Wi-Fi Aware application development faces challenges from limited device availability and a lack of scalable, accurate simulation tools, hindering realistic, reproducible testing. We introduce WFANS, a PeerSim-based simulation framework replicating the Android Wi-Fi Aware API. It implements core functionalities (clustering, service discovery, messaging and TCP communication), informed by empirical measurements. WFANS offers configurable models for network topology, mobility, radio conditions, and includes a graphical visualization interface. WFANS is validated against real-world metrics, showing accuracy in simulating short message loss and TCP throughput. Its applicability is demonstrated by porting Android applications with minimal changes. WFANS addresses a critical gap in the Wi-Fi Aware toolchain, offering a scalable, realistic environment for proximity networking research and development.

Decentralized Publish/Subscribe (P/S) systems deployed at the edge must cope with two major challenges: frequent membership churn and storage hot-spots caused by skewed topic popularity. In this work, we address these challenges in topic-based P/S systems built over Distributed Hash Tables (DHTs). We introduce PARSLEY, a group-based DHT based on a hybrid architecture that supports dynamic group management. Groups are flexibly maintained through splits, merges, and proactive peer relocation driven by soft size limits, ensuring balanced membership while minimizing expensive global operations. Additionally, we propose a lightweight sharding mechanism for popular topics, which partitions metadata and subscriptions across multiple DHT groups to alleviate overload by directing only subsequent data to new shards. Both mechanisms are coordinated by an edge server while preserving decentralized execution within the overlay. An implementation in the THYME framework demonstrates that proactive peer relocation reduces merge operations substantially lowers bandwidth consumption for state transfers, stabilizing group sizes under churn, while sharding alleviates storage pressure on popular topics, reducing maximum group load by up to 65% with moderate overhead. Together, they improve scalability, resilience, and responsiveness of edge-enabled P/S systems.

Work Stealing (Ws) is a provably efficient scheduler of parallel computations. In WS each processor owns a deque that it uses as a call stack; when out of work, processors try to steal tasks from other processors' deques. Unfortunately, the concurrent nature of processors' deques entails expensive synchronization even when processors access their own deques. Recently, Rito and Paulino have found that the use of split deques allows to provably avoid most synchronization costs while keeping WS's asymptotically optimal expected runtime; in Low-Cost Work Stealing (LCWS) - the variant of WS introduced in their work - processors need not synchronization for most local accesses to their (split) deques.

The implementation of collaborative applications in highly volatile environments, such as the ones composed of mobile devices, requires low coordination mechanisms. The replication without coordination semantics of Conflict-Free Replicated Data Types (CRDTs) makes them a natural solution for these execution contexts. However, the current CRDT models require each replica to know all other replicas beforehand or to discover them on-the-fly. Such solutions are not compatible with the dynamic ingress and egress of nodes in volatile environments. To cope with this limitation, we propose the Publish/Subscribe Conflict-Free Replicated Data Type (PS-CRDT) model that combines CRDTs with the publish/subscribe interaction model, and, with that, enable the spatial and temporal decoupling of update propagation. We implemented PS-CRDTs in Thyme, a reactive storage system for mobile edge computing. Our experimental results show that PS-CRDTs require less communication than other CRDT-based solutions in volatile environments.

Data-Centric Synchronization (DCS) shifts the reasoning about concurrency restrictions from control structures to data declaration. It is a high-level declarative approach that abstracts away from the actual concurrency control mechanism(s) in use. Despite its advantages, the practical use of DCS is hindered by the fact that it may require many annotations and/or multiple implementations of the same method to cope with differently qualified parameters. To overcome these limitations, in this paper we present AtomiS, a new DCS approach that requires only qualifying types of parameters and return values in interface definitions, and of fields in class definitions. The latter may also be abstracted away in type parameters, rendering class implementations virtually annotation-free. From this high level specification, a static analysis infers the atomicity constraints that are local to each method, considering valid only the method variants that are consistent with the specification, and performs code generation for all valid variants of each method. The generated code is then the target for automatic injection of concurrency control primitives that are responsible for ensuring the absence of data-races, atomicity-violations and deadlocks. We provide a Java implementation and showcase the applicability of AtomiS in real-life code. For the benchmarks analysed, AtomiS requires fewer annotations than the original number of regions requiring locks, as well as fewer annotations than Atomic Sets (a reference DCS proposal).

