Hybrid cascaded attention-guided refinement network-based optimal power allocation in MIMO-NOMA system

Ananth Kumar M.S.

doi:10.1117/12.2675103

10 April 2023 Hybrid cascaded attention-guided refinement network-based optimal power allocation in MIMO-NOMA system

Ananth Kumar M.S.

Proceedings Volume 12616, International Conference on Mathematical and Statistical Physics, Computational Science, Education, and Communication (ICMSCE 2022); 126160F (2023) https://doi.org/10.1117/12.2675103
Event: International Conference on Mathematical and Statistical Physics, Computational Science, Education, and Communication (ICMSCE 2022), 2022, Istanbul, Turkey

Abstract

The multiple input multiple output (MIMO) plays an integral role in improving the energy efficiency for enhancing the QoS of all users. For the 5G wireless communication (WC), NOMA strategy is used with MIMO system to improve the sum rate as well as the computational complexity of the system. This developed work mainly focuses on emphasizing deep learning based optimal power allocation and user pairing techniques in MIMO-NOMA technology to enhance the sum rate and to reduce computational complexity. Normally, NOMA system is used to improve the spectrum in 5G mobile communication. When NOMA is hybridizing with MIMO system, the spectral efficiency (SE) is highly improved. But user pairing problems arise in NOMA system. To overcome this, deep reinforcement learning approach (DRL) is established to receive data from the user equipment (UE) about CSI and position. To allocate the power in UE, cascaded attention guided refinement network (CAGR-Net) is proposed. In addition to this, tiki taka algorithm (TTA) is manipulated to perform clustering as well as to vary the power levels for optimizing the system overall performance of the proposed method. The performance measures such as energy efficiency (EE), spectral efficiency (SE), channel gain, ergodic sum capacity, MSE and error rate are evaluated. In experimental scenario, the error between user 1 and user 2 attained about 0.1044 and 0.5642 respectively with the SNR of 16dB. The performance of the developed model shows better outcome compared to other existing techniques.

Citation Download Citation

Ananth Kumar M.S. "Hybrid cascaded attention-guided refinement network-based optimal power allocation in MIMO-NOMA system", Proc. SPIE 12616, International Conference on Mathematical and Statistical Physics, Computational Science, Education, and Communication (ICMSCE 2022), 126160F (10 April 2023); https://doi.org/10.1117/12.2675103

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
23 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Antennas

Data modeling

Telecommunications

Data transmission

Mathematical optimization

Multiple input multiple output

Energy efficiency

Show All Keywords

Keywords/Phrases

Search In:

Publication Years