Predição de Cargas de Trabalho de Nós de Computação em Nuvem Usando Modelos ARIMA e Redes Neurais Recorrentes Tipo LSTM
Resumo
Manter ambientes de computação em nuvem sempre disponíveis e cumprindo os níveis mínimos de serviço é uma tarefa que exige um gerenciamento eficiente dos recursos computacionais. Prever cargas de trabalho computacionais é uma estratégia que pode trazer ganhos ao possibilitar a tomada de ações proativas no uso eficiente dos recursos, no entanto, fazer tais predições em ambientes heterogêneos e dinâmicos é um desafio. Neste sentido, este trabalho demonstra a aplicação de técnicas para predizer valores de séries temporais utilizando modelos ARIMA e Redes Neurais Recorrentes (RNR) tipo LSTM ao analisar cargas de trabalho de nós de computação em nuvem. Ao final, os resultados demonstram que os modelos ARIMA e as Redes Neurais Recorrentes apresentam capacidade preditiva bem próximas entre si considerando o cenário proposto, sendo o ARIMA ligeiramente melhor em todos os conjuntos de dados do experimento.
Palavras-chave:
computação em nuvem, cargas de trabalho, predição, séries temporais, ARIMA, redes neurais recorrentes, LSTM
Referências
K. Vu, K. Hartley, and A. Kankanhalli, “Predictors of cloud computing adoption: A cross-country study,” Telematics and Informatics, vol. 52, p. 101426, 2020.
P. Mell, T. Grance et al., “The nist definition of cloud computing,” NIST Special Publication 800-145, 2011.
Q. Zhang, L. Cheng, and R. Boutaba, “Cloud computing: state-of-the-art and research challenges,” Journal of internet services and applications, vol. 1, no. 1, pp. 7–18, 2010.
D. da Silva Santos and A. E. S. Freitas, “Um protótipo para experimentos de eficiência energética em nuvem openstack,” in Anais Estendidos do XXXVII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos. SBC, 2019, pp. 1–8.
M. Masdari and A. Khoshnevis, “A survey and classification of the workload forecasting methods in cloud computing,” Cluster Computing, vol. 23, no. 4, pp. 2399–2424, 2020.
Y. Chen, B. Yang, and J. Dong, “Time-series prediction using a local linear wavelet neural network,” Neurocomputing, vol. 69, no. 4-6, pp. 449–465, 2006.
G. E. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time series analysis: forecasting and control. John Wiley & Sons, 2015.
R. S. A. Alsudani and J. Liu, “The use of some of the information criterion in determining the best model for forecasting of thalassemia cases depending on iraqi patient data using arima model,” Journal of Applied Mathematics and Physics, vol. 5, no. 3, pp. 667–679, 2017.
S. Hiriyannaiah, A. Srinivas, G. K. Shetty, G. Siddesh, and K. Srinivasa, “A computationally intelligent agent for detecting fake news using generative adversarial networks,” Hybrid Computational Intelligence: Challenges and Applications, p. 69, 2020.
A. Subasi, Practical Machine Learning for Data Analysis Using Python. Academic Press, 2020.
L. Nashold and R. Krishnan, “Using lstm and sarima models to forecast cluster cpu usage,” arXiv preprint arXiv:2007.08092, 2020.
Y. Bengio, P. Simard, and P. Frasconi, “Learning long-term dependencies with gradient descent is difficult,” IEEE transactions on neural networks, vol. 5, no. 2, pp. 157–166, 1994.
C. Olah, “Understanding lstm networks,” 2015.
S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997.
H. Zhou, Y. Zhang, L. Yang, Q. Liu, K. Yan, and Y. Du, “Short-term photovoltaic power forecasting based on long short term memory neural network and attention mechanism,” IEEE Access, vol. 7, pp. 78 063– 78 074, 2019.
P. T. Yamak, L. Yujian, and P. K. Gadosey, “A comparison between arima, lstm, and gru for time series forecasting,” in Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence, 2019, pp. 49–55.
D. F. Kirchoff et al., “Avaliação de técnicas de aprendizado de máquina para previsão de cargas de trabalho aplicadas para otimizar o provisionamento de recursos em nuvens computacionais,” Master’s thesis, Pontifícia Universidade Católica do Rio Grande do Sul, 2019.
J. Kumar and A. K. Singh, “Workload prediction in cloud using artificial neural network and adaptive differential evolution,” Future Generation Computer Systems, vol. 81, pp. 41–52, 2018.
G. Kaur, A. Bala, and I. Chana, “An intelligent regressive ensemble approach for predicting resource usage in cloud computing,” Journal of Parallel and Distributed Computing, vol. 123, pp. 1–12, 2019.
