Auto-adaptive learning-based workload forecasting in dynamic cloud environment. Issue 6 (3rd June 2022)

• Record Type: Journal Article
• Authors: Saxena, Deepika; Singh, Ashutosh Kumar
• Is Part Of: International journal of computers and applications. Volume 44:Issue 6(2022)
• Page Start: 541
• Page End: 551
• Publication Date: 2022-06-03
• Subjects: Accuracy -- cloud computing -- data center -- differential evolution -- neural network -- workload forecasting; Computers -- Periodicals; Computer software -- Periodicals; Computer networks -- Periodicals; Multimedia systems -- Periodicals; Internet -- Periodicals; World Wide Web -- Periodicals; Minicomputers -- Periodicals; Microcomputers -- Periodicals; 004.05
• DOI: 10.1080/1206212X.2020.1830245
• Languages: English
• ISSNs: 1206-212X

Abstract

Abstract : To maintain elasticity and scalability of resources at cloud data centers, future workload prediction has become an indispensable requirement. However, there is high variance in resource demands, due to sudden peaks, drop of workload, noise and redundancy in user demands, that hinders accurate workload forecast. This article aims to present workload prediction adaptive neural network model to forecast average workload over consecutive prediction intervals in anticipation. The prediction model adaptively learns traces of workload for particular prediction interval from historical data by applying proposed novel Auto Adaptive Differential Evolution (AADE) algorithm. The two benchmark datasets viz. NASA and Saskatchewan HTTP traces are used for evaluating the performance of the proposed work. Experimental results reveal that AADE-trained neural network outperforms state-of-the-art schemes and achieves accuracy improvement upto 98.9%, 97.4% and 94.8% compared to Average, Backpropagation (BP) and Self adaptive Differential Evolution (SaDE) learning based workload prediction schemes respectively. In addition, the speed of convergence of AADE learning algorithm is observed to be 2-10 times faster than BP and SaDE based forecasting approaches for both datasets.