Power-efficient beam tracking during connected mode DRX in mmWave and sub-THz systems

Abstract

Discontinuous reception (DRX), wherein a user equipment (UE) temporarily disables its receiver, is a critical power saving feature in modern cellular systems. DRX is likely to be aggressively used at mmWave and sub-THz frequencies due to the high front-end power consumption. A key challenge for DRX at these frequencies is blockage-induced link outages: A UE will likely need to track many directional links to ensure reliable multi-connectivity, thereby increasing the power consumption. In this paper, we explore reinforcement learning-based link tracking policies in connected mode DRX that reduce power consumption by tracking only a fraction of the available links, but without adversely affecting the outage and throughput performance. Through detailed, system level simulations at 28 GHz (5G) and 140 GHz (6G), we observe that even sub-optimal link tracking policies can achieve considerable power savings with relatively little degradation in outage and throughput performance, especially with digital beamforming at the UE. In particular, we show that it is feasible to reduce power consumption by 75% and still achieve up to 95% (80%) of the maximum throughput using digital beamforming at 28 GHz (140 GHz), subject to an outage probability of at most 1%.

Multi-cell Multi-beam Prediction using Auto-encoder LSTM for mmWave systems

“…Importantly, since we consider tracking a much larger number of links, the role of the dimensionality reduction is key. As shown in [19], the beams increase as carrier frequency f c increases (∝ f 2 c ) 1 . Increasing f c results in severe blockage [20] and penetration loss [21], which necessitates more macrodiversity (multi-cell connectivity), thereby increasing the input dimensions even more.…”

“…These prediction capabilities will help in processes like proactive beam switching, handovers 1 For example, if fc is increased from 28 to 140 GHz (sub-THz, 6G), the number of directions to track increase by a factor of 32 [19], which equals increase in input dimension size in our case. [27] and adaptive rate prediction.…”

“…There is not much space for tuning for baseline predictors except for the parameter M (window size in this case). The training method for baseline predictors find a value of M that 19 All ML-based predictors have been trained for equal number of epochs (20) minimizes the losses in ( 3)-( 4) 20 . The values of M that provide a good trade-off between the two losses are obtained by brute-force method iterating over values of M localized to {1, • • • , 50} for all the N train trajectories.…”

“…Training ML-based PredictorsAfter creating an appropriate auto-encoder and PCA encoder/decoder set, we proceed to train LSTM-PCA, LSTM-AC, Vanilla RNN with AC, Transformer with AC and CNN with AC. ML-based methods are trained over 100 train trajectories of encoded SNRs (of dimensions d AC obtained using auto-encoder) to solve the one time step ahead prediction problem using MSE loss19 . LSTM-PCA is trained in a similar manner over PCA-encoded SNRs (of dimension d P CA ).…”

Power Efficient Multi-Carrier Baseband Processing for 5G and 6G Wireless

“…Another focus of this paper is to compare the beamforming architectures for the receiver. Although most mobile devices have used phased arrays for RF beamforming in 5G, fully digital architectures can offer the fast beam search in mobile environments [20], which is valuable for fast recovery from blocking [21]- [23], and aggressive use of idle and DRX modes [24], [25]. Fully digital architectures observe all directions simultaneously [8], [26], [27] to reduce the initial access time by an order of magnitude [28], [29].…”