Background and Motivation
User applications are evolving rapidly. Emerging technologies such as the Internet of Things (IoT), Virtual Reality (VR), Extended Reality (XR), Vehicle-to-Vehicle (V2V) communication, and the growing integration of Artificial Intelligence (AI) into everyday services are reshaping the demands placed on network infrastructure. At the same time, the underlying systems that support these applications — including cellular networks, cloud environments, and virtualized computing platforms — are becoming increasingly sophisticated. Both academia and industry are moving toward closed-loop automation and self-optimizing resource management as a way to efficiently support these complex, heterogeneous workloads. These developments introduce new challenges in defining and managing the Quality of Experience (QoE) perceived by end users across diverse application domains. A central question is how QoE requirements originating from applications can be effectively communicated to the underlying infrastructure and translated into actionable orchestration decisions. Applications may express their needs in terms of domain-specific metrics (e.g., frame rate, motion-to-photon latency, inference time), but mapping these high-level requirements to concrete infrastructure configurations and tunable system parameters remains a difficult and largely unsolved problem for network orchestrators.
This thesis aims to investigate how application-level requirements and infrastructure-level management can be better aligned. The goal is to bridge the gap between the two domains and enable effective closed-loop automation, where application feedback drives real-time infrastructure adaptation. The project is situated at the intersection of QoE modeling, network function orchestration, and edge-cloud resource management, and will be carried out in the context of cellular network environments.
Expected Outcomes
The student will work to:
- Conduct an extensive literature review covering application-driven QoE modeling, intent-based networking, and infrastructure resource orchestration, identifying gaps in current approaches;
- Analyze how different application types (e.g., XR, V2V, IoT, AI-based services) express their performance requirements and how these can be formalized into machine-readable intent or policy specifications;
- Design an interface or abstraction layer that translates application-level QoE requirements into infrastructure-level parameters (e.g., compute placement, bandwidth allocation, scheduling priorities);
- Propose and implement a closed-loop orchestration mechanism that uses application feedback to dynamically adjust infrastructure configurations;
- Evaluate the proposed solution through simulation, emulation, or prototyping in a cellular network or edge-cloud testbed (e.g., using Oakestra or similar orchestration platforms), measuring improvements in QoE satisfaction and resource efficiency.
Requirements
- Familiarity with networking fundamentals, particularly in cellular and edge-cloud architectures. Knowledge of 5G/6G concepts is a plus;
- Understanding of Linux environments. Knowledge of containerization (e.g., Docker, Kubernetes) is a plus;
- Background or strong interest in machine learning, optimization, or control systems;
- Interest in Quality of Experience modeling, intent-based networking, or resource orchestration;
- Willingness to work with real-world or realistic testbed environments and to engage with ongoing research projects at SPEAR Lab.
Related Work
Schwarzmann, S., Cassales Marquezan, C., Trivisonno, R., et al. 2019. Estimating Video Streaming QoE in the 5G Architecture Using Machine Learning. In Proceedings of the 4th Internet-QoE Workshop on QoE-based Analysis and Management of Data Communication Networks (Internet-QoE '19). ACM. DOI: 10.1145/3349611.3355546
Bartolomeo, G., Mohan, N., et al. 2023. Oakestra: A Lightweight Hierarchical Orchestration Framework for Edge Computing. In Proceedings of the 2023 USENIX Annual Technical Conference (USENIX ATC '23). USENIX Association. https://www.usenix.org/conference/atc23/presentation/bartolomeo
Seufert, M., Egger, S., Slanina, M., Zinner, T., Hoßfeld, T., and Tran-Gia, P. 2015. A Survey on Quality of Experience of HTTP Adaptive Streaming. IEEE Communications Surveys & Tutorials, 17(1), 469–492. DOI: 10.1109/COMST.2014.2360940
Pham, Q.-V., Fang, F., Ha, V. N., et al. 2020. A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art. IEEE Access, vol. 8, 116974–117017. DOI: 10.1109/ACCESS.2020.3001277
