Real Network Research Articles

Lifelong QoT prediction: an adaptation to real-world optical networks

Predicting the quality of transmission (QoT) is a critical task in the management and optimization of modern fiber-optic networks. Traditional machine learning (ML) QoT prediction models, typically trained on pre-collected datasets, are designed to make long-term predictions once deployed. However, this static training strategy often falls short in the face of time-dependent network evolution and variations. We identify the root cause of these shortcomings as shifts in data distribution, which are not accounted for in conventional static models. In response to these challenges, we propose an online continual learning pipeline that is specifically designed for stable QoT prediction in optical networks. This pipeline directly addresses the problem of distribution shifts by continuously updating the prediction model in response to real-time network data. We explore and compare various strategies within this framework and demonstrate that the integration of the adaptive retraining strategy and the regularized online continual learning algorithm (OCL-REG) significantly enhances the QoT prediction stability while optimizing the resource efficiency. OCL-REG demonstrates superior adaptability and stability, achieving an average cumulative mean squared error (C-MSE) of 0.19 on a testbench with a data distribution shift sequence containing 1000 batches. Moreover, the OCL-REG model requires fewer samples for adaptation, averaging around 107 samples, compared to the conventional retraining strategy, which requires an average of 253 samples. Our approach presents a paradigm shift in QoT prediction, moving from a static to a dynamic, lifelong learning model that is more attuned to the evolving realities of real fiber-optic networks.

Evaluating the performance of water distribution network deterioration using customer-oriented performance indices

ABSTRACT Water distribution networks (WDNs) are an essential urban infrastructure, with their performance directly influencing societal well-being. Our study applied to a real network model that employs a 24-h simulation with 1-h time steps and evaluates the impact of leaks and loss in the pipe cross-sectional area on WDN hydraulic performance as experienced by end users. Adhering to a UK utility's 20-m head pressure requirement as the water main benchmark, we present two new customer-oriented performance indices (CPIs) centred on network reliability and pressure deficit severity. The new CPIs adeptly quantify network performance degradation due to pipe deterioration. This degradation translates directly to a poor customer experience, highlighting the potential for these CPIs to pinpoint areas of the network where performance levels are compromised. Furthermore, the CPIs identify individual pipes within the network where defects would severely impact network performance and the sets of pipes which, when simultaneously experiencing defects, would lead to a more severe loss in network performance. Results show that the CPIs capture relatively small performance declines and identify sensitive pipes impacting network performance, providing insights for optimised inspection and maintenance intervention to provide better customer service.

A Modified TCP BBR to Enable High Fairness in High-Speed Wireless Networks

Wireless networks, especially 5G and WiFi networks, have made great strides in increasing network bandwidth and coverage over the past decades. However, the mobility and channel conditions inherent to wireless networks have the potential to impair the performance of traditional Transmission Control Protocol (TCP) congestion control algorithms (CCAs). Google proposed a novel TCP CCA based on Bottleneck Bandwidth and Round-Trip propagation time (BBR), which is capable of achieving high transmission rates and low latency through the estimation of the available bottleneck capacity. Nevertheless, some studies have revealed that BBR exhibits deficiencies in fairness among flows with disparate Round-Trip Times (RTTs) and also displays inter-protocol unfairness. In high-speed wireless networks, ensuring fairness is of paramount importance to guarantee equitable bandwidth allocation among diverse traffic types and to enhance overall network utilization. To address this issue, this paper proposes a BBR–Pacing Gain (BBR–PG) algorithm. By deriving the pacing rate control model, the impact of pacing gain on BBR fairness is revealed. Adjusting the pacing gain according to the RTT can improve BBR’s performance. Simulations and real network experiments have shown that the BBR–PG algorithm retains the throughput advantages of the original BBR algorithm while significantly enhancing fairness. In our simulation experiments, RTT fairness and intra-protocol fairness were improved by 50% and 46%, respectively.

Group Sparse β -Model for Network

Sparsity, homogeneity and heterogeneity are three important characteristics of many real-life networks. The recently proposed Sparse β -Model divides nodes into core ones and peripheral ones to accommodate sparsity, but the parameters of core nodes are assumed to be of similar magnitude, which may not be in line with applications. In this paper, we propose the Group Sparse β -Model that splits the core nodes into groups and assumes different orders of magnitude of parameters in different groups, accounting for the heterogeneity among core nodes. When the groups are known, we provide consistent and asymptotically normal moment estimators of the parameters that control the global and local density. Based on that, consistency and asymptotic normality of the maximum likelihood estimators of the remaining parameters are derived. We also establish finite-sample error bounds results. When the groups are unknown, a ratio method is proposed to detect groups, which is computationally efficient. Simulations show competitive results and the analysis of a corporate inter-relationships network illustrates the usefulness of the proposed model.

