Search

As a meta-heuristic algorithm, the Golden Jackal Optimization (GJO) algorithm has been widely used in traditional network intrusion detection due to its ease of use and high efficiency. This paper aims to extend its application to the emerging field of Software-Defined Networking (SDN), which is a new network architecture. To adapt the GJO for SDN intrusion detection, a modified Golden Jackal Optimization (mGJO) is proposed to enhance its performance with the use of two strategies. First, an Elite Dynamic Opposite Learning strategy operates during each iteration to find solutions opposite to the current global optimal solutions, which increases population diversity. Second, an updating strategy based on the Golden Sine II Algorithm is utilized in the exploitation phase to update the position information of the golden jackal pairs, which accelerates the search for the best feature subset indexes. To validate the feasibility of the mGJO algorithm, this paper first assesses its optimization capability using benchmark test functions. Then, four UCI datasets and the NSL-KDD dataset are used to test the classification capability of the mGJO algorithm and its application in traditional network intrusion detection. Furthermore, the InSDN dataset is used to validate the feasibility of the mGJO algorithm for SDN intrusion detection. The experimental results show that, when the mGJO algorithm is applied to SDN for intrusion detection, the various indexes of classification and the selection of feature subsets achieve better results. [ABSTRACT FROM AUTHOR]

For a system comprised of multiple Web servers that provide the same content, this paper proposes a method for the dynamic selection of servers that process requests, based on periodically obtained load information on servers. Previously proposed methods select servers probabilistically based on the weights calculated from server load information, and consequently, a server with a heavy load is selected by chance, often resulting in decreased performance. In contrast, the present method, instead of employing probabilistic server selection, selects servers by a round-robin scheme after eliminating any difference in load among the servers. A comparison of performance based on simulation studies with the conventional method indicates that the proposed method is immune to the impact of the intervals at which load information is acquired or the number of servers involved, and that it produces a low average response time even under heavy load conditions. © 2006 Wiley Periodicals, Inc. Electron Comm Jpn Pt 1, 89(10): 1–12, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecja.20309 [ABSTRACT FROM AUTHOR]

Blockchain integrates cryptography, distributed consensus, P2P networking, and timestamping technologies, which can achieve functions such as consistent data storage, tamper resistance, and non-repudiation, solving the trust issue in open networks that do not rely on any trusted third parties. The decentralized nature of blockchain gives it a broad range of application prospects. However, as the applications become more extensive and profound, the scalability issue has become a key challenge for unlocking the full potential of blockchain technology. Blockchain is essentially still a distributed system. Based on this, this paper reviewed the research work on blockchain from the perspective of the scalability of distributed systems. It discussed the ideas and methods for blockchain scalability from three aspects: on-chain scalability, off-chain scalability, and cross-chain scalability. Then it summarized the research achievements in recent years. Building on the summary and analysis of existing solutions, this paper explored the challenges faced in improving blockchain scalability and discussed future research trends in this area. [ABSTRACT FROM AUTHOR]

Violence detection is a critical task aimed at identifying violent behavior in video by extracting frames and applying classification models. However, the complexity of video data and the suddenness of violent events present significant hurdles in accurately pinpointing instances of violence, making the extraction of frames that indicate violence a challenging endeavor. Furthermore, designing and applying high-performance models for violence detection remains an open problem. Traditional models embed extracted spatial features from sampled frames directly into a temporal sequence, which ignores the spatio-temporal characteristics of video and limits the ability to express continuous changes between adjacent frames. To address the existing challenges, this paper proposes a novel framework called ACTION-VST. First, a keyframe extraction algorithm is developed to select frames that are most likely to represent violent scenes in videos. To transform visual sequences into spatio-temporal feature maps, a multi-path excitation module is proposed to activate spatio-temporal, channel and motion features. Next, an advanced Video Swin Transformer-based network is employed for both global and local spatio-temporal modeling, which enables comprehensive feature extraction and representation of violence. The proposed method was validated on two large-scale datasets, RLVS and RWF-2000, achieving accuracies of over 98 and 93%, respectively, surpassing the state of the art. [ABSTRACT FROM AUTHOR]

In most wireless networks, users/peers are connected to backbone networks using access links. The access link capacity is divided into upload and download capacity, and these capacities are used for upload and download of data, respectively. A peer can modify this division of link capacity between upload and download. A peer will allocate its entire link capacity for download to maximize utility. But incentive mechanism forces them to allocate some portion of capacity for upload. This paper investigates how to optimally divide link capacity so that peers receive maximum utility in a P2P network. We model this scenario as a game and determine capacity partitioning of peers during the Nash equilibrium NE. We also prove the social optimality of NE. As this portioning maximizes individual as well as social benefit, so NE is an optimal state of capacity partition. Using simulation, we verify that NE is an optimal state. BitTorrent network and a distributed algorithm for dividing access capacities are simulated, and partition providing maximum utility is compared with NE. This work provides a generalized expression and the mathematical proof for capacity partitioning at which peers receive maximum utility. [ABSTRACT FROM AUTHOR]

The fast development of the sensors in the wireless sensor networks (WSN) brings a big challenge of low energy consumption requirements, and Peer-to-peer (P2P) communication becomes the important way to break this bottleneck. However, the interference caused by different sensors sharing the spectrum and the power limitations seriously constrains the improvement of WSN. Therefore, in this paper, we proposed a deep reinforcement learning-based energy consumption optimization for P2P communication in WSN. Specifically, P2P sensors (PUs) are considered agents to share the spectrum of authorized sensors (AUs). An authorized sensor has permission to access specific data or systems, while a P2P sensor directly communicates with other sensors without needing a central server. One involves permission, the other is direct communication between sensors. Each agent can control the power and select the resources to avoid interference. Moreover, we use a double deep Q network (DDQN) algorithm to help the agent learn more detailed features of the interference. Simulation results show that the proposed algorithm can obtain a higher performance than the deep Q network scheme and the traditional algorithm, which can effectively lower the energy consumption for P2P communication in WSN. [ABSTRACT FROM AUTHOR]

