@article {Longo201737, title = {An approach for resiliency quantification of large scale systems}, journal = {Performance Evaluation Review}, volume = {44}, number = {4}, year = {2017}, note = {cited By 0}, pages = {37-48}, publisher = {Association for Computing Machinery}, abstract = {

We quantify the resiliency of large scale systems upon changes encountered beyond the normal system behavior. Formal definitions for resiliency and change are provided together with general steps for resiliency quantification and a set of resiliency metrics that can be used to quantify the effects of changes. A formalization of the approach is also shown in the form of a set of four algorithms that can be applied when large scale systems are modeled through stochastic analytic state space models (monolithic models or interacting sub-models). In particular, in the case of interacting submodels, since resiliency quantification involves understanding the transient behavior of the system, fixed-point variables evolve with time leading to non-homogenous Markov chains. At the best of our knowledge, this is the first paper facing this problem in a general way. The proposed approach is applied to an Infrastructure-As-A-Service (IaaS) Cloud use case. Specifically, we assess the impact of changes in demand and available capacity on the Cloud resiliency and we show that the approach proposed in this paper can scale for a real sized Cloud without significantly compromising the accuracy.

}, keywords = {Available capacity, Chains, Formal definition, Homogenous Markov chain, Infrastructure as a service (IaaS), Large scale systems, Markov processes, Non-homogeneous, Resiliency quantification, State - space models, State space methods, Stochastic models, Stochastic systems, Submodels, Transient behavior}, issn = {01635999}, doi = {10.1145/3092819.3092825}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85019853222\&doi=10.1145\%2f3092819.3092825\&partnerID=40\&md5=6266fffb7aad937fefad706e31fcd7da}, author = {Francesco Longo and Rahul Ghosh and Vijay K. Naik and A.J. Rindos and Kishor Trivedi} } @article {Longo201753, title = {Stack4Things: a sensing-and-actuation-as-a-service framework for IoT and cloud integration}, journal = {Annales des Telecommunications/Annals of Telecommunications - Institut Mines-T{\'e}l{\'e}com and Springer-Verlag France}, volume = {72}, number = {1-2}, year = {2017}, note = {cited By 0}, pages = {53-70}, publisher = {Springer-Verlag France}, abstract = {

With the increasing adoption of embedded smart devices and their involvement in different application fields, complexity may quickly grow, thus making vertical ad hoc solutions ineffective. Recently, the Internet of Things (IoT) and Cloud integration seems to be one of the winning solutions in order to opportunely manage the proliferation of both data and devices. In this paper, following the idea to reuse as much tooling as possible, we propose, with regards to infrastructure management, to adopt a widely used and competitive framework for Infrastructure-as-a-Service such as OpenStack. Therefore, we describe approaches and architectures so far preliminary implemented for enabling Cloud-mediated interactions with droves of sensor- and actuator-hosting nodes by presenting Stack4Things, a framework for Sensing-and-Actuation-as-a-Service (SAaaS). In particular, starting from a detailed requirement analysis, in this work, we focus on the subsystems of Stack4Things devoted to resource control and management as well as on those related to the management and collection of sensing data. Several use cases are presented justifying how our proposed framework can be viewed as a concrete step toward the complete fulfillment of the SAaaS vision. {\textcopyright} 2016, Institut Mines-T{\'e}l{\'e}com and Springer-Verlag France.

}, keywords = {Clouds, Information management, Infrastructure as a service (IaaS), Infrastructure managements, Internet of thing (IOT), Internet of Things, Mediated interaction, OpenStack, Requirement analysis, SAaaS, WAMP, WebSocket}, issn = {00034347}, doi = {10.1007/s12243-016-0528-5}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84976292948\&doi=10.1007\%2fs12243-016-0528-5\&partnerID=40\&md5=f334f652432ae0993795644204689e9c}, author = {Francesco Longo and Dario Bruneo and Salvatore Distefano and Giovanni Merlino and Antonio Puliafito} } @proceedings {Bruneo2016, title = {An IoT Testbed for the Software Defined City Vision: The $\#$SmartMe Project}, journal = {2016 IEEE International Conference on Smart Computing, SMARTCOMP 2016}, year = {2016}, note = {cited By 2; Conference of 2nd IEEE International Conference on Smart Computing, SMARTCOMP 2016 ; Conference Date: 18 May 2016 Through 20 May 2016; Conference Code:122466}, publisher = {Institute of Electrical and Electronics Engineers Inc.}, address = {St. Louis; United States; 18-20 May 2016}, abstract = {

