Learning to Broadcast for Ultra-Reliable Communication with Differential Quality of Service via the Conditional Value at Risk

Abstract

Broadcast/multicast communication systems are typically designed to optimize the outage rate criterion, which neglects the performance of the fraction of clients with the worst channel conditions.Targeting ultra-reliable communication scenarios, this paper takes a complementary approach by introducing the conditional value-at-risk (CVaR) rate as the expected rate of a worst-case fraction of clients. To support differential quality-of-service (QoS) levels in this class of clients, layered division multiplexing (LDM) is applied, which enables decoding at different rates. Focusing on a practical scenario in which the transmitter does not know the fading distribution, layer allocation is optimized based on a dataset sampled during deployment. The optimality gap caused by the availability of limited data is bounded via a generalization analysis, and the sample complexity is shown to increase as the designated fraction of worst-case clients decreases. Considering this theoretical result, meta-learning is introduced as a means to reduce sample complexity by leveraging data from previous deployments. Numerical experiments demonstrate that LDM improves spectral efficiency even for small datasets; that, for sufficiently large datasets, the proposed mirror-descentbased layer optimization scheme achieves a CVaR rate close to that achieved when the transmitter knows the fading distribution; and that meta-learning can significantly reduce data requirements.

Learning to Broadcast with Layered Division Multiplexing

“…Among related problems left open by this study, we mention the extension to multiple transmit antennas [11] and to channels with multiple uncoordinated transmitters [17], [18]. An extended version of this work, which introduces the conditional value-at-risk (CVaR) rate performance measure for ultra-reliable communication, and considers meta-learning as a means to reduce sample complexity by leveraging data from previous deployments, is available in [19].…”

Statistical Tools and Methodologies for URLLC- A Tutorial

“…Specifically, the authors in [15] use a risksensitive approach exploiting CVaR to schedule URLLC traffic in coexistence with punctured mobile broadband (MBB) services. Meanwhile, CVaR rate is a metric introduced and thoroughly investigated in [76] to characterize the expected rate of a worst-case fraction of clients in broadcast/multicast URLLC systems. Finally, in [77], the authors realize that the FBL error probability (see (54) and related discussions) is in fact a RV in fading scenarios, for which they provide accurate PDF analytical approximations.…”

“…Then, we calculate the delay bound as in ( 66) and upper bound the delay violation probability, i.e., P out = Pr [W (t ) > w] as in (76). Note that when we introduce fading to the model, the rate expressions include logarithmic terms, which makes it cumbersome to find closed-form expressions for MGFs and the metrics.…”

Speeding up Training of Linear Predictors for Multi-Antenna Frequency-Selective Channels via Meta-Learning

“…Previous applications of transfer learning to communication systems include beamforming for multi-user, multiple-input, single-output (MISO) downlink [ 25 ] and for intelligent reflecting surfaces (IRS)-assisted MISO downlink [ 26 ], and downlink channel prediction [ 27 , 28 ] (see also [ 25 , 27 ]). Meta-learning has been applied to communication systems, including demodulation [ 29 , 30 , 31 , 32 ], decoding [ 33 ], end-to-end design of encoding and decoding with and without a channel model [ 34 , 35 ]; MIMO detection [ 36 ], beamforming for multiuser MISO downlink systems via [ 37 ], layered division multiplexing for ultra-reliable communications [ 38 ], UAV trajectory design [ 39 ], and resource allocation [ 40 ].…”