Abstract
In point cloud video streaming systems, the field of view (FoV) prediction is critical for selecting the tiles, the objective of which is to optimize the expected long-term quality-of-experience (QoE) from the perspective of a user. On one hand, a satisfactory QoE accounts for not only the playback quality but also the playback smoothness. On the other hand, the large data volume of a selected tile requires the transmission to be adaptive to the system uncertainties. This paper applies a Markov decision process to formulate the problem of tile selection across the infinite discrete time horizon. In particular, a system state includes the FoV information, which is predicted from the Transformer. To alleviate the dependence on system uncertainty statistics, a deep reinforcement learning approach is derived for solving the optimal control policy. Under different settings, we conduct experiments based on the real throughput and head-mounted display data. The results show that compared to the existing baselines, our proposed prediction-control approach achieves a higher FoV prediction accuracy, better playback quality as well as smoothness, and hence a better average QoE for the user.
Original language | English |
---|---|
Title of host publication | 2022 IEEE Global Communications Conference, GLOBECOM 2022 |
Publisher | IEEE Institute of Electrical and Electronic Engineers |
Pages | 1899-1904 |
ISBN (Electronic) | 978-1-6654-3540-6 |
ISBN (Print) | 978-1-6654-3541-3 |
DOIs | |
Publication status | Published - 2023 |
MoE publication type | A4 Article in a conference publication |
Event | IEEE Global Communications Conference, GLOBECOM 2022: Accelerating the Digital Transformation through Smart Communications - Hybrid: In-Person and Virtual Conference, Rio de Janeiro, Brazil Duration: 4 Dec 2022 → 8 Dec 2022 |
Conference
Conference | IEEE Global Communications Conference, GLOBECOM 2022 |
---|---|
Country/Territory | Brazil |
City | Rio de Janeiro |
Period | 4/12/22 → 8/12/22 |
Funding
ACKNOWLEDGEMENT This work was supported in part by the Collaborative Innovation Major Project of Zhengzhou (20XTZX06013), in part by the National Natural Science Foundation of China (61972092), in part by the National Key Research and Development Program of China (2021YFB2900200), in part by the Key Research and Development Program of Zhejiang Province (2021C01197), and in part by the Zhejiang Lab Open Program under Grant 2021LC0AB06.
Keywords
- deep reinforcement learning
- FoV prediction
- Markov decision process
- Point cloud video
- quality of experience
- Transformer