& cplSiteName &

SDN + AI: A Powerful Combo for Better Networks

Carol Wilson
8/29/2016
50%
50%

The combination of software-defined networking and machine learning/artificial intelligence is becoming a powerful tool for making networks more reliable and secure.

And while not everyone is willing to talk about their activities yet -- CenturyLink Inc. (NYSE: CTL) and Verizon Communications Inc. (NYSE: VZ) declined interview requests on this topic -- a peek inside what is happening at AT&T Inc. (NYSE: T) and Level 3 Communications Inc. (NYSE: LVLT) offers a clear view of what's possible. In this first of two stories, executives at those companies share how machine learning and AI are being built into their networks today.

As Mazin Gilbert, AVP of Intelligent Services at AT&T Labs, explains, artificial intelligence and machine learning are hardly new concepts, nor is the idea of using these tools to improve network performance and security. There was talk about that as far back as the 1980s, he says.

But AI and machine learning "are engines that feed on data, like a car engine feeds on gasoline," Gilbert explains. "They require extensive computation to be able to make recommendations and decisions. Now we are at the era where we can do that and we can do it cost effectively. We can do it in a way that impacts the service and the application and the experience in real time, live as that communication is happening."

At Level 3, "we are passionate about this and have major investment going into" artificial intelligence and machine learning, says Travis Ewert, VP of network software development. Internally, the company has branded these efforts "See, Know and Act," for the three stages of collecting data, analyzing it and taking action on that analysis.

Both companies are combining their human intelligence, developed over decades of experience, with machine learning and AI in ways that take advantage of both. The critical piece of the latter is the much-coveted ability to rapidly analyze massive volumes of information to detect patterns, trigger warnings and find anomalies that can help network operators predict a range of network issues before they impact customers.

"Human experts are typically excellent at understanding context," Gilbert says. "We also are very good at understanding logic and we are very good at making reasonable and informative decisions. Those are weak areas of AI systems. We are taking the key differentiator of human experts and key differentiators of AI systems and bringing them together to provide us the security, reliability and best experience in our network."

Staggering numbers
To frame the "massive data" discussion, consider these numbers from Level 3: According to Ewert, Level 3 is collecting threat information on about 50 billion events a day across its global network. It is collecting tens of millions of NetFlow messages -- those generated by Cisco routers -- daily as well. On its global content delivery network infrastructure, Level 3 collects about 2 million logs a second, while on its data network, it gets about 3 million messages a second on network and service performance, tracking things like latency, loss and jitter in both passive and active ways.

All of that data goes into four massive data lakes that Level 3 maintains globally.

"What is kind of cool now is that we are grabbing so much data that all of a sudden, our lakes have become an ocean," Ewert says. "And that's just the 'See' piece of the branding statement, where it starts: Can you collect all of that data at scale?"


Want to know more about carrier SDN strategies? Check out our dedicated SDN content channel here on Light Reading.


AT&T also collects centralized data, for analysis, but Gilbert is more excited about discussing the data collection at the very edge of AT&T's network, made possible by the software-defined networking that allows the distribution of network intelligence to that edge.

"We can examine data at the end of the flow, which we have traditionally done," he says. "By putting the intelligence at the edge, and being able to detect that [issue or anomaly] fast enough and address that fast enough -- not ten or 20 minutes later -- that could be the tremendous difference between a disaster and having the best experience. It becomes a matter of how fast and how efficiently and how accurately you are able to address those issues."

Being able to analyze data in motion, starting at the edge, is what makes rapid response possible, Ewert says, and also enables a much higher degree of security.

"That is where things like string analytics, advanced algorithms, machine learning -- all of those things come into play," he comments. "The key to this one is how do you draw knowledge from this data that is in motion. We have built in some streaming analytics where we can literally be running analytics or advanced algorithms before the data goes to long-term data store, so we can look for triggers or detection points or 'if-then' statements and that could be for network or service performance."

So when latency is detected, or a certain level of utilization, an automatic response is triggered that mitigates the problem, or when a certain alignment of data matches a suspected threat profile, the network can quarantine or block traffic for security mitigation purposes.

"We have literally got algorithms on tens of thousands of flows," Ewert says. "And that gives us the ability to look at all those streams of data to be able to baseline a known state." The current traffic patterns can then be compared to that baseline, in detecting anomalies that might trigger a response, and those baseline comparisons can be done based on time of day or day of the week, or multiple other factors.

