Lightweight Machine Learning for Efficient Frequency-Offset-Aware Demodulation

Lightweight Machine Learning for Efficient Frequency-Offset-Aware Demodulation
复制标题

用于高效频偏感知解调的轻量级机器学习

DOI:
10.1109/jsac.2019.2933956
复制
发表时间:
2019
影响因子:
16.4
通讯作者:
Krunz, Marwan
Krunz, Marwan
中科院分区:
计算机科学1区
文献类型:
--
作者:
Siyari, Peyman;Rahbari, Hanif;Krunz, Marwan

文献摘要

参考文献

被引文献

相似文献

载波频率偏移(CFO)是由无线发射器和相应接收器的振荡器之间的固有不匹配以及它们的相对运动(即多普勒效应)引起的。尽管在CFO估计和跟踪技术方面取得了进展,但估计错误仍然存在。剩余CFO产生时变相位误差,增加符号错误率,降低译码器的性能。这种影响在密集的星座图中尤其明显(例如,高阶QAM调制),通常用于现代无线系统,如5G NR、802.11ax和毫米波,以及物理安全技术,如调制混淆(MO)。本文首先推导了高斯噪声下残差CFO的概率分布函数。利用这种分布,我们计算了非封闭形式OFDM信号的最大似然解调边界。对于具有不等振幅参考星座点的调制方案(例如16-QAM及更高,APSK等),“最优”边界具有不规则形状,更重要的是,它们依赖于最后一次CFO校正实例(例如接收帧序文)的时间。为了逼近最佳边界并提供实用的(实时)解调方案,我们探索了机器学习技术,特别是支持向量机(SVM)。与其他最先进的机器学习方法相比,我们的SVM方法在测试阶段表现出更高的准确性和更低的复杂性。作为一个案例研究,我们应用我们的cfo感知解调来提高MO技术的性能。我们的分析结果表明,与传统解调方案相比,增益高达3dB,在完整的系统模拟中超过3dB。最后,我们在usrp上实现了我们的方案,并通过实验证实了我们基于分析和模拟的发现。
Carrier frequency offset (CFO) arises from the intrinsic mismatch between the oscillators of a wireless transmitter and the corresponding receiver, as well as their relative motion (i.e., Doppler effect). Despite advances in CFO estimation and tracking techniques, estimation errors are still present. Residual CFO creates a time-varying phase error, which degrades the decoder's performance by increasing the symbol error rate. The impact is particularly visible in dense constellation maps (e.g., high-order QAM modulation), often used in modern wireless systems such as 5G NR, 802.11ax, and mmWave, as well as in physical security techniques, such as modulation obfuscation (MO). In this paper, we first derive the probability distribution function for the residual CFO under Gaussian noise. Using this distribution, we compute the maximum-likelihood demodulation boundaries for OFDM signals in a non-closed form. For modulation schemes with unequal-amplitude reference constellation points (e.g., 16-QAM and higher, APSK, etc.), the “optimal” boundaries have irregular shapes, and more importantly, they depend on the time since the last CFO correction instance, e.g., reception of frame preamble. To approximate the optimal boundaries and provide a practical (real-time) demodulation scheme, we explore machine learning techniques, specifically, support vector machine (SVM). Our SVM approach exhibits better accuracy and lower complexity in the test phase than other state-of-the-art machine-learning approaches. As a case study, we apply our CFO-aware demodulation to enhance the performance of a MO technique. Our analytical results show a gain of up to 3dB over conventional demodulation schemes, which exceeds 3dB in complete system simulations. Finally, we implement our scheme on USRPs and experimentally corroborate our analytic and simulation-based findings.
QAM 星座的联合检测和 CFO 估计
DOI: --
发表时间: 2011
期刊: IEEE Vehicular Technology Conference
影响因子: --
作者:
P. Pedrosa;R. Dinis;F. Nunes
通讯作者: F. Nunes
通过加密编码调制减轻速率攻击
DOI: --
发表时间: 2015
期刊: ACM Interational Symposium on Mobile Ad Hoc Networking and Computing
影响因子: --
作者:
Triet Vo Huu;G. Noubir
通讯作者: G. Noubir
超越加密的保密性:混淆无线通信中的传输签名
DOI: --
发表时间: 2015
影响因子: 11.2
作者:
Hanif Rahbari;M. Krunz
通讯作者: M. Krunz
机器学习在载波频率偏移感知解调中的应用
DOI: --
发表时间: 2019
期刊:
影响因子: --
作者:
Peyman Siyari;Hanif Rahbari;M. Krunz
通讯作者: M. Krunz
DOI: 10.1109/tit.1982.1056454
发表时间: 1982-01-01
影响因子: 2.5
作者:
UNGERBOECK, G
通讯作者: UNGERBOECK, G