Mean opinion score estimation for mobile broadband networks using Bayesian Networks
Mobile broadband (MBB) networks are expanding rapidly to deliver higher data speeds. The fifth-generation cellular network promises enhanced-MBB with high-speed data rates, low power connectivity, and ultra-low latency video streaming. However, existing cellular networks are unable to perform well d...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tech Science Press
2022
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/103263/1/AzizulAzizan2022_MeanOpinionScoreEstimationforMobile.pdf http://eprints.utm.my/103263/ http://dx.doi.org/10.32604/cmc.2022.024642 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Mobile broadband (MBB) networks are expanding rapidly to deliver higher data speeds. The fifth-generation cellular network promises enhanced-MBB with high-speed data rates, low power connectivity, and ultra-low latency video streaming. However, existing cellular networks are unable to perform well due to high latency and low bandwidth, which degrades the performance of various applications. As a result, monitoring and evaluation of the performance of these network-supported services is critical. Mobile network providers optimize and monitor their network performance to ensure the highest quality of service to their end-users. This paper proposes a Bayesian model to estimate the minimum opinion score (MOS) of video streaming services for any particular cellular network. The MOS is the most commonly used metric to assess the quality of experience. The proposed Bayesian model consists of several input data, namely, round-trip time, stalling load, and bite rates. It was examined and evaluated using several test data sizes with various performance metrics. Simulation results show the proposed Bayesian network achieved higher accuracy overall test data sizes than a neural network. The proposed Bayesian network obtained a remarkable overall accuracy of 90.36% and outperformed the neural network. |
|---|