CNN-LSTM is all you Need for Efficient Resource Allocation in Cloud Computing

Abstract:

Many organizations have embraced cloud computing in recent years to provide new services, easily expand their IT resources, and reduce the cost of their IT infrastructure. This has been made possible through the implementation of resource allocation strategies by cloud service providers. One of the major challenges during resource allocation is to minimize power consumption while ensuring the required Service Level Agreement (SLA). To solve this problem, a new approach to efficiently allocate resources in cloud computing while optimizing energy consumption and guaranteeing the required service level agreement has been proposed. The main idea of this proposal is to leverage the CNN-LSTM architecture to accurately predict resource utilization in order to make the appropriate resource allocation decision. The proposed solution was validated in two steps: step 1) a comprehensive set of statistical performance analysis and step 2) an intensive simulation of the solution for resource allocation using cloudSim Plus tool. The results of the experimentation demonstrated that the proposed solution can help cloud service providers achieve energy savings while guaranteeing the required SLA.

• Periodical: International Journal of Engineering Research in Africa (Volume 71)
• Pages: 141-162
• DOI: https://doi.org/10.4028/p-O4CrN9
• Online since: September 2024
• Authors: Moussa Aboubakar*, Yasmine Titouche, Mickael Fernandes, Ado Adamou Abba Ari, Md Siddiqur Rahman
• Keywords: Cloud Computing, Energy Consumption Optimization, Machine Learning, Resource Usage Prediction

References

[1] Peter Mell, Tim Grance, et al. The nist definition of cloud computing. 2011.

[2] Tharam Dillon, Chen Wu, and Elizabeth Chang. Cloud computing: issues and challenges. In 2010 24th IEEE international conference on advanced information networking and applications, pages 27–33. Ieee, 2010.

DOI: 10.1109/aina.2010.187

[3] Huigui Rong, Haomin Zhang, Sheng Xiao, Canbing Li, and Chunhua Hu. Optimizing energy consumption for data centers. Renewable and Sustainable Energy Reviews, 58:674–691, 2016.

DOI: 10.1016/j.rser.2015.12.283

[4] Karima Saidi, Ouassila Hioual, and Abderrahim Siam. Resources allocation in cloud computing: a survey. In International Conference in Artificial Intelligence in Renewable Energetic Systems, pages 356–364. Springer, 2019.

[5] Raouia Bouabdallah, Soufiene Lajmi, and Khaled Ghedira. Use of reactive and proactive elasticity to adjust resources provisioning in the cloud provider. In 2016 IEEE 18th International Conference on High Performance Computing and Communications; IEEE 14th International Conference on Smart City; IEEE 2nd International Conference on Data Science and Systems (HPCC/SmartCity/DSS), pages 1155–1162. IEEE, 2016.

DOI: 10.1109/hpcc-smartcity-dss.2016.0162

[6] JE Mboula, Vivient Corneille Kamla, MH Hilman, and C Tayou Djamegni. Energy-efficient workflow scheduling based on workflow structures under deadline and budget constraints in the cloud. arXiv preprint arXiv:2201.05429, 2022.

DOI: 10.1016/j.simpat.2020.102107

[7] Sepideh Goodarzy, Maziyar Nazari, Richard Han, Eric Keller, and Eric Rozner. Resource management in cloud computing using machine learning: A survey. In 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA), pages 811–816. IEEE, 2020.

DOI: 10.1109/icmla51294.2020.00132

[8] Mustafa Daraghmeh, Anjali Agarwal, Ricardo Manzano, and Marzia Zaman. Time series forecasting using facebook prophet for cloud resource management. In 2021 IEEE International Conference on Communications Workshops (ICC Workshops), pages 1–6. IEEE, 2021.

DOI: 10.1109/iccworkshops50388.2021.9473607

[9] Mustafa M Al-Sayed. Workload time series cumulative prediction mechanism for cloud resources using neural machine translation technique. Journal of Grid Computing, 20(2):1–29, 2022.

DOI: 10.1007/s10723-022-09607-0

[10] Shahin Vakilinia, Behdad Heidarpour, and Mohamed Cheriet. Energy efficient resource allocation in cloud computing environments. IEEE Access, 4:8544–8557, 2016.

