Search

With the continuous advancement of smart devices and their demand for data, the complex computation that was previously exclusive to the cloud server is now moving towards the edge of the network. For numerous reasons (e.g., applications demanding low latencies and data privacy), data-based computation has been brought closer to the originating source, forging the edge computing paradigm. Together with machine learning, edge computing has become a powerful local decision-making tool, fostering the advent of edge learning. However, the latter has become delay-sensitive and resource-thirsty in terms of hardware and networking. New methods have been developed to solve or minimize these issues, as proposed in this study. We first investigated representative communication methods for edge learning and inference (ELI), focusing on data compression, latency, and resource management. Next, we proposed an ELIbased video data prioritization framework that only considers data with events and hence significantly reduces the transmission and storage resources when implemented in surveillance networks. Furthermore, we critically examined various communication aspects related to edge learning by analyzing their issues and highlighting their advantages and disadvantages. Finally, we discuss the challenges and present issues that remain.

In surveillance systems, vast amounts of data are collected from different sources to monitor ongoing video activities. Usually, video data is passively captured by visual sensors and forwarded to the command center, without intelligent Edge functionalities to select essential video information and locally detect abnormal events therein. These shortcomings often seen in practical surveillance scenarios lead to a wastage of storage resources and make data management, retrieval, and informed decision complex and time-consuming. Therefore, endowing visual sensors with video summarization capabilities is of utmost importance for smarter surveillance systems. This study departs from this rationale to propose an efficient neural networks-based video summarization method for surveillance systems. The proposed approach learns how to optimally segment a video by measuring informative features from the data flow, followed by memorability and entropy to maintain the relevance and diversity of the video summary produced on the Edge. Experimental results over benchmark datasets reveal that the proposed scheme outperforms other state-of-the-art counterparts and proves the effectiveness of our method for video summarization in smart cities.

In the past, space trajectory design was limited to the optimal design of transfers to single destinations. However, a somewhat more daring approach is today making the space community to consider missions that visit, with one single spacecraft, a multitude of celestial objects; such as asteroid tour mission proposals CASTAway or MANTIS, which both proposed to visit 10 or more asteroids in a quick succession of asteroid fly-bys. The design of these so-called asteroid tours is complicated by the fact that the sequence of asteroids is not known a priori, but is the objective of the optimisation itself. This leads to a complex mixed-integer non-linear programming (MINLP) problem, on which the decision variables assume both continuous and discrete values. Beyond the obvious complexity of such problem formulation, preliminary mission design requires not only to locate the global optimum solution but, also, to map the ensemble of solutions that leads to feasible transfers. This paper analyses the complexity of such search space, which can be efficiently modelled as a tree-graph of interconnected Lambert arc solutions between two consecutive asteroids. This allows to exploit the optimal substructure of the problem and enables complete tree traverse explorations for limited asteroid catalogues. Nevertheless, the search space quickly grows in complexity for larger catalogues, featuring a labyrinthine multi-modal structure and extreme non-linearities. This underlying complexity ultimately renders common stochastic heuristics, such as Ant Colony Optimization, rather inefficient. Mostly, due to the fact that the metaheuristic processes are not able to gather any real understanding, or knowledge, such that it can efficiently guide the search. Instead, an astrodynamics-lead heuristic based on the distance between spacecraft and asteroid at the asteroid’s MOID-point crossing epoch, enables an efficient pruning of the asteroid catalogue. Then, deterministic processes based on dynamic programming and beam search can be efficiently applied, providing solutions to both the global optimum and the constraint satisfaction problems.

In the past, space trajectory optimization was limited to optimal design of transfers to single destinations, where optimality refers to minimum propellant consumption or transfer time. New technologies, and a more daring approach to space, are today making the space community consider missions that target multiple destinations. In the present paper, we focus on missions that aim to visit multiple asteroids within a single launch. The trajectory design of these missions is complicated by the fact that the asteroid sequences are not known a priori but are the objective of the optimization itself. Usually, these problems are formulated as global optimization (GO) problems, under the formulation of mixed-integer non-linear programming (MINLP), on which the decision variables assume both continuous and discrete values. However, beyond the aim of finding the global optimum, mission designers are usually interested in providing a wide range of mission design options reflecting the multi-modality of the problems at hand. In this sense, a Constraint Satisfaction Problem (CSP) formulation is also relevant. In this manuscript, we focus on these two needs (i.e. tackling both the GO and the CSP) for the asteroid tour problem. First, a tree-search algorithm based upon the Bellman’s principle of optimality is described using dynamic programming approach to address the feasibility of solving the GO problem. This results in an efficient and scalable procedure to obtain global optimum solutions within large datasets of asteroids. Secondly, tree-search strategies like Beam Search and Ant Colony Optimization with back-tracking are tested over the CSP formulations. Results reveal that BS handles better the multi-modality of the search space when compared to ACO, as this latter solver has a bias towards elite solutions, which eventually hinders the diversity needed to efficiently cope with CSP over graphs.

