Connect with us


Ciena uses machine learning to heal the scars, horror of network management



Does machine learning still need people?
Vijay Raghavan, executive vice president and chief technology officer Risk and Business Analytics for The RELX Group, talks with Tonya Hall about a balance between analytics and intuition.

“The scars” and “that horrible world” are some of the terms for network management, according to one who’s been in the trenches. 

Kailem Anderson was with Cisco Systems for 12 years prior to joining fiber-optics giant Ciena last year. As vice president of portfolio and engineering for the Blue Planet, a software division of Ciena, he is trying to help avoid such pain for those who must keep networks running. 

“I managed customer networks, and I spent a lot of time hiring analysts to watch the network, to watch alarms, and to build big strings of rules,” for networking monitoring, says Anderson. His breezy Aussie accent gives a certain lightness to what sounds like a rather miserable affair.

At $26 million in revenue in 2018, Blue Planet was a tiny fraction of Ciena’s roughly $200 million in software revenue in 2018 and $3 billion in total revenue. But it increased by a healthy 66%, and it can bring higher profit margin than Ciena’s optical networking equipment sale. It also offers the company a recurring revenue stream that is highly appreciated by Wall Street. Those economic aspects, plus the fact that it can be strategic in designing customers’ networks, make it an important part of where Ciena is headed as a company.   

Also: Is Google’s Snorkel DryBell the future of enterprise data management?

Figuring out what’s gone wrong in a network involves detective work at several levels of what’s known as the “stack” of protocols, the Open Systems Interconnect, or “OSI.” Some information comes from the bottom of the stack, if you will, the “layer one,” which consists of the physical medium of transmission. That could be, for example, coaxial cabling or fiber-optic links. 

At the next layer above that, layer two, raw bits are packaged into bundles, such as Ethernet frames, and there’s all kinds of information to be gleaned about the state of those frames of data as they move through the fibers and cables of the network. The next layer up is layer three, where data is packaged as Internet-addressable packets, again, with lots of their owing information to be gleaned, such as routing and switching information about where the packets are going. 

From there, one can go on up to higher levels, layers four through seven, the domain of applications, and get information about who an individual application is placing its data into those internet packets and whether it is having any trouble doing so. 

Take the example where there is an transponder failure on one of two optical links. That leads to a route change in the multi-protocol label system, or MPLS. The network equipment reports congestion along the IP route as a link shoulders the burden of more traffic, and an end user experiences heavy delays using the network. All these are part of the same problem, Anderson explains, but getting from the user experience to the transponder failure can be a mystery. 

Traditionally, a systems administrator sees the various items in a disparate fashion, with signals at each of the OSI layers coming from different telemetry systems, such as SNMP monitors, the systems log, a third thing that tracks “flows,” and then information coming from an individual piece of equipment, such as information about a recent configuration change — none of which are coordinated. 

What looks like bad user performance from one angle looks like an MPLS routing issue or an IP bandwidth issue at another level, leading to a serious piece of detective work to find the culprit, the transponder failure. 

Also: Google Brain, Microsoft plumb the mysteries of networks with AI

A ticket gets created, and it ping-pongs between teams, with no one team having visibility into the other side, says Anderson. “Eventually they solve it, they have engineers inspect the matter, but it’s very inefficient.”

Sys admins must try and construct systems of rules as to what every possible combination of factors could mean. “They spend 1,000s of hours building these rules,” says Anderson. “It’s a zero sum game to spend that time to identify all the different scenarios.”

Instead, Blue Planet tools can train the network software using a combination of labeled examples, known as supervised learning and reinforcement learning, where the computer explores states of affairs and possible next steps. 

With that combination, the software can be trained to identify patterns “up and down the stack” that are difficult to piece together with a rules-based system. 

“We want to have the system learn to identify those scenarios, to basically help us get to the root cause much more quickly, and to use that information to close the loop,” he says, and then have a supervisor come into the picture only once that outline has been determined. 

Also: Intel-backed startup Nyansa chases the total problem in the AI of network monitoring

The tools necessary to do this are mostly starting from off-the-shelf machine learning models, says Anderson. “Most of this, yes, we can get from the cloud guys,” he says, referring to the various enterprise-grade machine learning offerings in cloud computing facilities. “We use them all,” though the tools can also be run solely on-prem. “It’s six and one half dozen of the other at the moment, but I think analytics is ultimately a good thing to move into the cloud.”

