Efficient resource provisioning for elastic Cloud services based on machine learning techniques

Abstract

Automated resource provisioning techniques enable the implementation of elastic services, by adapting the available resources to the service demand. This is essential for reducing power consumption and guaranteeing QoS and SLA fulfillment, especially for those services with strict QoS requirements in terms of latency or response time, such as web servers with high traffic load, data stream processing, or real-time big data analytics. Elasticity is often implemented in cloud platforms and virtualized data-centers by means of auto-scaling mechanisms. These make automated resource provisioning decisions based on the value of specific infrastructure and/or service performance metrics. This paper presents and evaluates a novel predictive auto-scaling mechanism based on machine learning techniques for time series forecasting and queuing theory. The new mechanism aims to accurately predict the processing load of a distributed server and estimate the appropriate number of resources that must be provisioned in order to optimize the service response time and fulfill the SLA contracted by the user, while attenuating resource over-provisioning in order to reduce energy consumption and infrastructure costs. The results show that the proposed model obtains a better forecasting accuracy than other classical models, and makes a resource allocation closer to the optimal case.

Optimizing Energy Efficiencies in Cloud Data Center Resources with Availability Constraints

“…There have also been approaches which have looked to manage the responsiveness and Latency to ensure Availability during high workload, by using Multipathing and using the multiple paths for Availability through redundancy [131] or by using predictive ML-based Auto scaling mechanisms which manage responsiveness and latency aligned to the QoS expectation [132], or by avoiding congestion through per packet-based energy-aware segment routing and load balancing in SDNs while turning of links for energy efficiencies [133].…”

Design o f a Fault Tolerant Strategy f or Resource Scheduling i n Cloud Environment

“…The number of cloudlets successfully completed by the is given by and the number of cloudlets failed to be executed by is given by . The failure_rate of can be calculated as (2) The ready time of is defined s the time by which the VM completes the previously assigned cloudlets and become ready to execute the current . This is given by…”

“…In industrial terms, offering software is referred as Software as a Service (SaaS), offering platforms is referred as Platform as a Service (PaaS) and offering infrastructure is referred as Infrastructure as a Service (IaaS). Many computing service providers including Google, Microsoft, Yahoo and IBM are rapidly deploying data centers in various locations around the world to deliver Cloud computing services [2].…”

Load Balancing for Effective Resource Provisioning in a Heterogeneous Cluster using Machine Learning

“…Machine learning techniques [1] for time series forecasting and queuing theory have been used to conceptually estimate the appropriate number of resources that must be provisioned by predicting the server's load in a distributed environment. This might guarantee user's SLA requirements and optimize the service response time.…”