Nowadays, smart mobile devices generate huge amounts of data in all sorts of gatherings. Much of that data has localized and ephemeral interest, but can be of great use if shared among co-located devices. However, mobile devices often experience poor connectivity, leading to availability issues if application storage and logic are fully delegated to a remote cloud infrastructure. In turn, the edge computing paradigm pushes computations and storage beyond the data center, closer to end-user devices where data is generated and consumed, enabling the execution of certain components of edge-enabled systems directly and cooperatively on edge devices. In this article, we address the challenge of supporting reliable and efficient data storage and dissemination among co-located wireless mobile devices without resorting to centralized services or network infrastructures. We propose Thyme, a novel time-aware reactive data storage system for pervasive edge computing environments, that exploits synergies between the storage substrate and the publish/subscribe paradigm. We present the design of Thyme and elaborate a three-fold evaluation, through an analytical study, and both simulation and real world experimentations, characterizing the scenarios best suited for its use. The evaluation shows that Thyme allows the notification and retrieval of relevant data with low overhead and latency, and also with low energy consumption, proving to be a practical solution in a variety of situations.

Device-to-device communication enables collaboration between mobile devices, even when no communication infrastructure is available. In this setting, WiFi-Direct emerges as a technology able to provide device-to-device communication with WiFi coverage and speed. WiFi-Direct specification only addresses communication inside small groups (typically up to 8 devices), but some solutions for inter-group communication have been proposed and, atop such solutions, automatic network formation algorithms are now appearing. However, these proposals are neither efficient for large scale scenarios, due to the use of broadcasts, nor effective, as they offer limited connectivity.

The edge computing paradigm has been recently introduced with the aim of bringing cloud services closer to endusers. It provides an intermediate layer between devices and the actual cloud infrastructure, resulting in faster response times. In this paper, we propose a framework that leverages stationary nodes within the edge infrastructure to provide a persistent publish/subscribe system to a set of mobile devices, distributed across multiple network regions. We combine device-to-device and device-to-edge interactions with the goal of optimizing access to relevant data and allowing such data to be available to all users, hence creating a persistent, local-area data storage and dissemination network. Our experimental results show adequate response times for interactive usage and low energy consumption. We also evaluate our system against a cloud solution and verify that our proposal yields considerable latency speedups.

Nowadays, smart mobile devices generate huge amounts of data in all sorts of gatherings. Much of that data has localized and ephemeral interest, but can be of great use if shared among co-located devices. However, these devices often experience poor connectivity, leading to availability issues if applications' storage and logic are fully delegated to a remote cloud infrastructure. In turn, the edge computing paradigm pushes computations and storage beyond the data center, closer to end-user devices where data is generated and consumed. Thus, enabling the execution of certain components of edge-enabled systems directly and cooperatively on edge devices. In this paper, we address the challenge of supporting reliable and efficient data storage and dissemination among co-located wireless mobile devices without resorting to centralized services or network infrastructures. We propose Thyme, a novel time-aware reactive data storage system for wireless edge networks, that exploits synergies between the storage substrate and the publish/subscribe paradigm. We present the design of Thyme and evaluate it through simulation, characterizing the scenarios best suited for its use. The evaluation shows that Thyme allows for reliable notification and retrieval of relevant data with low overhead and latency.

Although mobile devices can collaborate and interact when connected by a communication infrastructure, such interactions may also be greatly desired or even highly necessary when such infrastructures are not available or cannot be used, like in crowded spaces, disaster situations, and remote areas, or when there is no trust in the existing infrastructures. A major requirement to support such autonomous collaborative systems on top of mobile devices is to build a communication network to interconnect them all. In this quest, Wi-Fi Direct (WFD) stands out as a promising technology to offer infrastructure-less WiFi networking to off-the-shelf devices. However, the WFD standard only addresses communications inside one group of devices, and current WFD inter-group communication solutions have several limitations, as they must contend with intermittent connections, slow communication (broadcasts and/or multicasts), and/or a high number of nodes to interconnect groups. In this paper, we aim to overcome those limitations by proposing two novel topologies, named GOCRGO and GOGO, which use permanent radio connections, can rely on either UDP or TCP communication, and require the minimum number of nodes necessary to interconnect WFD groups. Both topologies present advantages over each other, in different scenarios, and thus can be used together in a complementary way.

The MapReduce framework is being increasingly used in the scientific computing and image/video processing fields. Relevant research has tailored it for the field's specificities but there are still overwhelming limitations when it comes to temporal locality-sensitive computations. The performance of this class of computations is closely tied to an efficient use of the memory hierarchy, concern that is not yet taken into consideration by the existing distributed MapReduce runtimes. Consequently, implementing temporal locality-sensitive computations, such as stencil algorithms, on top of MapReduce is a complex chore not rewarded with proportional dividends. This paper tackles both the complexity and the performance issues by integrating tiling techniques and memory hierarchy information into MapReduce's split stage. We prototyped our proposal atop the Apache Hadoop framework, and applied it to the context of stencil computations. Our experimental results reveal that, for a typical stencil computation, our prototype clearly outperforms Hadoop MapReduce, specially as the computation scales.