The goal of RGB-D salient object detection is to aggregate the information of the two modalities of RGB and depth to accurately detect and segment salient objects. Existing RGB-D SOD models can extract the multilevel features of single modality well and can also integrate cross-modal features, but it can rarely handle both at the same time. To tap into and make the most of the correlations of intra- and inter-modality information, in this paper, we proposed an attention-guided cross-modal multi-feature aggregation network for RGB-D SOD. Our motivation was that both cross-modal feature fusion and multilevel feature fusion are crucial for RGB-D SOD task. The main innovation of this work lies in two points: One is the cross-modal pyramid feature interaction (CPFI) module that integrates multilevel features from both RGB and depth modalities in a bottom-up manner, and the other is cross-modal feature decoder (CMFD) that aggregates the fused features to generate the final saliency map. Extensive experiments on six benchmark datasets showed that the proposed attention-guided cross-modal multiple feature aggregation network (ACFPA-Net) achieved competitive performance over 15 state of the art (SOTA) RGB-D SOD methods, both qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

Blockchains are becoming increasingly important in today's Internet, enabling large-scale decentralized applications with strong security and transparency properties. In a blockchain system, participants maintain and update the server-side state of an application by appending data as blocks onto an immutable, distributed ledger through a consensus protocol within a peer-to-peer network. There has been a significant increase in profit in mining blocks. For instance, Bitcoin miners currently receive over USD 200,000 per mined block. An essential determinant of these rewards is the time it takes to disseminate newly mined blocks across the network. This paper addresses the challenge of optimizing mining rewards by exploring topology design in a wide-area blockchain network utilizing a Proof-of-Work consensus protocol. We show that under low block times, the geographical location of a miner critically impacts the number of successful blocks mined by the miner. We also show that a miner may improve its success rate by increasing its connectivity to the network. However, contrary to the general wisdom that a faster network is always better for a miner, we show that increasing network connectivity (e.g., by adding more neighbors) is beneficial to a miner only up to a point after which the miner's rewards degrade. This is because when a miner improves its connectivity, it inadvertently also aids other miners in increasing their connectivity. We also present a network-level collusion attack in which a miner can increase its block success rate by becoming part of a tightly connected cluster. Here too, we observe that the mining gains obtained increase with cluster size only up to a point, and decrease thereafter. Our findings highlight that the network topology is a key variable affecting miner performance in PoW blockchains that must not be overlooked. We demonstrate our observations via detailed simulations modeled using real-world measurement data. [ABSTRACT FROM AUTHOR]

In recent years, peer-to-peer (P2P) as a means of content distribution and sharing service are receiving extensive attention. In this paper, the hybrid P2P network structure model is combined with the knowledge of queueing theory. In order to address the problem generated by unnecessary online behavior of nodes, the working sleep mechanism for the serving nodes is introduced, and the synchronous multiple working vacation strategy is also adopted to decrease the system energy consumption. Then a queueing model with working vacation and repairable fault is built, which used to simulate the resource transmission process of P2P network and to study the performance of P2P sharing system. The steady-state probability vector is derived by employing quasi-birth-and-death process and matrix-geometric solution method. And the expressions for system performance indicators, such as the average delay, are obtained by employing Gauss–Seidel iteration method. Through numerical experiments, the performance indicators of the P2P resource sharing system are studied, which provides a theoretical basis to decrease online energy consumption of nodes in the hybrid P2P network. And through employing Nash equilibrium and social optimal strategy, the value of the social maximum benefit under the social optimization is obtained. [ABSTRACT FROM AUTHOR]

The theoretical and practical progress that has occurred in the field of computer networks during the past fifteen years has enhanced the economical efficiency and social relevance of related real-world use cases. Nevertheless, this ubiquitous usage has also introduced numerous security risks. Therefore, monitoring hardware and software resources represents one of the main instruments used in order to prevent potential attacks and to ensure the security and reliability of a network. Various solutions have been reported in the related scientific literature. In essence, most of the existing approaches are not suitable to implement a real-time hardware monitoring and management solution, particularly in heterogeneous networks. Therefore, the main contribution of this paper is represented by an architectural and implementational model, which is effective in order to build an interconnected system that can help system and network administrators to secure a network. This requirement is met by considering symmetrical design and implementation features related to various operating systems. Thus, the existing symmetrical relationships among identified parameters allow for the data to be wrapped into the same custom network packages, which are transported over the communication medium or are stored using the same data structures or tables. The system has been thoroughly assessed considering several real-world use case scenarios, and the results demonstrate that the proposed model can be applied to software-defined networks, which can be protected by relevant intrusion detection systems (IDS). [ABSTRACT FROM AUTHOR]

Sustainable microgrid is a feasible approach to handle environmental impacts and satisfy customer demand due to its economic, environmental, and social benefits. Due to the high initial investment cost, the installation rate of microgrids has been limited. Various studies investigated the influence of government subsidies on sustainable microgrid design to increase the installation rate. However, the effect of government subsidies, financial factors, and elasticity coefficient of demand under peer-to-peer energy trading has not been explored in the current sustainable microgrids design literature. To overcome this limitation, this paper investigates the sustainable microgrid design problem to simultaneously consider the effect of government subsidies, peer-to-peer energy trading, time value of money, elasticity coefficient of demand, and uncertainties. The objectives are to maximize total profit and minimize the total environmental cost to satisfy electric energy demand. Fuzzy multi-objective programming is applied to determine the optimal decisions on the number, location, type of renewable energy, the capacity of renewable distributed generation sources, electricity flows, price for selling electricity to demand areas and P2P energy trading, and government subsidy rates. A genetic algorithm and its hybrid versions to include tabu search and simulated annealing are then used to solve the proposed model. Numerical experiments used to evaluate the performance of the proposed model and algorithms show that the proposed genetic algorithm is most effective in maximizing total profit and minimizing environmental cost. Computational results demonstrate that on average, the inclusion of the peer-to-peer trading and government subsidies in the proposed model increases total profit by 13.23% and reduces total environmental cost by 6.29%. [Display omitted] • Sustainable microgrid design problem under impacted factors is investigated. • The effect of government subsidies and peer-to-peer energy trading are assessed. • Economic, environmental, and social objectives are considered under impacted factors. • Fuzzy multi-objective programming model is developed to handle the uncertainty. • Genetic algorithm and its hybrid versions are used to solve the propose model. [ABSTRACT FROM AUTHOR]

