Search

Serverless computing has emerged as a very popular cloud technology, together with its companion Function-as-a-Service (FaaS) programming model enabling invocations of stateless functions from clients. An evolution of serverless is now taking place, shifting it towards the edge of the network and broadening its scope to stateful functions, as well. In this paper we argue that stateless vs. stateful is not a dichotomy of the application per se, but rather a time-varying property of most (if not all) applications, as confirmed by the analysis of real traces collected in a production environment. Based on this observation, we propose a mathematical formulation of a resource allocation problem that jointly encompasses both operation modes, dubbed lambda vs. mu, which can be solved efficiently at run-time by an edge orchestrator. We evaluate the proposed solution via simulation experiments in realistic network and workload conditions, which leads the way to the practical realization of a system where applications can freely adapt their current operation mode and optimize their performance at a minimum cost of operation from the network's perspective., Comment: Accepted at IEEE SMARTCOMP 2022

The evolution of quantum computing technologies has been advancing at a steady pace in the recent years, and the current trend suggests that it will become available at scale for commercial purposes in the near future. The acceleration can be boosted by pooling compute infrastructures to either parallelize algorithm execution or solve bigger instances that are not feasible on a single quantum computer, which requires an underlying Quantum Internet: the interconnection of quantum computers by quantum links and repeaters to exchange entangled quantum bits. However, Quantum Internet research so far has been focused on provisioning point-to-point flows only, which is suitable for (e.g.) quantum sensing and metrology, but not for distributed quantum computing. In this paper, after a primer on quantum computing and networking, we investigate the requirements and objectives of smart computing on distributed nodes from the perspective of quantum network provisioning. We then design a resource allocation strategy that is evaluated through a comprehensive simulation campaign, whose results highlight the key features and performance issues, and lead the way to further investigation in this direction., Comment: Accepted for presentation at IEEE SMARTCOMP 2022

Contacts between people are the absolute drivers of contagious respiratory infections. For this reason, limiting and tracking contacts is a key strategy for the control of the COVID-19 epidemic. Digital contact tracing has been proposed as an automated solution to scale up traditional contact tracing. However, the required penetration of contact tracing apps within a population to achieve a desired target in the control of the epidemic is currently under discussion within the research community. In order to understand the effects of digital contact tracing, several mathematical models have been proposed. In this article, we survey the main ones and we propose a compartmental SEIR model with which it is possible, differently from the models in the related literature, to derive closed-form conditions regarding the control of the epidemic as a function of the contact tracing apps penetration and the testing efficiency. Closed-form conditions are crucial for the understandability of models, and thus for decision makers (including digital contact tracing designers) to correctly assess the dependencies within the epidemic. With our model, we find that digital contact tracing alone can rarely tame an epidemic: for unrestrained COVID-19, this would require a testing turnaround of around 1 day and app uptake above 80% of the population, which are very difficult to achieve in practice. However, digital contact tracing can still be effective if complemented with other mitigation strategies, such as social distancing and mask-wearing., Comment: This work was partially funded by the H2020 SoBigData++ (Grant No 871042), H2020 HumaneAI-Net (Grant No 952026), and CHIST-ERA SAI (Grant No not yet available) projects

Well-established cognitive models coming from anthropology have shown that, due to the cognitive constraints that limit our "bandwidth" for social interactions, humans organize their social relations according to a regular structure. In this work, we postulate that similar regularities can be found in other cognitive processes, such as those involving language production. In order to investigate this claim, we analyse a dataset containing tweets of a heterogeneous group of Twitter users (regular users and professional writers). Leveraging a methodology similar to the one used to uncover the well-established social cognitive constraints, we find regularities at both the structural and semantic level. At the former, we find that a concentric layered structure (which we call ego network of words, in analogy to the ego network of social relationships) very well captures how individuals organise the words they use. The size of the layers in this structure regularly grows (approximately 2-3 times with respect to the previous one) when moving outwards, and the two penultimate external layers consistently account for approximately 60% and 30% of the used words, irrespective of the number of the total number of layers of the user. For the semantic analysis, each ring of each ego network is described by a semantic profile, which captures the topics associated with the words in the ring. We find that ring #1 has a special role in the model. It is semantically the most dissimilar and the most diverse among the rings. We also show that the topics that are important in the innermost ring also have the characteristic of being predominant in each of the other rings, as well as in the entire ego network. In this respect, ring #1 can be seen as the semantic fingerprint of the ego network of words., Comment: This work was partially funded by the H2020 SoBigData++ (Grant No 871042), H2020 HumaneAI-Net (Grant No 952026), and CHIST-ERA SAI (Grant No not yet available) projects. arXiv admin note: text overlap with arXiv:2110.06015

