Abstract:

The current static QoS model can not reflect the QoS time varying and location correlation of mobile application service.An QoS model was presented based on scene for mobile applications service.The QoS index system of mobile application service was defined and the QoS value matrix was constructed.Further,three types of assessment problems were proposed,which were QoS overall assessment,QoS assessment of specific region or specific time periods,and QoS assessment of hot region and busy time.By using genetic algorithm and data clustering algorithm,the location and time of the two scene conditions were quantified,which combine the region division of service request location density and the time division of service request frequency.According to the limiting conditions,QoS value matrix was reconstructed,and the service evaluation method was introduced based on the statistical analysis of the matrix.Finally,the normalized evaluation process and application framework of QoS were given.

Key words: mobile application, service quality, time varying, location correlation