Future Internet, Volume 16, Issue 4 (April 2024) – 37 articles

Path hopping serves as an active defense mechanism in network security, yet it encounters challenges like a restricted path switching space, the recurrent use of similar paths and vital nodes, a singular triggering mechanism for path switching, and fixed hopping intervals. This paper introduces an active defense method employing multiple constraints and strategies for path hopping. A depth-first search (DFS) traversal is utilized to compute all possible paths between nodes, thereby broadening the path switching space while simplifying path generation complexity. Subsequently, constraints are imposed on residual bandwidth, selection periods, path similitude, and critical nodes to reduce the likelihood of reusing similar paths and crucial nodes. Moreover, two path switching strategies are formulated based on the weights of residual bandwidth and critical nodes, along with the calculation of path switching periods. This facilitates adaptive switching of path hopping paths and intervals, contingent on the network’s residual bandwidth threshold, in response to diverse attack scenarios. Simulation outcomes illustrate that this method, while maintaining normal communication performance, expands the path switching space effectively, safeguards against eavesdropping and link-flooding attacks, enhances path switching diversity and unpredictability, and fortifies the network’s resilience against malicious attacks. Full article

This study focuses on optimizing federated learning in heterogeneous data environments. We implement the FedProx and a baseline algorithm (i.e., the FedAvg) with advanced optimization strategies to tackle non-IID data issues in distributed learning. Model freezing and pruning techniques are explored to showcase the effective operations of deep learning models on resource-constrained edge devices. Experimental results show that at a pruning rate of 10%, the FedProx with structured pruning in the MIT-BIH and ST databases achieved the best F1 scores, reaching 96.01% and 77.81%, respectively, which achieves a good balance between system efficiency and model accuracy compared to those of the FedProx with the original configuration, reaching F1 scores of 66.12% and 89.90%, respectively. Similarly, with layer freezing technique, unstructured pruning method, and a pruning rate of 20%, the FedAvg algorithm effectively balances classification performance and degradation of pruned model accuracy, achieving F1 scores of 88.75% and 72.75%, respectively, compared to those of the FedAvg with the original configuration, reaching 56.82% and 85.80%, respectively. By adopting model optimization strategies, a practical solution is developed for deploying complex models in edge federated learning, vital for its efficient implementation. Full article

With the expansion of network scale, new network services are emerging. Segment Routing over IPv6 (SRv6) can meet the diverse needs of more new services due to its excellent scalability and programmability. In the intelligent 6-Generation (6G) scenario, frequent SRv6 Traffic Engineering (TE) policy updates will result in the serious problem of unsynchronized updates across routers. Existing solutions suffer from issues such as long update cycles or large data overhead. To optimize the policy-update process, this paper proposes a scheme called Synchronous Update with the Division and Combination of SRv6 Policy (SUDC). Based on the characteristics of the SRv6 TE policy, SUDC divides the policies and introduces Bit Index Explicit Replication IPv6 Encapsulation (BIERv6) to multicast the policy blocks derived from policy dividing. The contribution of this paper is to propose the policy-dividing and combination mechanism and the policy-dividing algorithm. The simulation results demonstrate that compared with the existing schemes, the update overhead and update cycle of SUDC are reduced by 46.71% and 46.6%, respectively. The problem of unsynchronized updates across routers has been further improved. Full article

Detecting anomalies in human activities is increasingly crucial today, particularly in nuclear family settings, where there may not be constant monitoring of individuals’ health, especially the elderly, during critical periods. Early anomaly detection can prevent from attack scenarios and life-threatening situations. This task becomes notably more complex when multiple ambient sensors are deployed in homes with multiple residents, as opposed to single-resident environments. Additionally, the availability of datasets containing anomalies representing the full spectrum of abnormalities is limited. In our experimental study, we employed eight widely used machine learning and two deep learning classifiers to identify anomalies in human activities. We meticulously generated anomalies, considering all conceivable scenarios. Our findings reveal that the Gated Recurrent Unit (GRU) excels in accurately classifying normal and anomalous activities, while the naïve Bayes classifier demonstrates relatively poor performance among the ten classifiers considered. We conducted various experiments to assess the impact of different training–test splitting ratios, along with a five-fold cross-validation technique, on the performance. Notably, the GRU model consistently outperformed all other classifiers under both conditions. Furthermore, we offer insights into the computational costs associated with these classifiers, encompassing training and prediction phases. Extensive ablation experiments conducted in this study underscore that all these classifiers can effectively be deployed for anomaly detection in two-resident homes. Full article

