Ïã¸ÛÁùºÏ²Ê

XClose

Institute of Communications and Connected Systems

Home
Menu

Ïã¸ÛÁùºÏ²Ê technology can prevent future BBC 5G broadcast fails

21 June 2019

Technology developed by Ïã¸ÛÁùºÏ²Ê researchers as part of the EU-funded 5G-MEDIA project could help avoid scenes seen on the BBC’s failed first broadcast over a 5G network.

Screen shot of the corrupted 5G broadcast with inlay of a dial moving between 4G and 5G

´¡³Ü³Ù³ó´Ç°ùÌýÌýDavid Griffin, Principal Research Associate, andÌýRobert Thompson, ICCS Manager

Research theme logos - Intelligent High Capacity Networks, Infrastructures for Smart Services and Applications, Information and Data Processing
5GÌý| MediaÌý| Network OptimisationÌý| Machine Learning

On the 31st of May 5G publicly failed to support a BBC outside broadcast that attempted to be the first such aired transmission on the UK’s new 5GÌýnetwork, which had been launched on the same day.

The broadcast had to be cut short by the presenter in the studio due toÌývideo and audio distortion that made the footage impossible for theÌýaudience to follow.

An EU-funded research project entitled ‘5G-MEDIA’, in which members ofÌýthe Institute of Communications and Connected Systems (ICCS)Ìýhave a largeÌýinvolvement, believes it has the solution to future similar situations.

Ïã¸ÛÁùºÏ²Ê researcher Dr DavidÌýGriffinÌýsaid:

The BBC's live broadcast problem was not down to a failure of 5G,Ìý

however, it was due to limitations of existing 4G infrastructure uplinks

“

A view which has been expressed by experts across social media:

The 5G-MEDIA project successfully demonstrated a prototype system toÌýenable robust remote media production in broadcasting over a 5G networkÌýat its recent review. The successful demonstration took place with Spanish public broadcaster, RTVE, in Madrid.

In this demonstration a Cognitive Network Optimiser (CNO), built with reinforcement machine learning algorithms, was able to predict networkÌýcongestion and respond with an intelligent adjustment of videoÌýcompression levels to ensure a high quality of experience (QoE) evenÌýunder congested network conditions.

¶Ù°ùÌý³Ò°ù¾±´Ú´Ú¾±²ÔÌý±ð³æ±è±ô²¹¾±²Ô±ð»å:

This approach avoids packet and frame loss which caused the videoÌý

distortion as seen in the BBC live broadcast.

“

The 5G-MEDIA approach is not only for future 5G networks but it wouldÌýalso avoid problems caused by fluctuating capacity in current networkÌýuplinks, such as the 4G one used in the BBC broadcast.

The technology solution developed by the 5G-MEDIA project includes a newÌýquality of experience probe that provides essential feedback to theÌýmachine learning algorithms during their training phase. This probe alsoÌýenables a comprehensive Monitoring, Analysis, Planning and ExecutionÌý(MAPE) loop that embeds the machine learning logic of the CNO.

The EU-funded H2020 5G-MEDIA project is working on novel architecturesÌýfor the management of media applications on 5G networks.

The machine learning algorithms in the CNO were developed in Ïã¸ÛÁùºÏ²Ê'sÌýInstitute of Communications and Connected Systems by Dr MortezaÌýKheirkhah, Dr Khoa Phan, Dr DavidÌýGriffinÌýand Prof Miguel Rio.

A visual demonstration of the effects of the 5G-MEDIA, ensuring a good quality of experience in media broadcast over 5G. (Note there is intentionally no audio)


YouTube Widget Placeholder

Ìý


Cognitive Network Optimiser

The Cognitive Network Optimiser (CNO) provides a set of automated tools for optimising theÌýconfiguration of the network and the applications running over it. It isÌýbuilt from a combination of classical optimisation techniques, dataÌýanalytics and machine-learning algorithms.

Image

Feature image creditÌýBBC, used under permitted acts: Criticism, review and reporting current events.