DOI: 10.1109/access.2016.2633558

[11] Qinghao Hu, Peng Sun, Shengen Yan, Yonggang Wen, and Tianwei Zhang. Characterization and prediction of deep learning workloads in large-scale gpu datacenters. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pages 1–15, 2021.

DOI: 10.1145/3458817.3476223

[12] Deepika Saxena and Ashutosh Kumar Singh. Workload forecasting and resource management models based on machine learning for cloud computing environments. arXiv preprint arXiv:2106.15112, 2021.

[13] Abdul Hameed, Alireza Khoshkbarforoushha, Rajiv Ranjan, Prem Prakash Jayaraman, Joanna Kolodziej, Pavan Balaji, Sherali Zeadally, Qutaibah Marwan Malluhi, Nikos Tziritas, Abhinav Vishnu, et al. A survey and taxonomy on energy efficient resource allocation techniques for cloud computing systems. Computing, 98(7):751–774, 2016.

DOI: 10.1007/s00607-014-0407-8

[14] Weiwei Lin, James Z Wang, Chen Liang, and Deyu Qi. A threshold-based dynamic resource allocation scheme for cloud computing. Procedia Engineering, 23:695–703, 2011.

DOI: 10.1016/j.proeng.2011.11.2568

[15] Chandrashekhar S Pawar and Rajnikant B Wagh. Priority based dynamic resource allocation in cloud computing. In 2012 International Symposium on Cloud and Services Computing, pages 1–6. IEEE, 2012.

DOI: 10.1109/iscos.2012.14

[16] Michael Maurer, Ivan Breskovic, Vincent C Emeakaroha, and Ivona Brandic. Revealing the mape loop for the autonomic management of cloud infrastructures. In 2011 IEEE symposium on computers and communications (ISCC), pages 147–152. IEEE, 2011.

DOI: 10.1109/iscc.2011.5984008

[17] Omid Gheibi, Danny Weyns, and Federico Quin. Applying machine learning in self-adaptive systems: A systematic literature review. arXiv preprint arXiv:2103.04112, 2021.

[18] Arijit Khan, Xifeng Yan, Shu Tao, and Nikos Anerousis. Workload characterization and prediction in the cloud: A multiple time series approach. In 2012 IEEE Network Operations and Management Symposium, pages 1287–1294. IEEE, 2012.

DOI: 10.1109/noms.2012.6212065

[19] Yexi Jiang, Chang-Shing Perng, Tao Li, and Rong Chang. Asap: A self-adaptive prediction system for instant cloud resource demand provisioning. In 2011 IEEE 11th International Conference on Data Mining, pages 1104–1109. IEEE, 2011.

DOI: 10.1109/icdm.2011.25

[20] Archana Ganapathi, Yanpei Chen, Armando Fox, Randy Katz, and David Patterson. Statisticsdriven workload modeling for the cloud. In 2010 IEEE 26th International Conference on Data Engineering Workshops (ICDEW 2010), pages 87–92. IEEE, 2010.

DOI: 10.1109/icdew.2010.5452742

[21] Zhenhuan Gong, Xiaohui Gu, and John Wilkes. Press: Predictive elastic resource scaling for cloud systems. In 2010 International Conference on Network and Service Management, pages 9–16. Ieee, 2010.

DOI: 10.1109/cnsm.2010.5691343

[22] Fabio Jorge Almeida Morais, Francisco Vilar Brasileiro, Raquel Vigolvino Lopes, Ricardo Araújo Santos, Wade Satterfield, and Leandro Rosa. Autoflex: Service agnostic autoscaling framework for iaas deployment models. In 2013 13th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, pages 42–49. IEEE, 2013.

DOI: 10.1109/ccgrid.2013.74

[23] Abhishek Bajpai and Shivangi Nigam. A study on the techniques of computational offloading from mobile devices to cloud. Advances in Computational Sciences and Technology, 10(7):2037–2060, 2017.

[24] Abhishek Bajpai, Harshvardhan Rai, and Naveen Tiwari. An efficient cnn-based method for classification of red meat based on its freshness. In International Conference on Machine Learning, IoT and Big Data, pages 393–405. Springer, 2023.

DOI: 10.1007/978-981-99-3932-9_34

[25] Harshvardhan Rai, Abhishek Bajpai, Mohini Tyagi, and Kumkum Dubey. Parkinson's disease detection using a novel weighted ensemble of cnn models. In 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), pages 1–6. IEEE, 2023.

