基于Lagrange乘子法的神经网络盲多用户检测算法的研究
|
摘要
码分多址系统中，不同用户的随机接入，使得用户之间扩频码不完全正交，进而产生了多址干扰(Multi-access interference，MAI)和远近效应(Near-far effect，NFE)等问题，常规的匹配滤波器无法克服这些问题。多用户检测技术充分考虑造成多址干扰的用户结构和干扰信息，成为消除多址干扰和远近效应的关键技术。目前，大多数多用户检测算法存在算法复杂、收敛速度慢等缺点，使得长期以来没有真正的实现应用。近年来，基于神经网络的盲多用户检测结合了盲多用户检测对已知信息量需求少和神经网络运算速度快、并行处理能力强的优点，而成为研究的热点课题。
本文的主要工作如下：
1．在介绍多用户检测原理的基础上，对现有一些算法的性能、特点和不足进行了分析，并对今后的发展方向进行了研究。
2．针对现有算法收敛时间长、误码率高等不足，提出了两种盲多用户检测算法。第一种为多约束LNN盲多用户检测算法，通过增加约束项来使目标函数较快地收敛到最小点；第二种为改进型LNN盲多用户检测算法，通过将罚函数与Lagrange函数结合，构造出更适合
In the CDMA wireless communications system , multi-access interference and near-far effect exist because spread codes between users are not completely orthogonal along with different users random accessing, regular filter can not overcome these questions. Multiuser detection is a key technique erasing MAI and NFE due to think fully about user structure making MAI and interference information. Nowadays, a lot of multiuser detection algorithms hold flaws such as sophisticated algorithm, low speed of convergence and so on, thus, MUD isn't really realized using. Recently, blind multiuser detection based on neural network became a research focus, integrates merits needing a few using informations of blind MUD with merits of neural network such as quickly speed, stronge processing, and so on.
The major works of this paper are summarized as follow:
1. The principle of MUD is introduced in this paper, and the
本文的主要工作如下：
1．在介绍多用户检测原理的基础上，对现有一些算法的性能、特点和不足进行了分析，并对今后的发展方向进行了研究。
2．针对现有算法收敛时间长、误码率高等不足，提出了两种盲多用户检测算法。第一种为多约束LNN盲多用户检测算法，通过增加约束项来使目标函数较快地收敛到最小点；第二种为改进型LNN盲多用户检测算法，通过将罚函数与Lagrange函数结合，构造出更适合
In the CDMA wireless communications system , multi-access interference and near-far effect exist because spread codes between users are not completely orthogonal along with different users random accessing, regular filter can not overcome these questions. Multiuser detection is a key technique erasing MAI and NFE due to think fully about user structure making MAI and interference information. Nowadays, a lot of multiuser detection algorithms hold flaws such as sophisticated algorithm, low speed of convergence and so on, thus, MUD isn't really realized using. Recently, blind multiuser detection based on neural network became a research focus, integrates merits needing a few using informations of blind MUD with merits of neural network such as quickly speed, stronge processing, and so on.
The major works of this paper are summarized as follow:
1. The principle of MUD is introduced in this paper, and the
引文
[01] 袁超伟，陈德荣，冯志勇．CDMA蜂窝移动通信．北京：北京邮电大学出版社，2003．
[02] 曹达仲，候春萍．移动通信原理、系统技术．北京：清华大学出版社，2004．
[03] 纪越峰．现代通信技术．北京：北京邮电大学出版社，2004．
[04] Hamouda. A fast adaptive algorithm for MMSE receivers in DS～CDMA systems. IEEE S.P.Letters, 2004, 11 (4): 86～89
[05] K.S.Schneider. Optimum detection of code division multiplexed signals. IEEE Transactions on Aerospace and Electronic Systems, 1979, 15 (1): 664～670.
[06] R.Lupas, S.Verdu. Linear multistage detectors for synchronous code division multiple access channels. IEEE Trans.On Comm, 1991, 35: 123～136.
[07] U.Madhow, M.L.Hong. MMSE interference suppression for direct- sequence spread CDMA. IEEE Trans.On Comm, 1994, 42: 3178～3188.
[08] Ju Ho Lee, Hyung-Myung Kim. MMSE multiuser detector with an adaptive blind antenna array for DS/CDMA systems. Signal Processing, 1999, 79: 325～328.
