Search

The availability of network softwarization and virtualization technology in the field of telecommunications has opened the door to a radical review of the applications, protocols, and deployment models. In this evolving framework, old assumptions and constraints specific to satellite communications must be carefully re-assessed. To this aim, we revisit the role of the performance enhancing proxy (PEP), replaced by a chain of custom virtual network functions properly enabled to optimize common web traffic performance over a backhaul dynamically enabled with a supplementary satellite link. The resulting virtual PEP (vPEP) is compliant with the breakthrough virtualization and slicing paradigms and can fruitfully exploit the advanced features of the most recent IETF technologies such as QUIC and MPTCP.

Serverless computing is an emerging proposition in the cloud offering landscape that promotes a higher level of abstraction, further decoupling software operations from the underlying hardware. Often recognized as an economically driven computational approach, the serverless model relies on the execution of short-lived stateless functions, enabling a fine-grained accounting and control of resources. In this context, function composition represents an appealing feature, allowing the composition of two or more functions to create tailored processing pipelines, incentivizingmodularityandreusabilityof functions, while paving the way to application-specific run-time optimizations. This work presents DIFFUSE: a DIstributed and decentralized platForm enabling Function composition in Serverless Environments. DIFFUSE embodies an innovative infrastructural support, enabling the efficient and transparent composition of functions by relying on pluggable middleware support, serving as a conveyor of messages among the platform components. Broadening the deployment spectrum of our proposal, we assess differentmiddleware solutions, each presenting distinct delivery profiles, evidencing the tradeoffs that emerge.

When COVID-19 first struck the provinces of Northern Italy in early 2020 (especially in Lombardy and in EmiliaRomagna), the conditions there made it a perfect storm. The virus outbreak spread with an unusual violence (in the period from late February to April 2020), with a catastrophic toll in terms of human deaths. Taken by surprise, Italy mandated a complete nation-wide lockdown, successively resorting to ministerial decrees alleviating and postponing the restrictions. Now more than ever, there is an increased awareness on ICT used to combat the pandemic. In this article, we present a quantitative analysis evidencing the impact of restrictions on mobility. To this end, we rely on a vehicular mobility dataset confined in the downtown area of Bologna, Italy. Pursuing the objective, we propose a modified version of a state-of-theart data mining algorithm, allowing us to efficiently identify and quantify mobility flows. The proposal, if combined with additional data sources, could allow for a fine-grained and timely decision making, combating the pandemic.

Mobile Ad-Hoc Networks are currently experiencing a second youth in terms of research interest as well as providing benefits to our society. Clearly, this has been fostered by the wide range of applications that have become actually feasible thanks to the pervasive and increasing presence of smartphones, drones, sensors and other small devices with communication and sensing capability. Aiming to deploy solutions able to self-organize without the need for any infrastructure support, packet routing remains an open and critical research problem. Several routing solutions have been conceived to guarantee delivery and low overhead in this context. A promising approach, trying to limit the information needed and stored in the network, is represented by stateless solutions, a class of solutions not relying on topology state information. However, since they exploit local knowledge, the achieved performance in terms of packet delivery and latency is not always up to expectations. To this aim, we propose a dynamic routing protocol based on a tabu search approach, relying on local network knowledge and in-packet short-term memory to alleviate the local minima problem. A through experimental assessment is conducted, measuring protocol performance under different configurations and profiles, evidencing its benefits.

Wearable technology is no longer science fiction. Thanks to the growing capability in the production chain to miniaturize complex electronics, a wide variety of gadgets that can be worn or included in dresses and accessories have emerged. These smart gadgets can collect data about the physical condition of the user and/or the environment providing the basis for innovative and valuable services. The main goal of this paper is to assess this context through field experiments undertaken in a testbed comprised of sensing hardware deployed on open source boards such as Arduino. Moreover, coupled with the sensing tier, we propose a proof-of-concept deployment architecture enabling a wide range of wearable sensors to collect and transmit data to a logically centralized unit.