Payment apps and digital wallets are powerful tools used to exchange e-money via the internet. However, with the progressive disappearance of cash, there is a need for the digital equivalent of physical banknotes to guarantee the same level of anonymity of private payments. Few efforts to solve the double-spending problem exist in P2P payments (i.e., in avoiding the possibility of a payer retaining copies of digital coins in absence of a trusted third party (TTP)), and further research efforts are needed to explore options to preserve the privacy of payments, as per the mandates of numerous central bank digital currency (CBDC) exploratory initiatives, such as the digital euro. Moreover, generic programmability requirements and energetic impacts should be considered. In this paper, we present a sustainable offline P2P payment scheme to face the double-spending problem by means of a one-time program (OTP) approach. The approach consists of wiping the business logic out of a client's app and allowing financial intermediaries to inject a certified payment code into the user's device, which will execute (asynchronously and offline) at the time of payment. To do so, we wrap each coin in a program at the time of withdrawal. Then the program exploits the trusted execution environment (TEE) of modern smartphones to transfer itself from the payer to the payee via a direct IoT link. To confirm the validity of the approach, we performed qualitative and quantitative evaluations, specifically focusing on the energetic sustainability of the proposed scheme. Results show that our payment scheme is energetically sustainable as the current absorbed for sending one coin is, at most, ~1.8 mAh on an Apple smartphone. We advance the state-of-the-art because the scheme meets the programmability, anonymity, and sustainability requirements (at the same time). [ABSTRACT FROM AUTHOR]

Blockchain technology, with its peer-to-peer trading feature, influences the management of energy consumption by offering the potential to transform transparency, efficiency, and sustainability within the energy sector. Nonetheless, there is a need to develop analytical decision-making models tailored for managing peer-to-peer energy transactions to improve energy resilience. Therefore, the purpose of this paper is to address the research question: How can energy distribution systems be protected via blockchain technology to enhance energy resilience and mitigate vulnerabilities to disruptions ? This paper employs a conceptual research model design and a mathematical decision-making model to address the research question by capturing the peer-to-peer trading capability of blockchain technology. The theory of planned behavior provides theoretical explanations for the proposed model. The sample includes longitudinal energy consumption data from 2015 to 2023 in Texas. The findings indicate a significant improvement in energy efficiency along with a considerable decrease in total electricity consumption. Post hoc analysis results reveal that the seasonal autoregressive integrated moving average algorithm is effective as a reliable input for the proposed mathematical model. The significant implications are to implement blockchain-based smart grids in which energy systems become more resilient to disruptions, as the peer-to-peer capability enables users to trade energy. The proposed model suggests that energy will be used more efficiently and effectively. This paper contributes to prior works by introducing a mathematical model that captures the trading behavior of energy consumers. Moreover, this paper proposes the SARIMA algorithm to predict energy demand. • A mathematical peer-to-peer trading model is presented to improve resilience. • A blockchain-based smart grid is presented for consumer energy consumption. • Five machine learning algorithms are presented in energy demand management. • Longitudinal energy consumption data of Texas is used in the model. • Theoretical support is provided using the theory of planned behavior. [ABSTRACT FROM AUTHOR]

• Existing technologies like smart grid (SG) and smart meters play a significant role in meeting the everlasting demand of energy consumption, supply, and generation for Peer-to-Peer (P2P) energy trading between different distributed prosumers. Whereas blockchain when used with P2P energy trading plays a major role in cost and security for trading by eliminating any involvement of outsiders and third parties. However, existing works related to the blockchain with P2P energy trading are engaged in increasing the cost related to resource allocation, latency, computational processing, and large network setup. • Moreover, in current existing techniques, peer nodes can send 25-200 transactions per second. By expanding the number of peer nodes, the network traffic volume can also be enhanced. This resulted in a significant reduction in network throughput. The network latency will increase as the number of peer nodes grows. • The objective of this paper is to design and develop a 3-tier architecture, an analytical model, and a hybrid algorithm for network analysis in a blockchain-based P2P energy trading system using reinforcement learning (RL) and feed-forward neural network (FFNN) techniques. In this model, we will examine the various parameters and tradeoffs which affect the delay, throughput, and security in P2P energy trading. This will lead to profitable P2P energy trading between different distributed prosumers. Existing technology like smart grid (SG) and smart meters play a significant role in meeting the everlasting demand of energy consumption, supply, and generation for peer-to-peer (P2P) energy trading between different distributed prosumers. Whereas blockchain when used with P2P energy trading plays a major role in cost and security by eliminating any involvement of outsiders and third parties. However, existing works related to the blockchain with P2P energy trading are engaged in increasing the cost related to resource allocation, latency, computational processing, and large network setup. The objective of this paper is to design and develop a three-tier architecture, an analytical model, and a hybrid algorithm for network analysis in a blockchain-based P2P energy trading system using reinforcement learning (RL) and feed forward neural network (FFNN) techniques. In this model, we will examine the various parameters and tradeoffs which affect the delay, throughput, and security in P2P energy trading. This will lead to profitable P2P energy trading between different distributed prosumers. By analyzing the simulation results of the proposed model and algorithm by benchmarking with the existing state-of-the-art techniques it's clear that the proposed algorithm shows marked improvement over network latency generated results. The simulation of the model is conducted using the iFogSim simulator, Ganache with Ethereum platform, Truffle, Python editor tool, and ATOM IDE with solidity. [ABSTRACT FROM AUTHOR]

Capsule network is a promising network architecture in computer vision that integrates feature information and feature relationships of images. However, the original capsule network performs poorly with complex datasets, and the network is computationally intensive, which is not conducive to deployment in end-side devices. In this paper, a novel hardware-friendly capsule network named MRCapsNet is proposed to improve the performance of the capsule network and make it deployable in end-side devices. In the proposed network, the multi-level residual capsule block is constructed to extract features with multi-granularity from images. Moreover, a novel reconstruction subnetwork is designed to facilitate network training. Experiments show that MRCapsNet achieved competitive results on the CIFAR-10 (90.34 %) and SVHN (96.59 %) datasets compared with other variants of CapsNet. Further, the hardware implementation scheme of MRCapsNet based on memristor crossbars is designed to provide a nano-scale, low-power capsule network deployment scheme. Finally, the power consumption of the core computing unit built by memristor elements is analyzed and calculated, and the maximum power consumption of a memristive neuron is only 6.4 μ W during the inference of the network, which is significantly less than the CMOS-based circuit. [ABSTRACT FROM AUTHOR]