A new network platform
Some of what AT&T is doing today in its software-centric transformation of its network was done previously in individual applications or services or for specific customers, Gilbert says. But the move to SDN is enabling AT&T to build machine learning and artificial intelligence into its network platform, so they become tools on which all other services and applications are built.

"It becomes core to our network," he says. "Our network is not just serving big customers or high-valued customers only; it is serving everybody. We are going from an application-centric solution to a platform-centric network solution that is really supporting everybody and all applications."

Artificial intelligence is being used to monitor the behavior of the virtual machines and applications running in AT&T's SDN, so that when any issues or degradations are noticed, the decision can be quickly made on how to handle that issue. "That is where we apply our traditional intelligence to decide whether we move the traffic to another machine without the customer even knowing or without being impacted, or do we reboot the machine during a downtime, or is there another solution," Gilbert says. "That is what we are doing today to help us build a more reliable network."

Tomorrow: What lies ahead

— Carol Wilson, Editor-at-Large, Light Reading

(5)  | 
Comment  | 
Print  | 
Newest First  |  Oldest First  |  Threaded View        ADD A COMMENT
Gabriel Brown
50%
50%
Gabriel Brown,
User Rank: Light Sabre
3/21/2017 | 11:28:14 AM
Re: Automating Decision-making is Key
Bit of a dredge, but great article Carol!
Virtual_Robert
50%
50%
Virtual_Robert,
User Rank: Moderator
9/1/2016 | 5:11:48 AM
Automating Decision-making is Key
Great article, Carol. I like Travis' "See, Know, Act" mantra - the truly big results come when artificial intelligence is making the decisions on the optimum course of action to take, in terms of actually changing and rearranging resources. There's still a gap between spotting (or predicting) a problem, and figuring out the best action to take to minimise its impact. The nature of both makes AI a key technology for telcos going forward.
tojofay
50%
50%
tojofay,
User Rank: Light Sabre
8/31/2016 | 9:36:39 AM
game changer for real
http://www.telecomasia.net/content/infinera-software-suite-aims-bring-sdn-services-optical-layer
cnwedit
100%
0%
cnwedit,
User Rank: Light Beer
8/30/2016 | 9:12:05 AM
Re: This looks gamechanging
This is definitely happening. It's been most visible in the security space because it's enabling the network to provide security for data in transit and in storage, and for greater predictive capabilities where threats are concerned. 

There is still a long way to go, obviously, but the strides being made are considerable. 
Ray@LR
100%
0%
Ray@LR,
User Rank: Blogger
8/30/2016 | 5:32:18 AM
This looks gamechanging
The increasingly smart, autonomous network... that has been the goal of R&D teams since I can remember. Maybe we're finally at the start of the curve that sees that start to happen and that, of course, will have a major impact not only on business opportunities but also on headcount and skills requirements.
From The Founder
Following a recent board meeting, the New IP Agency (NIA) has a new strategy to help accelerate the adoption of NFV capabilities, explains the Agency's Founder and Secretary, Steve Saunders.
Flash Poll
Live Streaming Video
Charting the CSP's Future
Six different communications service providers join to debate their visions of the future CSP, following a landmark presentation from AT&T on its massive virtualization efforts and a look back on where the telecom industry has been and where it's going from two industry veterans.
LRTV Interviews
BT's McRae Sheds Light on 4K Strategy

5|25|17   |   4:45   |   (0) comments


At Light Reading's Big Communications Event 2017 in Austin, Texas, BT Group's Chief Network Architect Neil McRae talks about what it took for BT to broadcast live sports in 4K. Catch up with all our BCE coverage at http://www.lightreading.com/bce.asp.
From the Founder
How the NIA Aims to Advance NFV

5|25|17   |   08:07   |   (0) comments


Following a recent board meeting, the New IP Agency (NIA) has a new strategy to help accelerate the adoption of NFV capabilities, explains the Agency's Founder and Secretary, Steve Saunders.
LRTV Custom TV
Better Solutions That Address Growing Scale

5|25|17   |     |   (0) comments


For Comcast, the X1 rollout and 17-fold increases in broadband speeds in the past 16 years are among factors driving the need for Energy 2020 solutions that reduce cost and consumption, says Mark Hess.
LRTV Custom TV
Ethernity Network Delivers Instant Offloading of Network Functions With All-Programmable Intelligent NIC

5|25|17   |     |   (0) comments


David Levi, CEO of Ethernity Networks, explains that programmability of the hardware makes the company's All-Programmable Intelligent NIC uniquely beneficial for communications service providers that need advanced data appliances with agile support of virtualization. Utilizing the company's patented network processing technology, Ethernity offers data path ...
LRTV Documentaries
BCE 2017: Vodafone Gets Obsessed With Cloud-Native