In this paper, we address the problem of supporting stateful workflows following a Function-as-a-Service (FaaS) model in edge networks. In particular we focus on the problem of data transfer, which can be a performance bottleneck due to the limited speed of communication links in some edge scenarios and we propose three different schemes: a pure FaaS implementation, StateProp, i.e., propagation of the application state throughout the entire chain of functions, and StateLocal, i.e., a solution where the state is kept local to the workers that run functions and retrieved only as needed. We then extend the proposed schemes to the more general case of applications modeled as Directed Acyclic Graphs (DAGs), which cover a broad range of practical applications, e.g., in the Internet of Things (IoT) area. Our contribution is validated via a prototype implementation. Experiments in emulated conditions show that applying the data locality principle reduces significantly the volume of network traffic required and improves the end-to-end delay performance, especially with local caching on edge nodes and low link speeds., Comment: To appear in Elsevier Pervasive and Mobile Computing

Cloud auto-scaling mechanisms are typically based on reactive automation rules that scale a cluster whenever some metric, e.g., the average CPU usage among instances, exceeds a predefined threshold. Tuning these rules becomes particularly cumbersome when scaling-up a cluster involves non-negligible times to bootstrap new instances, as it happens frequently in production cloud services. To deal with this problem, we propose an architecture for auto-scaling cloud services based on the status in which the system is expected to evolve in the near future. Our approach leverages on time-series forecasting techniques, like those based on machine learning and artificial neural networks, to predict the future dynamics of key metrics, e.g., resource consumption metrics, and apply a threshold-based scaling policy on them. The result is a predictive automation policy that is able, for instance, to automatically anticipate peaks in the load of a cloud application and trigger ahead of time appropriate scaling actions to accommodate the expected increase in traffic. We prototyped our approach as an open-source OpenStack component, which relies on, and extends, the monitoring capabilities offered by Monasca, resulting in the addition of predictive metrics that can be leveraged by orchestration components like Heat or Senlin. We show experimental results using a recurrent neural network and a multi-layer perceptron as predictor, which are compared with a simple linear regression and a traditional non-predictive auto-scaling policy. However, the proposed framework allows for the easy customization of the prediction policy as needed., Comment: Accepted at 2021 IEEE/ACM 14th International Conference on Utility and Cloud Computing (UCC'21)

Serverless computing is becoming widely adopted among cloud providers, thus making increasingly popular the Function-as-a-Service (FaaS) programming model, where the developers realize services by packaging sequences of stateless function calls. The current technologies are very well suited to data centers, but cannot provide equally good performance in decentralized environments, such as edge computing systems, which are expected to be typical for Internet of Things (IoT) applications. In this paper, we fill this gap by proposing a framework for efficient dispatching of stateless tasks to in-network executors so as to minimize the response times while exhibiting short- and long-term fairness, also leveraging information from a virtualized network infrastructure when available. Our solution is shown to be simple enough to be installed on devices with limited computational capabilities, such as IoT gateways, especially when using a hierarchical forwarding extension. We evaluate the proposed platform by means of extensive emulation experiments with a prototype implementation in realistic conditions. The results show that it is able to smoothly adapt to the mobility of clients and to the variations of their service request patterns, while coping promptly with network congestion.

The cognitive constraints that humans exhibit in their social interactions have been extensively studied by anthropologists, who have highlighted their regularities across different types of social networks. We postulate that similar regularities can be found in other cognitive processes, such as those involving language production. In order to provide preliminary evidence for this claim, we analyse a dataset containing tweets of a heterogeneous group of Twitter users (regular users and professional writers). Leveraging a methodology similar to the one used to uncover the well-established social cognitive constraints, we find that a concentric layered structure (which we call ego network of words, in analogy to the ego network of social relationships) very well captures how individuals organise the words they use. The size of the layers in this structure regularly grows (approximately 2-3 times with respect to the previous one) when moving outwards, and the two penultimate external layers consistently account for approximately 60% and 30% of the used words (the outermost layer contains 100% of the words), irrespective of the number of the total number of layers of the user., Comment: This work was partially funded by the following projects. European Union's Horizon 2020 research and innovation programme: SoBigData++ (No 871042), HumaneAI-Net (No 952026), MARVEL (No 957337). Italian PON-MISE program: OK-INSAID project (No ARS01 00917)