Immersive technology is expected to become a key player in the next wave of consumer electronics with potential applications spanning a wide variety of sectors. Yet, there are a number of technological hurdles which need to be addressed. Without speed and computation capability, interactivity cannot be ensured. More than often the constrained nature of the mobile device demands is complemented by cloud ones through the use of cloud offloading techniques. With cloud offloading, battery consumption and processing performance problems are translated into sensor data selection and network latency problems. In this context, we focus our study on some functional building blocks that can be used in conjunction and deployed in a 5G virtualized architecture to alleviate bandwidth and latency requirements of immersive application scenarios. To this end, we have created an experimental scenario exploiting real data to test our combined solution based on the field of view cut and optimized transport protocols, discussing the tradeoffs that emerge.

The ubiquity of mobile technology has opened the door to the new era of mobile sensing. Through this new paradigm, physical phenomena can be observed in a distributed way, crowd-sourcing the data measurement tasks to smartphones and/or other popular smart wearables. Mobile sensing and wireless communications can hence be employed to gather data and generate new information and services, benefiting our society. As a proof-of-concept, we have developed a mobile sensing platform able to pervasively collect environmental data. To improve the quality of collected data we have also created an application for pedestrian navigation that works both on smartphones (also using Augmented Reality) and on smartwatches, thus ensuring an appropriate exposition of the mobile device (and its sensors) when collecting data. Furthermore, our navigation app is able to provide users with personalized pedestrian routes that take into account environmental parameters and not only the route length. Finally, we have also devised a web service able to provide graphical visualization and historical evolution of sensed data.

Recent market trends in self-driving technology have revived the attention on vehicular networks, posing a demand for intelligent solutions supporting the proliferation of many useful applications. Inter-vehicular communication presents an opportunity, capable of providing the basis for localized, timely, collective intelligence. In this context, critical safety applications are particularly challenging, urging for quick multi-hop message propagation schemes within an area of interest. The anycast communication model embodied by safety applications and the shared broadcast medium demand for intelligent message propagation schemes minimizing latency. To this end, the state of the art approach is based on having different contention windows among vehicles so as to probabilistically select specific ones as forwarders in order to reduce the number of hops and transmissions needed to propagate the message. However, this solution has been mainly studied empirically. In this article, we present and discuss an analytical model, shedding light on the expected behavior and performance of such approach, along with a validation analysis conducted through the well known simulator NS-2.

In the recent years, ICT use in vehicular technology has expanded very fast. Inter-vehicle communication (IVC) is seen as the natural next step in this evolution whose availability will give rise to the next generation of smart vehicles. As this technology is deployed, a wide range of services varying from safety to entertainment will become factually accessible to passengers. Many of these envisaged services require a one-to-many communication model which demand for intelligent solutions able to propagate the message in areas of the network where it has not been heard before. To this end, we propose an enhancement of an existent optimal message propagation scheme proposed in the context of one dimensional vehicular networks, namely Fast-Broadcast. Our proposal generalizes the former with the objective of guiding message dissemination to an entire area of interest in generic road topologies. Our proposed scheme exploits bloom filter properties to further advance message propagation into the network. We contrast our approach with the original, lightweight state-of-the-art proposal, showing that it fulfills its design objectives.

We discuss MDTN: a delay tolerant application platform built on top of the Public Transportation System (PTS) and able to provide service access while exploiting opportunistic connectivity. Our solution adopts a carrier-based approach where buses act as data collectors for user requests requiring Internet access. Simulations based on real maps and PTS routes with state-of-the-art routing protocols demonstrate that MDTN represents a viable solution for elastic nonreal-time service delivery. Nevertheless, performance indexes of the considered routing policies show that there is no golden rule for optimal performance and a tailored routing strategy is required for each specific case.

Interactive applications as online games and mobile devices have become more and more popular in recent years. From their combination, new and interesting cooperative services could be generated. For instance, gamers endowed with Augmented Reality (AR) visors connected as wireless nodes in an ad-hoc network, can interact with each other while immersed in the game. To enable this vision, we discuss here a hybrid architecture enabling game play in ad-hoc mode instead of the traditional client-server setting. In our architecture, one of the player nodes also acts as the server of the game, whereas other backup server nodes are ready to become active servers in case of disconnection of the network i.e. due to low energy level of the currently active server. This allows to have a longer gaming session before incurring in disconnections or energy exhaustion. In this context, the server election strategy with the aim of maximizing network lifetime is not so straightforward. To this end, we have hence analyzed this issue through a Mixed Integer Linear Programming (MILP) model and both numerical and simulation-based analysis shows that the backup servers solution fulfills its design objective.

