Self-Distributing Systems in the Wild: An Experimental Study on a Real-world Edge-Cloud Continuum Platform

• Matheus Ávila Naspolini UFSC
• Alison R. Panisson UFSC https://orcid.org/0000-0002-9438-5508
• Jim Lau UFSC https://orcid.org/0000-0002-3497-5522
• Martín Vigil UFSC https://orcid.org/0000-0001-8379-4309
• Luiz F. Bittencourt UNICAMP https://orcid.org/0000-0001-6305-9059
• Roberto Rodrigues-Filho UnB https://orcid.org/0000-0002-3323-0246

DOI: https://doi.org/10.5753/sbrc.2026.19398

Resumo

Contemporary distributed applications must often simultaneously satisfy low-latency requirements and high computational demand in order to deliver high Quality of Experience to end users. The edge–cloud continuum has emerged as a promising infrastructure paradigm to address these requirements by combining proximity to users at the edge with the abundant computing resources of the cloud. However, despite this infrastructural potential, service-level mechanisms capable of jointly exploiting network and computing resources remain limited, as these dimensions are often managed independently. To address this gap, the concept of self-distributing systems (SDS) has been proposed, enabling applications originally designed for local execution to autonomously spread themselves across distributed infrastructures at runtime. By dynamically relocating and replicating components, SDS facilitate the simultaneous exploitation of low-latency edge resources and high-performance cloud resources. Nevertheless, the practical integration of SDS with modern deployment and orchestration environments is still unexplored. This paper presents SDS_SWARM, an architecture that integrates the SDS paradigm with Docker and Docker Swarm for real-world edge and cloud infrastructures. We evaluate the architecture using a CPU-intensive service to assess its adaptive capabilities. Experimental results demonstrate improved adaptability across heterogeneous environments, validating the feasibility and benefits of combining self-distributing systems with modern edge–cloud technologies.

Referências

Barcelona-Pons, D., Sánchez-Artigas, M., París, G., Sutra, P., and García-López, P. (2019). On the faas track: Building stateful distributed applications with serverless architectures. In Proceedings of the 20th International Middleware Conference, Middleware ’19, page 41–54, New York, NY, USA. Association for Computing Machinery.

Bittencourt, L., Immich, R., Sakellariou, R., Fonseca, N., Madeira, E., Curado, M., Villas, L., DaSilva, L., Lee, C., and Rana, O. (2018). The internet of things, fog and cloud continuum: Integration and challenges. Internet of Things, 3–4:134–155.

Bittencourt, L. F., Rodrigues-Filho, R., Spillner, J., De Turck, F., Santos, J., da Fonseca, N. L. S., Rana, O., Parashar, M., and Foster, I. (2025). The computing continuum: Past, present, and future. Computer Science Review, 58:100782.

Calavaro, C., Cardellini, V., Presti, F. L., and Russo, G. R. (2025). Beyond cloud: Serverless functions in the compute continuum. SN Computer Science, 6(3):194.

Cicconetti, C., Conti, M., and Passarella, A. (2021). On realizing stateful faas in serverless edge networks: State propagation. In 2021 IEEE International Conference on Smart Computing (SMARTCOMP), pages 89–96.

Costa, B. P., da Silva, H. H., Morales, A. S., Bittencourt, L. F., Panisson, A. R., and Rodrigues-Filho, R. (2025). A multi-agent approach to self-distributing systems. In Barolli, L., editor, Advanced Information Networking and Applications, pages 128–139, Cham. Springer Nature Switzerland.

Fu, K., Zhang, W., Chen, Q., Zeng, D., and Guo, M. (2022). Adaptive resource efficient microservice deployment in cloud-edge continuum. IEEE Transactions on Parallel and Distributed Systems, 33(8):1825–1840.

Gama, E. S., Rodrigues-Filho, R., Madeira, E. R. M., Immich, R., and Bittencourt, L. F. (2024). Enabling adaptive video streaming via content steering on the edge-cloud continuum. In 2024 IEEE 8th International Conference on Fog and Edge Computing (ICFEC), pages 35–42.

Gao, G. and Wen, Y. (2021). Video transcoding for adaptive bitrate streaming over edge-cloud continuum. Digital Communications and Networks, 7(4):598–604.

Pfandzelter, T. and Bermbach, D. (2023). Enoki: Stateful distributed faas from edge to cloud. In Proceedings of the 2nd International Workshop on Middleware for the Edge, pages 19–24.

Rappa, F. M., Rodrigues-Filho, R., Panisson, A. R., Marcolino, L. S., and Bittencourt, L. F. (2024). Multi-armed bandits for self-distributing stateful services across networking infrastructures. In NOMS 2024-2024 IEEE Network Operations and Management Symposium, pages 1–6.

Rodrigues-Filho, R., Dias, R. S., Seródio, J., Porter, B., Costa, F. M., Borin, E., and Bittencourt, L. F. (2023). A self-distributing system framework for the computing continuum. In 2023 32nd International Conference on Computer Communications and Networks (ICCCN), pages 1–10.

Rodrigues-Filho, R. and Porter, B. (2022). Hatch: Self-distributing systems for data centers. Future Generation Computer Systems, 132:80–92.

Sreekanti, V., Wu, C., Lin, X. C., Schleier-Smith, J., Gonzalez, J. E., Hellerstein, J. M., and Tumanov, A. (2020). Cloudburst: stateful functions-as-a-service. Proc. VLDB Endow., 13(12):2438–2452.