Escalonamento Horizontal em Kubernetes com Redes Neurais Artificiais para Predição de Carga
Resumo
Este artigo apresenta uma abordagem inovadora para o escalonamento horizontal automático em cluster Kubernetes (K8s), utilizando Redes Neurais Artificiais. A proposta é chamada de ANN-HS e em comparação com o Escalonador Horizontal padrão do K8s (HPA), o ANN-HS demonstra eficiência superior em termos de consumo de recursos, alocação otimizada de réplicas, adaptação flexível à demanda e aderência a níveis de latência. Com modelos de regressão pré-treinados, o ANN-HS oferece ajuste personalizado de recursos, promovendo uma alternativa promissora para aprimorar o escalonamento horizontal de aplicações em ambientes de micro-serviços.
Palavras-chave:
Escalonamento horizontal, Kubernetes, Aprendizagem de Máquina, Redes Neurais Artificiais, HPA
Referências
M.-N. Tran, D.-D. Vu, and Y. Kim, “A survey of autoscaling in kubernetes,” in 2022 Thirteenth International Conference on Ubiquitous and Future Networks (ICUFN). IEEE, 2022, pp. 263–265.
Q. Huo, S. Li, Y. Xie, and Z. Li, “Horizontal pod autoscaling based on kubernetes with fast response and slow shrinkage,” in 2022 International Conference on Artificial Intelligence, Information Processing and Cloud Computing (AIIPCC). IEEE, 2022, pp. 203–206.
A. Zafeiropoulos, E. Fotopoulou, N. Filinis, and S. Papavassiliou, “Reinforcement learning-assisted autoscaling mechanisms for serverless computing platforms,” Simulation Modelling Practice and Theory, vol. 116, p. 102461, 2022.
H. Sami, H. Otrok, J. Bentahar, and A. Mourad, “Ai-based resource provisioning of ioe services in 6g: A deep reinforcement learning approach,” IEEE Transactions on Network and Service Management, vol. 18, no. 3, pp. 3527–3540, 2021.
Z. Xiao and S. Hu, “Dscaler: A horizontal autoscaler of microservice based on deep reinforcement learning,” in 2022 23rd Asia-Pacific Network Operations and Management Symposium (APNOMS), 2022, pp. 1–6.
H. T. Nguyen, T. Van Do, and C. Rotter, “Scaling upf instances in 5g/6g core with deep reinforcement learning,” IEEE Access, vol. 9, pp. 165 892–165 906, 2021.
A. A. Khaleq and I. Ra, “Intelligent autoscaling of microservices in the cloud for real-time applications,” IEEE Access, vol. 9, pp. 35 464–35 476, 2021.
V. Ojha, A. Abraham, and V. Snášel, “Heuristic design of fuzzy inference systems: A review of three decades of research,” Engineering Applications of Artificial Intelligence, vol. 85, pp. 845–864, 2019.
“Microk8s: Lightweight kubernetes,” https://microk8s.io/, acesso em: 18-07-2023.
The Apache Software Foundation, “Apache jmeter,” https://jmeter.apache.org/, 2023, acesso em: 18-07-2023.
Dropwizard Development Team, “Dropwizard,” https://www.dropwizard.io/, 2023, acesso em: 18-07-2023.
Red Hat, “Fabric8 kubernetes-client,” https://github.com/fabric8io/kubernetes-client, 2023, acesso em: 18-07-2023.
The Prometheus Authors, “Prometheus,” https://prometheus.io/, 2023, acesso em: 18-07-2023.
Q. Huo, S. Li, Y. Xie, and Z. Li, “Horizontal pod autoscaling based on kubernetes with fast response and slow shrinkage,” in 2022 International Conference on Artificial Intelligence, Information Processing and Cloud Computing (AIIPCC). IEEE, 2022, pp. 203–206.
A. Zafeiropoulos, E. Fotopoulou, N. Filinis, and S. Papavassiliou, “Reinforcement learning-assisted autoscaling mechanisms for serverless computing platforms,” Simulation Modelling Practice and Theory, vol. 116, p. 102461, 2022.
H. Sami, H. Otrok, J. Bentahar, and A. Mourad, “Ai-based resource provisioning of ioe services in 6g: A deep reinforcement learning approach,” IEEE Transactions on Network and Service Management, vol. 18, no. 3, pp. 3527–3540, 2021.
Z. Xiao and S. Hu, “Dscaler: A horizontal autoscaler of microservice based on deep reinforcement learning,” in 2022 23rd Asia-Pacific Network Operations and Management Symposium (APNOMS), 2022, pp. 1–6.
H. T. Nguyen, T. Van Do, and C. Rotter, “Scaling upf instances in 5g/6g core with deep reinforcement learning,” IEEE Access, vol. 9, pp. 165 892–165 906, 2021.
A. A. Khaleq and I. Ra, “Intelligent autoscaling of microservices in the cloud for real-time applications,” IEEE Access, vol. 9, pp. 35 464–35 476, 2021.
V. Ojha, A. Abraham, and V. Snášel, “Heuristic design of fuzzy inference systems: A review of three decades of research,” Engineering Applications of Artificial Intelligence, vol. 85, pp. 845–864, 2019.
“Microk8s: Lightweight kubernetes,” https://microk8s.io/, acesso em: 18-07-2023.
The Apache Software Foundation, “Apache jmeter,” https://jmeter.apache.org/, 2023, acesso em: 18-07-2023.
Dropwizard Development Team, “Dropwizard,” https://www.dropwizard.io/, 2023, acesso em: 18-07-2023.
Red Hat, “Fabric8 kubernetes-client,” https://github.com/fabric8io/kubernetes-client, 2023, acesso em: 18-07-2023.
The Prometheus Authors, “Prometheus,” https://prometheus.io/, 2023, acesso em: 18-07-2023.
Publicado
21/11/2023
Como Citar
SILVA, Lucileide M. D. da; SILVA, Sérgio N.; FERNANDES, Marcelo A. C..
Escalonamento Horizontal em Kubernetes com Redes Neurais Artificiais para Predição de Carga. In: ARTIGOS COMPLETOS - SIMPÓSIO BRASILEIRO DE ENGENHARIA DE SISTEMAS COMPUTACIONAIS (SBESC), 13. , 2023, Porto Alegre/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 7-12.
ISSN 2763-9002.
DOI: https://doi.org/10.5753/sbesc_estendido.2023.235886.