Ensuring compliance with the stringent latency requirements of edge services requires close cooperation between the network and computing components. Within mobile 5G networks, the nomadic behavior of users may impact the performance of edge services, prompting the need for workload migration techniques. These techniques allow services to follow users by moving between edge nodes. This paper introduces an innovative approach for edge service continuity by integrating Segment Routing over IPv6 (SRv6) into the 5G core data plane alongside the ETSI multi-access edge computing (MEC) architecture. Our approach maintains compatibility with non-SRv6 5G network components. We use SRv6 for packet steering and Software-Defined Networking (SDN) for dynamic network configuration. Leveraging the SRv6 Network Programming paradigm, we achieve lossless workload migration by implementing a packet buffer as a virtual network function. Our buffer may be dynamically allocated and configured within the network. We test our proposed solution on a small-scale testbed consisting of an Open Network Operating System (ONOS) SDN controller and a core network made of P4 BMv2 switches, emulated using Mininet. A comparison with a non-SRv6 alternative that uses IPv6 routing shows the higher scalability and flexibility of our approach in terms of the number of rules to be installed and time required for configuration. Full article

Low-rate Denial of Service (LDoS) attacks are today considered one of the biggest threats against modern data centers and industrial infrastructures. Unlike traditional Distributed Denial of Service (DDoS) attacks that are mainly volumetric, LDoS attacks exhibit a very small network footprint, and therefore can easily elude standard detection and defense mechanisms. This work introduces a defense strategy that may prove particularly effective against attacks that are based on long-lived connections, an inherent trait of LDoS attacks. Our approach is based on iteratively partitioning the active connections of a victim server across a number of replica servers, and then re-evaluating the health status of each replica instance. At its core, this approach relies on live migration and containerization technologies. The main advantage of the proposed approach is that it can discover and isolate malicious connections with virtually no information about the type and characteristics of the performed attack. Additionally, while the defense takes place, there is little to no indication of the fact to the attacker. We assess various rudimentary schemes to quantify the scalability of our approach. The results from the simulations indicate that it is possible to save the vast majority of the benign connections (80%) in less than 5 min. Full article

Multi-access edge computing (MEC) enhances service quality for users and reduces computational overhead by migrating workloads and application data to the network edge. However, current solutions for task offloading and cache replacement in edge scenarios are constrained by factors such as communication bandwidth, wireless network coverage, and limited storage capacity of edge devices, making it challenging to achieve high cache reuse and lower system energy consumption. To address these issues, a framework leveraging cooperative edge servers deployed in wireless access networks across different geographical regions is designed. Specifically, we propose the Distributed Edge Service Caching and Offloading (DESCO) network architecture and design a decentralized resource-sharing algorithm based on consistent hashing, named Cache Chord. Subsequently, based on DESCO and aiming to minimize overall user energy consumption while maintaining user latency constraints, we introduce the real-time computation offloading (RCO) problem and transform RCO into a multi-player static game, prove the existence of Nash equilibrium solutions, and solve it using a multi-dimensional particle swarm optimization algorithm. Finally, simulation results demonstrate that the proposed solution reduces the average energy consumption by over 27% in the DESCO network compared to existing algorithms. Full article

The growing complexity of construction supply chains and the significant impact of the construction industry on the environment demand an understanding of how to reuse and repurpose materials. In response to this critical challenge, research gaps that are significant in promoting material circularity are described. Despite its potential, the use of blockchain technology in construction faces challenges in verifiability, scalability, privacy, and interoperability. We propose a novel multilayer blockchain framework to enhance provenance tracking and data retrieval to enable a reliable audit trail. The framework utilises a privacy-centric solution that combines decentralised and centralised storage, security, and privacy. Furthermore, the framework implements access control to strengthen security and privacy, fostering transparency and information sharing among the stakeholders. These contributions collectively lead to trusted material circularity in a built environment. The implementation framework aims to create a prototype for blockchain applications in construction supply chains. Full article

