Latency-Based Analytic Approach to Forecast Cloud Workload Trend for Sustainable Datacenters

Abstract

Cloud datacentres are turning out to be massive energy consumers and environment polluters, which necessitate the need for promoting sustainable computing approaches for achieving environment-friendly datacentre execution. Direct causes of excess energy consumption of the datacentre include running servers at low level of workloads and over-provisioning of server resources to the arriving workloads during execution. To this end, predicting the future workload demands and their respective behaviours at the datacentres are being the focus of recent research in the context of sustainable datacentres. But prediction analytics of Cloud ds suffer various limitations imposed by the dynamic and unclear characteristics of Cloud workloads. This paper proposes a novel forecasting model named K-RVLBPNN (K-means based Rand Variable Learning Rate Backpropagation Neural Network) for predicting the future workload arrival trend, by exploiting the latency sensitivity characteristics of Cloud workloads, based on a combination of improved K-means clustering algorithm and BPNN (Backpropagation Neural Network) algorithm. Experiments conducted on real-world Cloud datasets exhibit that the proposed model exhibits better prediction accuracy, outperforming traditional Hidden Markov Model, Naïve Bayes Classifier and our earlier RVLBPNN model respectively.

A GRU-Based Prediction Framework for Intelligent Resource Management at Cloud Data Centres in the Age of 5G

“…Section VII concludes the paper, along with outlining our future research directions. [11]uses a variety of realistic policies and realistic test scenarios to analyse the impact of virtual machine allocation on resource consumption. This work have claimed that the total resource and energy usage can be reduced through the deployment of special allocation policies within various virtual machines.…”

“…In the recent years, with the breakthrough and development of AI (Artificial Intelligence) technology, the ways of achieving smart resource management are shifting directions. Researchers are attempting to exploit AI to optimise resource management in data centres [11] [16]- [18]. A LSTM neural network model has been used to predict the arrival number of jobs to schedule computational jobs in the works of [16]and [17].An improved N-LSTM [18] has been proposed to predict the anticipated amounts of workloads at the VM-level within a short-term.…”

“…A LSTM neural network model has been used to predict the arrival number of jobs to schedule computational jobs in the works of [16]and [17].An improved N-LSTM [18] has been proposed to predict the anticipated amounts of workloads at the VM-level within a short-term. A latency-based prediction approach has been proposed, which integrates the K-means clustering algorithm with an improved BP neural network [11] with the intention of forecasting the task-level CPU and memory consumption levels. Compared with the traditional statistical methods, AI models are more adept at capturing the internal characteristics of Cloud workload data.…”