On the Energy Efficiency of One-Layer SISO Rate-Splitting Multiple Access

Souza, Wilson de; Rodrigues, V.; Abrão, Taufik

doi:10.1109/urucon53396.2021.9647240

Cited by 2 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This comparison allows assessing the performance of the RSMA-based network against an SISO IBC network while at the same time proving that the employed DQL algorithm can generalize well and adapt to fit from less to more complicated network setups that require optimizing a higher number of communication resources. The "RS Algorithm in [5]" regards a similar RSMA network to ours with the difference that the joint power and rate allocation problem is decomposed into sub-problems that are independently solved optimally, and an algorithm is devised to combine the derived solutions. Last, we compare against the Weighted Minimum Mean Square Error (WMMSE) approach, based on which the power allocation is determined for sum-rate maximization, and then, the achieved energy efficiency is calculated, considering that the base station has exhausted its power budget p max .…”

Section: Evaluation and Resultsmentioning

confidence: 99%

“…Last, we compare against the Weighted Minimum Mean Square Error (WMMSE) approach, based on which the power allocation is determined for sum-rate maximization, and then, the achieved energy efficiency is calculated, considering that the base station has exhausted its power budget p max . RS DQL RS Algorithm in [5] No-RS DQL RS WMMSE Fig. 2: Achieved energy efficiency of "RS DQL", "No-RS DQL", "RS Algorithm in [5]", and "RS WMMSE" under different numbers of users.…”

Section: Evaluation and Resultsmentioning

confidence: 99%

“…RS DQL RS Algorithm in [5] No-RS DQL RS WMMSE Fig. 2: Achieved energy efficiency of "RS DQL", "No-RS DQL", "RS Algorithm in [5]", and "RS WMMSE" under different numbers of users.…”

Section: Evaluation and Resultsmentioning

confidence: 99%

“…In Fig. 2, the "RS DQL", "No-RS DQL", "RS Algorithm in [5]", and "RS WMMSE" approaches are compared in terms of achieved energy efficiency, while accounting for different numbers of users in the cell. Note that the results presented for "RS DQL" and "No-RS DQL" from this point and on correspond to the average energy efficiency concluded by the trained DQN over 50 random episodes of 500 time slots each.…”

Section: Evaluation and Resultsmentioning

confidence: 99%

“…In this context, quantifying the performance gain of the RSMA technique in terms of achieved energy efficiency is crucial though only a handful of research works have investigated it until now, e.g., [4]- [7]. Early work in [4] studied the optimization of beamforming and common-rate allocation in Multiple-Input Single-Output (MISO) broadcast channels, while a similar Single-Input Single Output (SISO) setting was examined in [5]. Both works compared the energy efficiency level of the network against the one achieved by different multiple access techniques, verifying that the energy efficiency region of RSMA is equal or higher.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Power and Rate Allocation for Energy-Efficient Rate-Splitting Multiple Access via Deep Q-Learning

Diamanti,

Kapsalis,

Tsiropoulou

et al. 2023

2023 IEEE Globecom Workshops (GC Wkshps)

View full text Add to dashboard Cite

Rate-Splitting Multiple Access (RSMA) has recently emerged as an effective technique for increasing network capacity by smartly controlling the tradeoff between decoding and treating interference as noise. In this paper, aligned with the need for sustainable wireless networks, we study the energy-efficient power and rate allocation of the common and private messages in the downlink of a network where rate-splitting is adopted. The corresponding energy efficiency maximization problem is transformed into a multi-agent Deep Reinforcement Learning (DRL) problem, based on which each private stream transmitted in the downlink constitutes a different DRL agent. The formulated DRL problem is solved by using Deep Q-Learning (DQL) algorithm and training a single Deep Q-Network (DQN) from the cumulative experiences gained from the DRL agents and their exploration of the environment, i.e., the exploration of different private-message power allocations. Numerical results obtained via modeling and simulation verify the effectiveness of the proposed DQL algorithm, demonstrating that it concludes solutions that outperform existing approaches from the literature in the achieved energy efficiency.

show abstract

Section: Evaluation and Resultsmentioning

confidence: 99%

Section: Evaluation and Resultsmentioning

confidence: 99%

“…RS DQL RS Algorithm in [5] No-RS DQL RS WMMSE Fig. 2: Achieved energy efficiency of "RS DQL", "No-RS DQL", "RS Algorithm in [5]", and "RS WMMSE" under different numbers of users.…”

Section: Evaluation and Resultsmentioning

confidence: 99%

Section: Evaluation and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Power and Rate Allocation for Energy-Efficient Rate-Splitting Multiple Access via Deep Q-Learning

Diamanti,

Kapsalis,

Tsiropoulou

et al. 2023

2023 IEEE Globecom Workshops (GC Wkshps)

View full text Add to dashboard Cite

show abstract

Energy-Efficient Rate-Splitting Multiple Access: A Deep Reinforcement Learning-Based Framework

Diamanti,

Kapsalis,

Tsiropoulou

et al. 2023

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Rate-Splitting Multiple Access (RSMA) has been recognized as an effective technique to reconcile the tradeoff between decoding interference and treating interference as noise in 6G and beyond networks. In this paper, in line with the need for network sustainability, we study the energy-efficient power and rate allocation of the common and private messages transmitted in the downlink of a single-cell single-antenna RSMA network. Contrary to the literature that resorts to heuristic approaches to deal with the joint problem, we transform the formulated energy efficiency maximization problem into a multiagent Deep Reinforcement Learning (DRL) problem, based on which each transmitted private message represents a different DRL agent. Each agent explores its own state-action space, the size of which is fixed and independent of the number of agents, and shares its gained experience by exploration with a common neural network. Two DRL algorithms, namely the value-based Deep Q-Learning (DQL) and the policy-based REINFORCE, are properly configured and utilized to solve it. The adaptation of the proposed DRL framework is also demonstrated for the treatment of the considered network's sum-rate maximization objective. Numerical results obtained via modeling and simulation verify the effectiveness of the proposed DRL framework to conclude a solution to the joint problem under both optimization objectives, outperforming existing heuristic approaches and algorithms from the literature.INDEX TERMS Energy efficiency maximization, rate-splitting multiple access (RSMA), deep reinforcement learning (DRL).

show abstract

On the Energy Efficiency of One-Layer SISO Rate-Splitting Multiple Access

Cited by 2 publications

References 8 publications

Power and Rate Allocation for Energy-Efficient Rate-Splitting Multiple Access via Deep Q-Learning

Power and Rate Allocation for Energy-Efficient Rate-Splitting Multiple Access via Deep Q-Learning

Energy-Efficient Rate-Splitting Multiple Access: A Deep Reinforcement Learning-Based Framework

Contact Info

Product

Resources

About