M = 3 and 4 for 32-ary APSK and 64-asry APSK, respectively. Then, we show with the best ring ratios that the (4, 12, 16) 32APSK scheme with M = 3 achieves a lower required received SNR considering the CM compared to that for the cross 32QAM scheme. Similarly, we show that the (4, 12, 20, 28) 64APSK scheme with M = 4 achieves almost the same required received SNR considering the CM as that for the square 64QAM scheme." />
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

Throughput Comparisons of 32/64APSK Schemes Based on Mutual Information Considering Cubic Metric

Reo KOBAYASHI
Teruo KAWAMURA
Nobuhiko MIKI
Mamoru SAWAHASHI

Publication
IEICE TRANSACTIONS on Communications   Vol.E95-B    No.12    pp.3719-3727
Publication Date: 2012/12/01
Online ISSN: 1745-1345
DOI: 10.1587/transcom.E95.B.3719
Print ISSN: 0916-8516
Type of Manuscript: Special Section PAPER (Special Section on Coding and Coding Theory-Based Signal Processing for Wireless Communications)
Category: 
Keyword: 
APSK,  throughput,  mutual information,  cubic metric,  

Full Text: PDF(2.9MB)>>
Buy this Article


Summary: 
This paper presents comprehensive comparisons of the achievable throughput between the 32-/64-ary amplitude and phase shift keying (APSK) and cross 32QAM/square 64QAM schemes based on mutual information (MI) considering the peak-to-average power ratio (PAPR) of the modulated signal. As a PAPR criterion, we use a cubic metric (CM) that directly corresponds to the transmission back-off of a power amplifier. In the analysis, we present the best ring ratio for the 32 or 64APSK scheme from the viewpoint of minimizing the required received signal-to-noise power ratio (SNR) considering the CM that achieves the peak throughput, i.e., maximum error-free transmission rate. We show that the required received SNR considering the CM at the peak throughput is minimized with the number of rings of M = 3 and 4 for 32-ary APSK and 64-asry APSK, respectively. Then, we show with the best ring ratios that the (4, 12, 16) 32APSK scheme with M = 3 achieves a lower required received SNR considering the CM compared to that for the cross 32QAM scheme. Similarly, we show that the (4, 12, 20, 28) 64APSK scheme with M = 4 achieves almost the same required received SNR considering the CM as that for the square 64QAM scheme.