An intelligent approach for predicting resource usage by combining decomposition techniques with NFTS network
- PDF / 1,836,030 Bytes
- 26 Pages / 595.276 x 790.866 pts Page_size
- 71 Downloads / 163 Views
(0123456789().,-volV)(0123456789().,-volV)
An intelligent approach for predicting resource usage by combining decomposition techniques with NFTS network Seyedeh Yasaman Rashida1 • Masoud Sabaei2 • Mohammad Mehdi Ebadzadeh2 • Amir Masoud Rahmani1 Received: 21 September 2019 / Revised: 13 March 2020 / Accepted: 22 March 2020 Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Time sensitive virtual machines that run real-time control tasks are constrained by hard timing requirements. Optimal resource management and guarantee the hard timing requirements of virtual machines are critical goals. Basically, cloud resource usage predicting and resource reservation play a crucial role to achieve these two goals. So, we propose a predicting approach based on two-phase decomposition method and hybrid neural network to predict future resource usage. This paper uses a clustering method based on the AnYa algorithm in an on-line manner in order to obtain the number of fuzzy rules and the initial value of the premise and consequent parameters. Since cloud resource usage varies widely from time to time and server to server, extracting the best time series model for predicting cloud resource usage depend not only on time but on the cloud resource usage trend. For this, we present a recursive hybrid technique based on singular spectrum analysis and adaptively fast ensemble empirical mode decomposition to identify the hidden characteristics of the time series data. This method tries to extract seasonal and irregular components of the time series. According to the simulation results, it can be found that the proposed model can have significantly better performance than the three comparison models from one-step to six-step CPU usage predictions with the MAPE of 33.83% average performance promotion, MAE of 36.54% average performance promotion, RMSE of 36.70% average performance promotion. Keywords Takagi–Sugeno network Singular spectrum analysis (SSA) Adaptive fast EEMD (AFEEMD) Cloud computing Future resource usage
1 Introduction Cloud computing has been widely used in various fields with the advantages of plenty of resource provision and pay-as-you-go model [1]. Resources are distributed & Masoud Sabaei [email protected] Seyedeh Yasaman Rashida [email protected] Mohammad Mehdi Ebadzadeh [email protected] Amir Masoud Rahmani [email protected] 1
Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
2
Department of Computer Engineering and Information Technology, Amir Kabir University of Technology, Tehran, Iran
geographically in different datacenters of cloud which are virtualized and allocated to the user applications. The applications can consist of hard real-time control tasks, which have strict timing requirements expressed as hard deadlines [2]. They could also be grouped into on–off, high-growth, periodic and aperiodic-burst depending on their workload [3]. Different user applications may require different on-demand resources with par
Data Loading...
