The burgeoning capabilities of Web browsers to exploit full-featured devices can turn the huge pool of social connected users into a powerful network of processing assets. HTML5 and JavaScript stacks support the deployment of social client-side processing infrastructure, while WebGL and WebCL fill the gap to gain full GPU and multi-CPU performance. Mobile Grid and Mobile Cloud Computing solutions leverage smart devices to relieve the processing tasks to be performed by the service infrastructure. Motivated to gain cost-efficiency, a social network service provider can outsource the video analysis to elements of a mobile grid as an infrastructure to complement an elastic cloud service. As long as users access to videos, batch image analysis tasks are dispatched from the server, executed in the background of the client-side hardware, and finally, results are consolidated by the server. This paper presents SaW (Social at Work) to provide a pure Web-based solution as a mobile grid to complement a cloud media service for image analysis on videos.

This paper presents an evaluation of three communication-efficient algorithms implementing the Omega class of failure detectors, which provides an eventual leader election functionality, in distributed systems where processes can crash and recover. Communication efficiency means that eventually only a correct process, i.e., the elected leader, keeps sending a message periodically to the rest of processes. The first algorithm relies on the use of stable storage to store the identity of the leader and an incarnation number. The second algorithm does not use stable storage, but requires a majority of correct processes. Also, it is near-communication-efficient, since besides the leader, unstable processes, i.e., those that crash and recover infinitely often, may send messages periodically before they receive a message from the leader. Finally, the third algorithm does neither use stable storage nor require a majority of correct processes, but assumes that each process has access to a nondecreasing and persistent local clock. Using the OMNeT++ network simulation framework, we evaluate the performance and the quality of service provided by these algorithms, in terms of the number of messages exchanged among processes and the capability of the failure detector to provide a single leader, respectively.

This paper addresses the leader election problem in dynamic distributed systems with mobile processes. To do so, it is assumed that the system alternates periods of good and bad behavior, in the line of the timed asynchronous model of Cristian and Fetzer. We extend the eventual leadership properties recently proposed by Larrea et al. for non-mobile dynamic systems, defining two new properties that take into account graph joins/fragmentations due to process mobility. We also propose a new leader election algorithm in a weak mobile dynamic distributed system model. Using a categorization framework, we compare our system model with a number of models proposed in the literature, showing that our leader election algorithm works in a model which is weaker than the rest.

The integration of mobile devices within distributed systems introduces a wide range of constraints for developers. Some constraints arise from the hardware, software and interaction features of mobile platforms, while others stem from the use of wireless networks that are more dynamic, less reliable and performing than wired networks. In either case, software engineering processes have to tackle these constraints in order to provide mobility-enabled systems and applications. Based on first-hand experience in the field, this paper provides a framework to categorise these constraints and their severity, and describes some of the strategies that can be used to cope with them, with an emphasis in those relevant to middleware design.

This paper presents Phoenix, a routing protocol for content-based publish/subscribe systems that supports seamless client mobility. Our protocol is based on the Simple Routing approach and requires brokers to maintain a global vision of the system with regards to its subscribers. As a consequence, Phoenix provides optimal event routing in both static and mobile client scenarios, and avoids mobility-related flooding of messages. Although the choice of Simple Routing sacrifices maximum scalability due to global propagation of subscriber interest, we show that several optimizations significantly minimize the loss of performance. In fact, when optimized, the performance of the Phoenix routing algorithm is suitable for the scenarios we envision: hybrid wireless networks for sensor/actuator deployments. Additionally, we note that our protocol can be extended to provide brokers with the ability to enforce client migrations for load-balancing purposes.

We present a modular redesign of TrustedPals, a smart card-based security framework for solving Secure Multiparty Computation (SMC). Originally, TrustedPals assumed a synchronous network setting and allowed to reduce SMC to the problem of fault-tolerant consensus among smart cards. We explore how to make TrustedPals applicable in environments with less synchrony and show how it can be used to solve asynchronous SMC. Within the redesign we investigate the problem of solving consensus in a general omission failure model augmented with failure detectors. To this end, we give novel definitions of both consensus and the class \diamond {\cal P} of failure detectors in the omission model, which we call \diamond {\cal P}({ om}), and show how to implement \diamond {\cal P}({ om}) and have consensus in such a system with very weak synchrony assumptions. The integration of failure detection and consensus into the TrustedPals framework uses tools from privacy enhancing techniques such as message padding and dummy traffic.

No abstract available.

This paper presents an evaluation of several communication-optimal algorithms implementing the diamP class of failure detectors. The first algorithm is based on a reliable broadcast primitive, involving a quadratic number of messages to manage a suspicion. The second algorithm uses exclusively one-to-one communication, involving a linear number of messages to manage a suspicion, but with a higher latency to propagate the suspicion to the rest of processes. A third algorithm reduces this latency using an additional one-to-all communication mechanism. We evaluate the quality of service provided by these algorithms, in terms of the capability of the failure detector to provide right answers and the reaction time after a failure.

No abstract available.

This paper presents an evaluation of two families of ring-based algorithms implementing the eventually perfect failure detector class (diamPscr). The evaluation is based on two kinds of performance parameters: communication efficiency, which refers to the number of links that carry messages forever, and quality of service, which includes the capability of the failure detector for providing right answers as well as reaction and initial stabilization times. The first family of algorithms includes several communication-efficient implementations of diamPscr introduced in a previous work. For the second family, introduced in this work, we start from the design of a non communication-efficient diamQscr algorithm, and then we apply a transformation to obtain a diamPscr algorithm, including some optimizations to improve the quality of service

Ubiquitous (or pervasive) systems are characterized by component distribution and dynamic behavior. In a ubiquitous environment, such as a future automated home (also called a domotic environment), user devices explore the environment to discover resources and services to control. This paper analyzes architectures for ubiquitous systems based on the structure of the environment and the way discovery mechanisms (such as Jini and UPnP) operate. As a result, a framework to classify the architectures is provided. As an example, a UPnP-based prototype for a domotic environment is presented. We use standard devices, such as PDAs and cell phones, to allow users to access and control virtual resources. The system provides user management capabilities, persistence, and standard interfaces, while preserving full UPnP compatibility. The prototype can be easily transferred to future realistic domotic installations.

Certain real-world applications present serious challenges to conventional neural-network design procedures. Blindly trying to train huge networks may lead to unsatisfactory results and wrong conclusions about the type of problems that can be tackled using that technology. In this paper a modular solution to power systems alarm handling and fault diagnosis is described that overcomes the limitations of "toy" alternatives constrained to small and fixed-topology electrical networks. In contrast to monolithic diagnosis systems, the neural-network-based approach presented here accomplishes the scalability and dynamic adaptability requirements of the application. Mapping the power grid onto a set of interconnected modules that model the functional behavior of electrical equipment provides the flexibility and speed demanded by the problem. After a preliminary generation of candidate fault locations, competition among hypotheses results in a fully justified diagnosis that may include simultaneous faults. The way in which the neural system is conceived allows for a natural parallel implementation.