A Hybrid Machine Learning Approach to Cloud Workload Prediction Using Decision Tree for Classification and Random Forest for Regression

Simhadri Mallikarjuna Rao; Gangadhara Rao Kancherla; Neelima Guntupalli

doi:10.32628/CSEIT2410488

Authors

Simhadri Mallikarjuna Rao Department of Computer Science & Engineering, Acharya Nagarjuna University, Guntur, 522510, Andhra Pradesh, India Author
Gangadhara Rao Kancherla Department of Computer Science & Engineering, Acharya Nagarjuna University, Guntur, 522510, Andhra Pradesh, India Author
Neelima Guntupalli Department of Computer Science & Engineering, Acharya Nagarjuna University, Guntur, 522510, Andhra Pradesh, India Author

DOI:

https://doi.org/10.32628/CSEIT2410488

Keywords:

Workload Prediction, Hybrid Model, Decision Tree Classifier, Random Forest Regression, Resource Management, DTCRFR

Abstract

The dynamic nature of cloud workloads necessitates accurate predictions to optimize resource utilization, enhance performance, and ensure quality of service (QoS). Consequently, numerous researchers have developed workload prediction models to improve cloud design and deployment. These models enable timely and reliable workload forecasting, facilitating critical decisions such as resource allocation and network bandwidth management. This study proposes a hybrid learning model, termed DTCRFR, which integrates Decision Tree Classification and Random Forest Regression techniques to predict reliable workloads. The DTCRFR model operates by initially assigning a workload state to each input data point based on historical workload data and system metrics. Subsequently, the regression model refines this prediction, producing a highly accurate workload value for the classified state. The combined approach enhances prediction accuracy while reducing computational complexity, making it highly suitable for real-time applications. Empirical results validate the effectiveness of this hybrid model, demonstrating improved prediction accuracy and reduced mean-squared error (MSE) and mean absolute error (MAE). This highlights the benefit of combining classification and regression techniques to leverage their complementary strengths for more reliable and granular workload predictions. The proposed method significantly enhances resource management and system performance in diverse computational environments. By merging classification and regression, DTCRFR adds precision and subtlety to workload forecasting, providing a notable advancement in the field. This hybrid model improves both efficiency and reliability in workload prediction, marking a relevant contribution to cloud resource optimization.

Downloads

Download data is not yet available.

References

L. Ruan et al., "Cloud Workload Turning Points Prediction via Cloud Feature-Enhanced Deep Learning," in IEEE Transactions on Cloud Computing, vol. 11, no. 2, pp. 1719-1732, 1 April-June 2023, doi: 10.1109/TCC.2022.3160228. keywords: {Cloud computing;Turning;Market research;Predictive models;Time series analysis;Servers;Prediction algorithms;Cloud computing;turning point prediction;deep learning;cloud feature-enhanced;time series analysis}, DOI: https://doi.org/10.1109/TCC.2022.3160228

I. K. Kim, W. Wang, Y. Qi and M. Humphrey, "Forecasting Cloud Application Workloads With CloudInsight for Predictive Resource Management," in IEEE Transactions on Cloud Computing, vol. 10, no. 3, pp. 1848-1863, 1 July-Sept. 2022, doi: 10.1109/TCC.2020.2998017. keywords: {Cloud computing;Resource management;Predictive models;Computational modeling;Support vector machines;Smoothing methods;Performance evaluation;Cloud computing;workload prediction;ensemble prediction model;predictive resource management;autoscaling;performance evaluation}, DOI: https://doi.org/10.1109/TCC.2020.2998017

Z. Amekraz and M. Y. Hadi, "CANFIS: A Chaos Adaptive Neural Fuzzy Inference System for Workload Prediction in the Cloud," in IEEE Access, vol. 10, pp. 49808-49828, 2022, doi: 10.1109/ACCESS.2022.3174061. keywords: {Predictive models;Adaptation models;Time series analysis;Prediction algorithms;Data models;Cloud computing;Adaptive systems;Adaptive neuro-fuzzy inference system;chaos analysis;cloud application workloads;proactive technique;workload prediction}, DOI: https://doi.org/10.1109/ACCESS.2022.3174061

