Automated control of computational resources in clusters with ESP32 and Naive Bayes to improve energy efficiency

• Elias J. Miranda UFAL
• Marluce R. Pereira UFAL

DOI: https://doi.org/10.5753/eradsp.2025.9713

Abstract

This paper presents an approach to improve the energy efficiency of a low-cost cluster by automatically turning on and off machines. The cluster infrastructure used to test the solution includes four machines with Intel Celeron and wired network, Alpine Linux operating system and an ESP32 microcontroller connected to the motherboard of each node. A Naive Bayes algorithm evaluates the trend of CPU and memory usage activities on each node, allowing ESP32 to decide whether to turn on or off cluster nodes, ensuring high availability. The results were promising for the set of machines used.

References

AlMadhoun, A. S. A. (2023). Microcontrolador. In Guia de Início Rápido de Design e Simulação de Circuitos, Série Maker Innovations, chapter 1. Apress.

de Oliveira, A. C. A., Spohn, M. A., Fetzer, C., Do, L. Q., and Martin, A. (2023). Cost-based virtual machine scheduling for data-as-a-service. Journal of Universal Computer Science, 29(12):1461–1481.

Dias, A. H. T., Correia, L. H. A., and Malheiros, N. (2021). A systematic literature review on virtual machine consolidation. ACM Comput. Surv., 54(8).

Katal, A., D. S. . C. T. (2023). Energy efficiency in cloud computing data centers: a survey on software technologies. Cluster Computing, 26:1845–1875.

Wickramasinghe, I. and Kalutarage, H. (2021). Naive bayes: applications, variations and vulnerabilities: a review of literature with code snippets for implementation. Soft Computing, 25(3):2277–2293.

Yang, C. C., Soh, C. S., and Yap, V. V. (2017). A non-intrusive appliance load monitoring for efficient energy consumption based on naive bayes classifier. Sustainable Computing: Informatics and Systems, 14:34–42.