To kickstart the process of morphing Messina into a {\guillemotleft}smart{\guillemotright} city, an explicit mission for the crowdfunded $\#$SmartME project, it is essential to set up an infrastructure of smart devices embedding sensors and actuators, to be scattered all over the urban area. An horizontal framework coupled with the Fog computing approach, by moving logic toward the {\guillemotleft}extreme{\guillemotright} edge of the Internet where data needs to be quickly elaborated, decisions made, and actions performed, is a suitable solution for data- intensive services with time-bound constraints as those usually required by citizens. This is especially true in the context of IoT and Smart City where thousands of smart objects, vehicles, mobiles, people interact to provide innovative services. We thus designed Stack4Things as an OpenStack-based framework spanning the Infrastructure-as-a-Service and Platform-as-a-Service layers. We present some of the core Stack4Things functionalities implementing a Fog computing approach towards a run- time {\guillemotleft}rewireable{\guillemotright} Smart City paradigm, by outlining node management and contextualization mechanisms, also describing its usage in terms of already supported and developed verticals, as well as a specific example related to environmental data collection through $\#$SmartME. {\textcopyright} 2016 IEEE.

}, keywords = {$\#$SmartME, Arduino, Clouds, Computation theory, IaaS, Infrastructure as a service (IaaS), Internet of Things, OpenStack, Platform as a Service (PaaS), smart cities, Stack4Things}, isbn = {9781509008988}, doi = {10.1109/SMARTCOMP.2016.7501678}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84979570937\&doi=10.1109\%2fSMARTCOMP.2016.7501678\&partnerID=40\&md5=c7d8b8c0b0cd880d9c781770a5721acc}, author = {Dario Bruneo and Salvatore Distefano and Francesco Longo and Giovanni Merlino} } @proceedings {Merlino2017213, title = {Quantitative evaluation of Cloud-based network virtualization mechanisms for IoT}, journal = {ValueTools 2016 - 10th EAI International Conference on Performance Evaluation Methodologies and Tools}, year = {2016}, note = {cited By 0; Conference of 10th EAI International Conference on Performance Evaluation Methodologies and Tools, ValueTools 2016 ; Conference Date: 25 October 2016 Through 28 October 2016; Conference Code:127816}, pages = {213-216}, publisher = {Association for Computing Machinery}, address = {Taormina; Italy; 25-28 October 2016}, abstract = {

Integration of the Internet of Things (IoT) with the Cloud may lead to a range of different architectures and solutions. Our efforts in this domain are mainly geared towards making IoT systems available as service-oriented infrastructure. Under Infrastructure-as-a-Service (IaaS) scenarios, network virtualization is a core building block of any solution, even more so for IoT-focused Cloud providers. Enabling mechanisms are required to support virtualization of the networking facilities for IoT resources that are managed by the Cloud. This work describes an approach to network virtualization based on popular off-the-shelf tools and protocols in place of application-specific logic, acting as a blueprint in the design of the Stack4Things architecture, an OpenStack-derived framework to provide IaaS-like services from a pool of IoT devices. We quantitatively evaluate the underlying mechanisms demonstrating that the proposed approach exhibits mostly comparable performance with respect to standard technologies for virtual private networks, or at least good enough for the kind of underlying hardware, e.g., smart boards, whilst still representing a more flexible solution. Copyright {\textcopyright} 2016 EAI.

}, keywords = {Application specific, Clouds, Distributed computer systems, Infrastructure as a service (IaaS), Internet of thing (IOT), Internet of Things, Network architecture, network virtualization, OpenStack, Performance evaluation, Platform as a Service (PaaS), Quantitative evaluation, Reverse tunneling, Service-oriented infrastructures, Virtual private networks, Virtual reality, Virtualization}, isbn = {9781631901416}, doi = {10.4108/eai.25-10-2016.2266600}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85021354856\&doi=10.4108\%2feai.25-10-2016.2266600\&partnerID=40\&md5=61d1e54a06f72746e6e5bd90c920b1c0}, author = {Giovanni Merlino and Francesco Longo and Salvatore Distefano and Dario Bruneo and Antonio Puliafito} } @proceedings {Ghosh2017227, title = {Resiliency quantification for large scale systems: An IaaS cloud use case}, journal = {ValueTools 2016 - 10th EAI International Conference on Performance Evaluation Methodologies and Tools}, year = {2016}, note = {cited By 0; Conference of 10th EAI International Conference on Performance Evaluation Methodologies and Tools, ValueTools 2016 ; Conference Date: 25 October 2016 Through 28 October 2016; Conference Code:127816}, pages = {227-234}, publisher = {Association for Computing Machinery}, address = {Taormina; Italy; 25-28 October 2016}, abstract = {

