Zero Attracting Recursive Least Squares Algorithms

Hong, Xia; Gao, Junbin; Chen, Sheng

doi:10.1109/tvt.2016.2533664

Cited by 28 publications

(23 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To possibly improve channel estimation performance with fast convergence speed, we find that developing sparse RLS algorithm is a promising solution. 21 By introducing sparse constraint function, eg, zero-attracting 10 and approximate ℓ 0 -norm (L0), 22 we propose 2 sparse RLS channel estimation algorithms: RLS using zero-attracting sparse constraint (RLS-ZA) and RLS using approximate ℓ 0 -norm sparse constraint (RLS-L0). First, the proposed sparse RLStype algorithms can achieve faster convergence speed than the LMS-type algorithms.…”

Section: Discussionmentioning

confidence: 99%

Recursive least square–based fast sparse multipath channel estimation

Gui

2017

Int J Communication

View full text Add to dashboard Cite

In the next-generation wireless communication systems, the broadband signal transmission over wireless channel often incurs the frequency-selective channel fading behavior and also results in the channel sparse structure, which is supported only by few large coefficients. For the stable wireless propagation to be ensured, linear adaptive channel estimation algorithms, eg, recursive least square and least mean square, have been developed. However, these traditional algorithms are unable to exploit the channel sparsity. Actually, channel estimation performance can be further improved by taking advantage of the sparsity. In this paper, 2 recursive least squarebased fast adaptive sparse channel estimation algorithm is proposed by introducing sparse constraints, L1-norm and L0-norm, respectively. To improve the flexibility of the proposed algorithms, this paper introduces a regularization parameter selection method to adaptively exploit the channel sparsity. Finally, Monte Carlo-based computer simulations are conducted to validate the effectiveness of the proposed algorithms.KEYWORDS adaptive filtering algorithm, recursive least square, sparse channel estimation, sparse constraintBroadband wireless transmission has been considered one of indispensable technologies for the next-generation wireless communications. 1-3 However, wireless signal transmission over the frequency-selective fading channel, accurate channel estimation is necessary to reconstruct finite impulse response (FIR). Currently, adaptive filtering algorithms can be acted as effective channel estimation because of their fast convergence and robust performance. Hence, various adaptive filtering algorithms have been developed during the last few years. On the basis of second-order statistical error criterion, least mean square (LMS) 4,5 and recursive least square (RLS) 5 have been developed.On the basis of fourth-order statistical error criterion, least mean fourth (LMF) 6,7 and (LMS/F) 8,9 have been developed as well. However, these kinds of linear channel estimation algorithms have not been considered to exploit channel sparsity in wireless channels. The channel estimation performance can be improved if we take the advantage of the prior sparsity information.For channel sparsity to be exploited, various sparse LMStype algorithms 10-12 have been proposed. Also, sparse LMF algorithms 7,13-16 and sparse LMS/F algorithms 14,17,18 have been developed in recent years. All of the mentioned sparse channel estimation algorithms based on error criterion function, hence, corresponding sparse channel estimation algorithms can keep the same convergence speed. It is well known that RLS algorithm can achieve faster convergence speed than LMS algorithm, 19 and it does not bring the eigenvalue spread problem. 5 The LMS algorithm aims to reduce the mean square error while the RLS algorithm finds the coefficients recursively to minimize a weighted linear least squares cost function relating to the input training signals. 5 In addition, in the derivation of the LMS and RLS,...

show abstract

Section: Discussionmentioning

confidence: 99%

Recursive least square–based fast sparse multipath channel estimation

Gui

2017

Int J Communication

View full text Add to dashboard Cite

show abstract

“…23,24 Thus, the proposed model is a new formulation by using the convex combination of EKFs, which not only enhances the tracking capability but also improves the error convergence property of the algorithm. 11,15,18 As stated in Equation (25), the state update equation to estimate the state variables is based on Kalman gain and estimation error. The cost function is normally MSE, which is quadratic in nature and thus minimization of cost function will lead to the optimal solution.…”

Section: Proposed Convex Combination Based Sparse Adaptive Estimationmentioning

confidence: 99%

“…Looking at the limitations of adaptive filters, current research works are oriented towards the development of adaptive estimation model with the inclusion of norm penalty in the cost function so that underlying sparseness will lead to faster convergence speed with reduced steady state mean square error (MSE). [11][12][13][14][15] Wu and Tong 14 proposed p-norm penalty in the cost function of the LMS-type algorithm to achieve better error performance than 0 and 1 norm. Hong et al 15 proposed ZA-RLS by adding the 1 norm of parameter vector penalty to RLS cost function for sparse channel estimation.…”

Section: Introductionmentioning

confidence: 99%

“…[11][12][13][14][15] Wu and Tong 14 proposed p-norm penalty in the cost function of the LMS-type algorithm to achieve better error performance than 0 and 1 norm. Hong et al 15 proposed ZA-RLS by adding the 1 norm of parameter vector penalty to RLS cost function for sparse channel estimation. However, these works have not focused much on the exploitation of sparseness in Kalman filters, which can be effective for tracking time-varying PQ disturbances.…”

Section: Introductionmentioning

confidence: 99%

“…The convex combination of EKF is designed by formulating a new cost function, which includes 1 norm to penalize the nonsparse solution of conventional EKF. 15 Benefits of convex combinations are two folds. One is the reduction of computational complexity and second is the guaranteed error convergence in a defined region of error surface.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Tracking of power quality disturbances using sparse model–based extended Kalman filters

Sahoo

Subudhi

Mishra

2018

Adaptive Control & Signal

View full text Add to dashboard Cite

Accurate estimation and tracking of power quality (PQ) disturbances requires efficient adaptive model-based techniques, which should have elegant structures to be applicable in practical systems. Though extended Kalman filter (EKF) has been used as a popular estimator to track the time-varying PQ events, the performance is limited due to higher-order nonlinearity exists in system dynamics.Moreover, the computational complexity and sensitivity to the measurement noise affect the estimation accuracy and error convergence properties. If the underlying sparse behavior of adaptive filters can be exploited through norm penalty, then significant improvement can be achieved in terms of convergence speed, stability, and steady state excess mean square error performance. In this paper, a modification to EKF is proposed by using sparse model to estimate PQ disturbances with better estimation accuracy and faster convergence speed.A thorough comparison is presented in terms of simulation results by using a family of existing algorithms like least mean square, recursive least square, and EKF. Adaptive estimation model incorporates real and complex state space representations to represent discrete time PQ disturbances. The convergence of the proposed sparse model-based filter is also mathematically proved considering the mean square error performance.

show abstract

Fully scheduled decomposition channel estimation based MIMO‐POMA structured LTE

Kumar

Ramana

2019

Int J Communication

View full text Add to dashboard Cite

Recent challenging channel estimation for antenna beam shape MIMO without performance loss is to be improved. In this paper, a fully scheduled decomposition-based channel estimation scheme is proposed by using the concept of MIMO with position-orthogonal multiple access (POMA) system. Furthermore, to improve power allocation, an iterative power decomposition is proposed by giving solution to power optimization problem. The proposed work channel estimation achieves better comparisons.

show abstract

Zero Attracting Recursive Least Squares Algorithms

Cited by 28 publications

References 24 publications

Recursive least square–based fast sparse multipath channel estimation

Recursive least square–based fast sparse multipath channel estimation

Tracking of power quality disturbances using sparse model–based extended Kalman filters

Fully scheduled decomposition channel estimation based MIMO‐POMA structured LTE

Contact Info

Product

Resources

About