K. Seshadri, K. Sindhu, S. N. Bhattu and C. Kollengode, "Design and Evaluation of a Hierarchical Characterization and Adaptive Prediction Model for Cloud Workloads," in IEEE Transactions on Cloud Computing, vol. 12, no. 2, pp. 712-724, April-June 2024, doi: 10.1109/TCC.2024.3393114. keywords: {Predictive models;Adaptation models;Computational modeling;Cloud computing;Data models;Load modeling;Task analysis;Workload prediction;cloud computing;deep learning;graph embedding;Markov model;elastic cloud;graph variational auto encoder}, DOI: https://doi.org/10.1109/TCC.2024.3393114

B. Feng, Z. Ding and C. Jiang, "FAST: A Forecasting Model With Adaptive Sliding Window and Time Locality Integration for Dynamic Cloud Workloads," in IEEE Transactions on Services Computing, vol. 16, no. 2, pp. 1184-1197, 1 March-April 2023, doi: 10.1109/TSC.2022.3156619.keywords: {Predictive models;Forecasting;Adaptation models;Market research;Analytical models;Load modeling;Cloud computing;Adaptive sliding window;cloud computing;integration strategy;time locality;workload decomposition;workload prediction}, DOI: https://doi.org/10.1109/TSC.2022.3156619

Z. Ding, B. Feng and C. Jiang, "COIN: A Container Workload Prediction Model Focusing on Common and Individual Changes in Workloads," in IEEE Transactions on Parallel and Distributed Systems, vol. 33, no. 12, pp. 4738-4751, 1 Dec. 2022, doi: 10.1109/TPDS.2022.3202833.keywords: {Containers;Predictive models;Data models;Adaptation models;Forecasting;Cloud computing;Load modeling;Cloud Computing;container;workload prediction;container similarity;online learning;transfer learning;integrated model}, DOI: https://doi.org/10.1109/TPDS.2022.3202833

Y. -M. Kim, S. Song, B. -M. Koo, J. Son, Y. Lee and J. -G. Baek, "Enhancing Long-Term Cloud Workload Forecasting Framework: Anomaly Handling and Ensemble Learning in Multivariate Time Series," in IEEE Transactions on Cloud Computing, vol. 12, no. 2, pp. 789-799, April-June 2024, doi: 10.1109/TCC.2024.3400859.keywords: {Cloud computing;Anomaly detection;ensemble learning;long-term cloud workload forecasting;multivariate time series analysis;resource management}, DOI: https://doi.org/10.1109/TCC.2024.3400859

X. Chen, F. Zhu, Z. Chen, G. Min, X. Zheng and C. Rong, "Resource Allocation for Cloud-Based Software Services Using Prediction-Enabled Feedback Control With Reinforcement Learning," in IEEE Transactions on Cloud Computing, vol. 10, no. 2, pp. 1117-1129, 1 April-June 2022, doi: 10.1109/TCC.2020.2992537. keywords: {Cloud computing;Resource management;Software;Quality of service;Predictive models;Feedback control;Prediction algorithms;Cloud-based software services;resource allocation;reinforcement learning;Q Value prediction;feedback control}, DOI: https://doi.org/10.1109/TCC.2020.2992537

N. I. Mahbub, M. D. Hossain, S. Akhter, M. I. Hossain, K. Jeong and E. -N. Huh, "Robustness of Workload Forecasting Models in Cloud Data Centers: A White-Box Adversarial Attack Perspective," in IEEE Access, vol. 12, pp. 55248-55263, 2024, doi: 10.1109/ACCESS.2024.3385863. keywords: {Cloud computing;Predictive models;Forecasting;Long short term memory;Logic gates;Glass box;Computational modeling;Deep learning;Cloud computing;workload prediction;cloud security;deep learning;adversarial attack}, DOI: https://doi.org/10.1109/ACCESS.2024.3385863

D. Saxena, J. Kumar, A. K. Singh and S. Schmid, "Performance Analysis of Machine Learning Centered Workload Prediction Models for Cloud," in IEEE Transactions on Parallel and Distributed Systems, vol. 34, no. 4, pp. 1313-1330, April 2023, doi: 10.1109/TPDS.2023.3240567. keywords: {Predictive models;Cloud computing;Servers;Neural networks;Resource management;Data models;Dynamic scheduling;Cloud computing;deep learning;ensemble lear- ning;evolutionary neural network;forecasting;hybrid learning;quantum neural network}, DOI: https://doi.org/10.1109/TPDS.2023.3240567