DOI: 10.1109/icccnt56998.2023.10306668

[26] Akindele A Bankole and Samuel A Ajila. Predicting cloud resource provisioning using machine learning techniques. In 2013 26th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), pages 1–4. IEEE, 2013.

DOI: 10.1109/ccece.2013.6567848

[27] Junxin Lin, Yuanfei Dai, Xing Chen, and Yihan Wu. Resource allocation of cloud application through machine learning: A case study. In 2017 International Conference on Green Informatics (ICGI), pages 263–268. IEEE, 2017.

DOI: 10.1109/icgi.2017.52

[28] Jiechao Gao, Haoyu Wang, and Haiying Shen. Machine learning based workload prediction in cloud computing. In 2020 29th international conference on computer communications and networks (ICCCN), pages 1–9. IEEE, 2020.

DOI: 10.1109/icccn49398.2020.9209730

[29] Patryk Osypanka and Piotr Nawrocki. Resource usage cost optimization in cloud computing using machine learning. IEEE Transactions on Cloud Computing, 2020.

DOI: 10.1109/tcc.2020.3015769

[30] Feng Qiu, Bin Zhang, and Jun Guo. A deep learning approach for vm workload prediction in the cloud. In 2016 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), pages 319–324. IEEE, 2016.

DOI: 10.1109/snpd.2016.7515919

[31] Qingchen Zhang, Laurence T Yang, Zheng Yan, Zhikui Chen, and Peng Li. An efficient deep learning model to predict cloud workload for industry informatics. IEEE transactions on industrial informatics, 14(7):3170–3178, 2018.

DOI: 10.1109/tii.2018.2808910

[32] Weishan Zhang, Pengcheng Duan, Laurence T Yang, Feng Xia, Zhongwei Li, Qinghua Lu, Wenjuan Gong, and Su Yang. Resource requests prediction in the cloud computing environment with a deep belief network. Software: Practice and Experience, 47(3):473–488, 2017.

DOI: 10.1002/spe.2426

[33] Ning Liu, Zhe Li, Jielong Xu, Zhiyuan Xu, Sheng Lin, Qinru Qiu, Jian Tang, and Yanzhi Wang. A hierarchical framework of cloud resource allocation and power management using deep reinforcement learning. In 2017 IEEE 37th international conference on distributed computing systems (ICDCS), pages 372–382. IEEE, 2017.

DOI: 10.1109/icdcs.2017.123

[34] Yonghua Zhu, Weilin Zhang, Yihai Chen, and Honghao Gao. A novel approach to workload prediction using attention-based lstm encoder-decoder network in cloud environment. EURASIP Journal on Wireless Communications and Networking, 2019(1):1–18, 2019.

DOI: 10.1186/s13638-019-1605-z

[35] Eva Patel and Dharmender Singh Kushwaha. A hybrid cnn-lstm model for predicting server load in cloud computing. The Journal of Supercomputing, 78(8):1–30, 2022.

DOI: 10.1007/s11227-021-04234-0

[36] Weiwei Jiang. Graph-based deep learning for communication networks: A survey. Computer Communications, 185:40–54, 2022.

DOI: 10.1016/j.comcom.2021.12.015

[37] Prohim Tam, Inseok Song, Seungwoo Kang, Seyha Ros, and Seokhoon Kim. Graph neural networks for intelligent modelling in network management and orchestration: a survey on communications. Electronics, 11(20):3371, 2022.

DOI: 10.3390/electronics11203371

[38] Ming Gao, Yuchan Li, and Jixiang Yu. Workload prediction of cloud workflow based on graph neural network. In Web Information Systems and Applications: 18th International Conference, WISA 2021, Kaifeng, China, September 24–26, 2021, Proceedings 18, pages 169–189. Springer, 2021.

DOI: 10.1007/978-3-030-87571-8_15

[39] Martin Happ, Jia Lei Du, Matthias Herlich, Christian Maier, Peter Dorfinger, and José Suárez- Varela. Exploring the limitations of current graph neural networks for network modeling. In NOMS 2022-2022 IEEE/IFIP Network Operations and Management Symposium, pages 1–8, 2022.

DOI: 10.1109/noms54207.2022.9789708

[40] Suzanne Rivoire, Parthasarathy Ranganathan, and Christos Kozyrakis. A comparison of highlevel full-system power models. HotPower, 8(2):32–39, 2008.

