For many, the intersection of 5G wireless and the Internet provides very little new information, just from a quick overview. However, things look very different when viewed in the light of the 5G New Radio (NR) standard.
Consider e.g. A new technology in 5G NR called URLLC- which is short for ultra-reliable low latency communication. Designed for mission-critical and latency-sensitive Internet services, URLLC is a configuration and technology feature that enables a new class of applications and services. These services include things like remote control of robots; thin, reinforced unrealistic headsets, smart car crash systems, road traffic control and entertainment services such as fast-acting multi-player multi-region gaming.
The delay specification provided by URLLC can be anywhere from one to four msec on-air latency, well within the required hard limit of the latency required by these applications. In many ways, however, this delay specification is simply not sufficient in light of the fact that many of these latency-sensitive applications only make sense in connection with the Internet. Interaction with users, devices and cloud services over long distances forces one to think about the end-to-end latency characteristics that include the Internet.
To learn more about our Azure for Operators strategy, see the Azure for Operators e-book.
Stretches the range of low latency applications
No network can include all end users and cloud services, so any network operator is ultimately dependent on the Internet at some point. Based on the location of the source and destination, Internet delays can range from a single order to multiple orders of magnitude more than on-air 5G wireless latencies. This high latency time can effectively remove all the benefits of the low latency features offered through the 5G network. As a result, the scope of services that people enthusiastically look forward to is significantly reduced.
In addition to URLLC, 5G traffic in general (high definition voice and video calling) will require performance and reliability from both the wireless and Internet paths, even more than traditional web and corporate traffic.
Operators spend a lot of money managing and maintaining their networks and peering relationships, but so does Microsoft. The question then is, why do two massive industries do the same thing? Because both parties are moving packages around, does it not make more sense for them to cooperate?
Here, the well-managed, reliable and efficient Azure network must be considered as the backbone that operators trust. With this mindset, all the benefits of innovation that IT companies like Microsoft will quickly bring will come.
For example, large operators operating extensive national backbone can benefit greatly by expanding their wide-area network (WAN) with Azure’s WAN. In this example, a 5G network that spans both will allow 5G devices to more efficiently access cloud services implemented on Azure data centers. This includes first-party services such as Xbox cloud games as well as third-party services operated by Azure customers. Smaller carriers (or new carriers) that do not have their own national backbone can save resources, including time, human capital and money, and instead leverage Azure’s extensive investment to build a unique 5G network on top of something it already has. proved to be reliable.
Azure planet-scale WAN
Azure maintains a massive WAN with significant capacity and one that is constantly growing. We have over 175,000 miles of lit fiber optic and subsea cable systems. This connection covers close to 200 networks of presence points (PoPs) across 60 regions in 140 countries.
Azure’s network is connected to many thousands of ISPs and other networks with significant peering capacity. Our global network is well-equipped, with redundant fiber paths that can handle multiple simultaneous failures, it also has massive spare capacity in unlit dark fiber. These optical fibers are wholly owned or leased by Microsoft, and all traffic between and among Azure data centers within a region or across regions is automatically encrypted on the physical layer.
This combination of redundant fault handling capacity, dark capacity for significant growth and research advances in increasing transmission speeds means we have a massive amount of spare capacity to service 5G traffic to a wide range of new carriers.
Challenges of transporting 5G traffic over a WAN in the cloud
Figure 1 illustrates how packets can move from one client (in 5G terminology, a “user equipment” (UE)) to another over the extremely low latency Azure cloud network.
Figure 1: A unified platform.
With 5G, there is tremendous pressure on traditional metrics, which include latency, vibration, throughput, availability, and loss, according to which transport quality is typically judged. With on-air 5G latencies reaching close to the sub-ms range, cable transport latency is likely to dominate end-to-end performance. But with on-air 5G transmissions in the tens of Gbps range in Enhanced Mobile Broadband (eMBB) mode, only a small number of UEs could overwhelm a single peering link that today would typically have a capacity of tens of thousands to hundreds of Gbps .
Increasing the capacity of the peering surface area and of the spinal cords that support them is still an expensive endeavor. Finding effective paths through the maze of WAN links is also crucial to achieving business success. Interruptions are a reality for any cloud network, but 5G experiences will be more sensitive to packet loss and accessibility than traditional web and corporate traffic.
Reliability must be increased. This will be done by protecting against peering interruptions and congestion and by checking configuration changes. Performance must also be increased. This includes support for streaming audio and video services by actively reducing jitter and queue delays. Additional factors such as cost, security, availability, and regulatory and business policies also need to be addressed.
Furthermore, there will be a need to orchestrate cable transport for 5G implementations. 5G networks will distribute many network features in a distributed way. Strict needs regarding scaling and fault tolerance will make these implementations more complex than typical implementations of enterprise applications. Orchestrating cloud networking features, such as virtual networking, virtual networking, peering, virtual WAN, and private endpoints, all while meeting performance and policy constraints (business and legislation), represents a new challenge.
Makes Azure WAN great for 5G traffic
For many years, Microsoft researchers and engineers have been working on a hybrid-global traffic orchestra for routing network packets across the Azures WAN. Our orchestrator takes control away from classic internet protocols and instead shifts control to software that we build and control for 5G traffic. We place 5G streams that require high performance on low latency, high bandwidth paths to and from the Internet. Network streams that are cost sensitive are routed through cheaper paths instead.
In fact, we have developed a fast forwarding mechanism to build a 5G overlay on our existing WAN, thereby supporting a range of 5G network disks with different wired transport characteristics, while avoiding interference with the operation of the underlying enterprise cloud. network.
We have also expanded our state-of-the-art network verification capability to cover complex network topologies by modeling Virtual WAN, Virtual Networks and other network function virtualizations (NFVs) as well as modeling accessibility using formal methods. Using fast resolvers, we can check availability limitations on customer topologies, at the time of implementation, or during configuration changes.
We have used machine learning to predict the impact of peering link interruptions and congestion reduction strategies and use the data to improve the availability of the WAN peering surface area.
Our expertise in optimization algorithms has ultimately proven to reduce cloud networking costs. Techniques like these will be invaluable when cutting 5G paths on the surface that are cost effective but still meet the performance needs of each network disk.
Figure 2: 5G WAN technical architecture. This is how we imagine the various technical components to be assembled to serve 5G operators.
The significant advantage for operators
To repeat, Microsoft is heavily invested in operating a well-managed, always-available global network. We have incorporated several cutting-edge technologies, including scalable optimization, formal verification of routing policies, machine learning and AI. We imagine that operators can not only use our WAN to transfer low latency 5G packets, but also take advantage of multiple network services such as DDoS protection, firewalls, traffic accelerators, connection analysis, load balancers and speed limiters, many of which we use for to run existing Azure network loads.
At Microsoft, we bring the full power of research and engineering leadership into our network and quickly integrate innovation and new features to deliver reliable, low latency and low-cost service. In turn, this effort will open up the significant potential for next-generation services and applications as envisioned by society at large. It is no understatement to say that collaboration between operators and Azure is the key to unleashing the true power of 5G.
These are just some of the challenges we face and their solutions. To learn more about our Azure for Operators strategy, see the Azure for Operators e-book and contact us.