S. Islam, J. Keung, K. Lee, and A. Liu, “Empirical prediction models for adaptive resource provisioning in the cloud,” Future Generation Computer Systems, vol. 28, no. 1, pp. 155–162, 2012.
J. Bi, S. Li, H. Yuan, and M. Zhou, “Integrated deep learning method for workload and resource prediction in cloud systems,” Neurocomputing, vol. 424, pp. 35–48, 2021.
Alibaba, “Alibaba cluster trace program: cluster data collected from production clusters in alibaba for cluster management research,” https://github.com/alibaba/clusterdata, 2018, (Accessed on 09/08/2020).
G. Milone, Estatística: geral e aplicada. Pioneira Thomson Learning, 2004.
G. P. Nason, “Stationary and non-stationary time series,” Statistics in volcanology, vol. 60, 2006.
J. D. Hamilton, Time series analysis. Princeton university press, 2020.
V. M. D. Santos, “Previsão de vendas: como elaborar a sua?” https://www.fm2s.com.br/previsao-de-vendas-manual/, 2021, (Accessed on 18/08/2021).
Statsmodels, “Statistical models, hypothesis tests, and data exploration,” https://www.statsmodels.org, 2021, (Accessed on 16/06/2021).
S.-L. Ho, M. Xie, and T. N. Goh, “A comparative study of neural network and box-jenkins arima modeling in time series prediction,” Computers & Industrial Engineering, vol. 42, no. 2-4, pp. 371–375, 2002.
J. Bergstra and Y. Bengio, “Random search for hyper-parameter optimization.” Journal of machine learning research, vol. 13, no. 2, 2012.
I. Sutskever, J. Martens, and G. E. Hinton, “Generating text with recurrent neural networks,” in ICML, 2011.
Keras, “Keras. simple. flexible. powerful.” https://keras.io/, 2021, (Accessed on 24/06/2021).
F. Feltrin, Redes Neurais Artificiais. Fernando Feltrin, 2020.
J. Brownlee, Deep learning for time series forecasting: predict the future with MLPs, CNNs and LSTMs in Python. Machine Learning Mastery, 2018.
N. Gayatri, S. Nickolas, A. Reddy, S. Reddy, and A. Nickolas, “Feature selection using decision tree induction in class level metrics dataset for software defect predictions,” in Proceedings of the world congress on engineering and computer science, vol. 1. Citeseer, 2010, pp. 124–129.
P. S. Nascimento and A. E. S. Freitas, “Cloudgi, gerenciando instâncias de um serviço replicado em uma plataforma de computação em nuvem,” Anais Estendidos do XXXIII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, 2015.
P. Mell, T. Grance et al., “The nist definition of cloud computing,” NIST Special Publication 800-145, 2011.
Q. Zhang, L. Cheng, and R. Boutaba, “Cloud computing: state-of-the-art and research challenges,” Journal of internet services and applications, vol. 1, no. 1, pp. 7–18, 2010.
D. da Silva Santos and A. E. S. Freitas, “Um protótipo para experimentos de eficiência energética em nuvem openstack,” in Anais Estendidos do XXXVII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos. SBC, 2019, pp. 1–8.
M. Masdari and A. Khoshnevis, “A survey and classification of the workload forecasting methods in cloud computing,” Cluster Computing, vol. 23, no. 4, pp. 2399–2424, 2020.
Y. Chen, B. Yang, and J. Dong, “Time-series prediction using a local linear wavelet neural network,” Neurocomputing, vol. 69, no. 4-6, pp. 449–465, 2006.
G. E. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time series analysis: forecasting and control. John Wiley & Sons, 2015.
R. S. A. Alsudani and J. Liu, “The use of some of the information criterion in determining the best model for forecasting of thalassemia cases depending on iraqi patient data using arima model,” Journal of Applied Mathematics and Physics, vol. 5, no. 3, pp. 667–679, 2017.
S. Hiriyannaiah, A. Srinivas, G. K. Shetty, G. Siddesh, and K. Srinivasa, “A computationally intelligent agent for detecting fake news using generative adversarial networks,” Hybrid Computational Intelligence: Challenges and Applications, p. 69, 2020.
A. Subasi, Practical Machine Learning for Data Analysis Using Python. Academic Press, 2020.
L. Nashold and R. Krishnan, “Using lstm and sarima models to forecast cluster cpu usage,” arXiv preprint arXiv:2007.08092, 2020.
