VTGAN: hybrid generative adversarial networks for cloud workload prediction
Abstract Efficient resource management approaches have become a fundamental challenge for distributed systems, especially dynamic environment systems such as cloud computing data centers. These approaches aim at load-balancing or minimizing power consumption. Due to the highly dynamic nature of clou...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-06-01
|
| Series: | Journal of Cloud Computing: Advances, Systems and Applications |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13677-023-00473-z |
| _version_ | 1797789599629574144 |
|---|---|
| author | Aya I. Maiyza Noha O. Korany Karim Banawan Hanan A. Hassan Walaa M. Sheta |
| author_facet | Aya I. Maiyza Noha O. Korany Karim Banawan Hanan A. Hassan Walaa M. Sheta |
| author_sort | Aya I. Maiyza |
| collection | DOAJ |
| description | Abstract Efficient resource management approaches have become a fundamental challenge for distributed systems, especially dynamic environment systems such as cloud computing data centers. These approaches aim at load-balancing or minimizing power consumption. Due to the highly dynamic nature of cloud workloads, traditional time series and machine learning models fail to achieve accurate predictions. In this paper, we propose novel hybrid VTGAN models. Our proposed models not only aim at predicting future workloads but also predicting the workload trend (i.e., the upward or downward direction of the workload). Trend classification could be less complex during the decision-making process in resource management approaches. Also, we study the effect of changing the sliding window size and the number of prediction steps. In addition, we investigate the impact of enhancing the features used for training using the technical indicators, Fourier transforms, and wavelet transforms. We validate our models using a real cloud workload dataset. Our results show that VTGAN models outperform traditional deep learning and hybrid models, such as LSTM/GRU and CNN-LSTM/GRU, concerning cloud workload prediction and trend classification. Our proposed model records an upward prediction accuracy ranging from $$95.4\%$$ 95.4 % to $$96.6\%$$ 96.6 % . |
| first_indexed | 2024-03-13T01:52:58Z |
| format | Article |
| id | doaj.art-e08e7f35a8d44e0aa4b516872a4ba69f |
| institution | Directory Open Access Journal |
| issn | 2192-113X |
| language | English |
| last_indexed | 2024-03-13T01:52:58Z |
| publishDate | 2023-06-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Cloud Computing: Advances, Systems and Applications |
| spelling | doaj.art-e08e7f35a8d44e0aa4b516872a4ba69f2023-07-02T11:27:00ZengSpringerOpenJournal of Cloud Computing: Advances, Systems and Applications2192-113X2023-06-0112113110.1186/s13677-023-00473-zVTGAN: hybrid generative adversarial networks for cloud workload predictionAya I. Maiyza0Noha O. Korany1Karim Banawan2Hanan A. Hassan3Walaa M. Sheta4Department of Electrical Engineering, Faculty of Engineering, Alexandria UniversityDepartment of Electrical Engineering, Faculty of Engineering, Alexandria UniversityDepartment of Electrical Engineering, Faculty of Engineering, Alexandria UniversityInformatics Research Institute, City of Scientific Research and Technological Applications (SRTA-City)Informatics Research Institute, City of Scientific Research and Technological Applications (SRTA-City)Abstract Efficient resource management approaches have become a fundamental challenge for distributed systems, especially dynamic environment systems such as cloud computing data centers. These approaches aim at load-balancing or minimizing power consumption. Due to the highly dynamic nature of cloud workloads, traditional time series and machine learning models fail to achieve accurate predictions. In this paper, we propose novel hybrid VTGAN models. Our proposed models not only aim at predicting future workloads but also predicting the workload trend (i.e., the upward or downward direction of the workload). Trend classification could be less complex during the decision-making process in resource management approaches. Also, we study the effect of changing the sliding window size and the number of prediction steps. In addition, we investigate the impact of enhancing the features used for training using the technical indicators, Fourier transforms, and wavelet transforms. We validate our models using a real cloud workload dataset. Our results show that VTGAN models outperform traditional deep learning and hybrid models, such as LSTM/GRU and CNN-LSTM/GRU, concerning cloud workload prediction and trend classification. Our proposed model records an upward prediction accuracy ranging from $$95.4\%$$ 95.4 % to $$96.6\%$$ 96.6 % .https://doi.org/10.1186/s13677-023-00473-zCloud computingWorkload predictionGANLSTMGRUConvolution neural network |
| spellingShingle | Aya I. Maiyza Noha O. Korany Karim Banawan Hanan A. Hassan Walaa M. Sheta VTGAN: hybrid generative adversarial networks for cloud workload prediction Journal of Cloud Computing: Advances, Systems and Applications Cloud computing Workload prediction GAN LSTM GRU Convolution neural network |
| title | VTGAN: hybrid generative adversarial networks for cloud workload prediction |
| title_full | VTGAN: hybrid generative adversarial networks for cloud workload prediction |
| title_fullStr | VTGAN: hybrid generative adversarial networks for cloud workload prediction |
| title_full_unstemmed | VTGAN: hybrid generative adversarial networks for cloud workload prediction |
| title_short | VTGAN: hybrid generative adversarial networks for cloud workload prediction |
| title_sort | vtgan hybrid generative adversarial networks for cloud workload prediction |
| topic | Cloud computing Workload prediction GAN LSTM GRU Convolution neural network |
| url | https://doi.org/10.1186/s13677-023-00473-z |
| work_keys_str_mv | AT ayaimaiyza vtganhybridgenerativeadversarialnetworksforcloudworkloadprediction AT nohaokorany vtganhybridgenerativeadversarialnetworksforcloudworkloadprediction AT karimbanawan vtganhybridgenerativeadversarialnetworksforcloudworkloadprediction AT hananahassan vtganhybridgenerativeadversarialnetworksforcloudworkloadprediction AT walaamsheta vtganhybridgenerativeadversarialnetworksforcloudworkloadprediction |