Global Traffic Spikes. No Panic at the Cisco!




from Global Traffic Spikes. No Panic at the Cisco!
by Jonathan Davidson

(Note: OK, so I know the title is a little cheesy, but being sheltered in place for two weeks with “High Hopes” playing in the background for inspiration has certainly influenced me.)

Seemingly overnight, social distancing across the globe has defined a new normal and we’re all on a fast-learning curve to adapt in our day-to-day lives. I’ve replaced physical meetings with video conferencing. I now have virtual “happy hours” with coworkers and friends to share concerns and also to laugh a little, much-needed in these uncertain times. Immersed in new methods of learning, my children spend their days in online classrooms, virtual museum tours, and social chat sessions. As a global community, we are relying on the Internet more than ever.

Shouldering the weight of these new digital experiences, service provider and cloud provider networks are experiencing a significant increase in traffic. Last week, in response to a request from the European Union, entertainment streaming service companies ‘turned down’ their video quality to lower bandwidth constraints. Netflix managed to reduce traffic load by 25% starting with Italy and Spain, which had experienced the largest spikes in traffic.

Cloud-based applications have also had a major increase in traffic. On March 18th, four million meetings took place over Cisco Webex, more than 2X what we typically handle on a high traffic day. At peak hours, we saw 24x the normal Webex volume. And we anticipate these numbers will continue to grow as people adjust and settle into a temporary virtual-first world.

These are daunting numbers to process and it’s important to understand what preparations are required to manage future traffic loads. The way we perceive Internet experiences will be influenced by both traffic volume on a particular network path and the performance of the applications we are trying to access. My team is currently analyzing traffic statistics with major carriers across Asia, Europe, and Americas and our data shows that typically, the most congested point in the network occurs at inter-provider peering points. However, the traffic exchanged at these bottlenecks is only a part of the total Internet traffic, meaning reports on traffic may be higher overall as private peering and local destinations also contribute to more traffic growth. Our analysis at these locations (see graph below) shows an increase in traffic of 10% to 33% over normal levels. In every country, traffic spiked with the decision to shut down non-essential businesses and keep people at home. Since then, traffic has remained stable or has experienced a slight uptick over the days that followed.

So, traffic volume is increasing overall, but what does that really mean? Appropriate network planning demands that we need to determine the effect and our response. Digging deeper, our analysis revealed that much of the growth resulted from a change in daily busy hour traffic patterns.

Typically, the busiest time on the network occurs between 6pm and 10pm, that’s when people are home watching streaming video. Although traffic during these hours has increased slightly (with some variance by carrier) it’s not the primary driver for the overall increase. As more of us use the Internet for work and school our traditional busy hour has changed, starting earlier and lasting longer (e.g. 9am to 10pm). Although this new traffic load between 9am – 6pm is considerable, it’s still below evening peak hours. Service providers are certainly paying attention to these changes, but they are not yet a dire concern, as most networks are designed for growth. Current capacities are utilized more over the course of the entire day.

We believe these usage trends do signal profound changes and future needs for service delivery and consumption. It’s likely that our “new normal” has caused us to jump the curve depicted in Cisco’s Annual Internet Report (AIR) and we anticipate the demand for connectivity will continue to grow from the new baseline. Unfortunately, there are still many without the privileges of broadband connectivity and the Internet of Things (IoT) remains in its infancy.

What does the future hold? The Internet is no longer simply critical, it has become ESSENTIAL. Economies, governments, and societies rely on the Internet to keep things moving. As the Internet grows from huge to MASSIVE, new architectures and innovations are required to change the economics. The Internet of the Future requires a completely different approach; how we built networks in the past is simply not sustainable. To briefly touch on a few points:

  • Ultra-high Performance: Lowering the cost-per-bit is table stakes. However, to do it significantly, you need to shift from bandwidth scarcity to bandwidth abundance. This unlocks new ways of thinking about network design. To learn more, check out what we introduced in December with the Internet for the Future
  • Automation: With modernized automation, networks can react and adapt to traffic peaks and valleys, in real-time, as well as proactively predict issues.
  • Telco Cloud: Agility is king. You need to be able to scale services and network functions up, out, and down – on demand.
  • Services Edge: Critical applications need to be moved closer to the end users. This reduces the ‘congestion radius’ that can result from high-demand applications (e.g. content streaming) and improves performance for critical applications (e.g. conferencing or security).
  • Peering: Security concerns and operational complexity typically dictate a small number of trusted/secured peering points to exchange traffic with other providers. By addressing these concerns with automation, service providers can relieve current bottlenecks with relatively low investment.
  • Fabric-based Architectures: Like large scale data centers, some service providers are considering fabric-based architectures as a means to add capacity and resiliency to networks.
  • Flexible Consumption Models: Using enterprise licensing agreements and subscription models, service providers can flexibly add more capacity during surges and they can install fully loaded systems; only paying for the bandwidth/infrastructure as needed.

Today, more than ever, I am grateful to live with the privilege of high-speed connectivity. Imagine how difficult and upended life would be without it during this global pandemic. I am grateful to work for a company that wants to change all of that for the better. I strongly believe Cisco has the focus to solve these problems. There is much work to do, but we do have a head start and “High Hopes”.

 

 

 

 

 

The post Global Traffic Spikes. No Panic at the Cisco! appeared first on Cisco Blogs.





Original article: Global Traffic Spikes. No Panic at the Cisco!
Author: