Abstract— Due to the advances of network technologies and multimedia communications, Quality of Service (QoS) becomes an increasingly important issue in network communications. Many traditional assessment techniques were designed to evaluate the QoS of multimedia applications transmitted over these networks. In this paper, a new QoS evaluation system has been developed. The proposed system is based on using the nonlinear autoregressive with exogenous input model (NARX). This model is preferred because it could reflect the dynamic characteristics of the QoS and network performance. In addition to the QoS parameters, previous QoS values were used as inputs to the developed NARX model. The output is the estimated QoS based on the given inputs. The proposed model was optimized, validated and evaluated based on specified criteria. Simulation results showed that the adopted model presented high accurate QoS prediction capabilities, where the forecasted QoS was very close to the actual QoS values in most of the time period. QoS, in a way, reflects performance resources availability of a network using the devised approach. The estimated QoS can be used to optimize and manage the utilization of network available resources and provide solutions for QoS provision, routing, monitoring, …etc.