Wireless operators spend millions of dollars every year paying for the electricity to power their cell sites and small cells. But there are new energy-saving features that are being developed that could make a dramatic difference in energy consumption. And these new features incorporate tools like artificial intelligence (AI) and machine learning.
In a new Ericsson white paper called “Breaking the Energy Curve,” the company said that machine learning can be used to make certain network features more autonomous. Two of those features, MIMO Sleep Mode and Cell Sleep Mode, are using machine learning to study data traffic patterns and save operators money.
For example, in a cell site with a 4×4 multiple-input multiple-output (MIMO) antenna, a machine learning algorithm for “Sleep Mode” can analyze traffic and then predict when the site should use all four radios or just one radio. Ericsson said that in trials, this technology was found to save operators about 14% in energy consumption per cell site.
Similarly, machine learning can also be used to detect low-traffic conditions and using Cell Sleep Mode can turn the cell site off. The software then monitors traffic conditions and will turn the sleeping cell back on when those conditions change.
Mats Pellback Scharp, head of sustainability at Ericsson, said that machine learning and AI allow the network to “learn” common traffic patterns and then use that data to determine when certain cell sites can be put into sleep mode.
While some operators are already putting cell sites in sleep mode at certain times, they are currently doing it manually, says Pellback Scharp. For example, operators know that in certain locations such as near a shopping mall or a subway station, the network will have less traffic when the mall is closed or when the subway has very few riders.
And while this manual method of turning down cell sites and putting them in sleep mode does save energy, the automated method using AI provides operators with a lot more options and they don’t run the risk of making a mistake, such as shutting down a cell site when there is traffic demand and leaving customers with poor or spotty coverage.
“AI will know when a 5G device is being used in certain parts of the network and then can direct it using compute software to more capable cell sites,” he added.
— Sue Marek, special to Light Reading. Follow her @suemarek.