Stream data processing has gained progressive momentum with the arriving of new stream applications and big data scenarios. One of the most promising techniques in stream learn- ing is the Spiking Neural Network, and some of them use an interesting population encod- ing scheme to transform the incoming stimuli into spikes. This study sheds lights on the key issue of this encoding scheme, the Gaussian receptive fields, and focuses on applying them as a pre-processing technique to any dataset in order to gain representativeness, and to boost the predictive performance of the stream learning methods. Experiments with synthetic and real data sets are presented, and lead to confirm that our approach can be applied successfully as a general pre-processing technique in many real cases.

Constraint Satisfaction Problems (CSP) belong to a kind of traditional NP-hard problems with a high impact on both research and industrial domains. The goal of these problems is to find a feasible assignment for a group of variables where a set of imposed restrictions is satisfied. This family of NP-hard problems demands a huge amount of computational resources even for their simplest cases. For this reason, different heuristic methods have been studied so far in order to discover feasible solutions at an affordable complexity level. This paper elaborates on the application of Ant Colony Optimization (ACO) algorithms with a novel CSP-graph based model to solve Resource-Constrained Project Scheduling Problems (RCPSP). The main drawback of this ACO-based model is related to the high number of pheromones created in the system. To overcome this issue we propose two adaptive Oblivion Rate heuristics to control the number of pheromones: the first one, called Dynamic Oblivion Rate, takes into account the overall number of pheromones produced in the system, whereas the second one inspires from the recently contributed Coral Reef Optimization (CRO) solver. A thorough experimental analysis has been carried out using the public PSPLIB library, and the obtained results have been compared to those of the most relevant contributions from the related literature. The performed experiments reveal that the Oblivion Rate heuristic removes at least 79% of the pheromones in the system, whereas the ACO algorithm renders statistically better results than other algorithmic counterparts from the literature.

Recently, millimeter-wave (mmWave) bands have been postulated as a means to accommodate the foreseen extreme bandwidth demands in vehicular communications, which result from the dissemination of sensory data to nearby vehicles for enhanced environmental awareness and improved safety level. However, the literature is particularly scarce in regards to principled resource allocation schemes that deal with the challenging radio conditions posed by the high mobility of vehicular scenarios. In this paper, we propose a novel framework that blends together matching theory and swarm intelligence to dynamically and efficiently pair vehicles and optimize both transmission and reception beamwidths. This is done by jointly considering channel state information and queue state information when establishing vehicle-to-vehicle (V2V) links. To validate the proposed framework, simulation results are presented and discussed, where the throughput performance as well as the latency/reliability tradeoffs of the proposed approach are assessed and compared with several baseline approaches recently proposed in the literature. The results obtained in this paper show performance gains of 25% in reliability and delay for ultra-dense vehicular scenarios with 50% more active V2V links than the baselines. These results shed light on the operational limits and practical feasibility of mmWave bands, as a viable radio access solution for future high-rate V2V communications.

Nowadays there is a global concern with the growing frequency and magnitude of natural disasters, many of them associated with climate change at a global scale. When tackled during a stringent economic era, the allocation of resources to efficiently deal with such disaster situations (e.g., brigades, vehicles and other support equipment for fire events) undergoes severe budgetary limitations which, in several proven cases, have lead to personal casualties due to a reduced support equipment. As such, the lack of enough communication resources to cover the disaster area at hand may cause a risky radio isolation of the deployed teams and ultimately fatal implications, as occurred in different recent episodes in Spain and USA during the last decade. This issue becomes even more dramatic when understood jointly with the strong budget cuts lately imposed by national authorities. In this context, this article postulates cost-efficient multi-hop communications as a technological solution to provide extended radio coverage to the deployed teams over disaster areas. Specifically, a Harmony Search (HS) based scheme is proposed to determine the optimal number, position and model of a set of wireless relays that must be deployed over a large-scale disaster area. The approach presented in this paper operates under a Pareto-optimal strategy, so a number of different deployments is then produced by balancing between redundant coverage and economical cost of the deployment. This information can assist authorities in their resource provisioning and/or operation duties. The performance of different heuristic operators to enhance the proposed HS algorithm are assessed and discussed by means of extensive simulations over synthetically generated scenarios, as well as over a more realistic, orography-aware setup constructed with LIDAR (Laser Imaging Detection and Ranging) data captured in the city center of Bilbao (Spain).

