An Intelligent Perception Model and Parameters Adjust Method for Quality of Experience
Abstract
:1. Introduction
2. Materials and Methods
2.1. QoE Perception Model
2.1.1. Introduction of QoE
2.1.2. Calculation Process for QoE
- (1)
- Establish the mapping relationship between KPIs and business-related KQIs, KEIs, and QoE.
- (2)
- Collect KPI measurement value.
- (3)
- Calculate the actual measurement values of the KQIs through KPIs. The KPIs and KQIs include multi-dimensional metrics which are shown in Figure 1. For different applications, the KQI metrics could be distinct.
- (4)
- Based on calculated KQIs, the gap between the network business and the customer expectation is defined as ER.
- (5)
- Furthermore, the actual customer perception of the each KQI based on the ER is calculated and named as EE.
- (6)
- Five customer key experience indicators are given in Figure 1, including line network business availability, stability, opening timeliness, assurance timeliness and service comfort. For each indicator, select the worst EE as the measurement of the customer experience because quite a lot of KQIs reflect the same experience indicator.
- (7)
- Then, the overall QoE based on the five indicators is evaluated to perceive the customer experience quality.
- (8)
- Finally, transmit QoE to other systems through the interface to drive business optimization.
2.1.3. Building Method of QoE Perception Model
2.2. Intelligent Adjustment Method for QoE Parameters
- (1)
- Receive customer complaints and collect customer data and network data.
- (2)
- Determine whether the QoE corresponding to the complaints need to be adjusted where the judgement rules are defined based on application types and the XGBoost is exploited to classify the application types of complaints from customers.
- (3)
- Determine the KQIs and customer behavior characteristics associated with the complaints, and optimized model to adjust the QoE parameters is defined.
- (4)
- Then, determine whether the recalculation results match the complaint. If they match, continue the process; otherwise re-adjust.
- (5)
- Finally, establish a mapping relationship between the adjusted QoE parameters and the analyzed customer behavior characteristics.
- (6)
- According to the mapping relationship, when the conditions of customer behavior characteristics are met, the adjusted QoE parameters are configured.
3. Results
3.1. Experiment Data
3.2. Evaluation Result for QoE Model Based on Customers Satisfaction Questionnaires
3.3. Evaluation Result for Adjusted QoE Model Based on Business Complaints
4. Discussion
5. Conclusions
6. Patents
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Le Callet, P.; Möller, S.; Andrew, P. Qualinet White Paper on Definitions of Quality of Experience. European Net-work on Quality of Experience in Multimedia Systems and Services (COST Action IC 1003). Available online: https://hal.archives-ouvertes.fr/hal-00977812 (accessed on 12 March 2012).
- Agiwal, M.; Roy, A.; Saxena, N. Next Generation 5G Wireless Networks: A Comprehensive Survey. IEEE Commun. Surv. Tutor. 2016, 18, 1617–1655. [Google Scholar] [CrossRef]
- Tsolkas, D.; Liotou, E.; Passas, N.; Merakos, L. A survey on parametric QoE estimation for popular services. J. Netw. Comput. Appl. 2017, 77, 1–17. [Google Scholar] [CrossRef]
- Chen, K.-T.; Tu, C.-C.; Xiao, W.-C. OneClick: A Framework for Measuring Network Quality of Experience. In Proceedings of the OneClick: A Framework for Measuring Network Quality of Experience, Rio de Janeiro, Brazil, 19–25 April 2009; pp. 702–710. [Google Scholar] [CrossRef] [Green Version]
- Wang, J.; Cheng, W. Heterogeneous quality of experience guarantees over wireless networks. China Commun. 2018, 15, 51–59. [Google Scholar] [CrossRef]
- Shaikh, J.; Fiedler, M.; Collange, D. Quality of experience from customer and network perspectives. Ann. Telecommun. 2010, 65, 47–57. [Google Scholar] [CrossRef]
- Ameigeiras, P.; Ramos-Munoz, J.J.; Navarro-Ortiz, J.; Mogensen, P.; Lopez-Soler, J.M. QoE oriented cross-layer design of a resource allocation algorithm in beyond 3G systems. Comput. Commun. 2010, 33, 571–582. [Google Scholar] [CrossRef]
- Alreshoodi, M.; Woods, J. Survey on QoE/QoS correlation models for multimedia services. Int. J. Distrib. Parallel Syst. 2013, 4, 20. [Google Scholar]