We quantify the resiliency of large scale systems upon changes encountered beyond the normal system behavior. General steps for resiliency quantification are shown and resiliency metrics are defined to quantify the effects of changes. The proposed approach is illustrated through an Infrastructureas-a-Service (IaaS) Cloud use case. Specifically, we assess the impact of changes in demand and available capacity on the Cloud resiliency using interacting state-space based submodels. Since resiliency quantification involves understanding the transient behavior of the system, fixed-point variables evolve with time leading to non-homogenous Markov chains. In this paper, we present an algorithm for resiliency analysis when dealing with such non-homogenous sub-models. A comparison is shown with our past research, where we quantified the resiliency of IaaS Cloud performance using a one level monolithic model. Numerical results show that the approach proposed in this paper can scale for a real sized Cloud without significantly compromising the accuracy. Copyright {\textcopyright} 2016 EAI.

}, keywords = {Available capacity, Chains, Clouds, Homogenous Markov chain, Impact of changes, Infrastructure as a service (IaaS), Large scale systems, Markov processes, Non-homogeneous, Numerical results, Resiliency, Submodels, Transient behavior}, isbn = {9781631901416}, doi = {10.4108/eai.25-10-2016.2266805}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85021320622\&doi=10.4108\%2feai.25-10-2016.2266805\&partnerID=40\&md5=a6167b2554cad8a9aae02963254c8b52}, author = {Rahul Ghosh and Francesco Longo and Vijay K. Naik and A.J. Rindos and Kishor Trivedi} } @proceedings {Bruneo2015797, title = {Analytical Modeling of Reactive Autonomic Management Techniques in IaaS Clouds}, journal = {Proceedings - 2015 IEEE 8th International Conference on Cloud Computing, CLOUD 2015}, year = {2015}, note = {cited By 2; Conference of 8th IEEE International Conference on Cloud Computing, CLOUD 2015 ; Conference Date: 27 June 2015 Through 2 July 2015; Conference Code:116940}, pages = {797-804}, publisher = {Institute of Electrical and Electronics Engineers Inc.}, address = {New York (USA)}, abstract = {

Cloud computing infrastructures provide services to a wide number of users whose behavior can deeply change at the occurrence of particular events. To correctly handle such situations a cloud infrastructure have to be reconfigured in a way that does not cause degradation in the overall performance. Otherwise, the quality of service specified in the service level agreement could be violated. To prevent such situations, the infrastructure could be organized as an autonomic system where self-adaptation and self-configuration techniques are implemented. Appropriate design choices become important in order not to fail in this goal. We propose a technique, based on a Petri net model and a specific analytical analysis approach, to represent Infrastructure-as-a-Service (IaaS) systems in the case in which the load conditions can suddenly change and reactive autonomic management techniques are applied to mitigate the consequences of the change. The model we propose is able to appropriately evaluate performance metrics in such critical situations making it suitable as a design tool for IaaS cloud systems. {\textcopyright} 2015 IEEE.

}, keywords = {Autonomic management, cloud computing, Cloud computing infrastructures, Cloud infrastructures, Iaas clouds, Industrial management, Infrastructure as a service (IaaS), Performance metrics, Petri nets, Quality of service, Resiliency, Service Level Agreements, Stochastic reward nets, Stochastic systems}, isbn = {9781467372879}, doi = {10.1109/CLOUD.2015.110}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84960155425\&doi=10.1109\%2fCLOUD.2015.110\&partnerID=40\&md5=2aa09923889aea0bc667deb1d6d250d8}, author = {Dario Bruneo and Francesco Longo and Rahul Ghosh and Marco Scarpa and Antonio Puliafito and Kishor Trivedi} } @proceedings {Bruneo201524, title = {Enabling collaborative development in an open stack testbed: The cloud wave use case}, journal = {Proceedings of the 7th International Workshop on Principles of Engineering Service-Oriented and Cloud Systems (PESOS 2015)}, year = {2015}, note = {cited By 0; Conference of 7th International Workshop on Principles of Engineering Service-Oriented and Cloud Systems, PESOS 2015 ; Conference Date: 23 May 2015; Conference Code:117285}, pages = {24-30}, publisher = {IEEE Computer Society}, address = {Florence, Italy, 23 May 2015 - }, abstract = {

