Radio Resource Management Design for RSMA: Optimization of Beamforming, User Admission, and Discrete/Continuous Rates with Imperfect SIC

TL;DR

This work addresses RSMA-based downlink RRM under practical constraints by formulating two MINLP problems for maximizing weighted spectral and energy efficiency with discrete/private/common rate decisions and imperfect SIC. It introduces OPT-MISOCP to globally solve the discrete-rate problems via convexifications, Big-M reformulations, and cutting planes, and complements this with OPT-SCA-SDR for continuous-rate cases, including UE admission and rate projections. The results show substantial gains of discrete-rate RSMA over naive rate projection (up to 89.7% in WSR and 21.5% in WEE), and demonstrate that UE admission and imperfect SIC modeling markedly improve robustness and resource utilization. Overall, the study provides a rigorous, scalable framework for deploying RSMA in practical systems, highlighting the importance of accounting for discreteness, user selection, and SIC imperfections in RRM design and offering algorithmic pathways to near-optimal solutions.

Abstract

This paper investigates the radio resource management (RRM) design for multiuser rate-splitting multiple access (RSMA), accounting for various characteristics of practical wireless systems, such as the use of discrete rates, the inability to serve all users, and the imperfect successive interference cancellation (SIC). Specifically, failure to consider these characteristics in RRM design may lead to inefficient use of radio resources. Therefore, we formulate the RRM of RSMA as optimization problems to maximize respectively the weighted sum rate (WSR) and weighted energy efficiency (WEE), and jointly optimize the beamforming, user admission, discrete/continuous rates, accounting for imperfect SIC, which result in nonconvex mixed-integer nonlinear programs that are challenging to solve. Despite the difficulty of the optimization problems, we develop algorithms that can find high-quality solutions. We show via simulations that carefully accounting for the aforementioned characteristics, can lead to significant gains. Precisely, by considering that transmission rates are discrete, the transmit power can be utilized more intelligently, allocating just enough power to guarantee a given discrete rate. Additionally, we reveal that user admission plays a crucial role in RSMA, enabling additional gains compared to random admission by facilitating the servicing of selected users with mutually beneficial channel characteristics. Furthermore, provisioning for possibly imperfect SIC makes RSMA more robust and reliable.

Figures (13)

• Figure 1: System model and RSMA with integrated RRM optimizer. In the system, $K$ out of $U$ UEs are admitted for downlink transmission. The messages for the admitted UEs are precoded via rate splitting and transmitted over the air.
• Figure 2: Analysis of time complexity, optimality, and convergence.
• Figure 3: (Scenario I) Two-user SE region of RSMA with discrete and continuous rates for $\frac{P_\mathrm{tx}^\mathrm{max}}{\sigma^2} = \left\lbrace 10, 20 \right\rbrace$ dB. Since OPT-SCA-SDR does not account for rate saturation, it continues upgrading the private rates, not necessarily leading to improved performance upon rate projection. In contrast, OPT-MISOCP considers that the rates are bounded and discrete, promoting more appropriate usage of power. Specifically, OPT-MISOCP uses the surplus of power to upgrade weaker private or common signals, preventing severe rate saturation of other signals.
• Figure 4: (Scenario II) Two-user SE region of RSMA and SDMA with discrete rates using OPT-MISOCP for $\frac{P_\mathrm{tx}^\mathrm{max}}{\sigma^2} = \left\lbrace 10, 15, 20 \right\rbrace$ dB. The advantage of RSMA stems from its capability of using the surplus of power to transmit the common signal, even in scenarios with highly uncorrelated channels, which SDMA is unable to do.
• Figure 5: (Scenario III) Two-user SE region of RSMA with discrete rates and imperfect SIC using OPT-MISOCP for $\frac{P_\mathrm{tx}^\mathrm{max}}{\sigma^2} = \left\lbrace 0, 10, 20 \right\rbrace$ dB and various $\Delta_\mathrm{SIC}$ values. Accounting for potentially imperfect SIC has an enormous performance benefit. In the worst case, RSMA collapses to SDMA, still providing outstanding performance compared to the case without protection. In the presence of large unmanaged residuals of the common signal, due to an imperfect SIC, the private rates cannot be guaranteed, thus collapsing to zero due to the inability to fulfill the target SINRs required for successful decoding.