Resolution of seamless switching within a set of available wireless access solutions applied in ITS (Intelligent Transport System) applications is presented. The CALM based system or specifically designed and configured L3/L2 switching can be an adequate solution for the multi-path access communication system. These systems have to meet requirements of the seamless secure communications functionality within even an extensive cluster of moving objects. Competent decision processes based on precisely quantified system requirements and each performance indicator tolerance range must be implemented to keep service up and running with no influence of continuously changing conditions in time and served space.
The method of different paths service quality evaluation and selection of the best possible active communications access path is introduced. This method is studied within project STATVU (System Requirements and Architecture of the Universal Telematic Vehicle Unit is grant 2A-1TP1/138 of the Ministry of Industry and Trade of the Czech Republic.). The proposed approach is based on Kalman filtering which separates reasonable part of noise and also allows prediction of the individual parameters near future behavior. The presented classification algorithm applied on filtered measured data combined with deterministic parameters is trained using historical data, i. e. combination of parameters vectors line and relevant decisions. Quality of classification is dependent on the size and quality of the training data sets.