[09] 陈超，宋文涛，罗汉文．采用迭代处理的多用户联合检测和译码方案．上海交通大学学报，2001，35(6)：826～890．
[10] Sylvie L.Perreau, Langford B.White. Nonlinear iterative multiuser detection and equalization for CDMA receivers in the presence of interchip interference. Digital Signal Processing, 2001 (11): 94～109.
[11] 王焱滨，胡志恒，虞厥邦．基于禁忌搜索的CDMA多用户检测算法研究．系统工程与电子技术，2003，25(1)：87～91．
[12] 王焱滨，李春光，虞厥邦．一种基于禁忌搜索的多用户检测方法．信号处理，2002，18(3)：212～216．
[13] 王艳，付永庆，孙晓岩．一种新的盲自适应多用户检测技术．通信技术，2003，??4: 63～65.
[14]. C.Yonina.Eldar, V.Alan.Oppenheim. Orthogonal multiuser detection. Signal Processing, 2002, 82: 321～325.
[15]. U.Madhow, M.Honing. MMSE interference suppression for direct-sequence spread-spectrum CDMA. IEEE Trans.Commun, 1994, 42:3178～3188.
[16] Ju Ho Lee, Hyung-Myung Kim. MMSE multi-user detector with an adaptive blind antenna array for DS/CDMA systems. Signal Processing, 1999, 79: 325～328.
[17]. Li-Mei Chen, Bor-Sen Chen, Wen-Shen Hou. Adaptive multiuser DFE with Kalman channel estimation for DSCDMA system in multipath fading channels channels. Signal Processing, 2001, 81: 713～733.
[18]. Enrico Del Re, Luca Simone Ronga. Blind adaptive MUD with silence listening. Signal Processing, 1997, 61: 91～100.
[19] R.kohno, H.Imai, M.Hatori. Cancellation Techniques of Co-Channel Interference in Asynchronous Spread Spectnun Multi-user Access System. Trans.IECE., 1983, 66: 416～423.
[20] 王正茂，叶梧等．衰落信道中的串并混合型多用户检测．华南理工大学学报，2003，31(12)：18～21．
[21] 刘向东，顾学迈．第三代移动通信系统中非线性多用户检测技术．华北航天工业学院学报，2004，14(1)：1～7．
[22] M.Honig, U.Mahow, Verdu. Blind adaptive multiuser detection. IEEE Trans.Inform.Theory, 1995, 41 (4): 944～960.
[23] 曾召华，刘贵忠等．一种等效的变步长盲多用户检测算法．西安电子科技大学学报，2003，30(5)：713～717．
[24] Z.Tian, K.L.Bell, H.L.Van Trees. Robust constrained linear receiver for CDMA wireless systems. IEEE Trans.Inform.Theory, 1998, 44 (2): 677～690.
[25] Brian G.Agee. The least-Squares CMA:A New Technique for Rapid Correction of Constant Modulus Signals. ICASSP, TOKYO, 1986: 953～956.[26] M.L.Honig. Orthogonally anchored interference suppression using the Sato cost criterion. Proceedings 1995 IEEE International Symposium on Information Theory, 1995, 9 (11): 314～317.
[27] 刘胜美，赵春明．基于最小二乘恒模算法及子空间方法的盲多用户检测算法．通信学报，2003，24(5)：129～133．
[28] 嵇建波，王卫东．多径信道中的线性约束差分恒模算法．桂林电子工业学院学报，2003，23(6)22～26．
[29] S.E.Bensley, B.Aazhang. Subspace-based channel estimation for code division multiple access communication systems. IEEE Trans on Communications, 1996, 44 (8): 1009～1020.
[30] X.D.Wang, H.V.Poor. Blind mulituser detection:a subspace approach. IEEE Trans.Inform.Theory, 1998, 44 (2): 677～690.
[31] 郑晖，叶梧．CDMA系统动态子空间跟踪算法．桂林电子工业学院学报，2000，20(2)：17～20．
[32] M.Honig, U.Mahow, Verdu. Blind adaptive multiuser detection. IEEE Trans IT, 1995, 41 (4): 944～960.