The convergence of cyber and physical systems through cyber–physical systems (CPSs) has been integrated into cyber–physical production systems (CPPSs), leading to a paradigm shift toward intelligent manufacturing. Despite the transformative benefits that CPPS provides, its increased connectivity exposes manufacturers to cyber-attacks through exploitable vulnerabilities. This paper presents a novel approach to CPPS security protection by leveraging digital twin (DT) technology to develop a comprehensive security model. This model enhances asset visibility and supports prioritization in mitigating vulnerable components through DT-based virtual tuning, providing quantitative assessment results for effective mitigation. Our proposed DT security model also serves as an advanced simulation environment, facilitating the evaluation of CPPS vulnerabilities across diverse attack scenarios without disrupting physical operations. The practicality and effectiveness of our approach are illustrated through its application in a human–robot collaborative assembly system, demonstrating the potential of DT technology. Full article

In this paper, we explore the realm of federated learning (FL), a distributed machine learning (ML) paradigm, and propose a novel approach that leverages the robustness of blockchain technology. FL, a concept introduced by Google in 2016, allows multiple entities to collaboratively train an ML model without the need to expose their raw data. However, it faces several challenges, such as privacy concerns and malicious attacks (e.g., data poisoning attacks). Our paper examines the existing EIFFeL framework, a protocol for decentralized real-time messaging in continuous integration and delivery pipelines, and introduces an enhanced scheme that leverages the trustworthy nature of blockchain technology. Our scheme eliminates the need for a central server and any other third party, such as a public bulletin board, thereby mitigating the risks associated with the compromise of such third parties. Full article

Farming is a major sector required for any nation to become self-sustainable. Quality seeds heavily influence the effectiveness of farming. Seeds cultivated by breeders pass through several entities in order to reach farmers. The existing seed supply chain is opaque and intractable, which not only hinders the growth of crops but also makes the life of a farmer miserable. Blockchain has been widely employed to enable fair and secure transactions between farmers and buyers, but concerns related to transparency and traceability in the seed supply chain, counterfeit seeds, middlemen involvement, and inefficient processes in the agricultural ecosystem have not received enough attention. To address these concerns, a blockchain-based solution is proposed that brings breeders, farmers, warehouse owners, transporters, and food corporations to a single platform to enhance transparency, traceability, and trust among trust-less parties. A smart contract updates the status of seeds from a breeder from $submitted$ to $approved$. Then, a non-fungible token (NFT) corresponding to approved seeds is minted for the breeder, which records the date of cultivation and its owner (breeder). The NFT enables farmers to keep track of seeds right from the date of their cultivation and their owner, which helps them to make better decisions about picking seeds from the correct owner. Farmers directly interact with warehouses to purchase seeds, which removes the need for middlemen and improves the trust among trust-less entities. Furthermore, a tender for the transportation of seeds is auctioned on the basis of the priority location $lo{c}_p$, Score, and bid_amount of every transporter, which provides a fair chance to every transporter to restrict the monopoly of a single transporter. The proposed system achieves immutability, decentralization, and efficiency inherently from the blockchain. We implemented the proposed scheme and deployed it on the Ethereum network. Smart contracts deployed over the Ethereum network interact with React-based web pages. The analysis and results of the proposed model indicate that it is viable and secure, as well as superior to the current seed supply chain system. Full article

In order to solve the congestion problem caused by the dramatic growth of traffic in data centers, many end-to-end congestion controls have been proposed to respond to congestion in one round-trip time (RTT). In this paper, we propose a new congestion control mechanism based on backpressure feedback (BFCC), which is designed with the primary goal of switch-to-switch congestion control to resolve congestion in a one-hop RTT. This approach utilizes a programmable data plane to continuously monitor network congestion in real time and identify real-congested flows. In addition, it employs targeted flow control through backpressure feedback. We validate the feasibility of this mechanism on BMV2, a programmable virtual switch based on programming protocol-independent packet processors (P4). Simulation results demonstrate that BFCC greatly enhances flow completion times (FCTs) compared to other end-to-end congestion control mechanisms. It achieves 1.2–2× faster average completion times than other mechanisms. Full article