Summary Current computational systems are heterogeneous by nature, featuring a combination of CPUs and graphics processing units (GPUs). As the latter are becoming an established platform for high‐performance computing, the focus is shifting towards the seamless programming of these hybrid systems as a whole. The distinct nature of the architectural and execution models in place raises several challenges, as the best hardware configuration is behavior and workload dependent. In this paper, we address the execution of compound, multi‐kernel, open computing language computations in multi‐CPU/multi‐GPU environments. We address how these computations may be efficiently scheduled onto the target hardware, and how the system may adapt itself to changes in the workload to process and to fluctuations in the CPU's load. An experimental evaluation attests the performance gains obtained by the conjoined use of the CPU and GPU devices, when compared with GPU‐only executions, and also by the use of data‐locality optimizations in CPU environments. Copyright © 2015 John Wiley & Sons, Ltd.

In this paper we propose a fully distributed storage system for everyday hand-held mobile devices, e.g., smartphones and tablets, that follows a best effort approach to ensure data persistence and availability even in the presence of churn (i.e., the unpredictable arrival and departure of nodes).

The rapidly increasing computing power, available storage and communication capabilities of mobile devices makes it possible to start processing and storing data locally, rather than offloading it to remote servers; allowing scenarios of mobile clouds without infrastructure dependency. We can now ai

The current capabilities of mobile phones in terms of communication, processing and storage, enables its use to form autonomous networks of devices that can be used in case of collapse or inexistent support from a communication infrastructure. In this paper, we propose a network configuration of nod

Wireless Sensor Networks (WSNs) are a fundamental technology for science in many domains, and their inclusion in Web environments, e.g. through Web services, allows for their open/standard access and integration. Although such Web enabled WSNs simplify data access, network parametrisation and aggregation, the available interaction models and run-time adaptation mechanisms are still scarce. Nevertheless, applications increasingly demand richer and more flexible interface accesses, for instance, the interaction model dynamic adaptation according to contextual information. To this extent, this paper discusses the relevance of the session and pattern abstractions on the design of a middleware prototype providing richer interaction models, as well as a few context-based dynamic adaptation mechanisms for Web enabled WSNs.

Many of the current service-oriented architectures are built on top of distributed object technologies. These technologies have, however, lost most of their initial appeal, mainly due to the inability to port their concepts to the World Wide Web, and to provide interoperability across many different platforms. The porting of these distributed object platforms to the current Web Service standard is, however, a costly process that requires high investments of both time and money. This paper presents OHMS, a framework that provides an easy and not resource consuming way of exposing a platform to the Web, thus enabling Web access, business-to-business interaction and service composition, by the means of orchestration. We address the framework's architecture, its implementation, and the support for orchestrating CORBA platforms. We evaluate the work regarding the initial requirements, the effort required to support a given distributed object technology, and performance issues. We also address the application of OHMS to a real-life scenario.

Abstract We present MOB, a service‐oriented scripting language, for programming mobile agents. We argue that combining the service‐oriented and mobile agent paradigms provides a very natural model for programming a large class of distributed applications. In MOB, mobile agents in a network simultaneously provide and use services. The service interfaces constitute contracts that bind agents among themselves. The language features static type‐checking to guarantee that contracts are respected at run‐time. Other language features, such as redundant service providers, allow a certain degree of fault‐tolerance by allowing applications to switch servers dynamically in case a failure is detected (e.g. a server crash). For these reasons, the target applications we envision more interesting to develop using MOBare services for networks with highly dynamic, volatile resources or simply highly adaptive, reconfigurable applications for more classical networks. The paper presents MOBand its implementation from an application programmer's and a systems developer's view. Copyright © 2007 John Wiley & Sons, Ltd.

Although mainly resorting to local communication, all mobile agent systems also provide some kind of remote communication facility. This introduces issues not addressed in the protocols provided by the transport layer, such as TCP, nor in its extensions to cope with physical mobility. The problem consists of tracking the agent to which the channel must be established, and providing support for the migration of any of the channel's endpoints. In this paper, we propose a model that solves both problems, transparently to the application, by resorting to sophisticated interaction with a naming service and by featuring a protocol to support the migration of both the connection's endpoints.

The execution of the client side of a mobile service is a task greatly conditioned by the limited resources available to perform computation and communication. Moving these operations to other computing elements reduces the energy spent by the device in the actual computing of the final result. This allows for a more efficient management of the device's energy, increasing its autonomy. In this paper, we use put to use the features of the MOB programming language to efficiently develop mobile device specific applications, namely the ability to remotely launch mobile agents, strong mobility and a service-oriented resource discovery model.