Open-source tools such as SparkML play a big role in organizing all the telemetry data. 

The technology of machine learning, says Anderson, has matured substantially in recent years to make the investment in labeling network events pay off. 

“Five years ago I was playing with this and with the amount of effort that needed to go into labeling, the risk versus value I was getting was questionable,” he says. “With the hardening of the algorithm, and the maturity of AI, that effort-to-reward ratio has compressed significantly. You only have to do a reasonable amount of tagging now and the outputs are significant.”

Anderson maintains there is another dimension in the shift to machine learning, which is that a more comprehensive sense of the network emerges that may lead to different ways or structuring and maintaining networks. 

Traditionally, many sys admins will simply turn off sources of information, says Anderson, which is understandable, because of the information overload, but it means that network administrators are throwing away important clues. 

“That’s the complexity in operating with a million different data sources,” he observes. “The traditional way to mange an operations team is to filter the information, almost turn off the information that is too much.

“At Cisco, if I was running a service provider network, I would get in the vicinity of a million events a day, and I might have an operations team of 40 to 50 people who have to handle all that.”

As a consequence, admins end up only looking for “what they deem fair scenarios,” and “are turning off performance-based scenarios,” information about the relative quality of the network. 

But, says Anderson, “you don’t want to turn off the information, you want to funnel it, and use it to identify what conditions are driving consistent scenarios,

Must read

“Eventually, solutions could be different if they’re trained,” he offers. Data may lead to structuring things differently. “Usually, you have a planned network condition, but then an actual network condition; through learning, you might find the actual is more optimal than planned, and then execute a policy” based on that new insight. 

There are new frontiers to achieve, such as delivering analysis of the data in a “graph database” format, says Anderson. “We are in the operations and network world, and so you want to visualize all this in a network graph concept.” Some customers “want to see it just programmatically propagate to northbound systems that are going to leverage that information, to be able to visualize with a graph database and have APIs to send that northbound information to the BSS layer.”

The one catch at the moment in all this is that systems administrators are not yet ready to close the loop, so to speak, and let machine learning completely take over and automate both detection and resolution of network issues. 

“This isn’t a tech limit, it’s a cultural aspect,” he says. Machine learning systems are probabilistic, not deterministic. Hence, while they can detect many failure issues, there is a reluctance to automate what could be a false positive scenario. “You only need to screw up .0001% of the time and that’s a big issue.”

“I still think we are a little bit away in terms of closing the loop, I think it’s trust in the technology. It will happen incrementally, where you can close the loop on something non-catastrophic, that doesn’t create a failure scenario, where there is low risk, and then other areas over time

Source link

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *


Chevrolet Bolt production stoppage extended until mid-October



GM has announced that it will extend its production stoppage for the Bolt electric vehicle through at least mid-October. The announcement marks an extension of its production stoppage announced in late August due to a massive battery recall for the electric vehicle. The defective battery packs have caused 12 fires.

Most recently, a Bolt caught fire in the owner’s garage, destroying the vehicle, damaging the home, and causing damage to another vehicle stored in the garage at the time. GM has confirmed that Bolt production at the Orion Assembly plant will not commence until at least October 15. The massive battery recall has already cost around $2 billion, and GM says it will recover most of that money from battery supplier LG.

Chevrolet’s latest production stoppage for the Bolt comes in the middle of a massive chip shortage that has forced production on other vehicle assembly lines to stop. Sales and production of the Bolt won’t begin until the automaker has a confirmed fix for the battery issues.

An investigation laid the blame on misaligned robots at the battery assembly factory. According to that report, the misaligned robots caused a torn anode tab placing it closer to the cathode leading to short-circuiting and fires. After another fire that happened this month, GM issued a new warning to owners of the small electric vehicle.

The new warning tells Bolt owners to keep their vehicles at least 50 feet away from homes, offices, and other vehicles. Unfortunately, it’s highly unlikely that any owner who heeds the warning and parks 50 feet away from homes or offices would be able to charge their vehicle, essentially making them useless until a fix is available. Defective battery packs have led to three injuries and multiple fires.

Continue Reading


2021 Jeep Grand Cherokee L gets over 75 factory Mopar accessories



As if configuring a 2021 Jeep Grand Cherokee L is not confusing enough, Mopar has released over 75 factory-backed accessories for Jeep’s first-ever seven-seat SUV. The highlights include new 21-inch Mopar-specific five-spoke wheels with a Jeep center cap and integrated side steps that install cleanly without drilling holes in your precious Grand Cherokee L.