Scalable routing for wireless communication systems is a compelling and challenging task. To this aim, routing algorithms exploiting geographic information have been proposed. These algorithms refer to nodes by their location, rather than their address, and use those coordinates to route greedily towards a destination. With the advent of unmanned airborne vehicle (UAV) technology, a lot of research effort has been devoted to extend position-based packet routing proposals to three dimensional environments. In this context, Flying Ad-hoc Networks (FANETs), comprised of autonomous flying vehicles, pose several issues. This work focuses on the state-of-the-art, stateless geographic packet routing protocols conceived or adapted for three-dimensional network scenarios. Proposals are evaluated over a common scenario through a comprehensive comparative analysis.

The number of physical objects connected to the Internet constantly grows and a common thought says the IoT scenario will change the way we live and work. Since IoT technologies have the potential to be pervasive in almost every aspect of a human life, in this paper, we deeply analyze the IoT scenario. First, we describe IoT in simple terms and then we investigate what current technologies can achieve. Our analysis shows four major issues that may limit the use of IoT (i.e., interoperability, security, privacy, and business models) and it highlights possible solutions to solve these problems. Finally, we provide a simulation analysis that emphasizes issues and suggests practical research directions.

In recent years we have seen a great proliferation of smart vehicles, ranging from cars to little drones (both terrestrial and aerial), all endowed with sensors and communication capabilities. It is hence easy to foresee a future with even more smart and connected vehicles moving around, occupying space and creating an Internet of Vehicles (IoV). In this IoV, a multitude of nodes (both static and mobile) will generate a continuous multihop flow of local information to support local smart environment applications. Therefore, one interesting environment for the IoV would be in the form of 3-D mobile ad-hoc networks (MANETs). Unfortunately, MANET routing protocols have generally been designed and analyzed keeping in mind a 2-D scenario; there is no guarantee on how they would support a 3-D topology of the IoV. To this end, we have considered routing protocols deemed as the state-of-the-art for classic MANETs and tested them over 3-D topologies to evaluate their assets and technical challenges.

One of the most profitable and emerging high-tech markets is the one that involves games for PC and consoles; a market that is growing year by year and that is rapidly evolving. Several big game corporations are implementing now the remote video streaming through the domestic network between two devices; a feature that regards not only PCs but also consoles. This paper investigates one of the main services of this type, the Steam In-Home Streaming, to analyze the generated network traffic when considering different types of game. Gathered data can help to understand whether this type of service can actually be supported by today's regular Internet connections.

[EN] Flying ad-hoc networks are becoming a promising solution for different application scenarios involving unmanned aerial vehicles, like urban surveillance or search and rescue missions. However, such networks present various and very specific communication issues. As a consequence, there are several research studies focused on analyzing their performance via simulation. Correctly modeling mobility is crucial in this context and although many mobility models are already available to reproduce the behavior of mobile nodes in an ad-hoc network, most of these models cannot be used to reliably simulate the motion of unmanned aerial vehicles. In this article, we list the existing mobility models and provide guidance to understand whether they could be actually adopted depending on the specific flying ad-hoc network application scenarios, while discussing their advantages and disadvantages.

Different theories state that future market values strongly depend on psychological and financial factors: when investors feel positive moods they invest and the value of the stock market increases; conversely, when they feel negative moods they do not invest and the value of the stock market decreases. Today, researchers are trying to exploit the data publicly available in social media and, in particular, different researches showed a connection between Twitter messages and the stock market index. In this paper, we do not focus on a generic stock market index, now we focus on the sole sentiment analysis. Instead, our goal is to investigate whether tweet messages can be used to predict the future trend (e.g., positive, negative or neutral) of the stocks of specific companies listed in the Dow Jones stock market. In particular, we focus on companies belonging to three different economic sectors (technology, service and health-care) and we consider the trend of 5 different metrics for each stock (e.g., highest, lowest, opening price, etc.) and the trend of 13 different variables of the tweets (e.g., volume, sentiment, tweets with links, etc.). Through an evaluation that employed more than 800,000 tweets, we show that some of the proposed ad-hoc prediction methods well predict (i.e., up to 82% of success) the next day trend of the stock values of specific companies.

