Showing posts with label AI. Show all posts
Showing posts with label AI. Show all posts

Monday, 24 May 2021

ITU Standardization Bureau on Machine Learning for 5G


Last year I blogged about Global ITU AI/ML 5G Challenge on the theme “How to apply ITU's ML architecture in 5G networks".  The grand challenge finale happened in December. All the recording and presentations are available here.

Back in October, Bilel Jamoussi from ITU presented a keynote to the 2020 IEEE 5G World Forum plenary session where he addressed the challenges of applying machine learning in networks, ITU’s ML toolkit, and ITU’s AI/ML in 5G Competition. IEEE Tv shared the presentation only in April so the competition part is a bit outdated. It does nevertheless an interesting 20 minute talk.

ITU Recommendation Y.3174, Framework for data handling to enable machine learning in future networks including IMT-2020 is available here.

Related Posts

Thursday, 13 May 2021

Anomaly Detection and other AI Algorithms in RAN Optimization


Yesterday I watched this very inspiring live chat that I would like to recommend to anyone who is interested in how machine learning techniques (aka "AI") can help to optimize and troubleshoot the Radio Access Network.

 [The real contents of in the video starts at approx. 42:00 min] 

My key takeaways from this fireside chat are: 

Verizon Wireless has enough data (100… 500 time series KPIs per cell) that they use to feed anomaly detection ML algorithms and this generates a huge number of alarms, but only a few actionable outputs. 

The “big elephant” (Nick Feamster) is to identify if these alarms indicating real problems that can and have to be fixed or if they just indicate a new behavior of e.g. a new handset or a SW version that was not present in the training phase of the ML algorithm and hence, its pattern is detected as a new “anomaly”. 

For Bryan Larish (Director Wireless AI Innovation, Verizon) the “big open problem” is “that it is not clear what the labels are” and “no standard training sets exist”. 

[For more details watch the video section between 52.00 min and 57:32 min and listen to Bryan’s experience!] 

In most cases Verizon seems to need subject matter experts to classify and label these anomaly alarms due to “the huge diversity” in data pattern. 

According to Bryan only for very few selected use cases it is possible to build an automated loop to fix the issue. Especially the root causes of radio interference are often mechanical or cabling issues that need manual work to get fixed. 

All in all it is my personal impression at the end of the session that anomaly detection is currently a bit overhyped and that the real challenges and problems to be resolved start after anomalies are detected.

Nevertheless, as Bryan summarizes: “ML is a very, very powerful tool.” 

However, strategically he seems not to see a lot of value in anomaly detection by itself, but rather: “Can we use machine learning (results) to change how we build networks in the future?”