INTELLIGENT ALGORITHMS FOR IMPROVING THE QUALITY OF USER EXPERIENCE IN ADAPTIVE VIDEO STREAMING SYSTEMS
Abstract
The paper addresses the problem of improving Quality of Experience (QoE) in adaptive video streaming systems applied within situational centers (SCs) integrated with robotic systems technology parks (RSTPs). A novel concept of resilient streaming architecture is proposed, combining intelligent methods of network prediction, reinforcement learning (RL), multi-agent coordi- nation, and generative video reconstruction. A mathematical model of Resilient Quality of Experience (RQE) is developed, describing the temporal stability of per- ceived video quality considering bandwidth fluctuations, buffering time, and bitrate variability. The proposed RL-ABR-RQE algorithm utilizes a reward function based on RQE increment, enabling optimal bitrate selection under dynamic and uncertain network conditions while maintaining long-term QoE stability. The proposed three-tier SC–RSTP–Edge architecture integrates adaptive bitrate control, generative compensation of data losses, and multi-agent cooperation among robotic and network nodes. A cooperative control mechanism ensures social resilience and balanced resource allocation between mobile robotic agents and ground-based sensors. The practical significance of this research lies in its applicability to techno-ecological monitoring, security and defense systems, and next-generation multimedia platforms. Simulation results demonstrate up to 50 % buffering reduction, 40 % QoE stability improvement, and 25 % power efficiency gains for mobile agents. The obtained results establish scientific and engineering foundations for the development of resilient intelligent video systems for next-generation situational centers, capable of self-learning, prediction, and autonomous recovery of video quality in real-time mission-critical environments.
References
2. Souane N., Bourenane M., Douga Y. Deep-Reinforcement-Learning-Based Approach for Video Streaming: Dynamic Adaptive Video Streaming over HTTP. Applied Sciences. 2023. Vol. 13, No. 21. DOI: 10.3390/app132111697.
3. Li Y., Zheng Q., Zhang Z., et al. Improving ABR Performance for Short Video Streaming Using Multi- Agent Reinforcement Learning with Expert Guidance. Proceedings of the 2023 ACM Conference on Multimedia Systems. 2023. DOI: 10.48550/arXiv.2304.04637.
4. Wang Y., Aggarwal V., Lan T. Learning-Based Online QoE Optimization in Multi-Agent Video Streaming. Algorithms. 2022. Vol. 15, No. 7. DOI: 10.3390/a15070227.
5. Artioli E. Generative AI for HTTP Adaptive Streaming. Proceedings of the 15th ACM Multimedia Systems Conference (MMSys ’24). New York: Association for Computing Machinery, 2024. P. 516–519. DOI: 10.1145/3625468.3652912.
6. Melkumian K., Pisarenko J., Koval A. Organization of Regional Situational Centers of the Intelligent System “Control_TEA” using UAVs. Proceedings of the 2021 IEEE 6th International Conference on Actual Problems of Unmanned Aerial Vehicles Development (APUAVD-2021). P. 37–40. DOI: 10.1109/APUAVD53804.2021.9615416.
This work is licensed under a Creative Commons Attribution 4.0 International License.
ISSN 