Cloud-based entertainment is becoming a hot topic for researchers and practitioners. In this context, thin client or cloud based gaming promise to attract users with the possibility to dematerialize the console and let the user play any possible game for any platform through the Internet. Basically, the computational burden is left to the cloud while the user enjoys a fat video feed accessed through her/his thin client via the shared wireless gateway. Unfortunately, this model of interaction also raises new complex technical issues that requires specific networking solutions. In this short paper we aim at addressing the heterogeneous flow coexistence problem at the home wireless gateway. We propose a solution based on a TCP Vegas-like congestion control algorithm deployed on top of the home gateway. Our solution works out of the box with the standard protocols at server, router and client level, thereby making deployment straightforward.

In these last few years we are witnessing a change in the way video games are implemented. Starting from an early age, where a single developer was sometimes in charge of the whole creative process, we have moved now toward extremely large groups with a multi-layered organisation. This increasing complexity of team organisation, together with a tremendous growth of projects size, calls for the adoptions of development approaches leveraging on scalability and distributed computing environments. Unfortunately, today's development and execution environments for games (usually called game engines) are suffering from a number of architectural constraints. As a result, we strongly believe current engines will not be able to provide the flexibility and scalability required by game developers of the next generation. To overcome the above limitations, in this paper we propose SMASH (Stackless Microkernel Architecture for SHared environments): an architecture where a game engine is decomposed in several dynamic and independent software modules interacting via a microkernel-like message bus. Game modules can just be inserted, debugged, and removed from a running engine once its internal messaging protocol is clearly defined. Moreover, following this approach, game modules can be dynamically dislocated on multiple machines to obtain a truly distributed, scalable, and fault-resilient system where adaptation can be achieved mostly without downtime.

Active Queue Management (AQM) techniques have been proposed to support scenarios with many connections sharing the same bottleneck. The basic idea is that a smart management of the bottleneck queue can avoid the saturation of the link and ensure a smoother use of the available bandwidth. This is generally achieved by exploiting the flux control mechanism of TCP and its behavior in case of packet losses or other explicit notifications. In this paper we consider classic and innovative AQM techniques and analyse their performance under different scenarios through the use of mean field models.

The Internet edge has evolved from a simple consumer of information and data to eager producer feeding sensed data at a societal scale. The crowdsensing paradigm is a representative example which has the potential to revolutionize the way we acquire and consume data. Indeed, especially in the era of smartphones, the geographical and temporalscopusof data is often local. For instance, users’ queries are more and more frequently about a nearby object, event, person, location, and so forth. These queries could certainly be processed and answered locally, without the need for contacting a remote server through the Internet. In this scenario, the data is alimented (sensed) by the users and, as a consequence, data lifetime is limited by human organizational factors (e.g., mobility). From this basis, data survivability in the Area of Interest (AoI) is crucial and, if not guaranteed, could undermine system deployment. Addressing this scenario, we discuss and contribute with a novel protocol named AirCache, whose aim is to guarantee data availability in the AoI while at the same time reducing the data access costs at the network edges. We assess our proposal through a simulation analysis showing that our approach effectively fulfills its design objectives.

Internetworking often requires a large amount of users to share a common gateway to obtain connectivity to the Internet. Congestion avoidance mechanisms are used to prevent the saturation of the gateway which represents a bottleneck of the system. The most popular congestion avoidance mechanisms are the Explicit Congestion Notification (ECN) and the Random Early Detection (RED). Recently, a new method for the congestion avoidance has been proposed: the Smart Access Point with Limited Advertised Window (SAP-LAW). The main idea is to hijack the acknowledge packets in the TCP connections in order to artificially reduce the advertised destination window according to some bandwidth allocation policy. Therefore, the flux control mechanism is artificially exploited to control the congestion at the bottleneck. The advantage of this approach is that it does not require any modification in the TCP implementations at the clients. In this paper, we propose stochastic models for the ECN/RED and SAP-LAW mechanisms in order to compare their performances under different scenarios. The models are studied in mean field regime, i.e., under a great number of TCP connections and UDP based transmissions. Augmenting previous work on ECN/RED, we consider the presence of UDP traffic with bursts, and short lived TCP connections. The models for SAP-LAW are totally new. The comparison is performed in terms of different performance indices including average queue length, system throughput and expected queuing time.

