Efficient Task Orchestration Including Mixed Reality Applications in a Combined Cloud-Edge Infrastructure
Resumo
Mixed Reality (MR) is establishing itself as one of the most prominent immersive applications, enabled by advanced computing and communication infrastructures that must deliver high throughput, low latency, and high reliability simultaneously. To meet the stringent requirements of MR applications, while balancing competition with less demanding workloads and varying operational costs, cloud and edge computing resources must be efficiently orchestrated. Despite extensive research on task offloading, key aspects such as accurately modeling MR demand and incorporating adequate infrastructure cost remain underexplored. In this work, we formalize the resource allocation problem and introduce LOTOS (Local Optimal Task Orchestration Solution), a novel approach that efficiently orchestrates multiple workloads, including MR applications. Through simulations using EdgeCloudSim, a load generator based on real MR application traces, and the real-world cloud and edge platform costs, we demonstrate the effectiveness of LOTOS. Compared to a widely cited approach in the literature, LOTOS achieves over 15% more successfully completed tasks while reducing costs by up to 8 times.
Referências
Almutairi, J. and Aldossary, M. (2021). A novel approach for IoT tasks offloading in edge-cloud environments. Journal of Cloud Computing, 10(1), 28.
AWS (2025). AWS Calculator. [link], 2025-01-08.
Buyya, R. et al. (2009). Modeling and simulation of scalable Cloud computing environments and the CloudSim toolkit: Challenges and opportunities. In 2009 International Conference on High Performance Computing & Simulation, pp. 1–11.
Jamil, M. N. et al. (2023). Workload Orchestration in Multi-Access Edge Computing Using Belief Rule-Based Approach. IEEE Access, 11, 118002–118023.
Karp, R. M. (2010). Reducibility Among Combinatorial Problems. In Springer Berlin Heidelberg, pp. 219–241.
Nowak, T. W. et al. (2021). Verticals in 5G MEC-Use Cases and Security Challenges. IEEE Access, 9, 87251–87298.
Peixoto, M. J. P. and Azim, A. (2023). Design and Development of a Machine Learning-Based Task Orchestrator for Intelligent Systems on Edge Networks. IEEE Access, 11, 33049–33060.
Sonmez, C. et al. (2017). EdgeCloudSim: An environment for performance evaluation of Edge Computing systems. In 2017 Second International Conference on Fog and Mobile Edge Computing (FMEC), pp. 39–44.
Sonmez, C. et al. (2019). Fuzzy Workload Orchestration for Edge Computing. IEEE Transactions on Network and Service Management, 16(2), 769–782.
Sonmez, C. et al. (2021). Machine Learning-Based Workload Orchestrator for Vehicular Edge Computing. IEEE Transactions on Intelligent Transportation Systems, 22(4), 2239–2251.
Theodoropoulos, T. et al. (2023). Graph neural networks for representing multivariate resource usage: A multiplayer mobile gaming case-study. International Journal of Information Management Data Insights, 3(1), 100158.
Toczé, K. et al. (2019). Performance Study of Mixed Reality for Edge Computing. In Proceedings of the 12th IEEE/ACM International Conference on Utility and Cloud Computing (UCC’19), pp. 285–294. Association for Computing Machinery.
Toczé, K. et al. (2020). Characterization and modeling of an edge computing mixed reality workload. Journal of Cloud Computing, 9(1), 46.
Toczé, K. and Nadjm-Tehrani, S. (2019). ORCH: Distributed Orchestration Framework using Mobile Edge Devices. In 2019 IEEE 3rd International Conference on Fog and Edge Computing (ICFEC), pp. 1–10.
Wang, H. et al. (2023). A Survey on the Metaverse: The State-of-the-Art, Technologies, Applications, and Challenges. IEEE Internet of Things Journal, 10(16), 14671–14688.
Zheng, T. et al. (2022). Deep Reinforcement Learning-Based Workload Scheduling for Edge Computing. Journal of Cloud Computing, 11(1), 3.