Abstract: Over the last decade, we have seen a significant increase in the number of projects aiming for integration of different kinds of media(mixed-media integration). However, most existing approaches tend to focus on the media technologies rather than on concepts for information integration and linking that enable users to move freely back and forth between various media information sources. In this paper, we discuss the issues of information semantics and granularity that arise in the design of highly interactive mixed-media information systems and present a general, flexible information server that meets the requirements of publishing information on different output channels (cross-media publishing). Specifically, we introduce the iServer framework as a generic link management and extensible integration platform and digitally augmented paper is presented as one specific application of the iServer technology. A case study shows how cross-media publishers could profit from using more elaborate information systems and some of the authoring issues of mixed-media information environments are discussed. [Copyright &y& Elsevier]

The 3rd Generation Partnership Project (3GPP) has defined based on the Long Term Evolution (LTE) enhanced Multicast Broadcast Multimedia Service (eMBMS) a set of new features to support the distribution of Terrestrial Broadcast services in Release 14. On the other hand, a new 5th Generation (5G) system architecture and radio access technology, 5G New Radio (NR), are being standardized from Release 15 onwards, which so far have only focused on unicast connectivity. This may change in Release 17 given a new Work Item set to specify basic Radio Access Network (RAN) functionalities for the provision of multicast/broadcast communications for NR. This work initially excludes some of the functionalities originally supported for Terrestrial Broadcast services under LTE, e.g., free to air, receive-only mode, large-area single frequency networks, etc. This paper proposes an enhanced Next Generation RAN architecture based on 3GPP Release 15 with a series of architectural and functional enhancements, to support an efficient, flexible and dynamic selection between unicast and multicast/broadcast transmission modes and also the delivery of Terrestrial Broadcast services. The paper elaborates on the Cloud-RAN based architecture and proposes new concepts such as the RAN Broadcast/Multicast Areas that allows a more flexible deployment in comparison to eMBMS. High-level assessment methodologies including complexity analysis and inspection are used to evaluate the feasibility of the proposed architecture design and compare it with the 3GPP architectural requirements. [ABSTRACT FROM AUTHOR]

The rapid increase in internet usage for the past few decades has steered to higher demand and for adequate support for the network mobility in heterogeneous networks. However, in the existing mobile IPv6 (Internet Protocol version 6) protocols such as traditional, hierarchical, proxy and related methodologies have been stated to manage the recurrent mobility of the devices in a network with the centralized feature. However, the single point of failure, route optimization, handoff latency and security threats are highly exposed when the number of mobile device increases in the centralized approach. Also, it leads to the limitation of the size of binding information when the mobile host needs to update its place. Hence, this paper suggests a secure and optimized architecture by distributing mobility functions as distributed access points. Also, the paper addresses the prevention measures for security attacks such as false binding message, rerun and hijack. The proposed scheme is simulated and validated using network simulator and security model verifier – AVISPA. Finally, the numerical and experimental outcomes demonstrate that the proposed scheme offers a substantial diminution in the cost of the binding update, binding refresh, and packet delivery. [ABSTRACT FROM AUTHOR]

In view of the needs of the training IoT engineering professionals, the paper deeply researched OPNET, SoftRadio, Qemu,Proteus,Docker and other software, and built a comprehensive IoT virtual simulation experiment teaching platform. The paper focused on the experimental simulation teaching of computer network, wireless network, embedded IoT gateway and others coursed in the network layer and embedded gateway layer. The basic experimental project and comprehensive experimental project of related courses were designed. The experimental project runs through the serial port, communication programming, network communication programming and database programming expertise. It better solves the problems of " communication, storage, use" in the design and implementation of IoT application systems. Practice has proved that the virtual simulation experimental teaching platform provides better support for the experimental teaching of the network layer of the IoT and the embedded gateway layer. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to draw on social exchange theory and heuristic–systematic model to examine how peer-to-peer (P2P) lending firms can enhance their customer acquisition by achieving mobile social media popularity. Design/methodology/approach: Content data collected from multiple sources (websites and mobile applications) were employed to validate the research model. Findings: The mobile social media popularity of P2P lending firms positively influences their customer acquisition. Furthermore, the heuristic cues (i.e. source credibility and content freshness) and the systematic cue (i.e. transaction relevance) potentially affect the firms' mobile social media popularity. Research limitations/implications: Mobile social media is not only a platform for firms' image-building but a critical means of acquiring actual customers. The appropriate use of heuristic–systematic cues in a mobile interface is useful for firms to achieve high user popularity despite the challenges derived from the mobile context. Practical implications: To achieve higher user popularity in the competitive online world, firms should dedicate greater effort in determining the adequate heuristic–systematic cues designed for the interface of their mobile social media account. The effect of popularity can then help the firms acquire more customers. Originality/value: This study extends the understanding of social exchange in the context of mobile social media accounts and enriches the knowledge on business value of mobile social media popularity. This paper also contributes to the literature by relating heuristic–systematic cues to firms' mobile social media popularity. [ABSTRACT FROM AUTHOR]

Learning representative, robust and discriminative information from images is essential for effective person re-identification (Re-Id). In this paper, we propose a compound approach for end-to-end discriminative deep feature learning for person Re-Id based on both body and hand images. We carefully design the Local-Aware Global Attention Network (LAGA-Net), a multi-branch deep network architecture consisting of one branch for spatial attention, one branch for channel attention, one branch for global feature representations and another branch for local feature representations. The attention branches focus on the relevant features of the image while suppressing the irrelevant backgrounds. The global and local branches intends to capture global context and fine-grained information, respectively. A set of ablation study shows that each component contributes to the increased performance of the LAGA-Net. Extensive evaluations on four popular body-based person Re-Id benchmarks and two publicly available hand datasets demonstrate that our proposed method consistently outperforms existing state-of-the-art methods. • We propose a multi-branch deep network by incorporating attention, global and local branches. • We include relative positional encodings into spatial attention module to capture pixels' positions. • We make extensive evaluations on popular four body datasets and two hands datasets. [ABSTRACT FROM AUTHOR]

Delay tolerant networks supporting heterogeneous communication are a promising network architecture solution that can meet today's communication requirements involving nodes in space, terrestrial and water networks. These networks with dynamic topology and dynamic set of participating nodes make enablement of secure authentication between nodes in this network architecture a critical requirement. In this paper, we propose a novel Quantum-Secure Authentication (QS-Auth) protocol that enables mutual-authentication in Heterogeneous Delay tolerant network environment, while achieving quantum-resistance using the combination of PUF and Post-Quantum signature. The proposed tree-based region structure enables scalability and distributes the responsibility for trust to individual region heads and eliminates high risk root nodes in other tree-based solutions. The proposed scheme can meet the high secure mutual-authentication requirement in critical networks like defence, disaster regions, satellite communications etc. We demonstrate the correctness of our proposed scheme by conducting thorough informal and formal security analysis. The performance analysis is done by the evaluation of efficiency, computation and communication cost. The results of our analysis proves that the proposed protocol meets the security criteria and is well suited for heterogeneous delay tolerant network environments. [ABSTRACT FROM AUTHOR]

