At the end of August, Santa Clara, Calif-based Frost & Sullivan, a business consultancy that offers companies advice on growth strategies, carried out an analysis of theof the edge computing market and how it will be impacted by the emergence of5G. Specifically, it looked at cloud workloads had how they would start moving to the edge.
The State of Edge Computing
Edge computing, the research reads, is a foundational technology for industrial enterprises as it offers shorter latencies, robust security, responsive data collection and lower costs. The research also predicts that approximately 90% of industrial enterprises will be using edge computing by 2022. It is not just edge computing that is set to grow, however, multi-access edge computing (MEC) is due to expand between now and 2024 too.
Multi-access edge computing (MEC), formerly mobile edge computing, is a network architecture concept that enables cloud computing capabilities and an IT service environment at the edge of the cellular network and, more to the point, at the edge of any network. The basic idea behind MEC is that by running applications and performing related processing tasks closer to the cellular customer, network congestion is reduced and applications perform better.
Despite problems, the research also pointed out that the demand for latency reduction in mobile networks for mission-critical applications is increasing in consumer, enterprise, and industrial use cases. This is particularly true as more work is being done through mobile devices.
Data-driven companies and governments are requiring a significant stream of data for real-time analytics while the growing adoption of IoT is resulting in increased demand for edge infrastructure globally. This will be enabled by reduced costs as implementation of edge infrastructure is resulting in lower operational expenses (lower traffic in backhaul, core) and better customer experience for telecom operators.
Edge infrastructure is helping telecom operators address the increasing consumption of high-definition video streaming in mobile devices. Enterprises are requiring network and application resiliency, achieved by distributed computing capabilities.
The new 5G network is being developed and is running parallel to the development of edge computing. In telecommunications, 5G is the fifth generation technology standard for broadband cellular networks, which cellular phone companies began deploying worldwide in 2019, and is the planned successor to the 4G networks which provide connectivity to most current cellphones.
Related Article: Edge Computing vs. Fog Computing: What's the Difference?
Edge and 5G Development
In a paper from UK-based STL partners, a consultancy that offers market development advice to telcos, at the end of last December, the author Dalia Adib, edge computing practice, lead, points out that 5G and edge computing are two inextricably linked technologies. According to the white paper they are both poised to significantly improve the performance of applications and enable huge amounts of data to be processed in real-time.
5G increases speeds by up to ten times that of 4G, whereas mobile edge computing reduces latency by bringing compute capabilities into the network, closer to the end user mobile edge computing reduces latency by bringing compute capabilities into the network, closer to the end user. He argues that both 5G and edge computing need to develop simultaneously for two reasons:
- It is inherent in the 5G standards as it is the only way to meet the latency targets that have been set. Improvements in the radio interface alone will not achieve these.
- The gradual approach operators are taking to deploy 5G — the 5G go slow cycle — will mean coverage of “full 5G” will be insufficient to cultivate an ecosystem of new applications. However, edge could seed a 5G market even before widespread coverage.
More Than Mobile
Ritesh Mukherjee is vice president at for product management at Burlington, Mass.-based networking company 128 Technology He says that, currently, 5G, is primarily focused on providing an enhanced mobile broadband experience primarily to consumers with compatible handsets. However, 5G will continue to evolve to support a broad range of features, many of which will require faster processing of large amounts of data quickly to provide enhanced experiences. The solution to this is edge computing which brings cloud resources-compute, storage, and networking-closer to applications, devices and users.
Eliminating round trip times by bringing machine learning, artificial intelligence, IoT processing, and decision making closer to the application will truly enable 5G. He cites the example of self-driving cars. With edge computing and 5G working together autonomous driving capabilities can brake immediately by having decisions made closer to the user by eliminating long round-trip times to the cloud. But this is still in the future.
How 5G Helps Edge Computing
This opens a bigger question: How 5G will provide greater benefits to edge computing? The 2ms tower-latency with 5G is fast, however the speeds offered by 5G do not improve user experience when businesses centralize their APIs, Stephen Blum, CTO and cofounder of San Francisco-based PubNub, told us. He points out that 99% of APIs are centralized in one or two data centers, so these businesses will not gain the benefits of 5G and are missing edge messaging connectivity. These businesses need to find new ways to bring data streaming edge messaging solutions or build a network that provides more geographically distributed access. The goal is to allow businesses to use the edge without needing to reimagine their existing centralized infrastructure. 5G with an edge messaging system brings your app's connectivity up to speed with 5G and delivers near-instant communication experiences.
“A crucial way to take advantage of the extensive capabilities of 5G and edge is securely sending events from data sources inside a business firewall out to mobile devices at the very moment they occur,” he said. “From database updates, to message bus events, to log entries, to cross-user behavior, efficiently and securing streaming data through business firewalls to externally connected devices.”As a final point, Marc Price, CTO of MATRIXX says that software development needs to follow 5G and edge computing development too. Software in the 5G era must support distributed architectures well, he said.
This is the biggest challenge to achieving the scale and scope of ambition required. The variety of 5G deployments is staggering. It encompasses solutions for massive IoT, densification of networks, and ultra-low latency. It involves isolation of network slices as well as edge-based components.
Microservices based functions must be independently scalable, and API first design should eliminate vendor lock-in. Software application vendors have a lot of work to do to design and develop solutions to support these needs. At the same time, agility and performance remain paramount while addressing these goals.
Finally, it should be kept in mind that all this technology is nascent from the Cloud Native Computing Foundation, a Linux Foundation project that was founded in 2015 to help advance container technology and align the tech industry around its evolution. While platform independence is paramount, there must be more mature solutions and support from the tools vendors to achieve success at scale to scale every component of the network for every possibility.