In vehicular scenarios context awareness is a key enabler for road safety. However, the amount of contextual information that can be collected by a vehicle is stringently limited by the sensor technology itself (e.g., line-of-sight, coverage, weather robustness) and by the low bandwidths offered by current wireless vehicular technologies such as DSRC/802.11p. Motivated by the upsurge of research around millimeter-wave vehicle-to-anything (V2X) communications, in this work we propose a distributed vehicle-to-vehicle (V2V) association scheme that considers a quantitative measure of the potential value of the shared contextual information in the pairing process. First, we properly define the utility function of every vehicle balancing classical channel state and queuing state information (CSI/QSI) with context information i.e., sensing content resolution, timeliness and enhanced range of the sensing. Next we solve the problem via a distributed many-to-one matching game in a junction scenario with realistic vehicular mobility traces. It is shown that when receivers are able to leverage information from different sources, the average volume of collected extended sensed information under our proposed scheme is up to 71% more than that of distance and minimum delay-based matching baselines.

Millimeter wave (mmWave) communications have been postulated as one of the most disruptive technologies for future 5G systems. Among mmWave bands the 60-GHz radio technology is specially suited for ultradense small cells and mobile data offloading scenarios. Many challenges remain to be addressed in mmWave communications but among them deafness, or misalignment between transmitter and receivers beams, and interference management lie among the most prominent ones. In the recent years, scenarios considering negligible interference on mmWave resource allocation have been rather common in literature. To this end, interestingly, many open issues still need to be addressed such as the applicability of noise-limited regime for mmWave. Furthermore, in mmWave the beam-steering mechanism imposes a forced silence period, in the course of which no data can be conveyed, that should not be neglected in throughput/delay calculations. This paper introduces mmWave enabled Small Cell Networks (SCNs) with relaying capabilities where as a result of a coordinated meta-heuristically optimized beamwidth/alignment-delay approach overall system throughput is optimized. Simulations have been conveyed for three transmitter densities under TDMA and naive 'all-on' scheduling producing average per node throughput increments of up to 248%. The paper further elaborates on the off-balancing impact of alignment delay and time-multiplexing strategies by illustrating how the foreseen transition that increasing the number of transmitters produces in the regime of a fixed-node size SCN in downlink operation fades out by a poor choice in the scheduling strategy., Comment: 6 pages, 4 figures, European Wireless 2016 Conference

MUGGES is a European research project with the goal of evaluating peer-to-peer service concepts based on GNSS systems for mobile phones. MUGGES provides an infrastructure to create, publish, provide and consume mobile micro-services directly from mobile devices. As part of the project four application prototypes have been developed, which allow for the description and sharing of places and routes between users. This paper reports about a user trial conducted in real environments with early adopters. The goal has been to identify benefits and best practices for the type of applications envisioned in the MUGGES project. The obtained results indicate that users like to share information about preferred places or routes, and see it as a complementary application to already existing applications such as Facebook or Twitter. These types of applications are often used in time-killing situations, e.g. at the bus stop. Their value lies on the highlighting of important places or non-everyday events, and on making daily coordinations simpler. People feel that the application is less intrusive, since no information such as the whereabouts of persons are shared anyhow

Energy, especially Electricity has become a critical concern of society. The generation and distribution are, to a large extent, not matched with each other. There are many initiatives to balance the load on the Grid vis-à-vis production and consumption. Recently, technology has made it possible to generate small amounts of energy in each household with solar, thermal, wind and other sources. With storage devices, it is possible to use the generated energy at the sources i.e., localized generation and consumption of energy. The system can be made efficient and possibly design a zero or positive-energy home with the use ICT infrastructure, wireless sensor networks, in particular. This paper proposes a three-layered architecture for this system and also lists several associated issues and challenges.