New machine learning approach could give a big boost to the efficiency of optical networks

• Updated on: 2019-02-26
• Read original article here

New machine learning approach could give a big boost to the efficiency of optical networks
February 25, 2019, Optical Society of America
Credit: CC0 Public Domain
New work leveraging machine learning could increase the efficiency of optical telecommunications networks. As our world becomes increasingly interconnected, fiber optic cables offer the ability to transmit more data over longer distances compared to traditional copper wires. Optical Transport Networks (OTNs) have emerged as a solution for packaging data in fiber optic cables, and improvements stand to make them more cost-effective.
A group of researchers from Universitat Politècnica de Catalunya in Barcelona and the telecom company Huawei have retooled an artificial intelligence technique used for chess and self-driving cars to make OTNs run more efficiently. They will present their research at the upcoming Optical Fiber Conference and Exposition, to be held 3-7 March in San Diego, California, USA.
OTNs require rules for how to divvy up the high amounts of traffic they manage and writing the rules for making those split-second decisions becomes very complex. If the network gives more space than needed for a voice call, for example, the unused space might have been better put to use ensuring that an end user streaming a video doesn't get "still buffering" messages.
What OTNs need is a better traffic guard.
The researchers' new approach to this problem combines two machine learning techniques: The first, called reinforcement learning , creates a virtual "agent" that learns through trial and error the particulars of a system to optimize how resources are managed. The second, called deep learning , adds an extra layer of sophistication to the reinforcement-based approach by using so-called neural networks , which are computer learning systems inspired by the human brain, to draw more abstract conclusions from each round of trial and error.
"Deep reinforcement learning has been successfully applied to many fields," said one of the researchers, Albert Cabellos-Aparicio. "However, its application to computer networks is very recent. We hope that our paper helps kickstart deep-reinforcement learning in networking and that other researchers propose different and even better approaches."
So far, the most advanced deep reinforcement learning algorithms have been able to optimize some resource allocation in OTNs, but they become stuck when they run into novel scenarios. The researchers worked to overcome this by varying the manner in which data are presented to the agent.
After putting the OTNs through 5,000 rounds of simulations, the deep reinforcement learning agent directed traffic with 30 percent greater efficiency than the current state-of-the-art algorithm.
One thing that surprised Cabellos-Aparicio and his team was how easily the new approach was able to learn about the networks after starting out with a blank slate.
"This means that without prior knowledge, a deep reinforcement learning agent can learn how to optimize a network autonomously," Cabellos-Aparicio said. "This results in optimization strategies that outperform expert algorithms."
With the enormous scale some optical transport networks already have, Cabellos-Aparicio said, even small advances in efficiency can reap large returns in reduced latency and operational costs.
Next, the group plans to apply their deep reinforcement strategies in combination with graph networks, an emerging field within artificial intelligence with the potential to transform scientific and industrial fields, such as computer networks, chemistry and logistics.
A new developmental reinforcement learning approach for sensorimotor space enlargement
October 10, 2018
Researchers at the University of Lorraine have recently devised a new type of transfer learning based on model-free deep reinforcement learning with continuous sensorimotor space enlargement. Their approach, presented in ...
Using a deep learning neural network to allow a car to learn to drive itself in just 20 minutes
July 9, 2018
A team of researchers at U.K. startup Wayve has developed a way to apply deep learning networking to autonomous driving. In a recent blog post (along with accompanying YouTube demonstration video) representatives outlined ...
Teaching machines to direct traffic through deep reinforcement learning
August 17, 2016
Rush hour—the dreaded time of day when traffic conditions seem bent on making you late. As your car slowly creeps in line behind countless others stuck at a stop light, you think to yourself, "Why aren't these lights changing ...
A new approach for modeling central pattern generators (CPGs) in reinforcement learning
January 23, 2019
Central pattern generators (CPGs) are biological neural circuits that can produce coordinated rhythmic outputs without requiring rhythmic inputs. CPGs are responsible for most rhythmic motions observed in living organisms, ...
How learning more about neuroscience might influence development of improved AI systems
February 15, 2019
Deep-learning neural networks have come a long way in the past several years—we now have systems that are capable of beating people at complex games such as shogi, Go and chess. But is the progress of such systems limited ...
New method for high-speed synthesis of natural voices
February 6, 2019
A research team at the National Institute of Informatics (NII/Tokyo, Japan) including Xin Wang, Shinji Takaki and Junichi Yamagishi has developed a neural source-filter (NSF) model for high-speed, high-quality voice synthesis. ...
Recommended for you
Quantum optical micro-combs
February 25, 2019
Compact quantum devices could be incorporated into laptops and mobile phones, thanks in part to small devices called quantum optical micro-combs.
New comparative study on DNA modifications across the fungal tree of life
February 25, 2019
DNA activity can change without changing the sequence of the DNA segment itself. Gene activation and inactivation can be the basis for how species produce unique individuals. Some processes that change gene activity are well ...
How a certain bacterium communicates and makes us sick
February 25, 2019
Researchers at Binghamton University, State University of New York have uncovered the unique way in which a type of Gram-negative bacterium delivers the toxins that make us sick. Understanding this mechanism may help design ...
Early life stress alters helping behavior of meerkat offspring
February 25, 2019
Parents make sacrifices to allow their children to have better lives than they did, but this isn't the case for Kalahari meerkat mothers, according to a new University of Michigan study.
New Horizons spacecraft returns its sharpest views of Ultima Thule
February 23, 2019
The mission team called it a "stretch goal" – just before closest approach, precisely point the cameras on NASA's New Horizons spacecraft to snap the sharpest possible pics of the Kuiper Belt object nicknamed Ultima Thule, ...
NASA greenlights SpaceX crew capsule test to ISS
February 23, 2019
NASA on Friday gave SpaceX the green light to test a new crew capsule by first sending an unmanned craft with a life-sized mannequin to the International Space Station.
After a reset, Сuriosity is operating normally
February 23, 2019
NASA's Curiosity rover is busy making new discoveries on Mars. The rover has been climbing Mount Sharp since 2014 and recently reached a clay region that may offer new clues about the ancient Martian environment's potential ...