LoRaWAN is a low-power wide-area network (LPWAN) technology that is well suited for industrial IoT (IIoT) applications. One of the challenges of using LoRaWAN for IIoT is the need to collect data from a large number of devices. Polling is a common way to collect data from devices, but it can be inefficient for LoRaWANs, which are designed for low data rates and long battery life. LoRaWAN devices operating in two specific modes can receive messages from a gateway even when they are not sending data themselves. This allows the gateway to send commands to devices at any time, without having to wait for them to check for messages. This paper proposes various polling mechanisms for industrial IoT applications in LoRaWANs and presents specific considerations for designing efficient polling mechanisms in the context of industrial IoT applications leveraging LoRaWAN technology. Full article

Although several years have passed since its first introduction, the significance of Delay-Tolerant Networking (DTN) remains evident, particularly in challenging environments where traditional networks face operational limitations such as disrupted communication or high latency. This survey paper aims to explore the diverse array of applications where DTN technologies have proven successful, with a focus on emerging and novel application paradigms. In particular, we focus on the contributions of DTN in the Future Internet, including its contribution to space applications, smart cities and the Internet of Things, but also to underwater communications. We also discuss its potential to be used jointly with information-centric networks to change the internet communication paradigm in the future. Full article

The Internet of Things (IoT) employs sensors and the Internet for information exchange, enabling intelligent identification, monitoring, and management, which has deeply impacted various sectors such as power, medical care, and security, transforming social activities and lifestyles. Regrettably, IoT systems suffer from two main challenges, namely sustainability and security. Hence, pondering how to enhance sustainable and energy-efficient practices for IoT systems to mitigate risks becomes a worthwhile endeavor. To address this issue, we conduct a survey of energy-aware security mechanisms in the Internet of Things. Specifically, we examine the challenges that IoT is facing in terms of energy efficiency and security, and we inspect current energy-saving and privacy-preserving technologies for IoT systems. Moreover, we delineate a vision for the future of IoT, emphasizing energy-aware security mechanisms. Finally, we outline the challenges encountered in achieving energy-aware security mechanisms, as well as the direction of future research. Motivated by this study, we envision advancements in the IoT that not only harness the benefits of science and technology but also enhance the security and safety of our data. Full article

With the proliferation of WiFi devices, WiFi-based identification technology has garnered attention in the security domain and has demonstrated initial success. Nonetheless, when untrained illegitimate users appear, the classifier tends to categorize them as if they were trained users. In response to this issue, researchers have proposed identity legitimacy authentication systems to identify illicit users, albeit only applicable to individual users. In this article, we propose a multi-user legitimacy authentication system based on WiFi, termed Multi-WiIR. Leveraging WiFi signals, the system captures users’ walking patterns to ascertain their legitimacy. The core concept entails training a multi-branch deep neural network, designated WiIR-Net, for feature extraction of individual users. Binary classifiers are then applied to each user, and legitimacy is established by comparing the model’s output to predefined thresholds, thus facilitating multi-user legitimacy authentication. Moreover, the study experimentally investigated the impact of the number of legitimate individuals on accuracy rates. The results demonstrated that The Multi-WiIR system showed commendable performance with low latency, being capable of conducting legitimacy recognition in scenarios involving up to four users, with an accuracy rate reaching 85.11%. Full article

The metaverse aims to merge the virtual and real worlds. The target is to generate a virtual community where social components play a crucial role and combine different areas such as entertainment, work, shopping, and services. This idea is explicitly appealing in the context of smart cities. The metaverse offers digitalization approaches and can strengthen citizens’ social community. While the existing literature covers the exemplary potential of smart city metaverse applications, this study aims to provide a comprehensive overview of the potential and already implemented metaverse applications in the context of cities and municipalities. In addition, challenges related to these applications are identified. The study combines literature reviews and expert interviews to ensure a broad overview. Forty-eight smart city metaverse applications from eleven areas were identified, and actual projects from eleven cities demonstrate the current state of development. Still, further research should evaluate the benefits of the various applications and find strategies to overcome the identified challenges. Full article