In this paper, we proposed a Many‐to‐One Input Network Architecture (MOINA) for the classification of similar structured vehicles (bus, truck and car). The inputs of the architecture are the multiple‐masked region‐of‐interest of the same detected vehicle from Range‐Doppler maps, which are acquired by FMCW radar. The proposed method is trained with a supervised system yielding a classification accuracy of 98%. MOINA shows good classification performance in a practical situation. Besides, the F1‐score of buses, trucks and cars are 98.7%, 98.0% and 97.6%, respectively. [ABSTRACT FROM AUTHOR]

Object detection is one of the vital and challenging tasks of computer vision. It supports a wide range of applications in real life, such as surveillance, shipping, and medical diagnostics. Object detection techniques aim to detect objects of certain target classes in a given image and assign each object to a corresponding class label. These techniques proceed differently in network architecture, training strategy and optimization function. In this paper, we focus on animal species detection as an initial step to mitigate the negative impacts of wildlife--human and wildlife--vehicle encounters in remote wilderness regions and on highways. Our goal is to provide a summary of object detection techniques based on R-CNN models, and to enhance the performance of detecting animal species in accuracy and speed, by using four different R-CNN models and a deformable convolutional neural network. Each model is applied on three wildlife datasets, results are compared and analyzed by using four evaluation metrics. Based on the evaluation, an animal species detection system is proposed. [ABSTRACT FROM AUTHOR]

The power distribution internet of things (PD-IoT) has the complex network architecture, various emerging services, and the enormous number of terminal devices, which poses rigid requirements on substrate network infrastructure. However, the traditional PD-IoT has the characteristics of single network function, management and maintenance difficulties, and poor service flexibility, which makes it hard to meet the differentiated quality of service (QoS) requirements of different services. In this paper, we propose the software-defined networking (SDN)- enabled PD-IoT framework to improve network compatibility and flexibility, and investigate the virtual network function (VNF) embedding problem of service orchestration in PD-IoT. To solve the preference conflicts among different VNFs towards the network function node (NFV) and provide differentiated service for services in various priorities, a matching-based priorityaware VNF embedding (MPVE) algorithm is proposed to reduce energy consumption while minimizing the total task processing delay. Simulation results demonstrate that MPVE significantly outperforms existing matching algorithm and random matching algorithm in terms of delay and energy consumption while ensuring the task processing requirements of high-priority services. [ABSTRACT FROM AUTHOR]

Cognitive radio networks (CRNs), which offer novel network architecture for utilising spectrums, have attracted significant attention in recent years. CRN users use spectrums opportunistically, which means they sense a channel, and if it is free, they start transmitting in that channel. In cooperative spectrum sensing, a secondary user (SU) decides about the presence of the primary user (PU) based on information from other SUs. Malicious SUs (MSUs) send false sensing information to other SUs so that they make wrong decisions about the spectrum status. As a result, an SU may transmit during the presence of the PU or may keep starving for the spectrum. In this paper, we propose a reputation-based mechanism which can minimise the effects of MSUs on decision making in cooperative spectrum sensing. Some of the SUs are selected as distributed fusion centres (DFCs), that are responsible for making decisions about the presence of PU and informing the reporting SUs. A DFC uses weighted majority voting among the reporting SUs, where weights are normalised reputation. The DFC updates reputations of SUs based on confidence of an election. If the majority wins by a significant margin, the confidence of the election is high. In this case, SUs that belong to the majority gain high reputations. We conduct extensive simulations to validate our proposed model. [ABSTRACT FROM AUTHOR]

The cloud service providers, their services, its users, and the requests for these services are increasing exponentially day by day. Consequently, it has turned out to be extremely difficult for the user to search a service according to his customized quality of service requirements. Besides, conventional service discovery techniques using centralized registries stumble upon performance bottlenecks and single point of failures. To address these issues, this paper proposes a Peer-to-Peer-based decentralized semantic service discovery approach. The outcome of the discovery process can be enhanced with a well-defined decentralized registry. To accomplish that, this paper introduces a multi-layered cloud ontology which closes the gap to represent cloud services in a standardized way. Here, service descriptions are mapped to a well-structured cloud ontology, which captures vital elements in different service description approaches. Peers are organized into clusters based on the semantic similarity of the service descriptions. To bolster the service discovery efficacy, semantic links are established between peers having higher similarity so that query forwarding is done only to relevant peers. Simulation results show that the proposed approach effectively enhances the query success rate and decreases the execution time. [ABSTRACT FROM AUTHOR]

Abstract The future of energy is complex, with fluctuating renewable resources in increasingly distributed systems. It is suggested that blockchain technology is a timely innovation with potential to facilitate this future. Peer-to-peer (P2P) microgrids can support renewable energy as well as economically empower consumers and prosumers. However, the rapid development of blockchain and prospects for P2P energy networks is coupled with several grey areas in the institutional landscape. The purpose of this paper is to holistically explore potential challenges of blockchain-based P2P microgrids , and propose practical implications for institutional development as well as academia. An analytical framework for P2P microgrids is developed based on literature review as well as expert interviews. The framework incorporates 1) Technological, 2) Economic, 3) Social, 4) Environmental and 5) Institutional dimensions. Directions for future work in practical and academic contexts are identified. It is suggested that bridging the gap from technological to institutional readiness would require the incorporation of all dimensions as well as their inter-relatedness. Gradual institutional change leveraging community-building and regulatory sandbox approaches are proposed as potential pathways in incorporating this multi-dimensionality, reducing cross-sectoral silos, and facilitating interoperability between current and future systems. By offering insight through holistic conceptualization, this paper aims to contribute to expanding research in building the pillars of a more substantiated institutional arch for blockchain in the energy sector. Highlights • Blockchain has significant potential in energy sector development. • Holistic review of factors of blockchain-based P2P microgrids. • Multi-dimensional analytical framework proposed. [ABSTRACT FROM AUTHOR]

