Explore how we are extending digital twins to wireless radio operations. Our demo shows the impact for analog beamforming performance in massive MIMO deployments. We also take a peek into the future of RAN automation, such as with our Qualcomm Dragonwing™ RAN Automation Suite. Discover how our digital twins contribute to efficient and robust mobile networks, paving the way for future applications of 6G. ========================= Frequently asked questions ========================= Q1) What is the objective of the wireless digital twin? The wireless digital twin is an accurate representation of the physical wireless network which is then used to evaluate ‘what-if’ scenarios to predict KPIs and enhance network performance and efficiency. In this demonstration, the digital twin of the physical model is used to draw insights into the propagation model, and this convergence is used to improve link and system performance of futuristic 6G wireless systems. Q2) What are the components of the digital twin? The key components of the digital twin in this work are the: [a] radio propagation model, [b] network model, and [c] beamforming design module. The radio model and network model are site-specific and deployment-specific respectively, i.e., “twins” of their physical counterparts. The beamforming design module extracts physical propagation model insights towards the design of better codebooks / beamforming schemes. Q3) How is a digital twin different from a simulation? The digital twin used here is an exact representation of the physical network instance, especially from a radio propagation perspective in this work, as opposed to statistical models that typically characterize simulations. The fidelity of the radio digital twin is verified and fine-tuned using observations from the physical network data. Q4) How do we envision the architecture of digital twin-assisted beamforming? The two variations of digital twin-assisted beamforming in this demo have different architectures: [1] The codebook enhancement variant that takes user distribution into account is envisioned to be deployed at the SMO, and [2] The UE-specific beamforming variant that could be implemented in 6G uses exact user locations and is more likely to be executed in the RAN intelligent controller (RIC) than the SMO for lower latency. Q5) Are the codebook enhancement and UE-specific beamforming techniques implemented end-to-end in this demo? No. What is demonstrated is a radio unit-only version. However, the architectural view of the two variants are presented for reference. Q6) What is meant by fine tuning of the radio digital twin? A small sample of the dataset collected over-the-air (OTA) is used to refine the digital twin using algorithmic approaches to improve its overall accuracy. Q7) How are the users physically distributed? There are a total of 7 clusters encompassing 70 users in total. Q8) How is the uniform codebook (the baseline) chosen? A few typical candidates with uniform rectangular spacing of beams spanning azimuth and elevation angles were evaluated. The most suitable ones were chosen, with a constraint of 4 beams in total in the codebook. Q9) How is the digital twin-assisted codebook chosen? With the radio propagation characteristics and the distribution of users being known, a codebook with a constraint of 4 total beams was chosen for the clusters of users. Q10) With user-specific beamforming, the position of the user may change. How is this handled? User-specific beamforming requires location as an input and the user’s dynamic or changing position is expected to be available when making the beamforming decision. Q11) With user-specific beamforming, decisions must be made dynamically. How is this handled? A: Yes, the architecture does need to handle dynamic inputs and outputs for this forward-looking scheme. There may be multiple ways to achieve this objective.

 10770      45