inproceedings by Marco Guazzone
ShareGrid is a peer-to-peer desktop grid aimed at satisfying the computing needs of the small res... more ShareGrid is a peer-to-peer desktop grid aimed at satisfying the computing needs of the small research laboratories located in the Piedmont area in Northern Italy. ShareGrid adopts a cooperative approach, in which each participant allows the other ones to use his/her own resources on a reciprocity basis. ShareGrid is based on the OurGrid middleware, that provides a set of mechanisms enabling participating entities to quickly, fairly, and securely share their resources. In this paper we report our experience in designing, deploying, and using ShareGrid, and we describe the applications using it, as well as the lessons we learned, the problems that still remain open, and some possible solutions to them.
Cloud computing is growing in popularity among computing paradigms for its appealing property of ... more Cloud computing is growing in popularity among computing paradigms for its appealing property of considering "Everything as a Service". The goal of a Cloud infrastructure provider is to maximize its profit by minimizing the amount of violations of Quality-of-Service (QoS) levels agreed with service providers, and, at the same time, by lowering infrastructure costs. Among these costs, the energy consumption induced by the Cloud infrastructure, for running Cloud services, plays a primary role. Unfortunately, the minimization of QoS violations and, at the same time, the reduction of energy consumption is a conflicting and challenging problem. In this paper, we propose a framework to automatically manage computing resources of Cloud infrastructures in order to simultaneously achieve suitable QoS levels and to reduce as much as possible the amount of energy used for providing services. We show, through simulation, that our approach is able to dynamically adapt to time-varying workloads (without any prior knowledge) and to significantly reduce QoS violations and energy consumption with respect to traditional static approaches.
Cloud computing is an emerging computing paradigm in which “Everything is as a Service”, includin... more Cloud computing is an emerging computing paradigm in which “Everything is as a Service”, including the provision of virtualized computing infrastructures (known as Infrastructure-as-a-Service modality) hosted on the physical infrastructure, owned by an infrastructure provider. The goal of this infrastructure provider is to maximize its profit by minimizing the amount of violations of Quality-of-Service (QoS) levels agreed with its customers and, at the same time, by lowering infrastructure costs among which energy consumption plays a major role. In this paper, we propose a framework able to automatically manage resources of cloud infrastructures in order to simultaneously achieve suitable QoS levels and to reduce as much as possible the amount of energy used for providing services. We show, through simulation, that our approach is able to dynamically adapt to time-varying workloads (without any prior knowledge) and to significantly reduce QoS violations and energy consumption with respect to traditional static approaches.
We address the problem of managing cloud applications, consisting of a set of virtual machines (V... more We address the problem of managing cloud applications, consisting of a set of virtual machines (VMs), characterized by bursty and dynamic workloads, in such a way to provide guarantees on their Quality-of-Services (QoS) and, at the same time, to minimize the energy consumption of the physical infrastructure running them. We propose a fuzzy controller, Fuzzy-Q& E, that is able to allocate to the VMs of each cloud application the minimum amount of physical capacity needed to meet its QoS requirements. In this way, the number of physical resources that must be switched-on at any given time is reduced with respect to the case in which physical machines are statically provisioned and, consequently, less energy is required to run a given cloud workload. We implement a prototype of our controller on a Xen-based testbed, and we perform a set of experiments using an E-Commerce benchmark in which we compare Fuzzy-Q&E against Dyna QoS, a state-of-the-art fuzzy controller for virtualized resources. Experimental results show that Fuzzy-Q&E out performs Dyna QoS both in terms of the ability of meeting the QoS level of the application, and of the amount of physical capacity allocated to each VM.
Federations among sets of Cloud Providers (CPs), whereby a set of CPs agree to mutually use their... more Federations among sets of Cloud Providers (CPs), whereby a set of CPs agree to mutually use their own resources to run the VMs of other CPs, are considered a promising solution to the problem of reducing the energy cost. In this paper, we address the problem of federation formation for a set of CPs, whose solution is necessary to exploit the potential of cloud federations for the reduction of the energy bill. We devise an algorithm, based on cooperative game theory, that can be readily implemented in a distributed fashion, and that allows a set of CPs to cooperatively set up their federations in such a way that their individual profit is increased with respect to the case in which they work in isolation. We show that, by using our algorithm and the proposed CPs' utility function, they are able to self-organize into Nash-stable federations and, by means of iterated executions, to adapt themselves to environmental changes. Numerical results are presented to demonstrate the effectiveness of the proposed algorithm.
Uploads
inproceedings by Marco Guazzone