N. Hogade and S. Pasricha, "A Survey on Machine Learning for Geo-Distributed Cloud Data Center Management," in IEEE Transactions on Sustainable Computing, vol. 8, no. 1, pp. 15-31, 1 Jan.-March 2023, doi: 10.1109/TSUSC.2022.3208781. keywords: {Cloud computing;Data centers;Quality of service;Optimization;Predictive models;Costs;Prediction algorithms;Cloud management;machine learning;geo-distributed data centers;workload management;resource management;cloud computing;load balancing;optimization;prediction}, DOI: https://doi.org/10.1109/TSUSC.2022.3208781

X. Chen, L. Yang, Z. Chen, G. Min, X. Zheng and C. Rong, "Resource Allocation With Workload-Time Windows for Cloud-Based Software Services: A Deep Reinforcement Learning Approach," in IEEE Transactions on Cloud Computing, vol. 11, no. 2, pp. 1871-1885, 1 April-June 2023, doi: 10.1109/TCC.2022.3169157. keywords: {Resource management;Cloud computing;Software;Quality of service;Costs;Control theory;Predictive models;Cloud-based software services;resource allocation;workload-time windows;deep reinforcement learning;feedback control}, DOI: https://doi.org/10.1109/TCC.2022.3169157

J. Li, J. Yao, D. Xiao, D. Yang and W. Wu, "EvoGWP: Predicting Long-Term Changes in Cloud Workloads Using Deep Graph-Evolution Learning," in IEEE Transactions on Parallel and Distributed Systems, vol. 35, no. 3, pp. 499-516, March 2024, doi: 10.1109/TPDS.2024.3357715. keywords: {Dynamic scheduling;Heuristic algorithms;Prediction algorithms;Correlation;Predictive models;Interference;Graph neural networks;Workload prediction;cloud computing;graph neural network;resource management;datacenter}, DOI: https://doi.org/10.1109/TPDS.2024.3357715

D. Alqahtani, "Leveraging Sparse Auto-Encoding and Dynamic Learning Rate for Efficient Cloud Workloads Prediction," in IEEE Access, vol. 11, pp. 64586-64599, 2023, doi: 10.1109/ACCESS.2023.3289884. keywords: {Cloud computing;Logic gates;Deep learning;Quality of service;Data centers;Predictive models;Forecasting;Cloud computing;deep learning;sparse auto-encoder;gated recurrent unit;learning rate}, DOI: https://doi.org/10.1109/ACCESS.2023.3289884

Takale, Dattatray & Wattamwar, Aditya & Saipatwar, Saksham & Saindane, Harshwardhan & Patil, Tushar. (2024). Comparative Analysis of LSTM, RNN, CNN and MLP Machine Learning Algorithms for Stock Value Prediction. 2. 1-10. 10.48001/JoFSN. DOI: https://doi.org/10.48001/jofsn.2024.211-10

M. D. P. P. Goonathilake and P. P. N. V. Kumara, "CNN, RNN-LSTM Based Hybrid Approach to Detect State-of-the-Art Stance-Based Fake News on Social Media," 2020 20th International Conference on Advances in ICT for Emerging Regions (ICTer), Colombo, Sri Lanka, 2020, pp. 23-28, doi: 10.1109/ICTer51097.2020.9325477. DOI: https://doi.org/10.1109/ICTer51097.2020.9325477

Ahamed, Z., Khemakhem, M., Eassa, F., Alsolami, F., Basuhail, A., Jambi, K. Deep Reinforcement Learning for Workload Prediction in Federated Cloud Environments. Sensors 2023, 23, 6911. https://doi.org/10.3390/s23156911 DOI: https://doi.org/10.3390/s23156911

AHAMED, Z. et al. Technical Study of Deep Learning in Cloud Computing for Accurate Workload Prediction. Electronics (2079-9292), [s. l.], v. 12, n. 3, p. 650, 2023. DOI 10.3390/electronics12030650. Disponível em: https://research.ebsco.com/linkprocessor/plink?id=9ac0e5da-5a35-30c7-b3b7-4d786019fe7e. Acesso em: 28 ago. 2024.