Deutsche Telekom is breaking new ground in its fibre optic roll-out, becoming the first network operator in Europe to plan a pilot project using Artificial Intelligence (AI). Thanks to faster and optimised route planning, the roll-out can cover more ground, faster. And, according to DT, customers will feel the benefits.
“The shortest route to the customer is not always the most economical. By using artificial intelligence in the planning phase we can speed up our fibre optic roll-out. This enables us to offer our customers broadband lines faster and, above all, more efficiently,” says Walter Goldenits, Head of Technology at Telekom Deutschland.
DT points out that it is often more economical to lay a few extra feet of cable. That is what the new software-based technology evaluates, using digitally-collected environmental data. It looks at things such as where would cobblestones have to be dug up and laid again, and where is there a risk of damaging tree roots?
A measuring vehicle was sent out in Bornheim (near Bonn) this summer, equipped with 360° cameras and laser scanners as part of DT’s FTTH project. It collected detailed environmental data using GPS technology. Depending on the terrain, the vehicle can cover 50 to 80 km per day. All told, it collects approximately 5 Gbytes of surface data per km.
The effort and thus costs involved in laying cable depend on the existing structure. First, civil engineers open the ground and lay the conduits and fibre optic cables. Then they have to restore the surface to its previous condition. Of course, the process takes longer with large paving stones than with dirt roads.
“Such huge amounts of data are both a blessing and a curse,” says Professor Dr. Alexander Reiterer, who heads the project at the Fraunhofer IPM. “We need as many details as possible. At the same time, the whole endeavour is only efficient if you can avoid laboriously combing through the data to find the information you need. For the planning process to be efficient the evaluation of these enormous amounts of data must be automated.”
Fraunhofer IPM has developed software that automatically recognises, localises and classifies relevant objects in the measurement data.
The neural network used for this recognises a total of approximately 30 different categories through deep learning algorithms. This includes trees, street lights, asphalt and cobblestones. Right down to the smallest detail. Examples include: do the pavements feature large pavement slabs or small cobblestones? are the trees deciduous or coniferous?
The trees’ root structure also has a decisive impact on civil engineering decisions.
Once the data has been collected, a specially-trained AI system is used to make all vehicles and individuals unidentifiable. The automated preparation phase then follows in a number of stages. The existing infrastructure is assessed to determine the optimal route. A Deutsche Telekom planner then double-checks and approves it.