DeepSig Blog

Reinventing Wireless with Deep Learning

DeepSig Achieves Industry’s First AI-Native 5G Call & Why You Should Care

Posted by DeepSig on Jan 11, 2022 11:44:50 AM

To fully realize the technical and economic potential of next generation wireless networks, technology providers and OEMs will implement AI technologies to improve upon generations of fixed algorithmic functions in their solutions for mobile network operators and service providers.

While AI is already used today to help manage wireless networks, AI’s usage in directly learning the signal processing algorithms to transmit and receive wireless signals is unprecedented. Proving AI’s advantages and implementations in 5G radio access components has started now with DeepSig’s AI software demonstrated in the industry’s first 5G AI-Native end-to-end call. DeepSig applies a leading form of AI called deep learning, uniquely implemented inside the physical layer of a 5GNR radio access network. The AI enhanced 5G network performs live over-the-air 5G data connections between smartphones and the internet.  This not only proved a deep neural network can be implemented into a working 5G radio access network but more importantly demonstrates reduced processing load and power consumption, reduced latency, and improved signal quality and coverage.

AI-Native wireless systems have the intelligence to learn “natively” from radio signals in real-world environments rather than the static and rigid models with pre-determined techniques used in today’s wireless networks. The AI-Native Air interface approach has gained broad interest in 6G working groups to intelligently learn how to best transmit and receive data rather than traditional models which generalize wireless conditions into static functions which cannot learn and improve from the local environment. 

Critical features of beyond-5G networks include ultra-low latency, high resiliency and ubiquitous connectivity for diverse applications and next-gen devices, human and machine, in very dense environments. International standard’s groups and technology R&D leaders agree that 6G will be AI-Native. However, mobile networks needn’t wait for the finalization of 5G Advanced or 6G standards in order to start benefiting from AI-Native designs in the 5G base station today.

DeepSig is showing that the application of AI-Native software components in existing 5G systems can provide substantial R&D savings to technology providers and OEMs, and that they can deliver higher performance and cost savings to MNOs and CSPs in 5G now with a realistic path to 6G.

Topics: 5G Wireless