Mobile games have come to revolutionize the mobile handset and gaming industry, pushing chip vendors to compete in order to provide better and better graphics capabilities by means of dedicated processors. This capability coupled with the sensing and communication ability offered by smartphones, provides the developers with the building blocks for innovative gaming solutions. In particular, multiplayer mobile games could exploit context and proximity information, providing an added value to the gaming experience. In this context, we present the design and analysis of a modern mobile and multiplayer version of the classic Pong game. In addition to the classic interaction model through remote server(s), players could interact and play locally by exploiting ad-hoc connectivity offered by the Wi-Fi Direct technology.

Mobile data traffic is becoming a key issue, causing traffic overload problems for classic resource providers. Tackling this issue, different solutions have been proposed, communed by the goal of alleviating the burden on the infrastructure while guaranteeing service availability. In this context, swarming protocols present the advantage of addressing the problem at its source, e.g., by engaging a lower number of direct connections with the network hosted server(s), while the requesters share these same resources among them. However, these solutions are generally verified only through simulation studies. While simulations consist in a necessary first step, they can be far from the actual outcome of employing real protocols and devices. To this end, we discuss BlueFall, an application platform that allows a rapid development and testing of swarming protocols using off-the-shelf smartphones and PCs. Pursuing our goal, we provide some evidence on two swarming schemes we have implemented in our testbed, profiling different access technologies.

Mobile communication devices are expected to overtake traditional desktop PCs and become the dominant point of entry to the Internet. This technology shift has boosted user demand for multimedia applications and services which are now typically accessed through the wireless interface. Users expect to be always connected and able to run a variety of applications which sometimes impose contrasting requirements. Of particular research interest in this scenario is the coexistence between two popular categories of traffic: elastic and real-time, both of them covering a wide range of user applications. In this paper, we investigate the above issue in the scenario where service connectivity is provided through a multihop wireless network. To this end, we study two representative applications, one for each of the above categories, which are content download and interactive game play. We show by means of extensive simulations, how both the content download's goodput and the online game's per-packet delivery delay can be improved through an appropriate solution implemented on the wireless Internet Gateway.

Computer-centered services and broadband wireless connectivity have boosted the demand for delivery of multimedia-based entertainment from the Internet to in-house wireless appliances. In this context, rich-media applications can be supported by a variety of protocols, each sharing the same bottleneck, affecting one another's performance. Indeed, in current systems, real-time applications (e.g., video streaming, online games) suffer from delays caused by the interference of elastic, best-effort (e.g., TCP-based download sessions) traffic. In this paper we propose a solution to this problem, addressed by deploying a Vegas-like congestion control algorithm at the home gateway, requiring no client-side modification.

In recent years, the number of appliances connected to the Interned has steadily increased thanks to the wide popularity of WIFI/3G enabled mobile devices. This has led to an increase of multimedia resource consumption, causing traffic overload problems for classic resource providers. Different solutions have been studied to shift this traffic overhead from the server(s) towards the client(s) through the employment of the so called swarming protocols. However, most of these solutions have been verified only through simulations. While simulations consist in a necessary first step, they can be far from the actual outcome of employing real protocols and devices. To this end, in this paper we describe BlueFall, an application that could allow to test swarming protocols using actual mobile phones. Pursuing our goal, we provide some preliminary evidence on two simple swarming schemes we have implemented in our testbed.

The mobile revolution has brought us the possibility to enjoy our favorite applications anywhere and anytime. In this context, interactive games over mobile networks embody a fascinating case study both for their commercial success and for their technical challenges, thus, sparking interest and development. The current state of the art of interactive games over mobile networks is captured in this article. We discuss main requirements and analyze possible combinations of existing solutions to provide better support for highly interactive game sessions with mobile players. Copyright © 2012 John Wiley & Sons, Ltd.

The market penetration of in-home entertainment systems is playing a crucial role in the diffusion of interactive multimedia services. In this context, thin-client game systems have received a lot of attention, shifting the computational burden of the game play toward the server while the client renders a fat video stream. This paper proposes an analysis of the network characteristics of the Remote Play for PlayStation 4 and PlayStation Vita, providing some insights on the network dynamics of this system under different game types. The measurements involve video games of different genres, analyzing the bitrates, the packet size, capturing the dynamics of the whole streaming session. Results indicate that the service generates a large quantity of big packets downstream and smaller and lesser packets upstream. Gathered data can help to understand if this type of service could be offered through the today's normal Internet connections.

