Vodafone Trials AI Robotic Mast for Dynamic Coverage

Vodafone is currently trialling a new mobile mast equipped with an AI brain and a robotic arm to dynamically adjust radio antennas.

The self-thinking system analyses where customer demand for mobile coverage is concentrated and alters its physical position to improve the local signal.

This autonomous mast evaluates local network demand alongside weather conditions before deciding where to focus its concentrated signal.

On sunny days the machinery directs signals outdoors while during rainy weather it shifts its focus to offer deeper indoor coverage.

Optimising local network coverage

An algorithm designed by Vodafone engineers directs the robotic arm to rotate or tilt the radio antenna to improve 4G and 5G coverage and performance. 

The system learns and adapts continuously and makes near-instantaneous decisions autonomously.

HUMAX Networks, a South Korean firm, manufactured the robotic arm.

The trial is taking place at a site in Tirana, Albania, overlooking a busy shopping centre.

During daytime hours the antenna serves shoppers at the mall, but it automatically shifts coverage to a nearby residential area at night to handle rising evening internet use. This process takes roughly 20 to 30 minutes.

Although technicians could speed up the movement, the current pace conserves energy and operates significantly faster than the days required for a manual intervention, while adding another antenna could take weeks. 

In addition to speed, there’s also a safety implication, as normally adjusting an antenna requires an engineer to climb the mast – something that this system doesn’t need.

Empowering autonomous network components

“This is an early example of Physical AI in telecoms”, says Francisco ‘Paco’ Martin Pignatelli, Director of Mobile Access Engineering, Vodafone.

“By analysing network demand and making autonomous decisions, the AI algorithm can adjust radio antennas to optimise coverage and capacity without human intervention.

“This enables us to deliver superior connectivity for our customers.”

This project supports a wider effort by the company to integrate autonomous antenna control into its company-wide platform to automate radio access network (RAN) components.

Internal teams and third-party developers can use this open standards-based platform to create intelligent network-optimisation algorithms.

These applications will eventually enable antennas to become active and dynamic parts of an adaptive RAN.

Anticipating changes in local conditions

Local environmental changes and weather patterns often dictate how and where users connect to the mobile network.

Sudden downpours or heavy traffic jams can quickly shift data usage across a wide metropolitan area.

Feeding these variables into self-organising network algorithms allows antennas across multiple sites to reposition and anticipate demand before congestion builds.

Vodafone expects similar autonomous products focusing on RAN automation to become available in the coming months.

Some future designs will alter the signal by shifting small components within the antenna container instead of moving the entire unit, which will reduce energy use.

Digitalisation of mobile assets

This trial builds on the rollout of satellite-guided sensors in new mobile mast antennas, which Vodafone initiated last year.

By using GPS technology, the company can remotely verify that antennas are installed correctly to maximise overall radio performance.

Correcting physical misalignments usually requires manual intervention, which remains both time-consuming and expensive.