Mobile Devices

Using AI and machine learning to help deploy 5G small cells

31 October 2019

Small cells help improve capacity and coverage of 5G wireless connections in cities, but only if they are placed in the very best locations. Using machine learning and artificial intelligence (AI) in network design can help reduce the cost of deployments while optimizing coverage over traditional manual methods, according to a new white paper from the Small Cell Forum (SCF) and 5G Americas.

Current 5G base stations offer coverage for limited areas of cities. But as the technology evolves to higher bandwidth frequencies such as millimeter wave (mmWave), base stations will not be enough, since mmWave signals have trouble moving through walls, trees and other infrastructure. Small cells will be critical to expanding coverage indoors as well as to areas that reside outside of the base station’s network strength. There are some companies already experimenting with ways to place small cells on street lamps to proliferate mmWave technology. Placing small cells on security poles and other hot spots are under investigation as possible solutions.

While small cells are lower in cost than macro towers, the low-power nature of the cells means that they serve a smaller area and that there must be numerous small cells located in various hotspots in order to cover the mobile data demands of customers, SCF said.

The two organizations used Manhattan, New York, as an example of how AI and machine learning automated the design process to provide coverage for the city while reducing the number of sites required from 185 to 111.

“Small cells will form one of the foundations on which 5G is built, particularly through dense HetNets in spectrum-hungry urban areas,” said Prabhakar Chitrapu, chairman of SCF, in a statement. “The potential for AI and ML is tremendous, and investing in good planning of small cells now can reap huge rewards later.”

In the white paper, the group suggests that small cells should be placed as close as possible for demand peaks, at around 20 to 40 meters in order to maximize return on investment. The networking equipment should use machine learning for estimated location of usage and quality reports to adopt smart algorithms. And machine learning should be used for any small cell design effort to get the best results generated.

Learn more about the Small Cell Forum’s findings with the white paper Precision Planning for 5G Era Networks with Small Cells.

To contact the author of this article, email PBrown@globalspec.com


Powered by CR4, the Engineering Community

Discussion – 0 comments

By posting a comment you confirm that you have read and accept our Posting Rules and Terms of Use.
Engineering Newsletter Signup
Get the Engineering360
Stay up to date on:
Features the top stories, latest news, charts, insights and more on the end-to-end electronics value chain.
Advertisement
Weekly Newsletter
Get news, research, and analysis
on the Electronics industry in your
inbox every week - for FREE
Sign up for our FREE eNewsletter
Advertisement