Covering Disruptive Technology Powering Business in The Digital Age

SK Telecom has announced that it has developed smartphone power saving technology using on-device AI (Artificial Intelligence). This innovation was done in collaboration with MediaTek, a global application processor maker, and Nota AI, a startup specialising in AI lightweighting,.

Smartphone battery life is an important factor that affects customer experience. Thus, from the hardware side, diverse efforts are being made to increase battery capacity and reduce the power consumption of components like displays, and at the same time, new attempts are also being made to develop communication technologies capable of reducing power consumption that occurs in regards to data transmission and reception.

In general, the device performs data transmission and reception while connected to the base station, and even after the completion of data transmission/reception, the device stays connected to the base station for a set amount of time to standby for data that may occur in the future, which leads to nonnegligible consumption of power.

SKT, together with MediaTek and Nota, developed an on-device AI-based smartphone power saving technology that enables the device to predict, in real-time, whether data transmission will occur within a certain period of time, thereby controlling an optimal connection status between the device and the base station.

SK Telecom, MediaTek, and Nota AI have collaborated to make Smartphone Power Saving Technology.

That is, if the prediction indicates that data is likely to occur, it will continue to maintain connection between the device and the base station. On the other hand, if it thinks that data is unlikely to occur, it will disconnect from the base station to prevent unnecessary use of power.

Leveraging Quantisation to Build v

The three companies focused on selecting optimal AI model and lightweighting the model using techniques such as quantisation and pruning to enable low-latency and low-power operation on smartphones. They then applied the lightweight AI model to a real smartphone modem to verify its real-time operation, and secured a level of prediction accuracy that can translate into smartphone power savings. This is the backbone of the smartphone power saving technology developed by the three tech firms.

The research and development achievement will be introduced at SKTs booth (Hall 3 Stand 3I30) during MWC Barcelona 2024, and continued efforts will be made to improve the completeness of the technology by further advancing AI models and conducting tests for network interworking.

(0)(0)