The performance goals for 5G are ambitious, impressive, and will be world-changing. Achieving them is also a significant challenge, and as the world races to develop, test, and deploy 5G technology, existing approaches using traditional design methodologies are starting to show some of their limits.
Need for a new Approach
Customer thirst for ever-increasing mobile data is driving the urgency to move from 4G to 5G. While 5G has the potential to offer a significantly enhanced user experience, its core wireless technology heritage is over 20 years old. Moore’s Law has reduced the rack scale systems of the 1990s to our present-day smart phones, but the core algorithms have not evolved. The result is 5G systems that consume dramatically more power than predicted or desired and achieve lower data rates than planned. DeepSig addresses these problems by replacing traditional wireless algorithms with Deep Learning AI to dramatically reduce power consumption and improve capacity. This is a fundamentally different and far more performant approach than other AI-based approaches that focus primarily on network management. DeepSig has productised this approach with its OmniPHY™ software product.
OmniPHY’s Technology Heritage
Our OmniPHY software leverages advances made in machine learning by companies like Google and Facebook, which improved computer vision accuracy from 85% in 2011 to 99% today, and applies its core concepts to wireless communications. The key insight is that human engineering can be replaced by deep (i.e., many-layered) neural networks that learn directly from real-world data. Instead of using engineering approximations and simplifications, a deep neural network embraces complexity and learns a near optimal solution for designed performance metrics - which for 5G are maximizing data capacity while minimizing latency and power consumption. This approach has the added benefit of increasing the overall quality of service, which reduces things like dropped calls and link degradation in poor weather.
OmniPHY Proof of Concept
When DeepSig began its R&D effort to improve wireless, we invented deep networks that learned entirely new waveforms by observing the wireless environment. One of our first successes was to send high-rate data over the NASA Tracking and Data Relay Satellite System (TDRSS) used to communicate with the ISS and other satellites. Our AI-based approach enabled the system to operate in a way that is extremely power efficient but not possible with human-designed approaches because it causes severe signal distortion. Using OmniPHY, we learned a new communications waveform that was resistant to the distortion and achieved higher data rates than conventional technology.
OmniPHY for 5G
5G employs industry standard waveforms, such as the “5G New Radio Air Interface”, which are developed by the 3GPP International Committee - so OmniPHY can’t develop entirely new waveforms for 5G (note that this is not the case for 6G). Thus, to achieve performance improvements in 5G, OmniPHY substitutes AI for existing processing algorithms while maintaining compatibility with the 3GPP 5G standard.
To illustrate how this works, we'll use Massive MIMO as an example, where the simple antennas of 4G are replaced by arrays of up to 192 antennas. The processing required to fully utilize Massive MIMO has turned out to be tremendously expensive in terms of computation, which also means it is tremendously power hungry. In fact, when operators tested this technology they discovered that their battery backups went from days worth of capacity to just a few hours. Using OmniPHY, DeepSig is able to design an AI that replaces that expensive processing with a deep learning neural network that achieves the same functional result but much faster and with substantially less power consumption.
This process, replacing hand-engineering algorithms with AI-based equivalents that use machine learning, could bring significant computational and power benefits to many areas of the 5G stack.
DeepSig is investing heavily in the application of AI for 5G and other consumer wireless technologies, and is productising these capabilities with our OmniPHY software product. If you would like to learn more, please get in touch using the contact form below!