QoE-Driven Optimization in 5G O-RAN-Enabled HetNets for Enhanced Video Service Quality

Agarwal, Bharat; Togou, Mohammed Amine; Ruffini, Marco; Muntean, Gabriel‐Miro

doi:10.1109/mcom.003.2200229

Cited by 14 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the translational pathway from languages to topic-specific emotions (e.g., sentiment) to detecting anomalies in QoE is challenging. This challenge lies in two issues: (1) the social experience data remains sparsely distributed across space, and (2) anomalies in experience jump across sub-topic spaces (e.g., from data rate to signal strength).…”

Section: Discussionmentioning

confidence: 99%

“…We thank our other industrial and academic project partners WINGS-ICT and University of Iowa for their advice. [1], but yet there very few ways to gauge QoE by the telecommunication operator in current practice (there are no 5G standards) for implementing QoE [2]. Whilst the app-base service themselves gauge general consumer experience of the platform, second-by-second network experience is important to understand both consumer demand dynamics and how the network supplies service-specific capacity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Federated Learning of Wireless Network Experience Anomalies Using Consumer Sentiment

Guo

Jin

Sun

et al. 2023

2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

View full text Add to dashboard Cite

In wireless networks, consumer experience is important for both short monitoring of the Quality of Experience (QoE) as well as long term customer retainment. Current 4G and 5G networks are not equipped to measure QoE in an automated way, and experience is still reported through traditional customer care and drive-testing. In recent years, large-scale social media analytics has enabled researchers to gather statistically significant data on consumer experience and correlate them to major events such as social celebrations or significant network outages. However, the translational pathway from languages to topicspecific emotions (e.g., sentiment) to detecting anomalies in QoE is challenging. This challenge lies in two issues: (1) the social experience data remains sparsely distributed across space, and (2) anomalies in experience jump across sub-topic spaces (e.g., from data rate to signal strength).Here, we solved these two challenges by examining the spectral space of experience across topics using federated learning (FL) to identify anomalies. This can inform telecom operators to pay attention to potential network demand or supply issues in real time using relatively sparse and distributed data. We use real social media data curated for our telecommunication projects across London and the United Kingdom to demonstrate our results. FL was able to achieve 74-92% QoE anomaly detection accuracy, with the benefit of 30-45% reduce data transfer and preserving privacy better than raw data transfer.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Federated Learning of Wireless Network Experience Anomalies Using Consumer Sentiment

Guo

Jin

Sun

et al. 2023

2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

View full text Add to dashboard Cite

show abstract

“…These concepts refer to the decomposition of software into smaller pieces or microservices, resulting in an application or a function being structured as a collection of loosely coupled stateless and stateful backing services [17]. Adopting a Cloud-Native architecture in O-RAN components would unlock several benefits, including adaptability, efficiency and performance, in which multiple works have conducted their research for the exploitation of the O-RAN capabilities [18,19,20,21].…”

Section: Terrestrial Resourcesmentioning

confidence: 99%

A 5G NTN Emulation Platform for VNF Orchestration: Design, Development, and Evaluation

Muro,

Baena,

Cola

et al. 2024

Preprint

View full text Add to dashboard Cite

The integration of Non-Terrestrial Networks (NTN) with 5G represents a monumental leap in wireless network capabilities, significantly enhancing capacity, range, and reliability. This fusion fosters technological innovation and global connectivity. Crucial to this development is the softwarization of 5G networks through Virtual Network Functions (VNFs) within the OpenRAN paradigm, which disaggregates radio access networks into Central and Distributed Units (CU and DU). This approach accelerates deployment and facilitates upgrades. However, incorporating edge computing in Low Earth Orbit (LEO) satellites into this virtualized infrastructure presents management complexities, particularly in the interaction and resource sharing among VNFs, including satellite components. The absence of advanced emulators capable of accurately simulating these dynamics is a significant hurdle. To address this, this study introduces a groundbreaking emulation framework based on the Open Air Interface platform, tailored to reflect OpenRAN’s disaggregated network architecture. This framework precisely emulates the functional behavior of 5G-NTN systems and, with the integration of Kubernetes, enhances VNF lifecycle management, boosting efficiency in hybrid networks. The framework’s efficacy in VNF deployment and resource optimization is validated by extensive performance metrics, proving its vital role in emulating 5G-NTN systems. This innovation lays the groundwork for future research in efficient resource management within complex network ecosystems, offering a vital tool for exploring diverse VNF deployment scenarios and enabling networks to adapt dynamically to advanced wireless communication demands.

show abstract

“…It is the basis of relationships between operators and consumers. Wireless networks have moved from Quality-of-Service (QoS) indicators (e.g., outage probability, throughput) to Quality-of-Experience (QoE) indicators (e.g., enjoyment, video clarity, gaming smoothness) [1], [2]. As we move towards the increased use of Artificial Intelligence (AI) in network automation, ranging from automated network integration to base station deployment to context profiling.…”

Section: Introductionmentioning

confidence: 99%

Quality-of-Trust in 6G: Combining Emotional and Physical Trust through Explainable AI

Li,

Qi,

Jin

et al. 2023

2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall)

View full text Add to dashboard Cite

Wireless networks like many multi-user services have to balance limited resources in real-time. In 6G, increased network automation makes consumer trust crucial. Trust is reflect in both a personal emotional sentiment as well as a physical understanding of the transparency of AI decision making. Whilst there has been isolated studies of consumer sentiment to wireless services, this is not well linked to the decision making engineering. Likewise, limited recent research in explainable AI (XAI) has not established a link to consumer perception.Here, we develop a Quality-of-Trust (QoT) KPI that balances personal perception with the quality of decision explanation. That is to say, the QoT varies with both the time-varying sentiment of the consumer as well as the accuracy of XAI outcomes. We demonstrate this idea with an example in Neural Water-Filling (N-WF) power allocation, where the channel capacity is perceived by artificial consumers that communicate through Large Language Model (LLM) generated text feedback. Natural Language Processing (NLP) analysis of emotional feedback is combined with a physical understanding of N-WF decisions via meta-symbolic XAI. Combined they form the basis for QoT. Our results show that whilst the XAI interface can explain up to 98.9% of the neural network decisions, a small proportion of explanations can have large errors causing drops in QoT. These drops have immediate transient effects in the physical mistrust, but emotional perception of consumers are more persistent. As such, QoT tends to combine both instant physical mistrust and long-term emotional trends.

show abstract

QoE-Driven Optimization in 5G O-RAN-Enabled HetNets for Enhanced Video Service Quality

Cited by 14 publications

References 11 publications

Federated Learning of Wireless Network Experience Anomalies Using Consumer Sentiment

Federated Learning of Wireless Network Experience Anomalies Using Consumer Sentiment

A 5G NTN Emulation Platform for VNF Orchestration: Design, Development, and Evaluation

Quality-of-Trust in 6G: Combining Emotional and Physical Trust through Explainable AI

Contact Info

Product

Resources

About