Oraculum: A Model for Self-Adaptive System Optimization in Smart Environments
Resumo
Ambientes inteligentes exigem gestão adaptativa de recursos para lidar com cargas de trabalho dinâmicas e variabilidade do sistema. Soluções tradicionais baseadas em configurações estáticas frequentemente falham em manter o desempenho sob condições mutáveis. Este trabalho apresenta o Oraculum, um modelo adaptativo que integra monitoramento em tempo real, análise preditiva e aprendizagem por reforço (TD3) para otimizar proativamente decisões de reconfiguração. Resultados experimentais mostram que o Oraculum reduz o Mean Adaptation Time (MAT), alcançando 97% de precisão de adaptação, 2% de overhead e 98% de estabilidade, superando arquiteturas reativas.Referências
Aguayo, O., Sepúlveda, S., and Mazo, R. (2024). Variability management in self-adaptive systems through deep learning: A dynamic software product line approach. Electronics, 13(5):905.
Cen, J. and Li, Y. (2022). Resource allocation strategy using deep reinforcement learning in cloud-edge collaborative computing environment. Security and Communication Networks, 2022:Article ID 9597429.
Etemadi, M., Ghobaei-Arani, M., and Shahidinejad, A. (2021). A cost-efficient autoscaling mechanism for iot applications in fog computing environment: A deep learning-based approach. Cluster Computing, 24:3277–3292.
Fang, X., Chen, Y., Bhuiyan, Z. A., He, X., Bian, G., Crespi, N., and Jing, X. (2025). Mixer-transformer: Adaptive anomaly detection with multivariate time series. Journal of Network and Computer Applications, 241:104216.
Hameed, A., Violos, J., Santi, N., Leivadeas, A., and Mitton, N. (2021). A machine learning regression approach for throughput estimation in an iot environment. pages 29–36.
Jamshidi, S., Amirnia, A., Nikanjam, A., Nafi, K. W., Khomh, F., and Keivanpour, S. (2025). Self-adaptive cyber defense for sustainable iot: A drl-based ids optimizing security and energy efficiency. Journal of Network and Computer Applications, 239:104176.
Liu, D., Zhen, H., Kong, D., Chen, X., Lei, Z., Yuan, M., and Wang, H. (2021). Sensors anomaly detection of industrial internet of things based on isolated forest algorithm and data compression. Scientific Programming, 2021:1–9.
Liu, Y., Liao, G., Jiang, G., Chen, Y., Cui, Y., Xu, H., and Yu, M. (2024). Multi-exposure fused light field image quality assessment for dynamic scenes: Benchmark dataset and objective metric. Expert Systems with Applications, 256:124881.
Petersen, K., Feldt, R., Mujtaba, S., and Mattsson, M. (2008). Systematic mapping studies in software engineering. In Proceedings of the 12th International Conference on Evaluation and Assessment in Software Engineering, pages 68–77, Swindon, UK. BCS Learning & Development Ltd.
Pinthurat, W., Surinkaew, T., and Hredzak, B. (2024). An overview of reinforcement learning-based approaches for smart home energy management systems with energy storages. Renewable and Sustainable Energy Reviews, 202:114648.
Priya, S. A., Bhat, N., Kanna, B. R., Rajalakshmi, S., Jeyavathana, R. B., and S, S. (2024). Proactive network optimization using deep learning in predicting iot traffic dynamics. In 2024 4th International Conference on Innovative Practices in Technology and Management (ICIPTM), pages 1–6.
Sah, D. K., Nguyen, T. N., Cengiz, K., Dumba, B., and Kumar, V. (2022). Load-balance scheduling for intelligent sensors deployment in industrial internet of things. Cluster Computing, 25(3):1715–1727.
Samarakoon, S., Bandara, S., Jayasanka, N., and Hettiarachchi, C. (2023). Self-healing and self-adaptive management for iot-edge computing infrastructure. In 2023 Moratuwa Engineering Research Conference (MERCon), pages 473–478.
SAP (2007). Standardized technical architecture modeling: Conceptual and design level. Available at: [link], Accessed in: March 28, 2025.
