Subject and Keywords:
The paper presents a new approach to Hybrid Kalman filtering, composed of Extended Kalman Filter and Unscented Kalman Filter. In known algorithms, the Unscented Kalman Filter algorithm is used as first and the result of this is given as an input to the Extended Kalman Filter. The authors checked modified Hybrid Kalman Filter with changed order of filters using theoretical object, which was created on the basis of power system. Besides traditional method, the modification of Hybrid Kalman Particle Filter was evaluated too. Results were compared with Extended Kalman Filter, Unscented Kalman Filter and Bootstrap Particle Filter. For particle filters the authors compared method estimation qualities for a different number of particles. The estimation quality was evaluated by three quality indices. Based on the obtained results, one can see that the changed order of methods in Hybrid Kalman filter can improve estimation quality.