addresses human-centric communications where user experience needs to be seamless. Examples include Video Streaming, supporting remote workers, mobile broadband, AR/VR, etc.
- Ultra-reliable and low-latency communications (URLLC): The second category of use cases include those where the latency of communication is critical in ensuring the safety of both consumer as well as industrial equipment. Thus, this covers both human and machine communication. Examples include vehicle-to-vehicle communication, industrial equipment controlled over wireless, supply chain automation, 3D gaming, and remote surgeries.
- Massive machine-type communications (mMTC): The final category deals with the explosion of devices that are all connected together and are low cost. These devices typically send out low volumes of data at regular intervals. A large category of these use cases deals with IoT scenarios.The following parameters are the requirements for IMT-2020 5G candidate radio access technologies
As 5G networks expand, operators are deploying Wavelength Zones so application traffic from 5G devices can take full advantage of the low latency and high bandwidth on offer. And when fast connections to the cloud are pushed to the farthest edges of the network, all sorts of interesting applications can be built.
AWS is still a leader in public cloud service domains according to many reports. During the pandemic, there has been exponential growth in subscribing AWS cloud services due to the high demand for digital applications. As per Q3 2020 report published by AWS, revenue of $11.6 billion for Q3 2020 is reported as compared to $8.9 billion for Q3 2019. AWS revenue grew 29% in that quarter. This makes it very much clear that a large number of enterprises who are AWS customers would like to deliver services to their end customers in an efficient manner. AWS Wavelength is cutting that barrier and avail the AWS services and tools, to deliver innovative 5G applications and next-generation user experiences.
AWS Wavelength Zone
It is an AWS global Infrastructure deployment within a communications/telecom service providers’ facility or architecture. This enables application traffic to reach application servers without leaving the telecommunications network. Each Wavelength Zone is specific to a carrier and location. Wavelength Zones are connected to the parent Region through a redundant and high-bandwidth private network, which provides the applications running in Wavelength Zones fast, secure, and seamless access to the rest of AWS’ services.
AWS Wavelength extends the 5G architecture to obtain agile application delivery to customers and get responses with the lowest possible latency.
As per the solution brief published by AWS, AWS Wavelength will be available within CSP networks such as Verizon, Vodafone, KDDI, and SK Telecom in places like the United States, Europe, Japan, and Korea. This will enable the delivery of ultra-low latency applications to a global base of end-users and connected devices.
To get more details and understand detailed use cases, please visit the solution catalog here.