The Cloud Wave project embodies a challenging set of goals, including the development of software components that have to be integrated into a single multi-layer Cloud stack based on Open Stack, while cutting across the Infrastructure-as-a-Service, Platform-as-a-Service, and Software-as-a-Service levels by targeting layer-spanning issues such as Feedback-Driven Development and Coordinated Adaptation. A DevOps-ready test bed environment should allow project partners to exert full control over deployed compo entry and collaborate on development. Goals include providing a flexible infrastructure capable of emulating several multi-node Cloud environments, as well as enabling the automatic deployment of Cloud Wave artifacts into such environment in order to simplify integration activities. This paper takes a snapshot of the current situation with regards to the design and implementation of such a setup, trying to gain relevant insight out of this effort. {\textcopyright} 2015 IEEE.

}, keywords = {Automatic deployments, cloud computing, Collaborative development, Continuous integrations, Design and implementations, DevOps, Distributed computer systems, Infrastructure as a service (IaaS), Integration, OpenStack, Platform as a Service (PaaS), Software as a service (SaaS), Test bed environment, Testbeds, Virtual infrastructures}, isbn = {9781479919345}, issn = {21567921}, doi = {10.1109/PESOS.2015.12}, url = {http://www.scopus.com/inward/record.url?eid=2-s2.0-84955273627\&partnerID=40\&md5=3fed56f69ce2ffdc46abcdf129e1e355}, author = {Dario Bruneo and Francesco Longo and Giovanni Merlino and Nicola Peditto and Carmelo Romeo and Fabio Verboso and Antonio Puliafito} } @proceedings {Merlino2015268, title = {Enabling mechanisms for Cloud-based network virtualization in IoT}, journal = {IEEE World Forum on Internet of Things, WF-IoT 2015 - Proceedings}, year = {2015}, note = {cited By 3; Conference of 2nd IEEE World Forum on Internet of Things, WF-IoT 2015 ; Conference Date: 14 December 2015 Through 16 December 2015; Conference Code:119271}, pages = {268-273}, publisher = {Institute of Electrical and Electronics Engineers Inc.}, address = {Milan (Italy)}, abstract = {

As part of a wider effort in integrating Internet of things (IoT) with the Cloud under the guise of infrastructure to be provided as-a-Service, network virtualization plays an essential role, both as an enabler of Infrastructure-as-a-Service scenarios and as a basic building block of the solution for the IoT-focused Cloud provider. Virtualization of the networking facilities for Cloud-managed IoT resources needs mechanisms to deal with the inherent complexity. This work outlines an implementation-agnostic approach to such a problem, reflected in our evolving Stack4Things architecture, derived from OpenStack, and implemented starting from such codebase, by leveraging also a choice of modern tooling and protocols. A specific use case and the discussion that follows are provided to frame the benefits of this strategy. {\textcopyright} 2015 IEEE.

}, keywords = {Basic building block, Cloud providers, Clouds, Complex networks, Infrastructure as a service (IaaS), Inherent complexity, Internet, Internet of Things, Internet of Things (IOT), Network architecture, network virtualization, OpenStack, Virtual reality, Virtualizations, WebSocket}, isbn = {9781509003655}, doi = {10.1109/WF-IoT.2015.7389064}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84964453184\&doi=10.1109\%2fWF-IoT.2015.7389064\&partnerID=40\&md5=555a2a5aad4f3af24fac04fc0e4a8280}, author = {Giovanni Merlino and Dario Bruneo and Salvatore Distefano and Francesco Longo and Antonio Puliafito} } @article {Merlino201516314, title = {A smart city lighting case study on an OpenStack-powered infrastructure}, journal = {Sensors}, volume = {15}, number = {7}, year = {2015}, note = {cited By 0}, pages = {16314-16335}, publisher = {MDPI AG}, abstract = {

