Elisa Turrini

QoS-Aware Clouds

In this paper we discuss the design and experimental evaluation of a middleware architecture that enables Service Level Agreement (SLA)-driven dynamic configuration, management and optimization of cloud resources and services. This architecture has been designed in order to respond effectively to the Quality of Service (QoS) requirements of the cloud customer applications. Typically, an application can be hosted in an execution platform constructed out of (real and virtual) cloud resources. In this context, the application QoS requirements can be specified in a SLA that binds the application to its hosting platform. Our architecture incorporates a load balancer that distributes the computational load across the platform resources, and monitors the QoS the platform delivers. If this deviates from that specified in the SLA, so as to violate it, the platform is reconfigured dynamically in order to incorporate additional resources from the cloud. In contrast, if the SLA is honored and platform resources result unused, platform reconfiguration occurs to release those unused resources.

SLA-Driven Clustering of QoS-Aware Application Servers

In this paper, we discuss the design, implementation, and experimental evaluation of a middleware architecture for enabling service level agreement (SLA)-driven clustering of QoS-aware application servers. Our middleware architecture supports application server technologies with dynamic resource management: application servers can dynamically change the amount of clustered resources assigned to hosted applications on-demand so as to meet application-level quality of service (QoS) requirements. These requirements can include timeliness, availability, and high throughput and are specified in SLAs. A prototype of our architecture has been implemented using the open-source J2EE application server JBoss. The evaluation of this prototype shows that our approach makes possible JBoss resource usage optimization and allows JBoss to effectively meet the QoS requirements of the applications it hosts, i.e., to honor the SLAs of those applications

Seamless Support of Multimedia Distributed Applications Through a Cloud

We describe a cross-layer architecture we are developing in order to offer mobility support to wireless devices executing multimedia applications which require seamless communications. This architecture is based on the use of pairs of proxies, which enable the adaptive and concurrent use of different network interfaces during the communications. A cloud computing environment is used as the infrastructure to set up (and release) dynamically the proxies on the server-side, in accordance with the pay-as-you-go principle of cloud based services.

Designing and architecting process-aware Web applications with EPML

An emerging class of Web applications is driving the evolution of the Web toward a Business System. These applications allow the participation of several actors to complex enterprise-wide (or even multi-enterprise) business processes and pose new challenges to the software designer and to the software architect. In this paper we show how, promoting an effective separation of concerns, a process modeling language and its enactment engine can be used in the modeling and in the implementation of process-aware Web applications.

Using P2P techniques for content distribution internetworking: a research proposal

In this paper we discuss the use of algorithms and techniques, currently deployed in peer-to-peer (P2P) systems, in the design of content distribution internetworks (CDIs). Specifically, we propose a CDI design approach that addresses issues of request routing, content delivery, and replication, based on P2P techniques.

Experimental Evaluation of a QoS-aware Application Server

This paper introduces an experimental evaluation of a set of middleware services we have developed in order to enable application server technology to meet such quality of service (QoS) application requirements as service availability, timeliness and throughput. These services, developed in the context of the EU funded project TAPAS, have been integrated in the open source JBoss application server, and are publicly available

Analyzing the Impact of Components Replication in High Available J2EE Clusters

Clustering is a well known technique that allows scalability and fault tolerance in distributed systems. In the J2EE framework, clustering can be used to improve the performance and the availability of an application. In this context, however, great care has to be taken with respect to the replication of stateful components; specifically, stateful components replication can adversely affect the performance of the system and can introduce unexpected modifications in the semantics of the application. In this paper, exploiting our experience in this area, we analyze and discuss these issues, and propose possible solutions. We also describe how component replication is implemented in a number of (open source and commercial) J2EE compliant application servers. The aim of this paper is to provide the insight to better evaluate the software solutions and the related costs/benefits trade-off issues that a software architect has to address when designing a critical, high available, system

Using a process modeling language for the design and implementation of process-driven applications

Process driven software architectures are establishing themselves as prominent examples of distributed software infrastructures. Workflow Management Systems, web service orchestration platforms, Business Process Management support systems are relevant instances of process driven software architectures all of which, as the name suggests, are characterized as having a process perspective. In this paper we show that a (well designed) process modeling language and its execution engine can address the process perspective in different architectures and be (re)used among different application domains resulting in useful tools for the design and the implementation of process-driven applications. This can be achieved by maximizing the suitability of such a language via high expressive power and good separation of concerns. We also show sample process driven architectures, addressing different application domains, that are built with it.

Exploiting Semantic Knowledge in Know Best

KnowBest is a system that has been designed to support recording/replaying/sharing best practices involving social software tools in an emergent coordination context. One of the main components of the system is a semantic wiki that, through the social management of content and its associated annotations, makes available semantically-enriched information that can be machine processed and exploited and reasoned upon allowing the development of inference-based applications. In order for this class of applications to be effective, the structure of the semantic knowledge is of fundamental importance. Not always, in fact, the use of pre-defined, accurately designed ontologies is possible (which is mostly true for wikis where not just the knowledge but also its structure is synthesized from social interactions). In this paper we show how it is possible to effectively support emergent ways of organizing knowledge with a two-layers approach in which a pre-defined core structure can be freely extended with domain-related concepts by exploiting semantic wikis editing facilities, we apply this approach in the implementation of KnowBests recommender, a component designed to leverage semantic inference in order to provide suggestions about existing best practices to the users in a way that is similar to what a car navigation system does for car drivers.

EPML: an executable process modeling language for process-aware applications

Process modeling and process enactment are becoming a prominent concern for a large class of modern applications. This is witnessed by the increasing number of modeling languages and software tools designed to assist the development of the so called process-aware applications. Most of these languages and tools are targeted to different application domains (workflow management, web service orchestration, business process management, etc.) and also differ about the way coordination is achieved. This forces software designers to address the very same concern, process coordination, with different, albeit often similar, languages when moving across application domains.n EPML is a process modeling language that, along with its enactment engine, can be used to address process coordination across different application domains. This result is achieved with high expressive power and by promoting an effective separation of concerns that increases software composability.