Intelligent Network Operations
We are in the middle of the fourth industrial revolution. At Ericsson, we see the potential to change how we operate networks as dramatically as the machines of the industrial revolution changed the factory floor. Ericsson has been exploring automation, driven by machine intelligence, in our research labs since 2007 and today we hold hundreds of patents in this area. We plan to lead the automation revolution for the telecom industry.
As new technologies like 5G, IoT and Cloud are gaining traction, networks are becoming more complex. It is becoming challenging for humans to keep up with this complexity and keeping networks operating at the level prescribed by the evolving services. We are already flooded by data and this is only the beginning.
So, let's take a closer look at how we address this and what it means for network operations.
In the past, all networks around the world were managed by people. Engineers monitored thousands of alarms that appeared daily on screens in network operations centers in order to create trouble tickets and eventually solve the underlying issues.
In our network operations centers today, only 5% of these trouble tickets are created manually – the rest is all automated. In the past, an engineer had to go through all the trouble tickets to assess what sort of corrective tasks were needed and then describe them in a work order. Keeping in mind that in 2017 we processed 51 million trouble tickets, you can imagine how big a task it is for engineers to review these tickets and assign work orders. Today, 95% of these work orders are created automatically.
On top of that, we have automation rules built into the network. The system processes information in real time and, when a specific activity is triggered, a carefully designed sequence of automated tasks is performed. This automation engine already sends about one million commands to the network every day and processes 70% of the alarms we monitor.
By boosting automation with machine intelligence technologies – such as advanced analytics, deep learning, machine learning and artificial intelligence solutions – predictions and models can be provided that could not be created by humans alone.
That's why we call it "Intelligent Network Operations". By taking advantage of the data available in the network – as well as various other forms of external data such as weather conditions and adding the intelligence of machines – network operations can be performed in a smarter way.
Applying machine learning and artificial intelligence to automation takes it to a new level – intelligent automation. The objective is to predict events before they happen and take preventative or corrective action to ensure incidents do not occur.
We will continue to invest in machine learning and machine reasoning to fully exploit the opportunities inherent in new networking technologies. With our global presence, industry insights, domain expertise and thought leadership in machine intelligence, we are in a unique position. We are bringing Intelligent Network Operations to life and automating the telecom industry.