QoS to QoE Mapping Based on Optimised BP Neural Networks
Ruicheng Wu, Shufeng Li, Xiaohan Zhang, Wenting Gao · 2023
With the commercialization of 5G technology, network video operators are paying more attention to the end-user experience due to higher network speeds and larger network coverage areas. In this paper, a user-centric Quality of Service (QoS) to Quality of Experience (QoE) mapping model is proposed based on BP neural networks (BPNN), incorporating network parameters and Mean Opinion Score (MOS). A combination of algorithms for network optimization is applied, and improvements are made to the optimization algorithm based on the internal characteristics of the QoS/QoE mapping. The WRprop algorithm is proposed as a suitable solution to the problem. Experimental results indicate that the combination of WRprop and PSO has better performance.