Empirical QoE/QoS correlation model based on multiple parameters for VoD flows

The Quality of Experience (QoE) determines the user satisfaction degree of communication services. Quantifying the relationship between User QoE and Network Quality of Service (QoS) enables the services providers to estimate the contribution of network performance in overall user satisfaction. Based on the Multiple Linear Regression (MLR) and the exponential hypothesis, we propose in this paper a global correlation model between QoE and QoS. The main contribution of our proposal is the use of a combination of more than one QoS parameter in the model. The proposed method is validated for Video on Demand services where the QoE considers the quality of video and the QoS is impacted with two parameters (delay and loss ratio). According to the experimental results, we obtained a composite correlation model with a good correlation coefficient.