A Deep Reinforcement Learning Framework for Data Compression in Uplink NOMA-SWIPT Systems

Sayed, Mohamed El; Badawy, Ahmed; Shafie, Ahmed El; Mohamed, Amr; Khattab, Tamer

doi:10.1109/jiot.2021.3131524

Cited by 13 publications

(13 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By assuming the case of null interference in (23), a loose upperbound 38 on the sum rates can be determined as follows:…”

Section: A Upper Bound On Performancementioning

confidence: 99%

See 1 more Smart Citation

Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology

Shehab¹,

Almohamad²,

El-Sayed³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…By assuming the case of null interference in (23), a loose upperbound 38 on the sum rates can be determined as follows:…”

Section: A Upper Bound On Performancementioning

confidence: 99%

“…Further, the DRL algorithm will always select the action A that yields the highest reward, and performs a linear search on the output. Therefore, the overall computational complexity of one forward pass in the neural network is expressed as [23]:…”

mentioning

confidence: 99%

Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology

Shehab¹,

Almohamad²,

El-Sayed³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The weak user sees the powerful user’s signal as noise and instantly recognizes its signal. 57 Figure 2 illustrates a typical D/L NOMA situation for two users without sacrificing generality. The traditional D/L NOMA employs a power allocation scheme, with users with poor channel conditions receiving more transmission power and vice versa.…”

Section: System Modelmentioning

confidence: 99%

Analysis of user pairing non-orthogonal multiple access network using deep Q-network algorithm for defense applications

Ravi¹,

Kulkarni

Ray

et al. 2022

Journal of Defense Modeling & Simulation

View full text Add to dashboard Cite

Non-orthogonal multiple access (NOMA) networks play an important role in defense communication scenarios. Deep learning (DL)-based solutions are being considered as viable ways to solve the issues in fifth-generation (5G) and beyond 5G (B5G) wireless networks, since they can provide a more realistic solution in the real-world wireless environment. In this work, we consider the deep Q-Network (DQN) algorithm-based user pairing downlink (D/L) NOMA network. We have applied the convex optimization (CO) technique and optimized the sum rate of all the wireless users. First, the near-far (N-F) pairing and near-near and far-far (N-N and F-F) pairing strategies are investigated for the multiple numbers of users, and a closed-form (CF) expression of the achievable rate is derived. After that, the optimal power allocation (OPA) factors are derived using the CO technique. Through simulations, it has been demonstrated that the DQN algorithms perform much better than the deep reinforcement learning (DRL) and conventional orthogonal frequency-division multiple access (OFDMA) schemes. The sum-rate performance significantly increases with OPA factors. The simulation results are in close agreement with the analytical results.

show abstract

“…However, the AF protocol leads to noise amplification problems and the channel is static, which is not suitable for military applications. Elsayed 26 proposes a power-efficient algorithm for wirelessly exchanging extreme information received from the IoT devices connected to a cluster head edge node. The combination of NOMA and SWIPT helps to increase both energy and SE simultaneously.…”

Section: Introductionmentioning

confidence: 99%

“…In So and Wong, 27 the authors investigated the PS-based SWIPT NOMA network and proposed a dual-layer approach to solving the non-CO optimization framework considering the EH network. Even though a wide range of NOMA methods have been provided in the literature, 20–27 the suggested techniques’ key assessment scenario is communications with poor bandwidth efficiency in fading channels with large-scale fading and short root mean square delay spread (40,300 nanoseconds), since they are aimed at commercial platforms. Since the BS, NU, and FU are all traveling in a military situation, the channel is always not stagnant and changes, so the channel situations and usage cases can be very different from commercial ones.…”

Section: Introductionmentioning

confidence: 99%

Examination of the fifth-generation vehicular simultaneous wireless information and power transfer cooperative non-orthogonal multiple access network in military scenarios considering time-varying and imperfect channel state information conditions

Pandya

Krishna

Shankar³

et al. 2021

Journal of Defense Modeling & Simulation

View full text Add to dashboard Cite

In a defense scenario, the communicating nodes are mobile and, due to this, the fading channel links become time selective in nature. Non-orthogonal multiple access (NOMA) is a promising technique in modern wireless communication systems, and it is employed in a variety of defense ad hoc wireless communication scenarios where nodes are mobile and it is difficult to estimate the channel coefficients perfectly. NOMA contributes to increased spectral efficiency (SE), firstly by enabling fifth-generation new radio deployment in the 3.5 GHz frequency range, and secondly by employing a simultaneous wireless information and power transfer (SWIPT) time switching and power splitting-based cooperative NOMA (C-NOMA) network where simple radio frequency circuitry is used for energy harvesting. NOMA together with the selective decode-and-forward (S-DF) protocol will increase the SE and energy efficiency simultaneously. The outage probability performance is evaluated for various values of the fading severity parameter and node velocity forming the channel error. It is significant to note that digital S-DF-based SWIPT C-NOMA performs much better than an analog amplify-and-forward-based C-NOMA SWIPT system.

show abstract

A Deep Reinforcement Learning Framework for Data Compression in Uplink NOMA-SWIPT Systems

Cited by 13 publications

References 48 publications

Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology

Terahertz Multiple Access: A Deep Reinforcement Learning Controlled Multihop IRS Topology

Analysis of user pairing non-orthogonal multiple access network using deep Q-network algorithm for defense applications

Examination of the fifth-generation vehicular simultaneous wireless information and power transfer cooperative non-orthogonal multiple access network in military scenarios considering time-varying and imperfect channel state information conditions

Contact Info

Product

Resources

About