Currently, there are a wide range of approaches to deploying digital ads, with advanced technologies now being harnessed to craft advertising that is engaging and even tailored to personal interests and preferences, yet potentially distracting and irritating. This research seeks to evaluate contemporary digital advertising methods by assessing how annoying they are to users, particularly when they distract users from intended tasks or cause delays in regular online activities. To pursue this, an eye-tracking study was conducted, with 51 participants navigating a specially designed website featuring seven distinct types of advertisements without a specific content to avoid the effect of ad content on the collected data. Participants were asked to execute specific information-seeking tasks during the experiment and afterwards to report if they recalled seeing each ad and the degree of annoyance by each ad type. Ad effectiveness is assessed by eye-tracking metrics (time to first fixation, average fixation duration, dwell time, fixation count, and revisit count) depicting how appealing an ad is as a marketing stimulus. Findings indicated that pop-ups, ads with content reorganization, and non-skippable videos ranked as the most annoying forms of advertising. Conversely, in-content ads without content reorganization, banners, and right rail ads were indicated as less intrusive options, seeming to strike a balance between effectiveness and user acceptance. Full article

The objective of task allocation in unmanned systems is to complete tasks at minimal costs. However, the current algorithms employed for coordinating multiple unmanned systems in task allocation tasks frequently converge to local optima, thus impeding the identification of the best solutions. To address these challenges, this study builds upon the sheep flock optimization algorithm (SFOA) by preserving individuals eliminated during the iterative process within a prior knowledge set, which is continuously updated. During the reproduction phase of the algorithm, this prior knowledge is utilized to guide the generation of new individuals, preventing their rapid reconvergence to local optima. This approach aids in reducing the frequency at which the algorithm converges to local optima, continually steering the algorithm towards the global optimum and thereby enhancing the efficiency of task allocation. Finally, various task scenarios are presented to evaluate the performances of various algorithms. The results show that the algorithm proposed in this paper is more likely than other algorithms to escape from local optima and find the global optimum. Full article

The exponential growth in data traffic in the real world has drawn attention to the emerging computing technique called Fog Computing (FC) for offloading tasks in fault-free environments. This is a promising computing standard that offers higher computing benefits with a reduced cost, higher flexibility, and increased availability. With the increased number of tasks, the occurrence of faults increases and affects the offloading of tasks. A suitable mechanism is essential to rectify the faults that occur in the Fog network. In this research, the fault-tolerance (FT) mechanism is proposed based on cost optimization and fault minimization. Initially, the faulty nodes are identified based on the remaining residual energy with the proposed Priority Task-based Fault-Tolerance (PTFT) mechanism. The Minimum-Cost Neighbour Candidate Node Discovery (MCNCND) algorithm is proposed to discover the neighbouring candidate Fog access node that can replace the faulty Fog node. The Replication and Pre-emptive Forwarding (RPF) algorithm is proposed to forward the task information to the new candidate Fog access node for reliable transmission. These proposed mechanisms are simulated, analysed, and compared with existing FT methods. It is observed that the proposed FT mechanism improves the utilization of an active number of Fog access nodes. It also saved a residual energy of 1.55 J without replicas, compared to the 0.85 J of energy that is used without the FT method. Full article

In the near future, there will be a greater emphasis on sharing network resources between roads and railways to improve transportation efficiency and reduce infrastructure costs. This could enable the development of global Cooperative Intelligent Transport Systems (C-ITSs). In this paper, a software-defined networking (SDN)-based common emergency service is developed and validated for a railway and road telecommunication shared infrastructure. Along with this, the developed application is capable of reducing the chances of distributed denial-of-service (DDoS) situations. A level-crossing scenario is considered to demonstrate the developed solution where railway tracks are perpendicular to the roads. Two cases are considered to validate and analyze the developed SDN application for common emergency scenarios. In case 1, no cross-communication is available between the road and railway domains. In this case, emergency message distribution is carried out by the assigned emergency servers with the help of the SDN controller. In case 2, nodes (cars and trains) are defined with two wireless interfaces, and one interface is reserved for emergency data communication. To add the DDoS resiliency to the developed system the messaging behavior of each node is observed and if an abnormality is detected, packets are dropped to avoid malicious activity. Full article

