We are hearing amazing stories from our Cisco customers as they roll out intelligent analytics and assurance solutions in the form of Cisco DNA Center, Meraki insight, and Network Assurance Engine (NAE). The comments are on the accuracy and complexity of the analytical models that we have built, based on 30 years of Cisco networking leadership. You can read my blog post on how analytics works here. But, the back story to this is the approach of Machine Learning. When we add advanced machine learning algorithms to these products, the intelligence and system flexibility will be even more exciting. Let me explain…

Assurance in IP networking uses an analytics engine to verify that the network is operating based on the intents of the business. These intents are translated based on the network policies that IT configured when the system was set-up. The resulting model drives the decisions that an assurance solution makes to improve the network. This model is very good at network optimization, but every network is different, and network utilization is always changing as we change the way we use it.

Machine learning offers a way to constantly update our analytics model, in real time, to better represent the ever-changing dynamic function of todays complex IP networks. It also provides a way for the analytics engine to see into future events and prepare for them in advance. So how does machine learning work?

Simply put, machine learning is where a computer can learn from experience as it optimizes the network. As it learns, the analytics model it uses for decisions is optimized and becomes a better representation of the true intent of the network and its business goals. Cisco is developing three machine learning techniques to enhance our analytics engines:

  • Cognitive analytics
  • Predictive analytics
  • Trending analytics

Cognitive analytics is where behavioral patterns are extracted from the network. For example, we can look at the patterns in Wi-Fi roaming around the network, or number of clients on certain access points, or smart phone models. Patterns in network usage give the analytics engine a benchmark for comparison. Performance below the benchmark in any given pattern could then be flagged for optimization. And, of course, as patterns change in network usage, the machine learning engine would update the benchmark.

Predictive analytics seeks to predict an expected network and user experience.  Here, the machine learning engine can predict increases in Wi-Fi interference, WAN/Cloud/Internet congestion, office traffic load, etc. This is because in IP networks, a problematic event is often proceeded by a benign event or series of events. By learning how series of events are correlated to one another, predictive analytics can see the future before it happens. – Truly a paradigm shift in network troubleshooting!

Trending analytics takes on the “what-if” scenarios. What if we had 80 wireless devices in the conference room? What if all of our android clients switched to iPhone? What changes would be required to network QoS if our Skype traffic increased by 60%?  By looking at scenarios beyond the norm, trending analytics can plan for the unexpected and suggest for contingencies in the analytics model.

So, while I am proud to hear the enthusiasm in our customers’ stories as they roll-out our latest analytics and assurance solutions, I can’t wait to see the effect that machine learning has on these products.  The upcoming blog posts in this series will go into more detail on each of these three types of machine learning and how Cisco will implement them in order to make our networks more intelligent.


Get the latest news about Cisco network analytics at www.cisco.com/go/assurance

and read this blog on how Cisco AI Network Analytics is making networks smarter and simpler to manage.


Duval Yeager

Engineering Product Manager

DNA Center Product Management