Shin, M., Kim, M., Park, G., and Abraham, A. (2023). Adaptive variable sampling model for performance analysis in high cache-performance computing environments. Heliyon, 9(6):e16777.
Steventon, A. and Wright, S. (2006). Intelligent Spaces: The Application of Pervasive ICT. Springer-Verlag, London, UK. Accessed on: Jul 11, 2025.
Tam, P., Math, S., and Kim, S. (2022). Priority-aware resource management for adaptive service function chaining in real-time intelligent iot services. Electronics, 11(19):2976.
Velrajan, S. and Sharmila, V. C. (2023). Qos-aware service migration in multi-access edge computing using closed-loop adaptive particle swarm optimization algorithm. Journal of Network and Systems Management, 31(1):17.
Wang, Q., Su, F., Dai, S., Lu, X., and Liu, Y. (2024). Adagc: A novel adaptive optimization algorithm with gradient bias correction. Expert Systems with Applications, 256:124956.
Wang, X., Luo, Q., Liu, K., Mao, R., and Wu, G. (2025). Deep learning method based on multiscale enhanced feature fusion for vehicle behavior prediction. IEEE Internet of Things Journal, 12(7):9142–9155.
Yang, F., Ge, S., Liu, J., Yan, K., Gao, A., Dong, Y., Yang, M., and Zhang, W. (2025). High-precision short-term industrial energy consumption forecasting via parallel-nn with adaptive universal decomposition. Expert Systems with Applications, 289:128366.
Yang, Z., Abbasi, I. A., Mustafa, E. E., Ali, S., and Zhang, M. (2021). An anomaly detection algorithm selection service for iot stream data based on tsfresh tool and genetic algorithm. Security and Communication Networks, 2021(1):6677027.
Zeshan, F., Ahmad, A., Babar, M. I., Hamid, M., Hajjej, F., and Ashraf, M. (2023). An iot-enabled ontology-based intelligent healthcare framework for remote patient monitoring. IEEE Access, 11:133947–133966.
Zhang, J., Liu, G., Chen, J., and Cheng, Y. (2025). Multi-scale adaptive residual cold diffusion model for low-dose ct denoising. Expert Systems with Applications, 294:128817.
Zhao, S. and Guo, M. (2024). Electric vehicle power system in intelligent manufacturing based on soft computing optimization. Heliyon, 10(21):e38946.
Cen, J. and Li, Y. (2022). Resource allocation strategy using deep reinforcement learning in cloud-edge collaborative computing environment. Security and Communication Networks, 2022:Article ID 9597429.
Etemadi, M., Ghobaei-Arani, M., and Shahidinejad, A. (2021). A cost-efficient autoscaling mechanism for iot applications in fog computing environment: A deep learning-based approach. Cluster Computing, 24:3277–3292.
Fang, X., Chen, Y., Bhuiyan, Z. A., He, X., Bian, G., Crespi, N., and Jing, X. (2025). Mixer-transformer: Adaptive anomaly detection with multivariate time series. Journal of Network and Computer Applications, 241:104216.
Hameed, A., Violos, J., Santi, N., Leivadeas, A., and Mitton, N. (2021). A machine learning regression approach for throughput estimation in an iot environment. pages 29–36.
Jamshidi, S., Amirnia, A., Nikanjam, A., Nafi, K. W., Khomh, F., and Keivanpour, S. (2025). Self-adaptive cyber defense for sustainable iot: A drl-based ids optimizing security and energy efficiency. Journal of Network and Computer Applications, 239:104176.
Liu, D., Zhen, H., Kong, D., Chen, X., Lei, Z., Yuan, M., and Wang, H. (2021). Sensors anomaly detection of industrial internet of things based on isolated forest algorithm and data compression. Scientific Programming, 2021:1–9.
Liu, Y., Liao, G., Jiang, G., Chen, Y., Cui, Y., Xu, H., and Yu, M. (2024). Multi-exposure fused light field image quality assessment for dynamic scenes: Benchmark dataset and objective metric. Expert Systems with Applications, 256:124881.
