Investigation of the fifth generation non-orthogonal multiple access technique for defense applications using deep learning
| Autor: | Ravi Shankar, Manoj Kumar Beuria, Sudhansu Sekhar Singh, Ravisankar Malladi |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
business.industry Deep learning 020206 networking & telecommunications 020302 automobile design & engineering 02 engineering and technology Spectral efficiency Non orthogonal Fifth generation medicine.disease Noma 0203 mechanical engineering Computer architecture Modeling and Simulation 0202 electrical engineering electronic engineering information engineering medicine Wireless Artificial intelligence business Engineering (miscellaneous) Throughput (business) 5G |
| Zdroj: | The Journal of Defense Modeling and Simulation: Applications, Methodology, Technology. 19:829-838 |
| ISSN: | 1557-380X 1548-5129 |
| DOI: | 10.1177/15485129211022857 |
| Popis: | In modern wireless communication scenarios, non-orthogonal multiple access (NOMA) provides high throughput and spectral efficiency for fifth generation (5G) and beyond 5G systems. Traditional NOMA detectors are based on successive interference cancellation (SIC) techniques at both uplink and downlink NOMA transmissions. However, due to imperfect SIC, these detectors are not suitable for defense applications. In this paper, we investigate the 5G multiple-input multiple-output NOMA deep learning technique for defense applications and proposed a learning approach that investigates the communication system’s channel state information automatically and identifies the initial transmission sequences. With the use of the proposed deep neural network, the optimal solution is provided, and performance is much better than the traditional SIC-based NOMA detectors. Through simulations, the analytical outcomes are verified. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|