Peer-to-peer (P2P) overlay networks and mobile ad hoc networks share many key characteristics such as self-organization and decentralization; they also face the crucial challenge of providing connectivity in a decentralized, dynamic environment. However, when considering ad hoc networks composed of mobile devices such as smartphones, we cannot rely on the continuous end-to-end path between peers as for classic Internet P2P applications; rather, we have to deal with low node density that creates mobile-disconnected networks. Porting the P2P paradigm into mobile networks to create a mobile-to-mobile file sharing application will create a modern type of delay/disruption tolerant network. In this context, we discuss our new approach for P2P file sharing that considers networks composed of mobile smartphones. As an innovative feature, we leverage on peer mobility to reach data in other disconnected networks by implementing a delay/disruption tolerant network-like store-delegate-and-forward communication model, where a peer can delegate unaccomplished file download tasks to other peers. In order to increase the chances of eventually receiving the requested file while reducing the number of transmitted messages and data, social awareness is exploited by nodes to delegate unaccomplished tasks only to peers that are expected to be encountered again in the future. Copyright © 2011 John Wiley & Sons, Ltd.

Testing Vehicular Network protocols can be quite problematic. In fact, vehicular experiments are often expensive in both economic and temporal terms. As a consequence, researchers generally resort to software simulations which are a neccessary first step but still not sufficient. In this paper, we present two possible experimentation frameworks that could give a boost to the testing of protocols for vehicular networks: the first framework is based on Android smartphones, while the second is based on commodity laptop computers. In order to assess the feasibility and the performance of the proposed frameworks, we implemented through them a representative vehicle-to-vehicle multi-hop broadcast algorithm, i.e., the Fast Broadcast algorithm.

The wide diffusion of Online Social Networks (OSNs) presents several advantages, like the definition of simple tools for information sharing and spreading. However, OSNs present also some drawbacks, one of the most important one is the problem of privacy disclosures. Distributed Online Social Networks (DOSNs), which decentralize the control of the social network, have been recently proposed to overcome these issues. The decentralization of the control has issued several challenges, one of the main ones is guaranteeing data availability without relying on a central server. To define users’ data allocation strategies, the knowledge of the structure of the ego network and of the user’ temporal behaviour is required. Unfortunately, the lack of real datasets limits the research in this field. The goal of this paper is the study of the behaviour of users in a real social network in order to define proper strategies to allocate the users’ data on the DOSN nodes. In particular, we present an analysis of the temporal affinity and of the social communities based on a real Facebook dataset.

Many researchers have nowadays shown a paramount interest in the rising field of Mobile Crowdsensing (MCS). Such paradigm is considered an easy and cost-effective choice for observing phenomena of common interest within the scope of Smart Cities and environmental monitoring. Nevertheless, it brings along many issues, such as fostering participation, reducing the power consumption of end devices and granting coverage. In this paper we focus on the problem of data collection control, which aims to avoid data redundancy and useless power consuming data transfers while assuring a sufficient number of observations for the purpose of coverage. In particular, we design a probabilistic distributed algorithm that aims to achieve a total per-zone number of observations close to a defined amount, while maximizing the fairness among users. We provide both the analytical definition of our algorithm and the performance evaluation through extensive simulations, establishing our algorithm as a good baseline for a poorly investigated problem.

In recent years, the growing prevalence of social networks makes it possible to utilize human users as sensors to inspect city environment and human activities. Consequently, valuable insights can be gained by applying data mining techniques to the data generated through social networks. In this work, a practical approach to combine data mining techniques with statistical analysis is proposed to implement crowd sensing in a smart city. A case study to analyze the relationship between weather conditions and traffic congestion in Beijing based on tweets posted on Sina Weibo platform is presented to demonstrate the proposed approach. Following the steps of raw dataset pre-processing, target dataset processing and statistical data analysis, analytic corpus containing tweets related to different weather conditions, traffic congestion and human outdoor activity is selected to test causal relationships by Granger Causality Test. The mediation analysis is also implemented to verify human outdoor activity as a mediator variable significantly carrying the influence of good weather to traffic congestion. The result demonstrates that outdoor activity serves as a mediator transmitting the effect of good weather on traffic congestion.