A bipolar resource management framework for resource provisioning in Cloud’s virtualized environment

•In this paper a novel bipolar framework is proposed for improving efficiency in Cloud’s resource provisioning.•The proposed bipolar framework enables the cloud provider to provide resources for clients’ requests proactively based on demands rather than conventional workload based predictive resource allocation.•Artificial neural networks are employed to provide anticipation for demand.

Cloud’s profitability is mainly driven by the business, and on the other hand, a successful business is hardly geared with clients’ satisfaction. Therefore, there is high competition between cloud providers for satisfying clients and attracting more of them. In this way, long term business success factors should also be considered in addition to short term profit factors regarded in conventional resource provisioning procedures. Conventional resource management approaches to achieve short term profit inevitably lead to job rejection and violation from response time based SLAs while short response time and low job rejection are of those important factors to clients’ satisfaction. Therefore, this paper proposes a novel bipolar resource management framework which results in preventing from job rejection and having considerably reduced violations from response time based SLAs as well as providing short term profits. The proposed framework uses a neural network based predictor and genetic algorithm for optimal resource management through live migration. It also employs a prediction based temporal infinite pool, called the temporal cloud, which regards job rejection prevention. The evaluation of the proposed framework demonstrates that it can provide short term profits, beside it prevents from job rejection and reduces response time violations considerably.

Graphical abstractFigure optionsDownload full-size imageDownload as PowerPoint slide