A new rls adaptive filtering algorithm has been developed by enforcing a constraint on the a posteriori error of the conventional exponentially-weighted rlsalgorithm and modifying its coefficient update equation. The...
详细信息
A new rls adaptive filtering algorithm has been developed by enforcing a constraint on the a posteriori error of the conventional exponentially-weighted rlsalgorithm and modifying its coefficient update equation. The motivation behind the new algorithm is to attain improved tracking capability when the target system features fast variations in time. The proposed algorithm requires only slightly more computations than the conventional rlsalgorithm and is specifically suitable for estimation and tracking of fast-fading MIMO channels. Simulations demonstrate that a MIMO channel estimator utilising the proposed algorithm outperforms those using the conventional rlsalgorithm, the set-membership-based BEACON algorithm and the extended rlsalgorithm without requiring prior knowledge of the Doppler shift.
暂无评论