The adoption of embedded systems, mobile devices and other smart devices keeps rising globally, and the scope of their involvement broadens, for instance, in smart city-like scenarios. In light of this, a pressing need emerges to tame such complexity and reuse as much tooling as possible without resorting to vertical ad hoc solutions, while at the same time taking into account valid options with regard to infrastructure management and other more advanced functionalities. Existing solutions mainly focus on core mechanisms and do not allow one to scale by leveraging infrastructure or adapt to a variety of scenarios, especially if actuators are involved in the loop. A new, more flexible, cloud-based approach, able to provide device-focused workflows, is required. In this sense, a widely-used and competitive framework for infrastructure as a service, such as OpenStack, with its breadth in terms of feature coverage and expanded scope, looks to fit the bill, replacing current application-specific approaches with an innovative application-agnostic one. This work thus describes the rationale, efforts and results so far achieved for an integration of IoT paradigms and resource ecosystems with such a kind of cloud-oriented device-centric environment, by focusing on a smart city scenario, namely a park smart lighting example, and featuring data collection, data visualization, event detection and coordinated reaction, as example use cases of such integration. {\textcopyright} 2015 by the authors; licensee MDPI, Basel, Switzerland.

}, keywords = {AMQP, Ceilometer, CEP, Clouds, CoAP, Coordination reactions, data visualization, embedded systems, IaaS, Infrastructure as a service (IaaS), IoT, Lighting, Meteorological instruments, Mobile devices, MOM, OpenStack, REST, smart cities}, issn = {14248220}, doi = {10.3390/s150716314}, url = {http://www.scopus.com/inward/record.url?eid=2-s2.0-84940184863\&partnerID=40\&md5=6b5fc8b27ed3943f0529cb3323f22e88}, author = {Giovanni Merlino and Dario Bruneo and Salvatore Distefano and Francesco Longo and Antonio Puliafito and Adnan H. Al-Anbuky} } @proceedings {Longo2015204, title = {Stack4Things: An OpenStack-Based Framework for IoT}, journal = {Proceedings - 2015 International Conference on Future Internet of Things and Cloud, FiCloud 2015 and 2015 International Conference on Open and Big Data, OBD 2015}, year = {2015}, note = {cited By 2; Conference of 3rd International Conference on Future Internet of Things and Cloud, FiCloud 2015 ; Conference Date: 24 August 2015 Through 26 August 2015; Conference Code:117067}, pages = {204-211}, publisher = {Institute of Electrical and Electronics Engineers Inc.}, address = {Rome (Italy)}, abstract = {

In the wake of the massive adoption of embedded systems, mobiles, and other smart devices, as the scope of their involvement keeps broadening, complexity may quickly become overwhelming and vertical ad-hoc solutions will not cut it anymore. We propose to reuse as much tooling as possible, taking into account suitable options with regard to infrastructure management, then piggybacking as much advanced functionalities as possible in such kind of environment. In this sense, a widely used and competitive framework for Infrastructure-as-a-Service such as OpenStack, with its breadth in terms of feature coverage and expanded scope, looks like fitting the bill. This work therefore describes the approach and the solutions so far preliminary implemented for enabling Cloud-mediated interactions with droves of sensor-and actuator-hosting nodes by proposing Stack4Things, a framework for Sensing-and-Actuation-as-a-Service. In particular, we focused on describing the subsystem of Stack4Things devoted to resource control and management, highlighting relevant requirements and justifying how our proposed framework addresses them, while also opening up possibilities for a range of future extensions towards complete fulfillment of the Sensing-and-Actuation-as-a-Service vision. {\textcopyright} 2015 IEEE.

