{"title":"基于全局代表点选择和随机 SVD 算法的新型稀疏行为模型设计方法","authors":"","doi":"10.1016/j.aeue.2024.155432","DOIUrl":null,"url":null,"abstract":"<div><p>Digital pre-distortion (DPD) technology is currently the dominant technology employed to compensate for the nonlinearity of power amplifiers (PAs). Recently, PA modeling methods based on machine learning have attracted much attention. However, the traditional model still suffers from the defects of long modeling time or insufficiently high modeling accuracy. To solve this problem, the global representative point selection (GRPS) algorithm and the randomized SVD (RSVD) algorithm based on the least squares twin support vector regression (LSTSVR) model are introduced. The GRPS algorithm is first used to select a specific number of globally representative points from all the data to construct the support vector set. Then the RSVD algorithm is used to perform a low-rank approximation to the target kernel matrix. The modeling performance of the proposed approach is compared with the existing model using different communication signals, and the results show that the proposed model can improve the modeling accuracy and reduce the modeling time. Further, a pre-distortion experimental platform is established, and the proposed model is used to pre-distort the Class F PA and the Doherty PA respectively, which proves that the proposed model has a good nonlinear correction effect.</p></div>","PeriodicalId":50844,"journal":{"name":"Aeu-International Journal of Electronics and Communications","volume":null,"pages":null},"PeriodicalIF":3.0000,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A novel sparse behavioral model design method based on the global representative point selection and the randomized SVD algorithm\",\"authors\":\"\",\"doi\":\"10.1016/j.aeue.2024.155432\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Digital pre-distortion (DPD) technology is currently the dominant technology employed to compensate for the nonlinearity of power amplifiers (PAs). Recently, PA modeling methods based on machine learning have attracted much attention. However, the traditional model still suffers from the defects of long modeling time or insufficiently high modeling accuracy. To solve this problem, the global representative point selection (GRPS) algorithm and the randomized SVD (RSVD) algorithm based on the least squares twin support vector regression (LSTSVR) model are introduced. The GRPS algorithm is first used to select a specific number of globally representative points from all the data to construct the support vector set. Then the RSVD algorithm is used to perform a low-rank approximation to the target kernel matrix. The modeling performance of the proposed approach is compared with the existing model using different communication signals, and the results show that the proposed model can improve the modeling accuracy and reduce the modeling time. Further, a pre-distortion experimental platform is established, and the proposed model is used to pre-distort the Class F PA and the Doherty PA respectively, which proves that the proposed model has a good nonlinear correction effect.</p></div>\",\"PeriodicalId\":50844,\"journal\":{\"name\":\"Aeu-International Journal of Electronics and Communications\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.0000,\"publicationDate\":\"2024-07-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Aeu-International Journal of Electronics and Communications\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1434841124003182\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Aeu-International Journal of Electronics and Communications","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1434841124003182","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
摘要
数字预失真(DPD)技术是目前用于补偿功率放大器(PA)非线性的主流技术。最近,基于机器学习的功率放大器建模方法备受关注。然而,传统模型仍然存在建模时间长或建模精度不够高等缺陷。为解决这一问题,本文引入了基于最小二乘孪生支持向量回归(LSTSVR)模型的全局代表点选择(GRPS)算法和随机 SVD(RSVD)算法。首先使用 GRPS 算法从所有数据中选择特定数量的全局代表性点来构建支持向量集。然后使用 RSVD 算法对目标核矩阵进行低秩逼近。利用不同的通信信号,将所提方法的建模性能与现有模型进行了比较,结果表明所提模型可以提高建模精度并缩短建模时间。此外,还建立了预失真实验平台,并利用所提出的模型分别对 F 类功率放大器和 Doherty 功率放大器进行了预失真实验,证明所提出的模型具有良好的非线性修正效果。
A novel sparse behavioral model design method based on the global representative point selection and the randomized SVD algorithm
Digital pre-distortion (DPD) technology is currently the dominant technology employed to compensate for the nonlinearity of power amplifiers (PAs). Recently, PA modeling methods based on machine learning have attracted much attention. However, the traditional model still suffers from the defects of long modeling time or insufficiently high modeling accuracy. To solve this problem, the global representative point selection (GRPS) algorithm and the randomized SVD (RSVD) algorithm based on the least squares twin support vector regression (LSTSVR) model are introduced. The GRPS algorithm is first used to select a specific number of globally representative points from all the data to construct the support vector set. Then the RSVD algorithm is used to perform a low-rank approximation to the target kernel matrix. The modeling performance of the proposed approach is compared with the existing model using different communication signals, and the results show that the proposed model can improve the modeling accuracy and reduce the modeling time. Further, a pre-distortion experimental platform is established, and the proposed model is used to pre-distort the Class F PA and the Doherty PA respectively, which proves that the proposed model has a good nonlinear correction effect.
期刊介绍:
AEÜ is an international scientific journal which publishes both original works and invited tutorials. The journal''s scope covers all aspects of theory and design of circuits, systems and devices for electronics, signal processing, and communication, including:
signal and system theory, digital signal processing
network theory and circuit design
information theory, communication theory and techniques, modulation, source and channel coding
switching theory and techniques, communication protocols
optical communications
microwave theory and techniques, radar, sonar
antennas, wave propagation
AEÜ publishes full papers and letters with very short turn around time but a high standard review process. Review cycles are typically finished within twelve weeks by application of modern electronic communication facilities.