Academic migration is the change of host institution by a researcher, typically aimed at achieving a stronger research profile. Scientific features such as the number of collaborations, the productivity and its research impact tend to be directly affected by such movements. In this paper, we analyse the dynamics of the collaboration network of researchers as they move from an institution to the next one. We specifically highlight cases where they increase and when they shrink, and quantify the dependency between the collaboration networks before and after such a movement. Finally, we drill down the analysis by dividing movements depending on the career stage of the researchers. The analysis shows a remarkable dynamism of collaboration networks across migrations. Interestingly, not always movements result in larger collaboration networks, while the overall similarity between networks across movements is quite limited on average. Qualitatively, the same effects can be found at all career stages, while, clearly, the magnitude of them might vary. These results are based on a dataset extracted from Scopus, containing detailed scientific information for the publications of 84,141 researchers., Comment: This work was partially funded by the following projects. European Union's Horizon 2020 research and innovation programme: SoBigData++ (No 871042), HumaneAI-Net (No 952026), MARVEL (No 957337). Italian PON-MISE program: OK-INSAID project (No ARS01 00917)

Ego networks have proved to be a valuable tool for understanding the relationships that individuals establish with their peers, both in offline and online social networks. Particularly interesting are the cognitive constraints associated with the interactions between the ego and the members of their ego network, which limit individuals to maintain meaningful interactions with no more than 150 people, on average, and to arrange such relationships along concentric circles of decreasing engagement. In this work, we focus on the ego networks of journalists on Twitter, considering 17 different countries, and we investigate whether they feature the same characteristics observed for other relevant classes of Twitter users, like politicians and generic users. Our findings are that journalists are generally more active and interact with more people than generic users, regardless of their country. Their ego network structure is very aligned with reference models derived in anthropology and observed in general human ego networks. Remarkably, the similarity is even higher than the one of politicians and generic users ego networks. This may imply a greater cognitive involvement with Twitter for journalists than for other user categories. From a dynamic perspective, journalists have stable short-term relationships that do not change much over time. In the longer term, though, ego networks can be pretty dynamic, especially in the innermost circles. Moreover, the ego-alter ties of journalists are often information-driven, as they are mediated by hashtags both at their inception and during their lifetime. Finally, we found that relationships between journalists are assortative in popularity: journalists tend to engage with other journalists of similar popularity, in all layers but especially in their innermost ones., Comment: This work was partially funded by the following projects. European Union's Horizon 2020 research and innovation programme: SoBigData++ (No 871042), HumaneAI-Net (No 952026), MARVEL (No 957337). Italian PON-MISE program: OK-INSAID project (No ARS01 00917). CHIST-ERA program: SAI project (grant CHIST-ERA-19-XAI-010, funded by MUR, grant number not yet available)

The widespread diffusion of mobile phones is triggering an exponential growth of mobile data traffic that is likely to cause, in the near future, considerable traffic overload issues even in last-generation cellular networks. Offloading part of the traffic to other networks is considered a very promising approach and, in particular, in this paper, we consider offloading through opportunistic networks of users' devices. However, the performance of this solution strongly depends on the pattern of encounters between mobile nodes, which should therefore be taken into account when designing offloading control algorithms. In this paper, we propose an adaptive offloading solution based on the Reinforcement Learning framework and we evaluate and compare the performance of two well-known learning algorithms: Actor-Critic and Q-Learning. More precisely, in our solution the controller of the dissemination process, once trained, is able to select a proper number of content replicas to be injected into the opportunistic network to guarantee the timely delivery of contents to all interested users. We show that our system based on Reinforcement Learning is able to automatically learn a very efficient strategy to reduce the traffic on the cellular network, without relying on any additional context information about the opportunistic network. Our solution achieves a higher level of offloading with respect to other state-of-the-art approaches, in a range of different mobility settings. Moreover, we show that a more refined learning solution, based on the Actor-Critic algorithm, is significantly more efficient than a simpler solution based on Q-learning.

