Predicting provisioning and booting times in a Metal-as-a-service system

Cloud management automation and management of SLA incidents become a research challenges for any Cloud service-based system. In the era of ongoing adoption of Cloud Computing at a fast rate the Metal-as-a-service (MaaS) platforms assure a higher level of performance, but at the cost of a more complex provisioning system, all of these being imposed by SLA assurance. More, disaster recovery and critical infrastructure protection become important aspects for any real-time applications that use Cloud Services. This paper deals with the problem of predicting provisioning and booting times in a MaaS system, and proposed a solution based on platform monitoring and a multi-variate regression algorithm. The configuration, provisioning flow, and capacity management capabilities were tested on Bigstep Full Metal Cloud platform an event-based tracking system, based on which provisioning times can be calculated for each individual element. We analyzed the performance of proposed solution by comparing the predicted booting and provisioning times with real times using different scenarios. Architecture, entities and operations for a MaaS system.Provisioning flow and stages.Regression-based prediction algorithm for booting time.Performance evaluation of instances and cluster provisioning.

[1]  Florin Pop,et al.  MaaS advanced provisioning and reservation system , 2015, AIMC '15.

[2]  Ryszard Kowalczyk,et al.  Policy-Based Automation of SLA Establishment for Cloud Computing Services , 2012, 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012).

[3]  Elizabeth Chang,et al.  Conceptual SLA framework for cloud computing , 2010, 4th IEEE International Conference on Digital Ecosystems and Technologies.

[4]  Florin Pop,et al.  Asymptotic scheduling for many task computing in Big Data platforms , 2015, Inf. Sci..

[5]  Ciprian Dobre,et al.  Resource usage prediction algorithms for optimal selection of multimedia content delivery methods , 2015, 2015 IEEE International Conference on Communications (ICC).

[6]  George Mastorakis,et al.  Resource usage prediction for optimal and balanced provision of multimedia services , 2014, 2014 IEEE 19th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD).

[7]  Prashant J. Shenoy,et al.  A flexible elastic control plane for private clouds , 2013, CAC.

[8]  Christos Faloutsos,et al.  Storage device performance prediction with CART models , 2004, The IEEE Computer Society's 12th Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, 2004. (MASCOTS 2004). Proceedings..

[9]  Doina Precup,et al.  Combining TD-learning with Cascade-correlation Networks , 2003, ICML.

[10]  George Mastorakis,et al.  Efficient entertainment services provision over a novel network architecture , 2016, IEEE Wireless Communications.

[11]  Kazuhiko Kato,et al.  Improving Agility and Elasticity in Bare-metal Clouds , 2015, ASPLOS.

[12]  Xiaodong Zhang,et al.  Erratum: "An Effective and Practical Performance Prediction Model for Parallel Computing on Nondedicated Heterogeneous NOW" , 1997, J. Parallel Distributed Comput..

[13]  Evangelos Kotsovinos.  Challenges in building a real, large private cloud , 2012, VEE '12.

[14]  Valentin Cristea,et al.  Optimizing the Energy Efficiency of Message Exchanging for Service Distribution in Interoperable Infrastructures , 2012, 2012 Fourth International Conference on Intelligent Networking and Collaborative Systems.

[15]  John Bresnahan,et al.  Managing appliance launches in infrastructure clouds , 2011, TG.

[16]  Valentin Cristea,et al.  Resource-aware hybrid scheduling algorithm in heterogeneous distributed computing , 2015, Future Gener. Comput. Syst..

[17]  Kevin Lee,et al.  Empirical prediction models for adaptive resource provisioning in the cloud , 2012, Future Gener. Comput. Syst..

[18]  Samuel A. Ajila,et al.  Using Machine Learning Algorithms for Cloud Client Prediction Models in a Web VM Resource Provisioning Environment , 2016 .

[19]  Valentin Cristea,et al.  Decomposition Based Algorithm for State Prediction in Large Scale Distributed Systems , 2010, 2010 Ninth International Symposium on Parallel and Distributed Computing.

[20]  George Mastorakis,et al.  Predicting and quantifying the technical debt in cloud software engineering , 2014, 2014 IEEE 19th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD).

[21]  K. Saravanan,et al.  Optimizing the Cost for Resource Subscription Policy in IaaS Cloud , 2014, ArXiv.

[22]  Jacob Cohen,et al.  Applied multiple regression/correlation analysis for the behavioral sciences , 1979 .

[23]  Peter Vamplew,et al.  Global Versus Local Constructive Function Approximation for On-Line Reinforcement Learning , 2005, Australian Conference on Artificial Intelligence.