With the innovation of wireless communication technology and the surge of data in mobile networks, traditional routing strategies need to be improved. Given the shortcomings of existing opportunistic routing strategies in transmission performance and security, this paper proposes a community opportunistic routing decision-making method based on the trust model. This algorithm calculates the node’s trust value through the node’s historical forwarding behavior and then calculates the node’s trust value based on the trust model. Thresholds and trust attenuation divide dynamic security communities. For message forwarding, nodes in the security community are prioritized as next-hop relay nodes, thus ensuring that message delivery is always in a safe and reliable environment. On this basis, better relay nodes are further selected for message forwarding based on the node centrality, remaining cache space, and remaining energy, effectively improving the message forwarding efficiency. Through node trust value and community cooperation, safe and efficient data transmission is achieved, thereby improving the transmission performance and security of the network. Through comparison of simulation and opportunistic network routing algorithms, compared with traditional methods, this strategy has the highest transmission success rate of 81% with slightly increased routing overhead, and this algorithm has the lowest average transmission delay. Full article

Time-Sensitive Networking (TSN) aims to provide deterministic communications over Ethernet. The main characteristics of TSN are bounded latency and very high reliability, thus complying with the strict requirements of industrial communications or automotive applications, to name a couple of examples. In order to achieve this goal, TSN defines several scheduling algorithms, among them the Time-Aware Shaper (TAS), which is based on time slots and Gate Control Lists (GCLs). The configuration of network elements to allocate time slots, paths, and GCLs is laborious, and has to be updated promptly and in a dynamic way, as new data flows arrive or disappear. The IEEE 802.1Qcc standard provides the basis to design a TSN control plane to face these challenges, following the Software-Defined Networking (SDN) paradigm. However, most of the current SDN/TSN control plane solutions are monolithic applications designed to run on dedicated servers, and do not provide the required flexibility to escalate when facing increasing service requests. This work presents $\mu$TSN-CP, an SDN/TSN microservices-based control plane, based on the 802.1Qcc standard. Our architecture leverages the advantages of microservices, enabling the control plane to scale up or down in response to varying workloads dynamically. We achieve enhanced flexibility and resilience by breaking down the control plane into smaller, independent microservices. The performance of $\mu$TSN-CP is evaluated in a real environment with TSN switches, and various integer linear problem solvers, running over different computing platforms. Full article

In data center networks, when facing challenges such as traffic volatility, low resource utilization, and the difficulty of a single traffic scheduling strategy to meet demands, it is necessary to introduce intelligent traffic scheduling mechanisms to improve network resource utilization, optimize network performance, and adapt to the traffic scheduling requirements in a dynamic environment. This paper proposes a fine-grained traffic scheduling scheme based on multi-agent deep reinforcement learning (MAFS). This approach utilizes In-Band Network Telemetry to collect real-time network states on the programmable data plane, establishes the mapping relationship between real-time network state information and the forwarding efficiency on the control plane, and designs a multi-agent deep reinforcement learning algorithm to calculate the optimal routing strategy under the current network state. The experimental results demonstrate that compared to other traffic scheduling methods, MAFS can effectively enhance network throughput. It achieves a 1.2× better average throughput and achieves a 1.4–1.7× lower packet loss rate. Full article

Named Data Networking (NDN) is a future Internet architecture that requires an Inter-Domain Routing (IDR) to route its traffic globally. Address resolution is a vital component of any IDR system that relies on a Domain Name System (DNS) resolver to translate domain names into their IP addresses in TCP/IP networks. This paper presents a novel two-element solution to enhance name-to-delivery location resolution in NDN networks, consisting of (1) a mapping table data structure and a searching mechanism and (2) a management protocol to automatically populate and modify the mapping table. The proposed solution is implemented and tested on the Peer Name Provider Server (PNPS) mapping table, and its performance is compared with two other algorithms: component and character tries. The findings show a notable enhancement in the operational speed of the mapping table when utilizing the proposed data structure. For instance, the insertion process is 37 times faster compared to previous algorithms. Full article