In recent times, vehicular network research has attracted the attention of both researchers and the industry partly due to its potential applications in efficient traffic management, road safety, entertainment, etc. Resources such as communication, on-board unit, storage and computing units, and battery are generally installed in the vehicles participating in intelligent transportation systems. The need to maximize the utilization of these resources has also resulted in interest in cloud based vehicular networks (CVNs), an area of active research. This paper survey the CVNs literature published between 2010 and 2016. In addition, a taxonomy based on three main CVN categories, namely vehicular cloud computing (VCC), vehicle using cloud (VuC) and hybrid cloud (HC), is presented. In the taxonomy, we focus on related systems, architectures, applications and services. Although VCC has been extensively discussed in the literature, a comprehensive survey on the two other categories is lacking. Hence, this motivates our research. Through an extensive comparison of common characteristics among cloud computing, mobile cloud computing, VCC, VuC and HC and overview of the existing architectures, we present a conceptual HC architecture. Finally, we conclude the paper with open issues and challenges. [ABSTRACT FROM AUTHOR]

Conventional planning and optimization of cellular mobile networks for supporting the peak-time user demand leads to substantial wastage of electrical energy. Infrastructure sharing among geographically collocated networks is considered promising for energy efficient operation of future cellular systems. Therefore, this paper proposes a generalized energy-efficient cooperation framework for sharing BSs between two cellular radio-access networks (RANs) serving the same geographical area. Previous works have the constraint of cooperation only among the collocated BSs belonging to different RANs, while the proposed framework is free from such limitation. To the best of our knowledge, this paper is the first for developing cooperation mechanisms among the non-collated BSs. Independent Poisson point process is used for modeling the near realistic random locations of both BSs and user equipment (UEs). Under the proposed framework, BSs belonging to different RANs dynamically share each others traffic and thus allow some BSs to switch into low power sleep mode for saving energy. During this BS switching through traffic-sharing, connection continuity (no drop of the existing calls) is maintained throughout the network. A generalized optimization problem for maximizing energy savings is formulated. Due to the high complexity of the optimization problem, heuristically guided algorithms differing in BS selection and UE association policies are proposed. More specifically, two different BSs selection schemes and three separate UE association policies are integrated in the algorithms. Performance of the proposed inter-RAN cooperation framework is evaluated using extensive simulations demonstrating a substantial energy savings and gain in energy efficiency. Impact of different network parameters, such as BS selection and UE association policies, BS and UE densities, BS power profile and SINR requirements for connection continuity on the system performance is thoroughly investigated and analyzed. [ABSTRACT FROM AUTHOR]

Abstract Several technical contributions are emerging nowadays to fulfill the new requirements foreseen in the 5th generation (5G) of mobile communication systems. Among these contributions, different variants of waveform design are proposed for the new radio air interface as alternative to orthogonal frequency-division multiplexing (OFDM) adopted in 4G. However, in order to prove the feasibility and the benefits of the proposed waveforms, practical hardware implementations are necessary. This paper presents one of the first flexible and efficient hardware platforms for waveform design and proof-of-concept. The proposed platform constitutes a complete hardware/software development environment, with digital processing, radio frequency boards, and all associated interfaces for control, communication, and display. Furthermore, the proposed platform allows the support of several communication scenarios as foreseen in 5G. Promising waveform candidates are implemented, in addition to OFDM, with careful architectural choices to allow fair comparisons. Particularly, this paper presents novel hardware architectures for the UF-OFDM transmitter and receiver. [ABSTRACT FROM AUTHOR]

This paper presents a review and analysis of pricing strategies in peer-to-peer (P2P) energy trading to provide new insights into the design of pricing mechanisms and the establishment of sustainable and effective P2P energy markets in distribution networks. P2P energy trading is emerging as an effective management scheme for prosumers with renewable energy sources in distribution networks. Several studies have focused on designing pricing mechanisms for P2P energy trading with a focus on energy pricing but not on network service pricing. To understand the extant pricing mechanisms, 169 papers were systematically reviewed. These papers, published between 2015 and 2022, were retrieved by academic search engines. The review showed that energy pricing can be categorized into synchronous and asynchronous, while network service pricing can be classified into ex-ante and ex-post schemes. Synchronous energy pricing provides economic efficiency. Asynchronous energy pricing offers Pareto optimality and price transparency and accommodates market participant preferences. Market participation can be reduced by conflicts of interest in network service pricing, between system operators and market participants owing to the settlement of network service costs, and among participants due to pricing methods. Energy and network service pricing compatibility between different methodologies relies on market results to distinguish matched counterparties. [Display omitted] • Systematic classification of energy and network service pricing suggested. • Procedure and function of energy-pricing methods clarified. • Potential conflicts of interest in network service pricing discussed. • Compatibility between energy and network service pricing presented. • Key challenges and opportunities for future research identified. [ABSTRACT FROM AUTHOR]

• Reputation-distance index is built. • Self-adaption algorithm for iterative auction based on game theory is proposed. • Floyd algorithm is used to find shortest electrical distance. • The model improves economic benefits, power reliability and reduce network losses. Peer-to-peer energy trading is a promising approach for decentralized electricity markets to achieve the decarbonization of power. In the trading process, the misbehavior of contracted users and power loss in network delivery can lead to transaction failure and higher delivery costs. This paper presents a distributed reputation-distance-driven iterative auction mechanism to promote energy trading among users who commit contracts well and among electrically closer peers. A reputation-distance index is built based on the historical trading performance and the electricity distance between users. The index is introduced into the auction matching process. Then, a self-adaption algorithm based on game theory is used to model the iterative auction to arrive at a Nash equilibrium. This paper also extends the combined factors framework to improve the flexibility and extensibility of the mechanism. A case study validates that the proposed decentralized mechanism can reduce network loss and peak loads, ensure power reliability, achieve high market efficiency, social welfare. Specifically, compared with the traditional model without considering reputation and distance, the proposed decentralized mechanism can reduce network loss by 50%, increase 7.1% the market share of users with good reputations, improve market efficiency by 10%, and increase social welfare by 7.69%. [ABSTRACT FROM AUTHOR]