In FaaS, users invoke remote functions, which encapsulate service(s). These functions typically need to remotely access a persistent state via external services: this makes the paradigm less attractive in edge systems, especially for IoT applications, due to the increased delay and outbound traffic. We propose to generalize the FaaS paradigm by allowing functions to alternate between remote-state and local-state phases, depending on internal and external conditions, and dedicating a container with persistent memory to functions when in a local-state phase. We present initial results showing that this simple yet powerful pattern allows to better utilize the available resources, which are scarce on edge nodes, while significantly reducing tail latencies, which is key to enable many new applications based on real-time ML, e.g., in smart vehicles and smart factory scenarios, Comment: Accepted for publication at IEEE Computer

It is commonly agreed that data will be one of the cornerstones of Future Internet systems. In this context, mobile Opportunistic Networks (ONs) are one of the key paradigms to support, in a self-organising and decentralised manner, the growth of data generated by localized interactions between users mobile devices, and between them and nearby devices such as IoT nodes. In ONs, the spontaneous collaboration among mobile devices is exploited to disseminate data toward interested users. However, the limited resources and knowledge available at each node, and the vast amount of data available, make it difficult to devise efficient schemes to accomplish this task. Recent solutions propose to equip each device with data filtering methods derived from human data processing schemes, known as Cognitive Heuristics, i.e. very effective methods used by the brain to quickly drop useless information, while keeping the most relevant one. These solutions can become less effective when facing dynamic scenarios or situations where nodes cannot fully collaborate. One of the reasons is that the solutions proposed so far do not take take into account the social structure of the environment where the nodes move in. To be more effective, the selection of information performed by each node should take into consideration this dimension of the environment. In this paper we propose a social-based data dissemination scheme, based on the cognitive Social Circle Heuristic. This evaluation method exploits the structure of the social environment to make inferences about the relevance of discovered information. We show how the Social Circle Heuristic, coupled with a cognitive-based community detection scheme, can be exploited to design an effective data dissemination algorithm for ONs. We provide a detailed analysis of the performance of the proposed solution via simulation.

Data management using Device-to-Device (D2D) communications and opportunistic networks (ONs) is one of the main focuses of human-centric pervasive Internet services. In the recently proposed "Internet of People" paradigm, accessing relevant data dynamically generated in the environment nearby is one of the key services. Moreover, personal mobile devices become proxies of their human users while exchanging data in the cyber world and, thus, largely use ONs and D2D communications for exchanging data directly. Recently, researchers have successfully demonstrated the viability of embedding human cognitive schemes in data dissemination algorithms for ONs. In this paper, we consider one such scheme based on the recognition heuristic, a human decision-making scheme used to efficiently assess the relevance of data. While initial evidence about its effectiveness is available, the evaluation of its behaviour in large-scale settings is still unsatisfactory. To overcome these limitations, we have developed a novel hybrid modelling methodology, which combines an analytical model of data dissemination within small-scale communities of mobile users, with detailed simulations of interactions between different communities. This methodology allows us to evaluate the algorithm in large-scale city- and country-wide scenarios. Results confirm the effectiveness of cognitive data dissemination schemes, even when content popularity is very heterogenous.

Due to the pervasive diffusion of personal mobile and IoT devices, many ``smart environments'' (e.g., smart cities and smart factories) will be, among others, generators of huge amounts of data. Currently, this is typically achieved through centralised cloud-based data analytics services. However, according to many studies, this approach may present significant issues from the standpoint of data ownership, and even wireless network capacity. One possibility to cope with these shortcomings is to move data analytics closer to where data is generated. In this paper, we tackle this issue by proposing and analyzing a distributed learning framework, whereby data analytics are performed at the edge of the network, i.e., on locations very close to where data is generated. Specifically, in our framework, partial data analytics are performed directly on the nodes that generate the data, or on nodes close by (e.g., some of the data generators can take this role on behalf of subsets of other nodes nearby). Then, nodes exchange partial models and refine them accordingly. Our framework is general enough to host different analytics services. In the specific case analysed in the paper, we focus on a learning task, considering two distributed learning algorithms. Using an activity recognition and a pattern recognition task, both on reference datasets, we compare the two learning algorithms between each other and with a central cloud solution (i.e., one that has access to the complete datasets). Our results show that using distributed machine learning techniques, it is possible to drastically reduce the network overhead, while obtaining performance comparable to the cloud solution in terms of learning accuracy. The analysis also shows when each distributed learning approach is preferable, based on the specific distribution of the data on the nodes.

