Agendamento de Contêineres Ciente da QoE
Abstract
The cloud provider shares its computing resources among different clients, co-locating the applications on the same server. However, this can cause application degradation. In addition, cloud providers use Quality of Service (QoS) metrics as a way to measure the quality of service delivered to their customers. These metrics are pre-established and specified in the Service Level Objective (SLO). However, the SLO based on QoS is insufficient to guarantee the users of the applications a good Quality of Experience (QoE). The dissertation addresses this problem by proposing a QoE-aware container scheduler in a cloud environment where applications suffer interference caused by co-location. We propose a new approach that uses machine learning methods to estimate the QoE that the cloud can offer, considering cloud attributes. Experiments have shown that QoE-aware scheduling can improve users’ QoE as well as reduce resource usage.
References
Carvalho, M. and Macedo, D. F. (2021). Qoe-aware container scheduler for co-located cloud environments. In 2021 IFIP/IEEE International Symposium on Integrated Network Management (IM), pages 286–294.
De Cicco, L., Mascolo, S., and Palmisano, V. (2019). QoE-driven resource allocation for massive video distribution. Ad Hoc Networks, 89:170–176.
Haouari, F., Baccour, E., Erbad, A., Mohamed, A., and Guizani, M. (2019). Qoe-aware resource allocation for crowdsourced live streaming: A machine learning approach. In ICC 2019-2019 IEEE International Conference on Communications (ICC), pages 1–6. IEEE.
ITU Telecommunication Standardization Sector (2017). ITU-T Rec P.1203: Parametric bitstream-based quality assessment of progressive download and adaptive audiovisual streaming services over reliable transport.
Juluri, P., Tamarapalli, V., and Medhi, D. (2015). Measurement of quality of experience of video-on-demand services: A survey. IEEE Communications Surveys & Tutorials, 18(1):401–418.
Lai, Y.-J., Liu, T.-Y., and Hwang, C.-L. (1994). Topsis for modm. European journal of operational research, 76(3):486–500.
Liu, B., Li, P., Lin, W., Shu, N., Li, Y., and Chang, V. (2018). A new container scheduling algorithm based on multi-objective optimization. Soft Computing, 22(23):7741–7752.
Mao, Y., Oak, J., Pompili, A., Beer, D., Han, T., and Hu, P. (2017). Draps: Dynamic and resource-aware placement scheme for docker containers in a heterogeneous cluster. In 2017 IEEE 36th International Performance Computing and Communications Conference (IPCCC), pages 1–8. IEEE.
Masdari, M. and Khoshnevis, A. (2020). A survey and classification of the workload forecasting methods in cloud computing. Cluster Computing, 23(4):2399–2424.
Menouer, T. (2021). Kcss: Kubernetes container scheduling strategy. The Journal of Supercomputing, 77(5):4267–4293.
Municio, E., Cevik, M., Ruth, P., and Marquez-Barja, J. M. (2021). Experimenting in a global multi-domain testbed. In IEEE INFOCOM 2021-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), pages 1–2. IEEE.