5|25|17   |     |   (0) comments


Vodafone's Matt Beal updates us on Project Ocean and explains why simple virtualization isn't enough of a goal for network transformation. Catch up with other BCE 2017 keynotes and news at http://www.lightreading.com/bce.asp.
LRTV Documentaries
BCE 2017: Intel's Take on Network Transformation

5|24|17   |     |   (0) comments


In this BCE 2017 keynote, Lynn Comp discusses Intel's vision for areas such as analytics, automation and service assurance. For more videos and BCE coverage, see http://www.lightreading.com/bce.asp.
LRTV Documentaries
Order From Chaos: The Steve Saunders BCE Keynote

5|24|17   |   17:27   |   (0) comments


Kicking off BCE 2017, Light Reading founder Steve Saunders lays blame for NFV's slow ramp-up and urges telecom to return to old-fashioned standards building and interoperability testing.
Think of this as the video sequel to the recent columns he's written about NFV and the prospect of a telecom app store. (See

LRTV Documentaries
Service Provider Panel: Partnering in the Digital Era

5|22|17   |     |   (0) comments


Coopetition has always been part of telecom, but the ecosphere now includes data centers, vendors, apps developers, cloud service providers and Internet content providers. This BCE 2017 panel explores the new attitudes among network operators as to the value and variety of ...
LRTV Interviews
Site Demo: AT&T's IoT Flow Platform

5|19|17   |   04:25   |   (0) comments


At AT&T's R&D center in Tel Aviv, Israel, project leader Eyal Segev talks about the operator's Flow platform and how it helps to prototype IoT applications.
LRTV Documentaries
Agent of Change: A Q&A With AT&T's John Donovan

5|18|17   |     |   (0) comments


Carol Wilson talks with the man leading AT&T's transformation efforts about the challenge of change.
LRTV Documentaries
BCE Service Provider Panel: The New Business Realities

5|18|17   |     |   (0) comments


For virtualization to happen, the telecom industry first has to grapple with key functional aspects of SDN and NFV that need to be universal, such as onboarding of virtualized network functions and federation of software-defined networks.
LRTV Interviews
BCE Service Provider Keynote: CenturyLink

5|16|17   |   22:32   |   (0) comments


Aamir Hussain leads the Product Development and Technology organization at CenturyLink, which includes the company's information technology function. He is an experienced senior technology executive with more than 25 years of proven success in the implementation of global technology operations, operationalization of complex technology, infrastructures and business ...
Infographics
With the mobile ecosystem becoming increasingly vulnerable to security threats, AdaptiveMobile has laid out some of the key considerations for the wireless community.
Hot Topics
Cities Clamor for More Clout at FCC
Mari Silbey, Senior Editor, Cable/Video, 5/23/2017
What's Blocking 4K TV Today
Alan Breznick, Cable/Video Practice Leader, Light Reading, 5/22/2017
Sonus & Genband Finally Combine to Form $745M Company
Dan Jones, Mobile Editor, 5/23/2017
Fright Wigs & Cocktails: BCE 2017 in Pics
Mitch Wagner, Editor, Enterprise Cloud, 5/19/2017
Apple Looking to Cook 5G Test Devices
Dan Jones, Mobile Editor, 5/24/2017
Like Us on Facebook
Twitter Feed
BETWEEN THE CEOs - Executive Interviews
One of the nice bits of my job (other than the teeny tiny salary, obviously) is that I get to pick and choose who I interview for this slot on the Light Reading home ...
TEOCO Founder and CEO Atul Jain talks to Light Reading Founder and CEO Steve Saunders about the challenges around cost control and service monetization in the mobile and IoT sectors.
Animals with Phones
What Brogrammers Look Like to the Rest of Us Click Here
Live Digital Audio

Playing it safe can only get you so far. Sometimes the biggest bets have the biggest payouts, and that is true in your career as well. For this radio show, Caroline Chan, general manager of the 5G Infrastructure Division of the Network Platform Group at Intel, will share her own personal story of how she successfully took big bets to build a successful career, as well as offer advice on how you can do the same. We’ll cover everything from how to overcome fear and manage risk, how to be prepared for where technology is going in the future and how to structure your career in a way to ensure you keep progressing. Chan, a seasoned telecom veteran and effective risk taker herself, will also leave plenty of time to answer all your questions live on the air.