• The irregularity and complexity of mesh data make shape segmentation challenging. • Mesh data are similar to point cloud data in spatial property so shape segmentation can be treated as a pointwise labeling problem. • Spatial information of mesh data is able to be learned by a point based network architecture by transforming shapes into point sets. • A simple and effective shape segmentation method which treats mesh segmentation as point labeling by converting each face into its barycenter and normal vector per shape with the spatial information of given shape preserving. • A intuitive and efficient operation, called Barycentric Dual Graph Edge Convolution (BDGEC), extracts edge features by operating over the nodes of Barycentric Dual Graph (BDG) intrinsic for the given shape. • A novel point based DNN, named LGCP Net, is proposed for mesh segmentation which can capture local and global features of shape efficient to obtain satisfying segmentation performance. [Display omitted] Segmenting 3D shapes represented by meshes remains a challenging problem, due to the irregularity and complexity of meshes. Point cloud, on the other hand, can be considered as the simplest no-frills approximation for meshes. Therefore, in this paper, we regard the shape segmentation problem as a point labeling task: Given a shape, we first transform it into points encoding barycenters and normal vectors of faces. Then we construct a Barycentric Dual Graph (BDG) on the transformed points, and propose a Barycentric Dual Graph Edge Convolution (BDGEC) to extract features from the graph. Based on the BDGEC, we further propose a novel point-based deep neural network (DNN) named local-global combined point-based network (LGCPNet). Our LGCPNet consists of three modules, of which the Local Module and Global Module capture local and global features respectively, while the Fusion Module uses a gate mechanism to aggregate local features and global features, and obtain the point labeling result. Comprehensive experimental results on various datasets demonstrate that the proposed network inherits the merits of point-based DNNs and achieves the state-of-the-art performance. [ABSTRACT FROM AUTHOR]

A Peer-to-Peer (P2P) network is a dynamic collection of nodes that connect with each other via virtual overlay links built upon an underlying network (usually, the Internet). P2P networks are highly dynamic and can experience very heavy churn, i.e., a large number of nodes join/leave the network continuously. Thus, building and maintaining a stable overlay network is an important problem that has been studied extensively for two decades. In this paper, we present our P2P overlay network called Sparse Robust Addressable Network (Spartan). Spartan can be quickly and efficiently built in a fully distributed fashion within O (log n) rounds. Furthermore, the Spartan overlay structure can be maintained, again, in a fully distributed manner despite adversarially controlled churn (i.e., nodes joining and leaving) and significant variation in the number of nodes. Moreover, new nodes can join a committee within O (1) rounds and leaving nodes can leave without any notice. The number of nodes in the network lies in [ n , f n ] for any fixed f ≥ 1. Up to ϵ n nodes (for some small but fixed ϵ > 0) can be adversarially added/deleted within any period of P rounds for some P ∈ O (log log n). Despite such uncertainty in the network, Spartan maintains Θ (n ∕ log n) committees that are stable and addressable collections of Θ (log n) nodes each for polynomial (n) rounds with high probability. Spartan's committees are also capable of performing sustained computation and passing messages between each other. Thus, any protocol designed for static networks can be simulated on Spartan with minimal overhead. This makes Spartan an ideal platform for developing applications. We experimentally show that Spartan will remain robust as long as each committee, on average, contains 24 nodes for networks of size up to 10240. • We introduce a novel overlay network design called Spartan. • We provide procedures to build and maintain it. • Spartan comprises Θ (n ∕ log n) addressable " committees." • Each committee consists of Θ (log n) randomly chosen peers. • The committees are arranged in the form of a butterfly network. • We show that Spartan is provably robust to heavy churn. • Any algorithm for the CONGEST model can be simulated by the committees of Spartan. • We can build robust distributed hash tables on Spartan despite heavy churn. [ABSTRACT FROM AUTHOR]

Beyond the scope of conventional metasurface, which necessitates plenty of computational resources and time, an inverse design approach using machine learning algorithms promises an effective way for metasurface design. In this paper, benefiting from Deep Neural Network (DNN), an inverse design procedure of a metasurface in an ultra-wide working frequency band is presented in which the output unit cell structure can be directly computed by a specified design target. To reach the highest working frequency for training the DNN, we consider 8 ring-shaped patterns to generate resonant notches at a wide range of working frequencies from 4 to 45 GHz. We propose two network architectures. In one architecture, we restrict the output of the DNN, so the network can only generate the metasurface structure from the input of 8 ring-shaped patterns. This approach drastically reduces the computational time, while keeping the network's accuracy above 91%. We show that our model based on DNN can satisfactorily generate the output metasurface structure with an average accuracy of over 90% in both network architectures. Determination of the metasurface structure directly without time-consuming optimization procedures, an ultra-wide working frequency, and high average accuracy equip an inspiring platform for engineering projects without the need for complex electromagnetic theory. [ABSTRACT FROM AUTHOR]

This paper studies the optimal clearing problem for prosumers in peer-to-peer (P2P) energy markets. It is proved that if no trade weights are enforced and the communication structure between successfully traded peers is connected, then the optimal clearing price and total traded powers in P2P market are the same with that in the pool-based market. However, if such communication structure is unconnected, then the P2P market is clustered into smaller P2P markets. If the trade weights are imposed, then the derived P2P market solutions can be significantly changed. Next, a novel decentralized optimization approach is proposed to derive a trading mechanism for P2P markets, based on the alternating direction method of multipliers (ADMM) which naturally fits into the bidirectional trading in P2P energy systems and converges reasonably fast. Analytical formulas of variable updates reveal insightful relations for each pair of prosumers on their individually traded prices and powers with their total traded powers. Further, based on those formulas, decentralized learning schemes for tuning parameters of prosumers cost functions are proposed to attain successful trading with total traded power amount as desired. Case studies on a synthetic system and the IEEE European Low Voltage Test Feeder are then carried out to verify the proposed approaches. [ABSTRACT FROM AUTHOR]

With the vision of Internet of Things gaining popularity at a global level, efficient publish/subscribe middleware for communication within and across data centers is extremely desirable. In this respect, the very popular Software-Defined Networking, which enables publish/subscribe middleware to perform line-rate filtering of events directly on hardware, can prove to be very useful. While deploying content filters directly on switches of a software-defined network allows optimized paths, high throughput rates, and low end-to-end latency, it suffers from certain inherent limitations with respect to number of bits available on hardware switches to represent these filters. Such a limitation affects expressiveness of filters, resulting in unnecessary traffic in the network. In this paper, we explore various complementary techniques to represent content filters expressively while being limited by hardware. We implement and evaluate techniques that i) use workload, in terms of events and subscriptions, to represent content, and ii) efficiently select attributes to reduce redundancy in content. Our detailed performance evaluations show the potential of these techniques in reducing unnecessary traffic when subjected to different workloads. Furthermore, the techniques proposed in this paper require significant updates to the network, i.e., the data plane, which must be performed in a consistent manner to ensure desired system behavior. As a result, in this paper, we, also, design and evaluate a light-weight approach that ensures data plane consistency in the presence of dynamic network updates. [ABSTRACT FROM AUTHOR]

