Dynamic Power Allocation Scheme for NOMA Uplink in Cognitive Radio Networks Using Deep Q Learning

Giang, Hoang Thi Huong; Thanh, Pham Duy; Koo, Insoo

doi:10.1109/ictc49870.2020.9289435

Cited by 6 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hoang Thi Huong Giang et al [25] offered a dynamic PA model based on deep Q learning for long term throughput maximization of uplink CR-NOMA. Here, it was suggested to combine time division multiple access (TDMA) with NOMA to lessen the complexity of massive wireless communication systems.…”

Section: Related Workmentioning

confidence: 99%

Bio-inspired hybrid lyrebird optimization-based power allocation and relay-selection scheme

M.S.

2024

International Conference on Medical Imaging, Electronic Imaging, Information Technologies, and Sensors (MIEITS 2024)

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Bio-inspired hybrid lyrebird optimization-based power allocation and relay-selection scheme

M.S.

2024

International Conference on Medical Imaging, Electronic Imaging, Information Technologies, and Sensors (MIEITS 2024)

View full text Add to dashboard Cite

“…The performance measure like energy efficiency, throughput and average response time of the proposed model are compared with the existing methods like deep Q learning, conventional TDMA and conventional NOMA/ TDMA 27 . Further, the theoretical and simulation outcomes of the proposed and existing models are presented.…”

Section: Performance Of the Proposed Crn-noma With Other Modelsmentioning

confidence: 99%

“…But, the proposed CRN-NOMA model efficiently allocates the data transmission to the users by powerful signal detection. When, the value of mean harvested energy is 5 J  , the average transmission rate is 12.13, 11.58, 9.66 and 12.72, for the methods like deep Q learning, conventional TDMA, conventional NOMA/ TDMA in Giang et al 27 and the proposed model respectively. Figure 8 represents the comparison of convergence analysis of various models for the training episodes of 0 to 100.…”

Section: Performance Of the Proposed Crn-noma With Other Modelsmentioning

confidence: 99%

ICA-ResNet-based signal detection and optimal power allocation for CRN-NOMA system

Kumar

2023

International Conference on Mathematical and Statistical Physics, Computational Science, Education, and Communication (ICMSCE 2

View full text Add to dashboard Cite

Non-orthogonal multiple access (NOMA) system is one of the assuring solutions for the upcoming wireless communication systems for achieving better spectral efficiency. The NOMA based wireless communication system is mainly transformed with cognitive radio network (CRN) to improve the performance. This research work focuses on signal detection and optimal power allocation for uplink CRN-NOMA system using optimal deep learning (DL) model. This model combines the channel state estimation process and signal detection. In the proposed work, the signal detection is carried out on the basis of allocated power to the user. Initially, the power allocation process is carried out by the Bisection water filling algorithm to achieve optimal power allocation. Then, the signal detection process is enabled by the DL model ResNet-152. Then, the metaheuristic optimization using Imperialist Competitive Algorithm (ICA) is exploited to provide optimal solution for better signal detection. The noisy channel's information like Rayleigh fading and AWGN are set for wireless transmission medium to transmit a signal. The combined model of power allocation and signal detection is carried out on MATLAB platform. The performance measures like spectral efficiency, energy efficiency, BER and average response rate of the proposed techniques are compared with the previous research works. When the value of mean harvested energy is 4.5 J  , the energy efficiency of the proposed model, deep Q learning, conventional TDMA and conventional NOMA/ TDMA are 0.74 [bit/s/Hz], 0.71 [bit/s/Hz], 0.67 [bit/s/Hz] and 0.57 [bit/s/Hz] respectively. It has been hence proved that the performance of this methodology is accurate and effective than the existing models.

show abstract

“…This paper [21] proposes a deep Q-learning-based RA approach for uplink NOMA in a cognitive radio network (CRN) to maximize long-term throughput. This work focuses on secondary users (SUs) with limited battery capacity, which can extend their operations using energy harvested from solar sources.…”

Section: Introductionmentioning

confidence: 99%

AI-Based Q-Learning Approach for Performance Optimization in MIMO-NOMA Wireless Communication Systems

A. Majeed,

Ali Saed,

Hburi

2023

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

In this paper, we investigate the performance enhancement of Multiple Input, Multiple Output, and Non-Orthogonal Multiple Access (MIMO-NOMA) wireless communication systems using an Artificial Intelligence (AI) based Q-Learning reinforcement learning approach. The primary challenge addressed is the optimization of power allocation in a MIMO-NOMA system, a complex task given the non-convex nature of the problem. Our proposed Q-Learning approach adaptively adjusts power allocation strategy for proximal and distant users, optimizing the trade-off between various conflicting metrics and significantly improving the system’s performance. Compared to traditional power allocation strategies, our approach showed superior performance across three principal parameters: spectral efficiency, achievable sum rate, and energy efficiency. Specifically, our methodology achieved approximately a 140% increase in the achievable sum rate and about 93% improvement in energy efficiency at a transmitted power of 20 dB while also enhancing spectral efficiency by approximately 88.6% at 30 dB transmitted Power. These results underscore the potential of reinforcement learning techniques, particularly Q-Learning, as practical solutions for complex optimization problems in wireless communication systems. Future research may investigate the inclusion of enhanced channel simulations and network limitations into the machine learning framework to assess the feasibility and resilience of such intelligent approaches.

show abstract

Dynamic Power Allocation Scheme for NOMA Uplink in Cognitive Radio Networks Using Deep Q Learning

Cited by 6 publications

References 24 publications

Bio-inspired hybrid lyrebird optimization-based power allocation and relay-selection scheme

Bio-inspired hybrid lyrebird optimization-based power allocation and relay-selection scheme

ICA-ResNet-based signal detection and optimal power allocation for CRN-NOMA system

AI-Based Q-Learning Approach for Performance Optimization in MIMO-NOMA Wireless Communication Systems

Contact Info

Product

Resources

About