Softbank implements Machine Learning in the RAN with Ericsson

SoftBank is using machine-learning software developed by Ericsson for advanced radio network design in the Tokai region. The service groups cells in clusters and takes statistics from cell overlapping and potential to use carrier aggregation between cells into account, thus reducing operational expenditure and improving network performance. The machine learning evaluates cell coverage overlap, signal strength and receive diversity. Big data analytics was applied to a cluster of 2000 radio cells and data was analyzed for the optimal configuration.

Ericsson’s centralized and elastic radio access network design is sold as a service and supports LTE networks. Ericsson says that compared to traditional network design methods, the ML approach cuts the lead time by 40 percent.

Ryo Manda, Radio Technology Section Manager at the Tokai Network Technology Department of SoftBank, says: “We applied Ericsson’s service on dense urban clusters with multi-band complexity in the Tokai region. The positive outcome exceeded our expectations and we are currently proceeding in other geographical areas with the same method and close cooperation with Ericsson.”

Peter Laurin, Head of Managed Services at Ericsson, says: “There is a huge potential for machine learning in the telecom industry and we have made significant investments in this technology. It is very exciting to see that the new methods have been successfully applied in SoftBank’s network. There is a strong demand for this type of solutions and deployments of this service to other tier-one operators in other regions are ongoing.”

Read More

AT&T's Threat Intellect Sifts Billions of Security Events in Minutes

AT&T unveiled a new Threat Intellect service that takes a Big Data + machine learning approach in sifting through billions of security events captured on the AT&T backbone to identify abnormal and malicious activity based on data patterns.

This new approach, which will be the brains behind AT&T security services going forward, provides visibility into the data patterns and threat activity by using multitudes of unique threat signature data streams, analytics and intelligence. Data can come from mobile devices, applications, data centers, or through AT&T security services. The software-defined network can then apply policies to mitigate the threat.

AT&T estimates this automation will improve the speed at which we can deploy security protections by over 95%, greatly improving threat detection and resolution.

“AT&T secures more connections than any communications company in North America,” said Steve McGaw, chief marketing officer, AT&T Business Solutions. “No carrier experiences the depth and scale of security threats we see on a daily basis– more than 30 billion vulnerability scans and 400 million spam messages are detected on our IP network. The power of Threat Intellect gives us the ability to process 5 billion security events, a full day’s worth of activity for all of our security customers combined – in only 10 minutes.”

“In the past, you had to know exactly where a specific file was stored to access it. Now, you only need a key word to find that file,” McGaw said. “AT&T Threat Intellect has a similar capability. It is the power behind every AT&T firewall, network security protection and every other security capability we have integrated in our network and services.”

AT&T said 117 petabytes of traffic are traversing its network every day.

http://www.att.com




See video:  https://youtu.be/rLWKTxw1fcE

Read More