In future IoT environments it is expected that the role of personal devices of mobile users in the physical area where IoT devices are deployed will become more and more important. In particular, due to the push towards decentralisation of services towards the edge, it is likely that a significant share of data generated by IoT devices will be needed by other (mobile) nodes nearby, while global Internet access will be limited only to a small fraction of data. In this context, opportunistic networking schemes can be adopted to build efficient content-centric protocols, through which data generated by IoT devices (or by mobile nodes themselves) can be accessed by the other nodes nearby. In this paper, we propose MobCCN, which is an ICN-compliant protocol for this heterogeneous environment. MobCCN is designed to implement the routing and forwarding mechanisms of the main ICN realisations, such as CCN. The original aspect of MobCCN is to implement an efficient opportunistic networking routing scheme to populate the Forwarding Interest Base (FIB) tables of the nodes, in order to guide the propagation of Interest packets towards nodes that store the required data. Specifically, MobCCN defines the utility of each node as a forwarder of Interest packets for a certain type of content, such that Interest packets can be propagated along a positive utility gradient, until reaching some node storing the data. We evaluate MobCCN against protocols representing two possible endpoints of the spectrum, respectively in terms of minimising the data delivery delay and the resource consumption. Performance results show that MobCCN is very effective and efficient, as it guarantees very high delivery rates and low delays, while keeping the total generated traffic at a reasonable level and also saving local resources.

Due to the pervasive diffusion of personal mobile and IoT devices, many "smart environments" (e.g., smart cities and smart factories) will be, generators of huge amounts of data. Currently, analysis of this data is typically achieved through centralised cloud-based services. However, according to many studies, this approach may present significant issues from the standpoint of data ownership, as well as wireless network capacity. In this paper, we exploit the fog computing paradigm to move computation close to where data is produced. We exploit a well-known distributed machine learning framework (Hypothesis Transfer Learning), and perform data analytics on mobile nodes passing by IoT devices, in addition to fog gateways at the edge of the network infrastructure. We analyse the performance of different configurations of the distributed learning framework, in terms of (i) accuracy obtained in the learning task and (ii) energy spent to send data between the involved nodes. Specifically, we consider reference wireless technologies for communication between the different types of nodes we consider, e.g. LTE, Nb-IoT, 802.15.4, 802.11, etc. Our results show that collecting data through the mobile nodes and executing the distributed analytics using short-range communication technologies, such as 802.15.4 and 802.11, allows to strongly reduce the energy consumption of the system up to $94\%$ with a loss in accuracy w.r.t. a centralised cloud solution up to $2\%$.

Edge computing is an emerging paradigm to enable low-latency applications, like mobile augmented reality, because it takes the computation on processing devices that are closer to the users. On the other hand, the need for highly scalable execution of stateless tasks for cloud systems is driving the definition of new technologies based on serverless computing. In this paper, we propose a novel architecture where the two converge to enable low-latency applications: this is achieved by offloading short-lived stateless tasks from the user terminals to edge nodes. Furthermore, we design a distributed algorithm that tackles the research challenge of selecting the best executor, based on real-time measurements and simple, yet effective, prediction algorithms. Finally, we describe a new performance evaluation framework specifically designed for an accurate assessment of algorithms and protocols in edge computing environments, where the nodes may have very heterogeneous networking and processing capabilities. The proposed framework relies on the use of real components on lightweight virtualization mixed with simulated computation and is well-suited to the analysis of several applications and network environments. Using our framework, we evaluate our proposed architecture and algorithms in small- and large-scale edge computing scenarios, showing that our solution achieves similar or better delay performance than a centralized solution, with far less network utilization.