- Bouraqia, K.; Sabir, E.; Sadik, M.; Ladid, L. Quality of Experience for Streaming Services: Measurements, Challenges and Insights. IEEE Access 2020, 8, 13341–13361. [Google Scholar] [CrossRef]
- Anwar, M.S.; Wang, J.; Khan, W.; Ullah, A.; Ahmad, S.; Fei, Z. Subjective QoE of 360-Degree Virtual Reality Videos and Machine Learning Predictions. IEEE Access 2020, 8, 148084–148099. [Google Scholar] [CrossRef]
- Anchuen, P.; Uthansakul, P.; Uthansakul, M. QoE Analysis for Improving Multimedia Services Based on Different Operating Situations on Cellular Networks. IEEE Access 2021, 9, 116215–116230. [Google Scholar] [CrossRef]
- Boz, E.; Finley, B.; Oulasvirta, A.; Kilkki, K.; Manner, J. Mobile QoE prediction in the field. Pervasive Mob. Comput. 2019, 59, 101039. [Google Scholar] [CrossRef]
- Li, J.; Feng, R.; Liu, Z.; Sun, W.; Li, Q. Modeling QoE of Virtual Reality Video Transmission over Wireless Networks. In Proceedings of the 2018 IEEE Global Communications Conference (GLOBECOM), Abu Dhabi, United Arab Emirates, 9–13 December 2018; pp. 1–7. [Google Scholar] [CrossRef]
- De Fez, I.; Belda, R.; Guerri, J.C. New objective QoE models for evaluating ABR algorithms in DASH. Comput. Commun. 2020, 158, 126–140. [Google Scholar] [CrossRef]
- Yue, T.; Wang, H.; Cheng, S.; Shao, J. Deep learning based QoE evaluation for internet video. Neurocomputing 2020, 386, 179–190. [Google Scholar] [CrossRef]
- Huang, R.; Wei, X.; Gao, Y.; Lv, C.; Mao, J.; Bao, Q. Data-driven QoE prediction for IPTV service. Comput. Commun. 2018, 118, 195–204. [Google Scholar] [CrossRef]
- Bermudez, H.F.; Martinez-Caro, J.M.; Sanchez-Iborra, R.; Arciniegas, J.L.; Cano, M.D. Live video-streaming evaluation using the ITU-T P.1203 QoE model in LTE networks. Comput. Netw. 2019, 165, 106967. [Google Scholar] [CrossRef]
- Moura, H.D.; Macedo, D.F.; Vieira, M.A. Wireless control using reinforcement learning for practical web QoE. Comput. Commun. 2020, 154, 331–346. [Google Scholar] [CrossRef]
- Liu, Y. Analysis on Bilibili Video Categorical Segmentation Using XGBoost. In Proceedings of the 2021 2nd International Conference on E-Commerce and Internet Technology (ECIT), Hangzhou, China, 5–7 March 2021; pp. 259–263. [Google Scholar] [CrossRef]
- Yanqin, W.; Le, Z.; Li, L.; Jun, Z.; Hongbo, Z.; Zhenqiang, C.; Liwei, Z. A QoE Acquisition Method, Device and Customer Experience Management System. CN107609722A, 19 January 2018. [Google Scholar]
Interval | Level |
---|---|
(0, 30) | poor |
(30%, 60) | fair |
(60%, 80) | good |
(80%, 100) | excellent |
Application Type | Number of Business Complaints | Variance of QoE |
---|---|---|
office automation | 35 | 15.6 |
online transaction | 1 | 4.3 |
videoconferencing | 8 | 11.6 |
live broadcast | 57 | 23.7 |
overall | 100 | 27.6 |
Parameters | Value before Adjustment | Value after Adjustment |
---|---|---|
1 | 1 | |
0.8 | 0.7 | |
0.2 | 0.2 | |
240 min | 200 min | |
1 | 1 | |
90 min | 80 min | |
100% | 100% |
Application Type | Number of Complaints | Variance of QoE after Adjustment |
---|---|---|
office automation | 35 | 7.3 |
online transaction | 1 | 2.1 |
Videoconferencing | 8 | 5.6 |
live broadcast | 57 | 9.1 |
Overall | 100 | 9.8 |
Application Type | Variance of QoE before Adjustment | Variance of QoE after Adjustment | Comparison Result before and after Adjustment |
---|---|---|---|
office automation | 15.6 | 7.3 | 53.2% lower |
online transaction | 4.3 | 2.1 | 51.2% lower |
videoconferencing | 11.6 | 5.6 | 51.7% lower |
live broadcast | 23.7 | 9.1 | 61.6% lower |
overall | 27.6 | 9.8 | 64.5% lower |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wu, Y.; Zhang, L.; Lv, T.; Guo, R.; Xing, L.; Wang, Y. An Intelligent Perception Model and Parameters Adjust Method for Quality of Experience. Electronics 2022, 11, 1732. https://doi.org/10.3390/electronics11111732
Wu Y, Zhang L, Lv T, Guo R, Xing L, Wang Y. An Intelligent Perception Model and Parameters Adjust Method for Quality of Experience. Electronics. 2022; 11(11):1732. https://doi.org/10.3390/electronics11111732
Chicago/Turabian StyleWu, Yanqin, Le Zhang, Tiantian Lv, Rongrong Guo, Liang Xing, and Yanchuan Wang. 2022. "An Intelligent Perception Model and Parameters Adjust Method for Quality of Experience" Electronics 11, no. 11: 1732. https://doi.org/10.3390/electronics11111732