[41] Anton Beloglazov, Rajkumar Buyya, Young Choon Lee, and Albert Zomaya. A taxonomy and survey of energy-efficient data centers and cloud computing systems. Advances in computers, 82:47–111, 2011.

DOI: 10.1016/b978-0-12-385512-1.00003-7

[42] Xiaobo Fan, Wolf-Dietrich Weber, and Luiz Andre Barroso. Power provisioning for a warehouse-sized computer. ACM SIGARCH computer architecture news, 35(2):13–23, 2007.

DOI: 10.1145/1273440.1250665

[43] Gianluca Bontempi, Souhaib Ben Taieb, and Yann-Aël Le Borgne. Machine learning strategies for time series forecasting. In European business intelligence summer school, pages 62–77. Springer, 2012.

DOI: 10.1007/978-3-642-36318-4_3

[44] Sima Siami-Namini, Neda Tavakoli, and Akbar Siami Namin. A comparison of arima and lstm in forecasting time series. In 2018 17th IEEE international conference on machine learning and applications (ICMLA), pages 1394–1401. IEEE, 2018.

DOI: 10.1109/icmla.2018.00227

[45] Débora SPENASSATO, Andréa C TRIERWEILLER, Antonio Cezar BORNIA, and Lorenzo Sanfelice FRAZZON. Dow jones sustainability index: Use of forecasting models to assist decision making. Revista ESPACIOS| Vol. 36 (Nº 11) Año 2015, 2015.

[46] Facebook. Forecasting at scale. https://facebook.github.io/prophet/, 2023. [Online; accessed 22-March-2023].

[47] Srinidhi Hiriyannaiah, AMD Srinivas, Gagan K Shetty, GM Siddesh, and KG Srinivasa. A computationally intelligent agent for detecting fake news using generative adversarial networks. In Hybrid Computational Intelligence, pages 69–96. Elsevier, 2020.

DOI: 10.1016/b978-0-12-818699-2.00004-4

[48] Jian Zheng, Cencen Xu, Ziang Zhang, and Xiaohua Li. Electric load forecasting in smart grids using long-short-term-memory based recurrent neural network. In 2017 51st Annual conference on information sciences and systems (CISS), pages 1–6. IEEE, 2017.

DOI: 10.1109/ciss.2017.7926112

[49] Ke Yan, Xudong Wang, Yang Du, Ning Jin, Haichao Huang, and Hangxia Zhou. Multi-step short-term power consumption forecasting with a hybrid deep learning strategy. Energies, 11(11):3089, 2018.

DOI: 10.3390/en11113089

[50] Manoel C Silva Filho, Raysa L Oliveira, Claudio C Monteiro, Pedro RM Inácio, and Mário M Freire. Cloudsim plus: a cloud computing simulation framework pursuing software engineering principles for improved modularity, extensibility and correctness. In 2017 IFIP/IEEE symposium on integrated network and service management (IM), pages 400–406. IEEE, 2017.

DOI: 10.23919/inm.2017.7987304

[51] Google. Google Cluster Workload Traces 2019. https://research.google/resources/ datasets/google-cluster-workload-traces-2019/, 2023. [Online; accessed 03-April- 2023].

DOI: 10.1109/infcomw.2016.7562213

[52] Python – Coefficient of Determination-R2 score. https://www.geeksforgeeks.org/ python-coefficient-of-determination-r2-score/. [Online; accessed 09-August-2022].

[53] MAE and RMSE — Which Metric is Better? https://medium.com/ human-in-a-machine-world/mae-and-rmse-which-metric-is-better-e60ac3bde13d.

[54] Taghreed Balharith and Fahd Alhaidari. Round robin scheduling algorithm in cpu and cloud computing: a review. In 2019 2nd International Conference on Computer Applications & Information Security (ICCAIS), pages 1–7. IEEE, 2019.

DOI: 10.1109/cais.2019.8769534

[55] Ziqian Dong, Wenjie Zhuang, and Roberto Rojas-Cessa. Energy-aware scheduling schemes for cloud data centers on google trace data. In 2014 IEEE Online Conference on Green Communications (OnlineGreencomm), pages 1–6. IEEE, 2014.

DOI: 10.1109/onlinegreencom.2014.7114422