Being able to recommend links between users in online social networks is important for users to connect with like-minded individuals as well as for the platforms themselves and third parties leveraging social media information to grow their business. Predictions are typically based on unsupervised or supervised learning, often leveraging simple yet effective graph topological information, such as the number of common neighbors. However, we argue that richer information about personal social structure of individuals might lead to better predictions. In this paper, we propose to leverage well-established social cognitive theories to improve link prediction performance. According to these theories, individuals arrange their social relationships along, on average, five concentric circles of decreasing intimacy. We postulate that relationships in different circles have different importance in predicting new links. In order to validate this claim, we focus on popular feature-extraction prediction algorithms (both unsupervised and supervised) and we extend them to include social-circles awareness. We validate the prediction performance of these circle-aware algorithms against several benchmarks (including their baseline versions as well as node-embedding- and GNN-based link prediction), leveraging two Twitter datasets comprising a community of video gamers and generic users. We show that social-awareness generally provides significant improvements in the prediction performance, beating also state-of-the-art solutions like node2vec and SEAL, and without increasing the computational complexity. Finally, we show that social-awareness can be used in place of using a classifier (which may be costly or impractical) for targeting a specific category of users., Comment: This work was partially funded by the following projects. European Union's Horizon 2020 research and innovation programme: SoBigData++ (No 871042), HumaneAI-Net (No 952026), MARVEL (No 957337). Italian PON-MISE program: OK-INSAID project (No ARS01 00917). CHIST-ERA program: SAI project (grant CHIST-ERA-19-XAI-010, funded by MUR, grant number not yet available). in IEEE Transactions on Computational Social Systems, 2022

Thanks to the widespread availability of large-scale datasets on scholarly outputs, science itself has come under the microscope with the aim of capturing a quantitative understanding of its workings. In this study, we leverage well-established cognitive models coming from anthropology in order to characterise the personal network of collaborations between scientists, i.e., the network considered from the standpoint of each individual researcher (referred to as ego network), in terms of the cognitive investment they devote to the different collaborations. Building upon these models, we study the interplay between the structure of academic collaborations, academic performance, and academic mobility at different career stages. We take into account both purely academic mobility (i.e., the number of affiliation changes) and geographical mobility (i.e., physical relocations to different countries). For our investigation, we rely on a dataset comprising the geo-referenced publications of a group of 81,500 authors extracted from Scopus, one of the biggest repositories of academic knowledge. Our main finding is that there is a clear correlation between the structure of co-authorship ego networks and academic performance indices: the more one publishes and the higher their impact, the larger their collaboration network. However, we observe a capacity bound effect, whereby, beyond a certain point, higher performances become increasingly less correlated with large collaboration networks. We also find that international academic migrants are better at growing their networks than researchers that only migrate within the same country, but the latter seem to be better in exploiting their collaboration to achieve higher impact. High academic mobility does not appear to translate into better academic performance or larger collaboration networks., Comment: This work was partially funded by SoBigData++ (871042) and HumanE-AI-Net (952026) projects, which received funding from the European Union (EU) Horizon 2020 program

Beyond 5G networks are expected to support massive traffic through decentralized solutions and advanced networking mechanisms. This paper aims at contributing towards this vision through the integration of device-centric wireless networks, including Device-to-Device (D2D) communications, and the Next Generation of Opportunistic networking (NGO). This integration offers multiple communication modes such as opportunistic cellular and opportunistic D2D-aided communications. Previous studies have demonstrated the potential and benefits of this integration in terms of energy efficiency, spectral efficiency and traffic offloading. We propose an integration of device-centric wireless networks and NGO that is not driven by a precise knowledge of the presence of the links. The proposed technique utilizes a novel concept of graph to model the evolution of the networking conditions and network connectivity. Uncertainties and future conditions are included in the proposed graph model through anticipatory mobile networking to estimate the transmission energy cost of the different communication modes. Based on these estimates, the devices schedule their transmissions using the most efficient communication mode. These decisions are later revisited in real-time using more precise knowledge about the network state. The conducted evaluation shows that the proposed technique significantly reduces the energy consumption (from 60% to 90% depending on the scenario) compared to traditional single-hop cellular communications and performs closely to an ideal oracle based system with full knowledge of present and future events. The transmission and computational overheads of the proposed technique show small impact on such energy gains., Comment: 17 pages, 6 figures

The exponential growth of devices and data at the edges of the Internet is rising scalability and privacy concerns on approaches based exclusively on remote cloud platforms. Data gravity, a fundamental concept in Fog Computing, points towards decentralisation of computation for data analysis, as a viable alternative to address those concerns. Decentralising AI tasks on several cooperative devices means identifying the optimal set of locations or Collection Points (CP for short) to use, in the continuum between full centralisation (i.e., all data on a single device) and full decentralisation (i.e., data on source locations). We propose an analytical framework able to find the optimal operating point in this continuum, linking the accuracy of the learning task with the corresponding network and computational cost for moving data and running the distributed training at the CPs. We show through simulations that the model accurately predicts the optimal trade-off, quite often an intermediate point between full centralisation and full decentralisation, showing also a significant cost saving w.r.t. both of them. Finally, the analytical model admits closed-form or numeric solutions, making it not only a performance evaluation instrument but also a design tool to configure a given distributed learning task optimally before its deployment., Comment: Accepted for publication in IEEE TNSE

