BiPhase adaptive learning-based neural network model for cloud datacenter workload forecasting
- PDF / 5,885,531 Bytes
- 18 Pages / 595.276 x 790.866 pts Page_size
- 20 Downloads / 209 Views
METHODOLOGIES AND APPLICATION
BiPhase adaptive learning-based neural network model for cloud datacenter workload forecasting Jitendra Kumar1,2 · Deepika Saxena2 · Ashutosh Kumar Singh2 · Anand Mohan3
© Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Cloud computing promises elasticity, flexibility and cost-effectiveness to satisfy service level agreement conditions. The cloud service providers should plan and provision the computing resources rapidly to ensure the availability of infrastructure to match the demands with closed proximity. The workload prediction has become critical as it can be helpful in managing the infrastructure effectively. In this paper, we present a workload forecasting framework based on neural network model with supervised learning technique. An improved and adaptive differential evolution algorithm is developed to improve the learning efficiency of predictive model. The algorithm is capable of optimizing the best suitable mutation operator and crossover operator. The prediction accuracy and convergence rate of the learning are observed to be improved due to its adaptive behavior in pattern learning from sampled data. The predictive model’s performance is evaluated on four real-world data traces including Google cluster trace and NASA Kennedy Space Center logs. The results are compared with stateof-the-art methods, and improvements up to 91%, 97% and 97.2% are observed over self-adaptive differential evolution, backpropagation and average-based workload prediction techniques, respectively. Keywords Adaptive learning · Cloud computing · Differential evolution · Ring crossover · Heuristic crossover · Uniform crossover · Workload forecasting
1 Introduction Cloud computing has emerged as an indispensable computing paradigm across the globe. It has enabled us to share IT resources among multiple users ubiquitously. It has been widely adopted in numerous fields including academics, medicine, image processing, research industry, business, government and private sectors, etc. In 2017, a survey estimated that about 90% enterprise workloads will be shifted on cloud infrastructure by 2021 (Credit Suisse 2017). The scalability and elasticity of resources are two prominent features of cloud computing that make on-demand computing and storCommunicated by V. Loia.
B
Jitendra Kumar [email protected]
1
Department of Computer Engineering and Applications, GLA University, Mathura, India
2
Department of Computer Applications, National Institute of Technology, Kurukshetra, Kurukshetra, India
3
Department of Electronics Engineering, Indian Institute of Technology-BHU Varanasi, Varanasi, India
age services available to the users (Wu et al. 2017; Herbst et al. 2013). However, it has been observed that there is lot of variation in user’s resource demand and actual usage (Alam et al. 2016) that needs to be addressed carefully to reduce wastage of resources at the datacenter. The cloud datacenters must be equipped with an effective resource provisioning approach to maximize the r
Data Loading...