“The all-new Jeep Grand Cherokee L presents a great opportunity for customization and personalization, said Mark Bosanac, North America Vice President, Mopar Service, Parts & Customer Care. “ The side steps mentioned above are made of black galvanized stainless steel with a chrome overlay, perfectly matching the premium vibe of the Grand Cherokee L. In addition, the powder-coated finish ensures durable protection against friction, bumps, and UV rays.

The 21-inch Granite Crystal wheels start at $500 each, while the side steps are $750. Other notable accessories include a roof-mount cargo basket ($350) with a 150-pound maximum load capacity, roof-rack crossbars ($300) that allows attachment of all Mopar roof carriers, and a $200 watersport carrier and bike carrier (sold separately) to accommodate kayaks, surfboards, and a bicycle.

Mopar’s rear-seat entertainment system ($1,625) has a roof-mounted DVD player and a 10-inch screen with two Bluetooth headphones to entertain the kids on long journeys. If you have pets, Mopar has a $190 collapsible kennel with a carrying handle. “Across the entire Jeep Grand Cherokee L lineup, we offer 75 factory-backed, quality-tested accessories,” added Bosanac.

Least to say, you won’t be running out of options when buying a 2021 Jeep Grand Cherokee L. The standard powerplant is a 3.6-liter Pentastar V6 with 293 horsepower, 260 pound-feet of torque, and up to 6,200 pounds of towing. You can have this engine in 2WD or 4WD, and both have an eight-speed automatic gearbox.

However, you can have a 5.7-liter V8 in the Jeep Grand Cherokee L Limited, Overland, and Summit 4×4. Pumping out 357 horsepower and 390 pound-feet of torque, V8-equipped Grand Cherokee L models have a maximum 7,200-pound towing capacity.

If you choose all-wheel-drive, you have three drivetrains to think about: Quadra-Trac I, Quadra-Trac II, and Quadra-Drive II. Also, the cabin is configurable with six or seven seats. The 2021 Jeep Grand Cherokee L has base prices at$38,690, while the range-topping Summit and Summit Reserve trims are $58,690 and $66,985, respectively.

Continue Reading


2022 Genesis GV60 EV to arrive with facial recognition like a smartphone



It seems the incoming 2022 Genesis GV60 EV will arrive with more than just love-it or hate-it styling, funky paint colors, and a mysterious floating oddity on the center console. In a recent announcement, Genesis said US-bound GV60 electric vehicles are coming with facial recognition technology.

This innovative new tech is more intelligent, faster, and offers better convenience than wristbands or physically entering PIN codes. Initially available for the 2022 GV60, Genesis said the tech would soon make its way across its vehicle portfolio. Facial recognition allows the EV to recognize faces and open or close the doors without using a keyfob. In addition, the vehicle will apply settings like the seating position, steering wheel height, and side mirror positioning upon recognizing your face.

The system uses a custom Near-Infra-Red (NIR) camera to recognize faces in low-light or foggy conditions, even in the darkness of night. In a burgeoning and highly competitive segment, new EVs are battling for supremacy by offering new-age tech. From the looks of it, it seems the GV60 will become the goalpost for future EVs in terms of clever, affordable technology.

In addition, a new fingerprint authentication system allows GV60 drivers to start the vehicle using a biometric scanner. This means you can leave the keyfob inside the car, go out for a swim, come back, and enter/start the vehicle using only your face and fingerprint. Genesis claims the system can store two facial profiles. All relevant data are encrypted and stored, and users can delete their data if preferred.

Based on the styling alone, you wouldn’t mistake the GV60 for a supremely high-tech car. Still, it’s turning out to be a technological hotbed. The Genesis GV60 is the first production EV to have wireless inductive charging like in the 2019 BMW 530e PHEV. The wireless charger has enough power to recharge the GV60’s batteries in six hours, four hours faster than using a wall charger.

It also has a gimmicky Crystal Sphere, but it does add a hi-tech look to the GV60’s interior. Finally, the GV60’s OTA (Over-the-air) updates will also cover vehicle settings like suspension, brakes, airbags, and steering upgrades. The 2022 GV60 will arrive in US showrooms in early to mid-2022.

Continue Reading