Application of an Intelligent Hybrid Optimization Technique for Parameter Estimation in the Presence of Colored Noise

Abstract

Parameter estimation is an important concept in engineering where a mathematical model of a system is identified with the help of input and output signals. The Classical Least Squares (LS) algorithm gives an unbiased estimate of the parameters when the system noise is white. This property is lost when the system noise is colored — which is generally the case. In order to overcome the bias problem associated with the colored noise environment, one can use a whitening filter. The cost function in the case of a colored noise environment becomes multimodal when the signal to noise ratio is high and hence some intelligent optimization technique is required to find the global minimum. A new hybrid algorithm combining intelligent optimization techniques is proposed. This algorithm includes Enhanced Continuous Tabu Search (ECTS) and an elitism based Genetic Algorithm (GA) which is applied to the parameter estimation problem. ECTS is a modified version of Tabu Search (TS) applied to continuous functions and has an advantage of covering large search spaces. GA is an evolutionary algorithm that has a better convergence towards the optimum solution. The hybrid algorithm combines the respective strengths of ECTS and GA. Simulation results show that the parameters estimated using the proposed algorithm is unbiased in the presence of colored noise.