An Objective MOS Prediction Approach Based on the Nb Interface Parameters

Abstract

In mobile networks, there exists a relationship between the quality of service (QoS) and the quality of experience (QoE). This is often determined by the mean opinion score (MOS). There are several approaches that are used to determine the MOS in mobile networks and these may be subjective and objective. While the subjective approaches are standardized in their own essence, they are expensive and laborious to perform. Often, objective approaches have been used to determining the MOS by using network parameters such as delay, jitter and packet loss that are normally derived from network interfaces. The main aim of this study is to reduce the cost of the capital expenditure (CAPEX) and the operational expenditure (OPEX) linked to the drive testing method of obtaining the MOS. Thus, in this paper, a cost-effective objective MOS evaluation method based on the core network parameters from the Nb interface of a 2G and 3G mobile network are used. The training and verification of the proposed model was evaluated using machine learning techniques with regression analysis. The experimental results of the proposed model were compared with the subjective MOS evaluation from the drive test. Generally, the results showed that there was a high correlation between the predicted MOS and the values collected through the drive test, which is a subjective MOS evaluation approach.