Steady-state Performance of Incremental LMS Strategies For Parameter Estimation Over Fading Wireless Channels
Provides theoretical performance bounds for distributed estimation under realistic channel conditions, relevant to wireless sensor networks.
The paper analyzes the impact of fading wireless channels on the incremental LMS algorithm for distributed parameter estimation, deriving steady-state performance metrics and convergence conditions, with simulations confirming theoretical predictions.
We study the effect of fading in the communication channels between nodes on the performance of the incremental least mean square (ILMS) algorithm. We derive steady-state performance metrics, including the mean-square deviation (MSD), excess mean-square error (EMSE), and mean-square error (MSE). We obtain the sufficient conditions to ensure mean-square convergence, and verify our results through simulations. Simulation results show that our theoretical analysis closely matches the actual steady state performance.