Wireless communication tower placement arises in many real-world applications. This paper investigates a new emerging wireless communication tower placement problem, namely, continuous space wireless communication tower placement. Unlike existing wireless communication tower placement problems, which are discrete computational problems, this new wireless communication tower placement problem is a continuous space computational problem. In this paper, we formulate the new wireless communication tower placement problem and propose a hybrid simulated annealing algorithm that can take advantage of the powerful exploration capacity of simulated annealing and the strong exploitation capacity of a local optimization procedure. We also demonstrate through experiments the effectiveness of this hybridization technique and the good performance and scalability of the hybrid simulated annulling in this paper. Full article

Graph representation is recognized as an efficient method for modeling networks, precisely illustrating intricate, dynamic interactions within various entities of networks by representing entities as nodes and their relationships as edges. Leveraging the advantage of the network graph data along with deep learning technologies specialized for analyzing graph data, Graph Neural Networks (GNNs) have revolutionized the field of computer networking by effectively handling structured graph data and enabling precise predictions for various use cases such as performance modeling, routing optimization, and resource allocation. The RouteNet model, utilizing a GNN, has been effectively applied in determining Quality of Service (QoS) parameters for each source-to-destination pair in computer networks. However, a prevalent issue in the current GNN model is their struggle with generalization and capturing the complex relationships and patterns within network data. This research aims to enhance the predictive power of GNN-based models by enhancing the original RouteNet model by incorporating an attention layer into its architecture. A comparative analysis is conducted to evaluate the performance of the Modified RouteNet model against the Original RouteNet model. The effectiveness of the added attention layer has been examined to determine its impact on the overall model performance. The outcomes of this research contribute to advancing GNN-based network performance prediction, addressing the limitations of existing models, and providing reliable frameworks for predicting network delay. Full article

Analytical data platforms have been used for decades to improve organizational performance. Starting from the data warehouses used primarily for structured data processing, through the data lakes oriented for raw data storage and post-hoc data analyses, to the data lakehouses—a combination of raw storage and business intelligence pre-processing for improving the platform’s efficacy. But in recent years, a new architecture called Data Mesh has emerged. The main promise of this architecture is to remove the barriers between operational and analytical teams in order to boost the overall value extraction from the big data. A number of attempts have been made to formalize and implement it in existing projects. Although being defined as a socio-technical paradigm, data mesh still lacks the technology support to enable its widespread adoption. To overcome this limitation, we propose a new view of the platform requirements alongside the formal governance definition that we believe can help in the successful adoption of the data mesh. It is based on fundamental aspects such as decentralized data domains and federated computational governance. In addition, we also present a blockchain-based implementation of a mesh platform as a practical validation of our theoretical proposal. Overall, this article demonstrates a novel research direction for information system decentralization technologies. Full article

Accurate perception is crucial for autonomous vehicles (AVs) to navigate safely, especially in adverse weather and lighting conditions where single-sensor networks (e.g., cameras or radar) struggle with reduced maneuverability and unrecognizable targets. Deep Camera-Radar fusion neural networks offer a promising solution for reliable AV perception under any weather and lighting conditions. Cameras provide rich semantic information, while radars act like an X-ray vision, piercing through fog and darkness. This work proposes a novel, efficient Camera-Radar fusion network called NeXtFusion for robust AV perception with an improvement in object detection accuracy and tracking. Our proposed approach of utilizing an attention module enhances crucial feature representation for object detection while minimizing information loss from multi-modal data. Extensive experiments on the challenging nuScenes dataset demonstrate NeXtFusion’s superior performance in detecting small and distant objects compared to other methods. Notably, NeXtFusion achieves the highest mAP score (0.473) on the nuScenes validation set, outperforming competitors like OFT (35.1% improvement) and MonoDIS (9.5% improvement). Additionally, NeXtFusion demonstrates strong performance in other metrics like mATE (0.449) and mAOE (0.534), highlighting its overall effectiveness in 3D object detection. Furthermore, visualizations of nuScenes data processed by NeXtFusion further demonstrate its capability to handle diverse real-world scenarios. These results suggest that NeXtFusion is a promising deep fusion network for improving AV perception and safety for autonomous driving. Full article