Michele Amoretti

DEUS: a discrete event universal simulator

Currently available discrete event simulation tools exhibit important limitations, either being too specific, or providing only a partial API and possibly not enough scalability. In this paper we introduce our novel general purpose simulator, called DEUS, which aims at becoming one of the reference tools in the field of complex system simulation. Its essential Java API provides basic interfaces and classes for modelling nodes, events and processes characterizing the structure and dynamics of any complex system. High usability, configurability and memory efficiency are among the strengths of DEUS, as exemplified in this paper by means of the simulator of Chord peer-to-peer systems we implemented with minor coding effort.

SP2A: a service-oriented framework for P2P-based Grids

Service-Oriented Architectures (SOAs) are rapidly becoming the key approach for achieving new levels of interoperability and scalability in the development of Grid applications. Within SOA solutions, current approaches for advertising service providers and for allowing prospective clients to discover them are mostly based on centralized registries. Envisioning Virtual Organizations in which all participants are both resource providers and consumers, in a peer-to-peer fashion, seems to be an appealing approach.In this paper we propose the Service-oriented Peer-to-Peer Architecture (SP2A), a framework enabling peer-to-peer resource sharing in Grid environments. Resources are not directly exposed but can be accessed through Resource Provision Services, whose semantically enriched interfaces are published in the network. The framework has been implemented as a Java API, which currently supports a number of important technologies such as JXTA (peer-to-peer routing), Web Services (service deployment), and OWL-S (semantic description of services).

Sensor data fusion for activity monitoring in the PERSONA ambient assisted living project

User activity monitoring is a major problem in ambient assisted living, since it requires to infer new knowledge from collected and fused sensor data while dealing with highly dynamic environments, where devices continuously change their availability and (or) physical location. In the context of the European project PERSONA, we have developed an activity monitoring sub-system characterized by high modularity, little invasiveness of the environment and good responsiveness. In this paper we first illustrate the functional architecture of the proposed solution from a general point of view, discussing the motivations of the design. Then we describe in details the software components—sensor abstraction and integration layer, human posture classification, activity monitor—and the resulting activity monitoring application, presenting also a performance evaluation.

A software framework based on real-time CORBA for telerobotic systems

The technological developments in distributed systems have led to new telerobotic applications, such as virtual laboratories and remote maintenance of complex equipment. These applications must satisfy both the general requirements of distributed computing, e.g. location transparency and interoperability, and the domain-specific requirements of reconfigurability, guaranteed performance, real-time operation, and cooperation among robots and sensory systems. In this paper, we describe a software framework for distributed telerobotic systems exploiting advanced CORBA features, including Asynchronous Method Invocation and real-time priorities. The framework allows development of portable multithreaded client-server applications supporting concurrent and preemptable actions in the target robot system, and has been evaluated in a laboratory setup including a robot manipulator and two cameras accessible by multiple clients.

Simulating mobile and distributed systems with DEUS and ns-3

Mobile and distributed systems are characterized by decentralized goals and control, with high levels of concurrency and asynchronous interaction. Their qualitative and quantitative analysis is usually based on discrete event modeling and simulation. As most simulation tools target a specific class of problems, only a few of them may be considered truly general-purpose, yet they can hardly support the analysis of distributed systems with thousands of nodes, characterized by a high level of churn (node joins and departures) and reconfiguration of connections among nodes. To fill this gap, a few years ago we started developing an open-source, general-purpose and discrete event simulation tool, called DEUS, which is application-level oriented, Java-based, and characterized by ease of use and flexibility. However, it does not provide any package for simulating networking layers and their implementation is not foreseen, since a number of specialized tools are already available. In this paper, we present a general methodology for achieving a more realistic DEUS-based simulation of mobile and distributed systems, by leveraging on ns-3, which is generally known as a highly reliable and complete open-source tool for the discrete event simulation of Internet systems. In particular, we describe our positive experience in using ns-3s LTE-EPC package to support the simulation of a peer-to-peer overlay scheme called Distributed Geographic Table (DGT), which allows mobile nodes to efficiently share information without centralized control.

Architectural paradigms for robotics applications

In recent years, several technical architectural paradigms have been proposed to support the development of distributed and concurrent systems. Object-oriented, component-based, service-oriented approaches are among the most recent paradigms for the implementation of heterogeneous software products that require complex interprocess communications and event synchronization. Despite the sharing of common objectives with distributed systems research, the robotics community is still late in applying these research results in the development of its architectures, often relying only on the most basic concepts. In this paper, we shortly illustrate these paradigms, their characteristics, and the successful stories about their application within the robotic domain. We discuss benefits and tradeoffs of the different solutions with the goal of deriving some practical principles and strategies to be exploited in robotics practice. Understanding the characteristics, features, advantages, and drawbacks of the different paradigms is, indeed, crucial for the successful design, implementation, and use of robotic architectures.

A computational field framework for collaborative task execution in volunteer clouds

The increasing diffusion of cloud technologies offers new opportunities for distributed and collaborative computing. Volunteer clouds are a prominent example, where participants join and leave the platform and collaborate by sharing computational resources. The high complexity, dynamism and unpredictability of such scenarios call for decentralized self-* approaches. We present in this paper a framework for the design and evaluation of self-adaptive collaborative task execution strategies in volunteer clouds. As a byproduct, we propose a novel strategy based on the Ant Colony Optimization paradigm, that we validate through simulation-based statistical analysis over Google cluster data.

Collaborative Mobile Application and Advanced Services for Smart Parking

The main reason of wasting time in search of free parking spaces is the lack of information, in particular for open/roadside parking availability. Various ICT-based solutions have been proposed to solve this issue, but still suffering from limited integration among each other and with external online services, such as touristic information services. In this paper we illustrate a modular, service-oriented smart parking system, which includes web applications for parking operators and end users, as well as mobile applications for end users and parking controllers. The proposed system allows (1) operators to draw parking areas and define their details, (2) end users to be guided to the most suitable parking area, with also the indication of points of interest, and (3) controllers to monitor all vehicles that have been parked in their area. Another important feature is the possibility for end users to share their knowledge about parking occupancy, which is very useful when a parking area is not provided with precise availability counters. The smart parking system has been successfully evaluated in our Campus.

GeoKad: A P2P distributed localization protocol

The widespread use of tracking and localization systems may be hindered by centralized server platforms whose performance can hardly scale up to the needs of very large numbers of concurrent mobile users. In this paper we introduce GeoKad, a peer-to-peer localization protocol based on the new concept of Distributed Geographic Table, that allows to retrieve nodes and resources that are close to any given global position. The preliminary simulation-based evaluation focuses on performance (covered area search, lookup results) and costs in terms of load balancing, protocol overhead and scalability.

A Survey of Peer-to-Peer Overlay Schemes: Effectiveness, Efficiency and Security

In distributed computing, the peer-to-peer paradigm enables two or more entities to collaborate spontaneously in an overlay network of equals (peers) by using appropriate information and communication schemes without the necessity for central coordination. The key concept of the peer-to-peer paradigm is leveraging idle resources to do something useful, based on a collaborative approach. The increasing academic and industrial interest is resulting in the definition of standards and writing of patents. In this paper we propose a categorization for the peer-to-peer overlay schemes and a survey of the most popular ones, comparing each other with respect to effectiveness and security. Most of them have been or are being used in content sharing systems, that over the last few years have enjoyed explosive popularity. Others are used in parallel and distributed computing, massively multi-player gaming, Internet streaming, ambient intelligence, etc. Considering such a wide range of applications, we discuss the importance of reputation management in supporting trust management among peer participants.