}, keywords = {Big Data, Clouds, embedded systems, Infrastructure as a service (IaaS), Infrastructure managements, Internet, Internet of Things, Mediated interaction, OpenStack, Resource control, SAaaS, Sensor and actuators, WAMP, Web Socket}, isbn = {9781467381031}, doi = {10.1109/FiCloud.2015.97}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84959059371\&doi=10.1109\%2fFiCloud.2015.97\&partnerID=40\&md5=e702319ada1b2cdde5d5d2061ec278f7}, author = {Francesco Longo and Dario Bruneo and Salvatore Distefano and Giovanni Merlino and Antonio Puliafito} } @article {Ghosh201457, title = {Scalable analytics for IaaS cloud availability}, journal = {IEEE Transactions on Cloud Computing - IEEE Computer Society}, volume = {2}, number = {1}, year = {2014}, note = {cited By 5}, pages = {57-70}, publisher = {Institute of Electrical and Electronics Engineers Inc.}, abstract = {

In a large Infrastructure-as-a-Service (IaaS) cloud, component failures are quite common. Such failures may lead to occasional system downtime and eventual violation of Service Level Agreements (SLAs) on the cloud service availability. The availability analysis of the underlying infrastructure is useful to the service provider to design a system capable of providing a defined SLA, as well as to evaluate the capabilities of an existing one. This paper presents a scalable, stochastic model-driven approach to quantify the availability of a large-scale IaaS cloud, where failures are typically dealt with through migration of physical machines among three pools: hot (running), warm (turned on, but not ready), and cold (turned off). Since monolithic models do not scale for large systems, we use an interacting Markov chain based approach to demonstrate the reduction in the complexity of analysis and the solution time. The three pools are modeled by interacting sub-models. Dependencies among them are resolved using fixed-point iteration, for which existence of a solution is proved. The analytic-numeric solutions obtained from the proposed approach and from the monolithic model are compared. We show that the errors introduced by interacting sub-models are insignificant and that our approach can handle very large size IaaS clouds. The simulative solution is also considered for the proposed model, and solution time of the methods are compared. {\textcopyright} 2014 IEEE.

}, keywords = {Availability, availability analysis, cloud computing, Downtime, Existence of a solutions, Infrastructure as a service (IaaS), Iterative methods, Lakes, Maintenance, Markov processes, Model driven approach, Numeric solutions, Service level agreement (SLAs), simulation, Stochastic models, Stochastic reward nets, Stochastic systems}, issn = {21687161}, doi = {10.1109/TCC.2014.2310737}, url = {http://www.scopus.com/inward/record.url?eid=2-s2.0-84906976356\&partnerID=40\&md5=a63dc67c92ef7620c8a3b33aca08348b}, author = {Rahul Ghosh and Francesco Longo and Flavio Frattini and Stefano Russo and Kishor S. Trivedi} } @proceedings {Merlino201521, title = {Stack4Things: Integrating IoT with OpenStack in a Smart City context}, journal = {Proceedings of the 2014 International Conference on Smart Computing Workshops (SMARTCOMP Workshops)}, year = {2014}, note = {cited By 1; Conference of 2014 International Conference on Smart Computing Workshops, SMARTCOMP Workshops 2014 ; Conference Date: 5 November 2014; Conference Code:111083}, pages = {21-28}, publisher = {IEEE Computer Society}, address = {Hong Kong, China, 5 November 2014}, abstract = {

As the adoption of embedded systems, mobiles and other smart devices keeps rising, and the scope of their involvement broadens, for instance in the enablement of Smart City-like scenarios, a pressing need emerges to tame such complexity and reuse as much tooling as possible without resorting to vertical ad-hoc solutions, while at the same time taking into account valid options with regards to infrastructure management, and other more advanced functionalities. In this sense, a widely used and competitive framework for Infrastructure as a Service such as OpenStack, with its breadth in terms of feature coverage and expanded scope, looks like fitting the bill. This work thus describes rationale, efforts, and results so far achieved, for an integration of IoT paradigms and resource ecosystems with such a kind of Cloud-oriented environment, by focusing on a Smart City scenario, and featuring data collection and visualization as example use cases of such integration. {\textcopyright} 2014 IEEE.

}, keywords = {AMQP, Ceilometer, CEP, Clouds, CoAP, data visualization, embedded systems, IaaS, Infrastructure as a service (IaaS), Internet of Things, IoT, Meteorological instruments, MOM, OpenStack, REST, smart cities}, isbn = {9781479964475}, doi = {10.1109/SMARTCOMP-W.2014.7046678}, url = {http://www.scopus.com/inward/record.url?eid=2-s2.0-84925651440\&partnerID=40\&md5=d36947c633a2c7b011bffa40aa32db9f}, author = {Giovanni Merlino and Dario Bruneo and Salvatore Distefano and Francesco Longo and Antonio Puliafito} } @article {Ghosh2014667, title = {Stochastic model driven capacity planning for an infrastructure-as-a-service cloud}, journal = {IEEE Transactions on Services Computing - IEEE Computer Society}, volume = {7}, number = {4}, year = {2014}, note = {cited By 1}, pages = {667-680}, publisher = {Institute of Electrical and Electronics Engineers}, abstract = {