Y. Bengio, P. Simard, and P. Frasconi, “Learning long-term dependencies with gradient descent is difficult,” IEEE transactions on neural networks, vol. 5, no. 2, pp. 157–166, 1994.
C. Olah, “Understanding lstm networks,” 2015.
S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997.
H. Zhou, Y. Zhang, L. Yang, Q. Liu, K. Yan, and Y. Du, “Short-term photovoltaic power forecasting based on long short term memory neural network and attention mechanism,” IEEE Access, vol. 7, pp. 78 063– 78 074, 2019.
P. T. Yamak, L. Yujian, and P. K. Gadosey, “A comparison between arima, lstm, and gru for time series forecasting,” in Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence, 2019, pp. 49–55.
D. F. Kirchoff et al., “Avaliação de técnicas de aprendizado de máquina para previsão de cargas de trabalho aplicadas para otimizar o provisionamento de recursos em nuvens computacionais,” Master’s thesis, Pontifícia Universidade Católica do Rio Grande do Sul, 2019.
J. Kumar and A. K. Singh, “Workload prediction in cloud using artificial neural network and adaptive differential evolution,” Future Generation Computer Systems, vol. 81, pp. 41–52, 2018.
G. Kaur, A. Bala, and I. Chana, “An intelligent regressive ensemble approach for predicting resource usage in cloud computing,” Journal of Parallel and Distributed Computing, vol. 123, pp. 1–12, 2019.
S. Islam, J. Keung, K. Lee, and A. Liu, “Empirical prediction models for adaptive resource provisioning in the cloud,” Future Generation Computer Systems, vol. 28, no. 1, pp. 155–162, 2012.
J. Bi, S. Li, H. Yuan, and M. Zhou, “Integrated deep learning method for workload and resource prediction in cloud systems,” Neurocomputing, vol. 424, pp. 35–48, 2021.
Alibaba, “Alibaba cluster trace program: cluster data collected from production clusters in alibaba for cluster management research,” https://github.com/alibaba/clusterdata, 2018, (Accessed on 09/08/2020).
G. Milone, Estatística: geral e aplicada. Pioneira Thomson Learning, 2004.
G. P. Nason, “Stationary and non-stationary time series,” Statistics in volcanology, vol. 60, 2006.
J. D. Hamilton, Time series analysis. Princeton university press, 2020.
V. M. D. Santos, “Previsão de vendas: como elaborar a sua?” https://www.fm2s.com.br/previsao-de-vendas-manual/, 2021, (Accessed on 18/08/2021).
Statsmodels, “Statistical models, hypothesis tests, and data exploration,” https://www.statsmodels.org, 2021, (Accessed on 16/06/2021).
S.-L. Ho, M. Xie, and T. N. Goh, “A comparative study of neural network and box-jenkins arima modeling in time series prediction,” Computers & Industrial Engineering, vol. 42, no. 2-4, pp. 371–375, 2002.
J. Bergstra and Y. Bengio, “Random search for hyper-parameter optimization.” Journal of machine learning research, vol. 13, no. 2, 2012.
I. Sutskever, J. Martens, and G. E. Hinton, “Generating text with recurrent neural networks,” in ICML, 2011.
Keras, “Keras. simple. flexible. powerful.” https://keras.io/, 2021, (Accessed on 24/06/2021).
F. Feltrin, Redes Neurais Artificiais. Fernando Feltrin, 2020.
J. Brownlee, Deep learning for time series forecasting: predict the future with MLPs, CNNs and LSTMs in Python. Machine Learning Mastery, 2018.
N. Gayatri, S. Nickolas, A. Reddy, S. Reddy, and A. Nickolas, “Feature selection using decision tree induction in class level metrics dataset for software defect predictions,” in Proceedings of the world congress on engineering and computer science, vol. 1. Citeseer, 2010, pp. 124–129.
P. S. Nascimento and A. E. S. Freitas, “Cloudgi, gerenciando instâncias de um serviço replicado em uma plataforma de computação em nuvem,” Anais Estendidos do XXXIII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, 2015.
Publicado
22/11/2021
Como Citar
SANTOS, Danilo da Silva; FREITAS, Allan Edgard Silva.
Predição de Cargas de Trabalho de Nós de Computação em Nuvem Usando Modelos ARIMA e Redes Neurais Recorrentes Tipo LSTM. In: ARTIGOS COMPLETOS - SIMPÓSIO BRASILEIRO DE ENGENHARIA DE SISTEMAS COMPUTACIONAIS (SBESC), 11. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 8-15.
ISSN 2763-9002.
DOI: https://doi.org/10.5753/sbesc_estendido.2021.18488.