Software Defined Network (SDN) is a new network architecture that has an operating system. Unlike conventional production networks, SDN allows more flexibility in network management using that operating system that is called the controller. The main advantage of having a controller in the network is the separation of the forwarding and the control planes, which provides central control over the network. Although central control is the major advantage of SDN, it is also a single point of failure if it is made unreachable by a Distributed Denial of Service (DDoS) attack. In this paper, that single point of failure is addressed by utilizing the controller to detect such attacks and protect the SDN architecture of the network in its early stages. The two main objectives of this paper are to (1) make use of the controller’s broad view of the network to detect DDoS attacks and (2) propose a solution that is effective and lightweight in terms of the resources that it uses. To accomplish these objectives, this paper examines the effect of DDoS attacks on the SDN controller and the way it can exhaust controller resources. The proposed solution to detect such attacks is based on the entropy variation of the destination IP address. Based on our experimental setup, the proposed method can detect DDoS within the first 250 packets of the attack traffic. [ABSTRACT FROM AUTHOR]

In a smart distribution power grid, cost efficient and reliable communication architecture plays a crucial role in achieving complete functionality. There are different sets of Quality of Services (QoS) requirements for different data packets transmitting inside the microgrid (a regionally limited smart distribution grid), making it challenging to derive optimal communication architecture. The objective of this research work is to determine the optimal communication technologies for each data packet based on its QoS requirement. In this paper, we have proposed an architecture for a smart distribution power grid with Cyber Physical System enabled microgrids, which accommodate almost all functional requirements of a smart distribution power grid. For easy transition towards optimal communication architecture, we have presented a six-tier communication topology, which is derived from the architecture for a smart distribution power grid. The optimization formulations for each packet structure presented in this paper minimize the overall cost and consider the QoS requirements for each packet. Based on the simulation results, we have made recommendations for optimal communication technologies for each packet and thereby developed a heterogeneous communication architecture for a microgrid. [ABSTRACT FROM AUTHOR]

An opportunistic network is a wireless ad hoc network that has frequently intermittent connectivity due to nodes’ mobility. These spare, unpredictable networks aim to solve the prolonged delay paths by a store-carry-forward scheme. It is difficult to determine the appropriate nodes to forward the messages since there are few opportunistic contacts. The nodes might decide based on the obtained data of the network as a guide to reach a destination. The aforementioned technique is not helpful in case the rate of change in the network topology is higher than the rate of data gathering due to usage restrictions and uncertain available information/knowledge of the future contacts. In this paper, to cope with the challenges imposed by the un-deterministic environment, a risk assessment strategy is considered to evaluate the short and long-term impact of each decision to find the optimal node/paths. This routing scheme can take advantage of the unanticipated connection to make the routing more flexible in short time and with less buffer usage. Our proposed risk assessment algorithms that are based on MALP are mixed with the knowledge about buffer management and network capacity. The prioritized messages to be disseminated as well as better decision to take a risk are the main contributions of this paper. Moreover, the self-adaptive threshold, distributed PID controller, is considered to tackle different threshold levels for each node individually. Numerical results prove that the proposed method drastically increases the delivery ratio and also minimizes the risk of exceeding resource consumption and packet loss. [ABSTRACT FROM AUTHOR]

Motivated by many networked computing systems used in data centers, Grid or Cloud computing infrastructures, and spatially distributed wireless sensor networks configured in aerospace and military industries, this paper considers a multi-state series-parallel system where n heterogeneous components can possess multiple states with different performance rates. Performability is concerned with the probability of such a system performing at a cumulative system performance W characterized in terms of the minimum of all cumulative subsystem performance G j (1 ≤  j  ≤  m ), G j is the sum of the performance rates of components belonging to the j th subsystem. This paper proposes a multi-valued decision diagram (MDD)-based approach to model and evaluate the concerned performability. A single compact MDD model is constructed by sharing all isomorphic model structures involved in different cumulative system performance. The MDD model can be reused when different versions of component state probability distributions are evaluated, thus it can facilitate solutions to further problems that require executing numerous iterations of performability evaluations, for example, the redundancy and/or reliability optimization problems. [ABSTRACT FROM AUTHOR]

Solid state drives (SSDs) have been widely deployed in personal computers, data centers, and cloud storages. In order to improve performance, SSDs are usually constructed with a number of channels with each channel connecting to a number of nand flash chips, each flash chip consisting of multiple dies and each die containing multiple planes. Based on this parallel architecture, I/O requests are potentially able to access parallel units simultaneously. Despite the rich parallelism offered by the parallel architecture, recent studies show that the utilization of flash parallel units is seriously low. This paper shows that the low parallel unit utilization is highly caused by the access conflict among I/O requests. In this paper, we propose parallel issue queueing (PIQ), a novel I/O scheduler at the host systems. PIQ groups I/O requests without conflicts into the same batch and I/O requests with conflicts into different batches. Hence, the multiple I/O requests in one batch can be fulfilled simultaneously by exploiting the rich parallelism of SSDs. Extensive experimental results show that PIQ delivers significant performance improvement especially for the applications which have heavy access conflicts. [ABSTRACT FROM PUBLISHER]

Nowadays, the complexity of global video products has substantially increased. They are composed of several associated services whose functionalities need to adapt across heterogeneous networks with different technologies and administrative domains. Each of these domains has different operational procedures; therefore, the comprehensive management of multi-domain services presents serious challenges. This paper discusses an approach to service management linking fault diagnosis system and Business Processes for Telefónica's global video service. The main contribution of this paper is the proposal of an extended service management architecture based on Multi Agent Systems able to integrate the fault diagnosis with other different service management functionalities. This architecture includes a distributed set of agents able to coordinate their actions under the umbrella of a Shared Knowledge Plane, inferring and sharing their knowledge with semantic techniques and three types of automatic reasoning: heterogeneous, ontology-based and Bayesian reasoning. This proposal has been deployed and validated in a real scenario in the video service offered by Telefónica Latam. [ABSTRACT FROM AUTHOR]