[33] 张贤达．通信信号处理．湖南：国防科技大学出版社，2000．
[34] 沈福民．自适应信号处理．西安：西安电子科技大学出版社，2002．
[35] 张立毅．数字通信系统中盲均衡技术的研究．北京：北京理工大学博士学位论文，2003．
[36] 张贤达．现代信号处理．北京：清华大学出版社，2003．
[37] 阎平凡，张长水．人工神经网络与模拟进化计算(第二版)．北京：清华大学出版社，2003．
[38] 张立明．人工神经网络的模型及应用．北京：复旦大学出版社，1993．
[39] B.Aazhang, B.P.Paris, G.Orsak. Neural networks for multi-user detection in CDMA communications. IEEE Trans.on Common, 1992, 40 (7): 1212～1222.
[40] Navin Singh, Fambiral Takawira. A neural network and extended Kalman filter??based adaptive multi-user receiver for CDMA systems. IEEE 1996, 414～418.
[41] Pei-Yuan Peng. An efficient multi-user detection algorithm for Direct Sequence Code Division Muliple Access by using neural network. IEEE International Conference on Communications, 2001, 1:36-40.
[42] U.Mitra, H.V.Poor. Neural network techniques for adaptive multi-user demodulation. IEEE Journal on Selected Areas in communications, 1994, 12 (9): 1460～1470.
[43] 余雪丽，孙承意等．神经网络与实例学习．北京：中国铁道出版社，1996．
[44] Romano Fantacci, Leonardo Mancini, Daniele Tarchi. Multiuser Interference Mitigation in Multipath Fading Channels using a Neural Network Based Blind Receiver. IEEE Trans.Circ.Syst., 2003, 50 (8): 488～482.
[45] Gabor Jeney, Janos Levendovszky, Lorant Kovacs. Blind Adaptive Stochastic Neural Network for Multiuser Detection. IEEE Trans Commun, 2001, 6 (1): 1868～1872.
[46] Shubao Liu, Jun Wang. Blind Adaptive Multiuser Detection Using a Recurrent Neural Network. IEEE Trans Commun, 2004, 7 (4): 1071～1705.
[47] Xiaodong Wang, H.V.Poor. Space-time multiuser detection in multipath CDMA channels. IEEE Trans. Signal processing, 1998, 47 (9): 2356～2374.
[48] 刘宇红，庞伟正．基于神经网络的多用户检测器．哈尔滨工业大学学报，2000，21(5)：64～67．
[49] Romano Fantacci, Leonardo Mancini, Daniele Tarchi. Multiuser Interference Mitigation in Multipath Fading Channels using a Neural Network Based Blind Receiver. IEEE Trans.Circ.Syst., 2003, 50 (8): 488～492.
[50] H.V.Poor, X.Wang. Code-aided interference suppression for DS/CDMA communications. IEEE Trans Comm., 1997, 45 (9): 1112～1122.
[51] S.Kapoor, S.Gollamudi. Adaptive multiuser detection and beamforming for interference suppression in CDMA mobile radio systems. IEEE Trans VEh??Technol, 1999, 48: 1341～1355.
[52] P.A.N.Bosman, D.Thierens. Continuous Iterated Density Estimation Evolutionary Algorithms within the IDEA Framework. In Wu, A.S., editor, Proceedings of the 2000 Genetic and Evolutionary Computation Conference Workshop Program, 2000: 197～200.
[53] 谢政，李建平，汤泽滢．非线性最优化．湖南：国防科技大学出版社，2003．
[54] 黄远灿，孙圣和，韩京清．基于Lagrange乘子法的非线性规划神经网络，电子学报，1998，26(1)：24～28．
[55] 陈艳丽，王华奎等．一种基于Lagrange神经网络的盲多用户检测器．太原理工大学学报，2004，35(5)：550～553．
[56] M.P.Kennedy, L.O.Chua. Neural networks for nonlinear program- ming. IEEE Transactions on Circuits and Systems, 1988, 35 (5): 554～562.
[02] 曹达仲，候春萍．移动通信原理、系统技术．北京：清华大学出版社，2004．
[03] 纪越峰．现代通信技术．北京：北京邮电大学出版社，2004．
[04] Hamouda. A fast adaptive algorithm for MMSE receivers in DS～CDMA systems. IEEE S.P.Letters, 2004, 11 (4): 86～89
[05] K.S.Schneider. Optimum detection of code division multiplexed signals. IEEE Transactions on Aerospace and Electronic Systems, 1979, 15 (1): 664～670.