Neural Networks (NN), although successfully applied to several Artificial Intelligence tasks, are often unnecessarily over-parametrised. In edge/fog computing, this might make their training prohibitive on resource-constrained devices, contrasting with the current trend of decentralising intelligence from remote data centres to local constrained devices. Therefore, we investigate the problem of training effective NN models on constrained devices having a fixed, potentially small, memory budget. We target techniques that are both resource-efficient and performance effective while enabling significant network compression. Our Dynamic Hard Pruning (DynHP) technique incrementally prunes the network during training, identifying neurons that marginally contribute to the model accuracy. DynHP enables a tunable size reduction of the final neural network and reduces the NN memory occupancy during training. Freed memory is reused by a \emph{dynamic batch sizing} approach to counterbalance the accuracy degradation caused by the hard pruning strategy, improving its convergence and effectiveness. We assess the performance of DynHP through reproducible experiments on three public datasets, comparing them against reference competitors. Results show that DynHP compresses a NN up to $10$ times without significant performance drops (up to $3.5\%$ additional error w.r.t. the competitors), reducing up to $80\%$ the training memory occupancy.

The rapid dynamics of COVID-19 calls for quick and effective tracking of virus transmission chains and early detection of outbreaks, especially in the phase 2 of the pandemic, when lockdown and other restriction measures are progressively withdrawn, in order to avoid or minimize contagion resurgence. For this purpose, contact-tracing apps are being proposed for large scale adoption by many countries. A centralized approach, where data sensed by the app are all sent to a nation-wide server, raises concerns about citizens' privacy and needlessly strong digital surveillance, thus alerting us to the need to minimize personal data collection and avoiding location tracking. We advocate the conceptual advantage of a decentralized approach, where both contact and location data are collected exclusively in individual citizens' "personal data stores", to be shared separately and selectively, voluntarily, only when the citizen has tested positive for COVID-19, and with a privacy preserving level of granularity. This approach better protects the personal sphere of citizens and affords multiple benefits: it allows for detailed information gathering for infected people in a privacy-preserving fashion; and, in turn this enables both contact tracing, and, the early detection of outbreak hotspots on more finely-granulated geographic scale. Our recommendation is two-fold. First to extend existing decentralized architectures with a light touch, in order to manage the collection of location data locally on the device, and allow the user to share spatio-temporal aggregates - if and when they want, for specific aims - with health authorities, for instance. Second, we favour a longer-term pursuit of realizing a Personal Data Store vision, giving users the opportunity to contribute to collective good in the measure they want, enhancing self-awareness, and cultivating collective efforts for rebuilding society., Comment: Revised text. Additional authors

Information and communication technologies are permeating all aspects of industrial and manufacturing systems, expediting the generation of large volumes of industrial data. This article surveys the recent literature on data management as it applies to networked industrial environments and identifies several open research challenges for the future. As a first step, we extract important data properties (volume, variety, traffic, criticality) and identify the corresponding data enabling technologies of diverse fundamental industrial use cases, based on practical applications. Secondly, we provide a detailed outline of recent industrial architectural designs with respect to their data management philosophy (data presence, data coordination, data computation) and the extent of their distributiveness. Then, we conduct a holistic survey of the recent literature from which we derive a taxonomy of the latest advances on industrial data enabling technologies and data centric services, spanning all the way from the field level deep in the physical deployments, up to the cloud and applications level. Finally, motivated by the rich conclusions of this critical analysis, we identify interesting open challenges for future research. The concepts presented in this article thematically cover the largest part of the industrial automation pyramid layers. Our approach is multidisciplinary, as the selected publications were drawn from two fields; the communications, networking and computation field as well as the industrial, manufacturing and automation field. The article can help the readers to deeply understand how data management is currently applied in networked industrial environments, and select interesting open research opportunities to pursue.