Petersen, K., Feldt, R., Mujtaba, S., and Mattsson, M. (2008). Systematic mapping studies in software engineering. In Proceedings of the 12th International Conference on Evaluation and Assessment in Software Engineering, pages 68–77, Swindon, UK. BCS Learning & Development Ltd.
Pinthurat, W., Surinkaew, T., and Hredzak, B. (2024). An overview of reinforcement learning-based approaches for smart home energy management systems with energy storages. Renewable and Sustainable Energy Reviews, 202:114648.
Priya, S. A., Bhat, N., Kanna, B. R., Rajalakshmi, S., Jeyavathana, R. B., and S, S. (2024). Proactive network optimization using deep learning in predicting iot traffic dynamics. In 2024 4th International Conference on Innovative Practices in Technology and Management (ICIPTM), pages 1–6.
Sah, D. K., Nguyen, T. N., Cengiz, K., Dumba, B., and Kumar, V. (2022). Load-balance scheduling for intelligent sensors deployment in industrial internet of things. Cluster Computing, 25(3):1715–1727.
Samarakoon, S., Bandara, S., Jayasanka, N., and Hettiarachchi, C. (2023). Self-healing and self-adaptive management for iot-edge computing infrastructure. In 2023 Moratuwa Engineering Research Conference (MERCon), pages 473–478.
SAP (2007). Standardized technical architecture modeling: Conceptual and design level. Available at: [link], Accessed in: March 28, 2025.
Shin, M., Kim, M., Park, G., and Abraham, A. (2023). Adaptive variable sampling model for performance analysis in high cache-performance computing environments. Heliyon, 9(6):e16777.
Steventon, A. and Wright, S. (2006). Intelligent Spaces: The Application of Pervasive ICT. Springer-Verlag, London, UK. Accessed on: Jul 11, 2025.
Tam, P., Math, S., and Kim, S. (2022). Priority-aware resource management for adaptive service function chaining in real-time intelligent iot services. Electronics, 11(19):2976.
Velrajan, S. and Sharmila, V. C. (2023). Qos-aware service migration in multi-access edge computing using closed-loop adaptive particle swarm optimization algorithm. Journal of Network and Systems Management, 31(1):17.
Wang, Q., Su, F., Dai, S., Lu, X., and Liu, Y. (2024). Adagc: A novel adaptive optimization algorithm with gradient bias correction. Expert Systems with Applications, 256:124956.
Wang, X., Luo, Q., Liu, K., Mao, R., and Wu, G. (2025). Deep learning method based on multiscale enhanced feature fusion for vehicle behavior prediction. IEEE Internet of Things Journal, 12(7):9142–9155.
Yang, F., Ge, S., Liu, J., Yan, K., Gao, A., Dong, Y., Yang, M., and Zhang, W. (2025). High-precision short-term industrial energy consumption forecasting via parallel-nn with adaptive universal decomposition. Expert Systems with Applications, 289:128366.
Yang, Z., Abbasi, I. A., Mustafa, E. E., Ali, S., and Zhang, M. (2021). An anomaly detection algorithm selection service for iot stream data based on tsfresh tool and genetic algorithm. Security and Communication Networks, 2021(1):6677027.
Zeshan, F., Ahmad, A., Babar, M. I., Hamid, M., Hajjej, F., and Ashraf, M. (2023). An iot-enabled ontology-based intelligent healthcare framework for remote patient monitoring. IEEE Access, 11:133947–133966.
Zhang, J., Liu, G., Chen, J., and Cheng, Y. (2025). Multi-scale adaptive residual cold diffusion model for low-dose ct denoising. Expert Systems with Applications, 294:128817.
Zhao, S. and Guo, M. (2024). Electric vehicle power system in intelligent manufacturing based on soft computing optimization. Heliyon, 10(21):e38946.
Publicado
19/07/2026
Como Citar
NOETZOLD, Darlan; LEITHARDT, Valderi Reis Quietinho; BARBOSA, Jorge Luis Victória.
Oraculum: A Model for Self-Adaptive System Optimization in Smart Environments. In: CONCURSO DE TESES E DISSERTAÇÕES DA SBC (CTD-SBC), 39. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 140-149.
ISSN 2763-8820.
DOI: https://doi.org/10.5753/ctd.2026.19468.