[06] R.Lupas, S.Verdu. Linear multistage detectors for synchronous code division multiple access channels. IEEE Trans.On Comm, 1991, 35: 123～136.
[07] U.Madhow, M.L.Hong. MMSE interference suppression for direct- sequence spread CDMA. IEEE Trans.On Comm, 1994, 42: 3178～3188.
[08] Ju Ho Lee, Hyung-Myung Kim. MMSE multiuser detector with an adaptive blind antenna array for DS/CDMA systems. Signal Processing, 1999, 79: 325～328.
[09] 陈超，宋文涛，罗汉文．采用迭代处理的多用户联合检测和译码方案．上海交通大学学报，2001，35(6)：826～890．
[10] Sylvie L.Perreau, Langford B.White. Nonlinear iterative multiuser detection and equalization for CDMA receivers in the presence of interchip interference. Digital Signal Processing, 2001 (11): 94～109.
[11] 王焱滨，胡志恒，虞厥邦．基于禁忌搜索的CDMA多用户检测算法研究．系统工程与电子技术，2003，25(1)：87～91．
[12] 王焱滨，李春光，虞厥邦．一种基于禁忌搜索的多用户检测方法．信号处理，2002，18(3)：212～216．
[13] 王艳，付永庆，孙晓岩．一种新的盲自适应多用户检测技术．通信技术，2003，??4: 63～65.
[14]. C.Yonina.Eldar, V.Alan.Oppenheim. Orthogonal multiuser detection. Signal Processing, 2002, 82: 321～325.
[15]. U.Madhow, M.Honing. MMSE interference suppression for direct-sequence spread-spectrum CDMA. IEEE Trans.Commun, 1994, 42:3178～3188.
[16] Ju Ho Lee, Hyung-Myung Kim. MMSE multi-user detector with an adaptive blind antenna array for DS/CDMA systems. Signal Processing, 1999, 79: 325～328.
[17]. Li-Mei Chen, Bor-Sen Chen, Wen-Shen Hou. Adaptive multiuser DFE with Kalman channel estimation for DSCDMA system in multipath fading channels channels. Signal Processing, 2001, 81: 713～733.
[18]. Enrico Del Re, Luca Simone Ronga. Blind adaptive MUD with silence listening. Signal Processing, 1997, 61: 91～100.
[19] R.kohno, H.Imai, M.Hatori. Cancellation Techniques of Co-Channel Interference in Asynchronous Spread Spectnun Multi-user Access System. Trans.IECE., 1983, 66: 416～423.
[20] 王正茂，叶梧等．衰落信道中的串并混合型多用户检测．华南理工大学学报，2003，31(12)：18～21．
[21] 刘向东，顾学迈．第三代移动通信系统中非线性多用户检测技术．华北航天工业学院学报，2004，14(1)：1～7．
[22] M.Honig, U.Mahow, Verdu. Blind adaptive multiuser detection. IEEE Trans.Inform.Theory, 1995, 41 (4): 944～960.
[23] 曾召华，刘贵忠等．一种等效的变步长盲多用户检测算法．西安电子科技大学学报，2003，30(5)：713～717．
[24] Z.Tian, K.L.Bell, H.L.Van Trees. Robust constrained linear receiver for CDMA wireless systems. IEEE Trans.Inform.Theory, 1998, 44 (2): 677～690.
[25] Brian G.Agee. The least-Squares CMA:A New Technique for Rapid Correction of Constant Modulus Signals. ICASSP, TOKYO, 1986: 953～956.[26] M.L.Honig. Orthogonally anchored interference suppression using the Sato cost criterion. Proceedings 1995 IEEE International Symposium on Information Theory, 1995, 9 (11): 314～317.
[27] 刘胜美，赵春明．基于最小二乘恒模算法及子空间方法的盲多用户检测算法．通信学报，2003，24(5)：129～133．
[28] 嵇建波，王卫东．多径信道中的线性约束差分恒模算法．桂林电子工业学院学报，2003，23(6)22～26．
[29] S.E.Bensley, B.Aazhang. Subspace-based channel estimation for code division multiple access communication systems. IEEE Trans on Communications, 1996, 44 (8): 1009～1020.
[30] X.D.Wang, H.V.Poor. Blind mulituser detection:a subspace approach. IEEE Trans.Inform.Theory, 1998, 44 (2): 677～690.