Within the framework of a Device-to-Device (D2D) data offloading system for cellular networks, we propose a Content Delivery Management System (CDMS) in which the instant for transmitting a content to a requesting node, through a D2D communication, is selected to minimize the energy consumption required for transmission. The proposed system is particularly fit to highly dynamic scenarios, such as vehicular networks, where the network topology changes at a rate which is comparable with the order of magnitude of the delay tolerance. We present an analytical framework able to predict the system performance, in terms of energy consumption, using tools from the theory of point processes, validating it through simulations, and provide a thorough performance evaluation of the proposed CDMS, in terms of energy consumption and spectrum use. Our performance analysis compares the energy consumption and spectrum use obtained with the proposed scheme with the performance of two benchmark systems. The first one is a plain classic cellular scheme, the second is a D2D data offloading scheme (that we proposed in previous works) in which the D2D transmissions are performed as soon as there is a device with the required content within the maximum D2D transmission range...

In today's typical industrial environments, the computation of the data distribution schedules is highly centralised. Typically, a central entity configures the data forwarding paths so as to guarantee low delivery delays between data producers and consumers. However, these requirements might become impossible to meet later on, due to link or node failures, or excessive degradation of their performance. In this paper, we focus on maintaining the network functionality required by the applications after such events. We avoid continuously recomputing the configuration centrally, by designing an energy efficient local and distributed path reconfiguration method. Specifically, given the operational parameters required by the applications, we provide several algorithmic functions which locally reconfigure the data distribution paths, when a communication link or a network node fails. We compare our method through simulations to other state of the art methods and we demonstrate performance gains in terms of energy consumption and data delivery success rate as well as some emerging key insights which can lead to further performance gains.

Ego networks have proved to be a valuable tool for understanding the relationships that individuals establish with their peers, both in offline and online social networks. Particularly interesting are the cognitive constraints associated with the interactions between the ego and the members of their ego network, whereby individuals cannot maintain meaningful interactions with more than 150 people, on average. In this work, we focus on the ego networks of journalists on Twitter, and we investigate whether they feature the same characteristics observed for other relevant classes of Twitter users, like politicians and generic users. Our findings are that journalists are generally more active and interact with more people than generic users. Their ego network structure is very aligned with reference models derived from the social brain hypothesis and observed in general human ego networks. Remarkably, the similarity is even higher than the one of politicians and generic users ego networks. This may imply a greater cognitive involvement with Twitter than with other social interaction means. Moreover, the ego networks of journalists are much stabler than those of politicians and generic users, and the ego-alter ties are often information-driven., Comment: Accepted at OSNED 2018 - colocated with WWW'18

We consider a scheme for offloading the delivery of contents to mobile devices in a vehicular networking scenario. Each content can be delivered to the requesting device either by a neighboring device or, at the expiration of a maximum delay, by the network infrastructure nodes. We compute the analytical expression of the probability that the content delivery is offloaded through a Device-to-Device (D2D) communication as a function of the maximum transmission range allowed for D2D communications, the content popularity, and the vehicles speed. We show that, using the model, it is possible to identify the optimal maximum transmission range, which minimizes the total energy consumption (of the infrastructure plus mobile devices)., Comment: v2 and v3 include minor corrections in the notation used in some equations, along with the correction of some typos

In opportunistic networks, putting devices in energy saving mode is crucial to preserve their battery, and hence to increase the lifetime of the network and foster user participation. A popular strategy for energy saving is duty cycling. However, when in energy saving mode, users cannot communicate with each other. The side effects of duty cycling are twofold. On the one hand, duty cycling may reduce the number of usable contacts for delivering messages, increasing intercontact times and delays. On the other hand, duty cycling may break long contacts into smaller contacts, thus also reducing the capacity of the opportunistic network. Despite the potential serious effects, the role played by duty cycling in opportunistic networks has been often neglected in the literature. In order to fill this gap, in this paper we propose a general model for deriving the pairwise contact and intercontact times measured when a duty cycling policy is superimposed on the original encounter process determined only by node mobility. The model we propose is general, i.e., not bound to a specific distribution of contact and intercontact times, and very accurate, as we show exploiting two traces of real human mobility for validation. Using this model, we derive several interesting results about the properties of measured contact and intercontact times with duty cycling: their distribution, how their coefficient of variation changes depending on the duty cycle value, how the duty cycling affects the capacity and delay of an opportunistic network. The applicability of these results is broad, ranging from performance models for opportunistic networks that factor in the duty cycling effect, to the optimisation of the duty cycle to meet a certain target performance., Comment: Accepted for publication on ACM Transactions on Modeling and Performance Evaluation of Computing Systems (ToMPECS)