5G networks are the next generation of mobile internet connectivity, offering faster speeds and more reliable connections on smartphones and other devices than ever before. Swisscom is already testing this technology which will be characterized by hundreds of billion devices connected simultaneously, sub millisecond latency and 10Gbps throughput. Processing these high volumes of data, at a faster speed, will require new antennas, new devices, and new applications for wireless data. No matter what the setup looks like, the influx of additional data - which will need to be processed in real-time - will drive the need for edge computing.
Recognized by many as the next significant enterprise tech trend after cloud computing, edge computing refers to infrastructure that enables data processing as close to the source as possible. Due to the fact that the computational power of the mobile devices is limited, machine learning or complex algorithms can be deployed on the cloud, next to the antenna, for solving any task in almost real time with unlimited computing power.
Swisscom has developed a prototype to showcase edge computing capabilities by designing a drone fully autonomous in a revolutionary's way: its stabilization and all its control algorithm is computed remotely on the cloud instead of on board computer! For none specialist, it is a big challenge particularly due to the currently 4G latency induced by the transmission that affects the drone's stability.
With the new 5G infrastructures, a ping less than 1ms is expected. As for now, only Wifi can simulate wireless transmission that compete with 5G speed. Our prototype has been equipped to communicate sensor by Wifi and is successfully flying, having all the processing power in the cloud. We demonstrated the possibility of having the control logic on the server and with a high-speed communication to perform all the computation on the cloud. This will be extended to 5G as the technology becomes available.
The edge computing technology offers the possibility to implement on the cloud very complex algorithms that can be processed at a very high computational power. For demonstrating this technology, a model predictive algorithm was implemented, which can anticipate the drone movements for the near future, counterbalancing the effect of the 4G communication lag.
Both the technologies will be a part of 5G having numerous use cases. An relevant one is the autonomous driving cars and intelligent traffic management in the smart cities. To guarantee traffic safety, when a control command, braking for example, is sent to a car, the car must receive the command within 1 ms. The latency of a 4G network cannot meet this requirement. With the latency of 4G network, a car driving at 100 km/h still moves 1.4 m from the time it finds an obstacle to the time when the braking command is executed.
Under the same condition, with the latency on a 5G network, the car will move just 2.8 cm, and this performance is comparable with the standard of an anti-lock braking system (ABS).
In summary, 5G will impact the way we design things today and tomorrow's innovations. This project is supported by Swisscom, the telco leader in Switzerland, and the Swisscom Digital Lab, an innovation lab located in the EPFL Innovation Park dedicated to conduct applied research in 5G, IoT, machine learning, data analytics, security and communication systems.