[31] 郑晖，叶梧．CDMA系统动态子空间跟踪算法．桂林电子工业学院学报，2000，20(2)：17～20．
[32] M.Honig, U.Mahow, Verdu. Blind adaptive multiuser detection. IEEE Trans IT, 1995, 41 (4): 944～960.
[33] 张贤达．通信信号处理．湖南：国防科技大学出版社，2000．
[34] 沈福民．自适应信号处理．西安：西安电子科技大学出版社，2002．
[35] 张立毅．数字通信系统中盲均衡技术的研究．北京：北京理工大学博士学位论文，2003．
[36] 张贤达．现代信号处理．北京：清华大学出版社，2003．
[37] 阎平凡，张长水．人工神经网络与模拟进化计算(第二版)．北京：清华大学出版社，2003．
[38] 张立明．人工神经网络的模型及应用．北京：复旦大学出版社，1993．
[39] B.Aazhang, B.P.Paris, G.Orsak. Neural networks for multi-user detection in CDMA communications. IEEE Trans.on Common, 1992, 40 (7): 1212～1222.
[40] Navin Singh, Fambiral Takawira. A neural network and extended Kalman filter??based adaptive multi-user receiver for CDMA systems. IEEE 1996, 414～418.
[41] Pei-Yuan Peng. An efficient multi-user detection algorithm for Direct Sequence Code Division Muliple Access by using neural network. IEEE International Conference on Communications, 2001, 1:36-40.
[42] U.Mitra, H.V.Poor. Neural network techniques for adaptive multi-user demodulation. IEEE Journal on Selected Areas in communications, 1994, 12 (9): 1460～1470.
[43] 余雪丽，孙承意等．神经网络与实例学习．北京：中国铁道出版社，1996．
[44] Romano Fantacci, Leonardo Mancini, Daniele Tarchi. Multiuser Interference Mitigation in Multipath Fading Channels using a Neural Network Based Blind Receiver. IEEE Trans.Circ.Syst., 2003, 50 (8): 488～482.
[45] Gabor Jeney, Janos Levendovszky, Lorant Kovacs. Blind Adaptive Stochastic Neural Network for Multiuser Detection. IEEE Trans Commun, 2001, 6 (1): 1868～1872.
[46] Shubao Liu, Jun Wang. Blind Adaptive Multiuser Detection Using a Recurrent Neural Network. IEEE Trans Commun, 2004, 7 (4): 1071～1705.
[47] Xiaodong Wang, H.V.Poor. Space-time multiuser detection in multipath CDMA channels. IEEE Trans. Signal processing, 1998, 47 (9): 2356～2374.
[48] 刘宇红，庞伟正．基于神经网络的多用户检测器．哈尔滨工业大学学报，2000，21(5)：64～67．
[49] Romano Fantacci, Leonardo Mancini, Daniele Tarchi. Multiuser Interference Mitigation in Multipath Fading Channels using a Neural Network Based Blind Receiver. IEEE Trans.Circ.Syst., 2003, 50 (8): 488～492.
[50] H.V.Poor, X.Wang. Code-aided interference suppression for DS/CDMA communications. IEEE Trans Comm., 1997, 45 (9): 1112～1122.
[51] S.Kapoor, S.Gollamudi. Adaptive multiuser detection and beamforming for interference suppression in CDMA mobile radio systems. IEEE Trans VEh??Technol, 1999, 48: 1341～1355.
[52] P.A.N.Bosman, D.Thierens. Continuous Iterated Density Estimation Evolutionary Algorithms within the IDEA Framework. In Wu, A.S., editor, Proceedings of the 2000 Genetic and Evolutionary Computation Conference Workshop Program, 2000: 197～200.
[53] 谢政，李建平，汤泽滢．非线性最优化．湖南：国防科技大学出版社，2003．
[54] 黄远灿，孙圣和，韩京清．基于Lagrange乘子法的非线性规划神经网络，电子学报，1998，26(1)：24～28．
[55] 陈艳丽，王华奎等．一种基于Lagrange神经网络的盲多用户检测器．太原理工大学学报，2004，35(5)：550～553．
[56] M.P.Kennedy, L.O.Chua. Neural networks for nonlinear program- ming. IEEE Transactions on Circuits and Systems, 1988, 35 (5): 554～562.