Exportar Publicação

Noetzold, D., Leithardt, V., de Paz Santana, J. & Barbosa, J. (2025). A self-adaptive architecture for predictive and reinforcement-based optimization in smart environments. 2025 International Symposium on Networks, Computers and Communications, ISNCC 2025. IEEE. https://doi.org/10.1109/ISNCC66965.2025.11250434

D. Noetzold et al.,  "A self-adaptive architecture for predictive and reinforcement-based optimization in smart environments", in 2025 Int. Symp. on Networks, Computers and Communications, ISNCC 2025, Paris, France, IEEE, 2025

@inproceedings{noetzold2025_1791383374470,
	author = "Noetzold, D. and Leithardt, V. and de Paz Santana, J. and Barbosa, J.",
	title = "A self-adaptive architecture for predictive and reinforcement-based optimization in smart environments",
	booktitle = "2025 International Symposium on Networks, Computers and Communications, ISNCC 2025",
	year = "2025",
	editor = "",
	volume = "",
	number = "",
	series = "",
	doi = "10.1109/ISNCC66965.2025.11250434",
	publisher = "IEEE",
	address = "Paris, France",
	organization = "",
	url = "https://ieeexplore.ieee.org/document/11250434"
}

TY  - CPAPER
TI  - A self-adaptive architecture for predictive and reinforcement-based optimization in smart environments
T2  - 2025 International Symposium on Networks, Computers and Communications, ISNCC 2025
AU  - Noetzold, D.
AU  - Leithardt, V.
AU  - de Paz Santana, J.
AU  - Barbosa, J.
PY  - 2025
SN  - 2472-4386
DO  - 10.1109/ISNCC66965.2025.11250434
CY  - Paris, France
UR  - https://ieeexplore.ieee.org/document/11250434
AB  - Smart environments frequently experience fluctuations in demand, infrastructure usage, and service-level expectations, requiring adaptive systems capable of dynamic selfoptimization. This work proposes a self-adaptive framework that integrates real-time monitoring, anomaly prediction, and reinforcement learning (RL) to proactively reconfigure systems before degradation occurs. Unlike previous approaches limited to specific layers or metrics, the proposed solution supports diverse performance indicators-ranging from hardware and software to network and SLA levels-and offers an extended repertoire of adaptation actions, such as resource scaling, node restarts, and heuristic tuning. Its design leverages predictive alerts to reduce reaction delays and improve adaptation timing. Experimental validation demonstrated a mean adaptation time of 0.05 seconds, approximately 94% adaptation accuracy, 4% overhead, and 98% operational stability, confirming its effectiveness for real-time optimization in heterogeneous and dynamic environments.
ER  -