From an enterprise perspective, one key motivation to transform the traditional IT management into Cloud is the cost reduction of the hosted services. In an Infrastructure-as-a-Service (IaaS) Cloud, virtual machine (VM) instances share the physical machines (PMs) in the provider{\textquoteright}s data center. With large number of PMs, providers can maintain low cost of service downtime at the expense of higher infrastructure and other operational costs (e.g., power consumption and cooling costs). Hence, determining the optimal PM capacity requirements that minimize the overall cost is of interest. In this paper, we show how a cost analysis and optimization framework can be developed using stochastic availability and performance models of an IaaS Cloud. Specifically, we study two cost minimization problems to address the capacity planning in an IaaS Cloud: 1) what is the optimal number of PMs that minimizes the total cost of ownership for a given downtime requirement set by service level agreements? and, 2) is it more economical to use cheaper but less reliable PMs or to use costlier but more reliable PMs for insuring the same availability characteristics? We use simulated annealing, a well-known stochastic search algorithm, to solve these optimization problems. Results from our analysis show that the optimal solutions are found within reasonable time. {\textcopyright} 2013 IEEE.

}, keywords = {Capacity planning, Capacity requirement, Clouds, Cost benefit analysis, Cost reduction, Downtime, Infrastructure as a service (IaaS), Maintenance, Optimization, Optimization framework, Optimization problems, Service Level Agreements, Simulated annealing, Stochastic models, Stochastic search algorithms, Stochastic systems, Total cost of ownership}, issn = {19391374}, doi = {10.1109/TSC.2013.44}, url = {http://www.scopus.com/inward/record.url?eid=2-s2.0-84919717849\&partnerID=40\&md5=34c70f14a9a3f838562335050a628985}, author = {Rahul Ghosh and Francesco Longo and Ruofan Xia and Vijay K. Naik and Kishor S. Trivedi} } @article {Ghosh20131216, title = {Modeling and performance analysis of large scale IaaS clouds}, journal = {Future Generation Computer Systems - Elsevier}, volume = {29}, number = {5}, year = {2013}, note = {cited By 10}, pages = {1216-1234}, abstract = {

For Cloud based services to support enterprise class production workloads, Mainframe like predictable performance is essential. However, the scale, complexity, and inherent resource sharing across workloads make the Cloud management for predictable performance difficult. As a first step towards designing Cloud based systems that achieve such performance and realize the service level objectives, we develop a scalable stochastic analytic model for performance quantification of Infrastructure-as-a-Service (IaaS) Cloud. Specifically, we model a class of IaaS Clouds that offer tiered services by configuring physical machines into three pools with different provisioning delay and power consumption characteristics. Performance behaviors in such IaaS Clouds are affected by a large set of parameters, e.g., workload, system characteristics and management policies. Thus, traditional analytic models for such systems tend to be intractable. To overcome this difficulty, we propose a multi-level interacting stochastic sub-models approach where the overall model solution is obtained iteratively over individual sub-model solutions. By comparing with a single-level monolithic model, we show that our approach is scalable, tractable, and yet retains high fidelity. Since the dependencies among the sub-models are resolved via fixed-point iteration, we prove the existence of a solution. Results from our analysis show the impact of workload and system characteristics on two performance measures: mean response delay and job rejection probability. {\textcopyright} 2012 Elsevier B.V. All rights reserved.

}, keywords = {Analytic modeling, Analytical models, Clouds, CTMC, Fixed-point iterations, IaaS, Infrastructure as a service (IaaS), Performance, Provisioning, Stochastic models, Stochastic systems, Submodels}, issn = {0167739X}, doi = {10.1016/j.future.2012.06.005}, url = {http://www.scopus.com/inward/record.url?eid=2-s2.0-84887062784\&partnerID=40\&md5=5aa7bb3aa9d27ba52b585a03501c8e18}, author = {Rahul Ghosh and Francesco Longo and Vijay K. Naik and Kishor S. Trivedi} }