Attention-Aware Resource Allocation and QoE Analysis for Metaverse xURLLC Services

Du, Hongyang; Liu, Jiazhen; Niyato, Dusit; Kang, Jiawen; Xiong, Zehui; Zhang, Junshan; Kim, Dong In

doi:10.1109/jsac.2023.3280978

Cited by 48 publications

(5 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This makes us unable to calculate x 0 by directly using (11). Instead, we apply (11) into (10) to estimate the mean…”

Section: The Reverse Process Of Probability Inferencementioning

confidence: 99%

See 1 more Smart Citation

Diffusion-Based Reinforcement Learning for Edge-Enabled AI-Generated Content Services

Du,

Li,

Niyato

et al. 2024

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

As Metaverse emerges as the next-generation Internet paradigm, the ability to efficiently generate content is paramount. AI-Generated Content (AIGC) emerges as a key solution, yet the resourceintensive nature of large Generative AI (GAI) models presents challenges. To address this issue, we introduce an AIGC-as-a-Service (AaaS) architecture, which deploys AIGC models in wireless edge networks to ensure broad AIGC services accessibility for Metaverse users. Nonetheless, an important aspect of providing personalized user experiences requires carefully selecting AIGC Service Providers (ASPs) capable of effectively executing user tasks, which is complicated by environmental uncertainty and variability. Addressing this gap in current research, we introduce the AI-Generated Optimal Decision (AGOD) algorithm, a diffusion model-based approach for generating the optimal ASP selection decisions. Integrating AGOD with Deep Reinforcement Learning (DRL), we develop the Deep Diffusion Soft Actor-Critic (D2SAC) algorithm, enhancing the efficiency and effectiveness of ASP selection. Our comprehensive experiments demonstrate that D2SAC outperforms seven leading DRL algorithms. Furthermore, the proposed AGOD algorithm has the potential for extension to various optimization problems in wireless networks, positioning it as a promising approach for future research on AIGC-driven services. The implementation of our proposed method is available at: https://github.com/Lizonghang/AGOD.

show abstract

“…This makes us unable to calculate x 0 by directly using (11). Instead, we apply (11) into (10) to estimate the mean…”

Section: The Reverse Process Of Probability Inferencementioning

confidence: 99%

“…Another major obstacle stems from the diversity of users [10]. The Metaverse is expected to accommodate many user types, including those with varying cultural backgrounds, languages, and preferences.…”

Section: Introductionmentioning

confidence: 99%

Diffusion-Based Reinforcement Learning for Edge-Enabled AI-Generated Content Services

Du,

Li,

Niyato

et al. 2024

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

show abstract

“…In addition, edge computing can be used to bring computing resources closer to the end users, which leads to a better QoE [ 78 , 79 ]. Implementing radio access technologies, such as THz communication, could also support more demanding applications and provide a better QoE for users, such as higher data rates or lower latency [ 80 , 81 ]. Personalizing QoE would be very useful to be implemented in specific cases, such as VR, AR, self-driving cars, Industrial IoT, and smart cities.…”

Section: 6g Visions and Requirementsmentioning

confidence: 99%

Emerging Technologies for 6G Communication Networks: Machine Learning Approaches

Puspitasari,

An,

Alsharif

et al. 2023

Sensors

View full text Add to dashboard Cite

The fifth generation achieved tremendous success, which brings high hopes for the next generation, as evidenced by the sixth generation (6G) key performance indicators, which include ultra-reliable low latency communication (URLLC), extremely high data rate, high energy and spectral efficiency, ultra-dense connectivity, integrated sensing and communication, and secure communication. Emerging technologies such as intelligent reflecting surface (IRS), unmanned aerial vehicles (UAVs), non-orthogonal multiple access (NOMA), and others have the ability to provide communications for massive users, high overhead, and computational complexity. This will address concerns over the outrageous 6G requirements. However, optimizing system functionality with these new technologies was found to be hard for conventional mathematical solutions. Therefore, using the ML algorithm and its derivatives could be the right solution. The present study aims to offer a thorough and organized overview of the various machine learning (ML), deep learning (DL), and reinforcement learning (RL) algorithms concerning the emerging 6G technologies. This study is motivated by the fact that there is a lack of research on the significance of these algorithms in this specific context. This study examines the potential of ML algorithms and their derivatives in optimizing emerging technologies to align with the visions and requirements of the 6G network. It is crucial in ushering in a new era of communication marked by substantial advancements and requires grand improvement. This study highlights potential challenges for wireless communications in 6G networks and suggests insights into possible ML algorithms and their derivatives as possible solutions. Finally, the survey concludes that integrating Ml algorithms and emerging technologies will play a vital role in developing 6G networks.

show abstract

“…Furthermore, the existing studies have primarily focused on only a few metaverse platforms for quality evaluation, such as VR services (e.g., [12], [13]) or mobile metaverse services (e.g., [4], [14]), despite the importance of comprehending the complete range of metaverse services to facilitate evaluation of the latter. Identifying the service features based on actual customer experiences is crucial for evaluating the quality of metaverse service experiences, as the success of future metaverse services relies on the management of these experiences [15].…”

Section: Introductionmentioning

confidence: 99%

Identification of Key Service Features for Evaluating the Quality of Metaverse Services: A Text Mining Approach

Kim,

Yoo

2024

IEEE Access

View full text Add to dashboard Cite

Recent advances in the metaverse have revolutionized the way services are experienced, creating a virtual world that seamlessly blends real-life and digital experiences. While research on metaverse services has traditionally focused on technological advancements, recent efforts emphasize the need for a customer-oriented approach to evaluating service quality. However, few studies have explored this customeroriented approach. To address this gap, this paper identifies and prioritizes nine service features that significantly influence customer satisfaction in metaverse services from a customer-oriented perspective. In particular, this study analyzed 437,527 online customer reviews of Roblox, Bitmoji, and VRchat by employing text mining and machine learning algorithms, such as topic modeling, sentiment analysis, and logistic regression. As a result, the 'co-experience' feature emerges as a crucial factor, closely aligned with user objectives when engaging with metaverse services. These findings provide valuable insights for service managers to enhance their offerings effectively, positioning them favorably in the evolving metaverse landscape.

show abstract

Attention-Aware Resource Allocation and QoE Analysis for Metaverse xURLLC Services

Cited by 48 publications

References 54 publications

Diffusion-Based Reinforcement Learning for Edge-Enabled AI-Generated Content Services

Diffusion-Based Reinforcement Learning for Edge-Enabled AI-Generated Content Services

Emerging Technologies for 6G Communication Networks: Machine Learning Approaches

Identification of Key Service Features for Evaluating the Quality of Metaverse Services: A Text Mining Approach

Contact Info

Product

Resources

About