Predicting 5G throughput with BAMMO, a boosted additive model for data with missing observations

Abstract To deliver on the promise of 5G, network providers and application developers need to understand the factors impacting millimetre wave (mmWave) 5G throughput. Missing data, however, pose significant challenges for modelling throughput. Even in controlled settings, signal strength data may be only intermittently observed when a device’s connection is weak, leading to missing predictor values in model training. In addition, users may choose not to share their data once the model is deployed, meaning that key predictors may be missing when we want to predict throughput for their devices. To address these challenges, we introduce boosted additive model for data with missing observation (BAMMO), a novel additive model estimator obtained via a componentwise boosting algorithm that naturally incorporates data with missing values in model fitting. We validate BAMMO’s approach to handling missing data by comparing it with competing methods on real 5G network data with a high proportion of missing values and in simulations, finding that it delivers more accurate predictions and takes less time to compute. To identify key predictors of mmWave 5G throughput, we develop a novel extension of sparsity oriented importance learning for BAMMO, giving us a measure of variable importance based on the entire boosting solution path rather than a single selected model.

Identifying influential nodes in social networks via improved Laplacian centrality

Identifying influential nodes in social networks has significant applications in terms of social analysis and information dissemination. How to capture the crucial features of influential nodes without increasing the computational complexity is an urgent issue to be solved in the context of big data. Laplacian centrality (LC) measures nodal influence by computing nodes' degree, making it extremely low complexity. However, there is still significant room for improvement. Consequently, we propose the improved Laplacian centrality (ILC) to identify influential nodes based on the concept of self-consistent. Identifying results on 9 real networks prove that ILC is superior to LC and other 6 classical measures in terms of ranking accuracy, top-k nodes identification and discrimination capability. Moreover, the computational complexity of ILC has not significantly increased compared to LC, and remains the linear order of magnitude O(m). Additionally, ILC has excellent robustness and universality such that there is no need to adjust parameters according to different network structures.

Exploring residential minimum night consumption in a real water distribution network based on smart-meter data

An accurate estimation of leakages in water distribution networks is of primary importance for the definition of strategies aimed at ensuring an efficient management of water resources and avoiding water waste. However, in the case of methods based on water balance—such as the Minimum Night Flow method—inaccurate assessment of the minimum night consumption (MNC), e.g. the assumption of fixed MNC values from the literature, can heavily mislead the quantification of leakage level. This study aims at providing insights into the variability of MNC and the related drivers. In greater detail, hourly water consumption data of approximately 200 users are collected over a period of two years and subjected to a multi-phase methodology to obtain a detailed characterization of MNC, with and without considering the users affected by post-meter leakages. The study demonstrates that factors such as seasonality or the presence of post-meter leakages may strongly impact the MNC—the values of which can significantly deviate from the literature references—and thus lead to significant misestimation of network leakages in water systems.Graphical

5G Network Slicing as a Service Enabler for the Automotive Sector

ABSTRACTNetwork slicing, a key technology introduced in 5G standards, enables mobile networks to simultaneously support a wide range of heterogeneous use cases with diverse quality of service (QoS) requirements. This work discusses the potential benefits of network slicing for the automotive sector, encompassing manufacturing processes and vehicular communications. The review of the state of the art reveals a clear gap regarding the application of network slicing from the perspective of industrial verticals such as automotive use cases and their specific requirements. Departing from this observation, we first identify limitations of previous cellular technologies and open challenges for supporting the data services required. Then we describe network slicing as an enabler to face these challenges. We present an analysis of the cost equilibrium for network slicing to be effective for car manufacturers, and tests in real 5G networks that demonstrate the performance improvement in OTA updates coexisting with other services.

Research on Smart City Road Network Capacity Optimization Configuration Based on Deep Learning Algorithms

At present, the urban traffic system is faced with the problems of congestion and low efficiency, and the traditional methods have certain limitations when dealing with the complex urban road network. This paper aims to explore a new method of capacity Optimization of Road Networks in a Smart City environment and proposes a method based on a Graph Neural network, named “Smart City Road optimization Graph Neural Network” (SCRO-GNN). SCRO-GNN first collects and preprocesses multi-source data, including road network data, traffic flow, accident records, environmental factors, etc. The key node and edge features, including the number of lanes at the intersection, the traffic flow of the section, and the adjacency matrix of the road network are defined to characterize the structure of the road network. Then, the graph neural network model is constructed and trained to predict the traffic flow of different sections and evaluate the road capacity by using the graph structure of the road network. This paper tests the performance of SCRO-GNN on real road networks in multiple cities. The results show that, compared with the traditional traffic flow prediction model, SCRO-GNN can significantly improve the prediction accuracy, especially when dealing with the highly complex urban road network structure. Based on these predictions, the proposed optimization strategy performed well in reducing traffic congestion and improving the efficiency of road use. The research in this paper not only demonstrates the potential of graph neural networks in smart city road network optimization, but also provides a new direction for future traffic system research. The successful implementation of the SCRO-GNN approach is expected to provide more efficient and intelligent solutions for urban traffic management and planning.

CESNET-TLS-Year22: A year-spanning TLS network traffic dataset from backbone lines.

The modern approach for network traffic classification (TC), which is an important part of operating and securing networks, is to use machine learning (ML) models that are able to learn intricate relationships between traffic characteristics and communicating applications. A crucial prerequisite is having representative datasets. However, datasets collected from real production networks are not being published in sufficient numbers. Thus, this paper presents a novel dataset, CESNET-TLS-Year22, that captures the evolution of TLS traffic in an ISP network over a year. The dataset contains 180 web service labels and standard TC features, such as packet sequences. The unique year-long time span enables comprehensive evaluation of TC models and assessment of their robustness in the face of the ever-changing environment of production networks.

Urban freight distribution with electric vehicles: comparing some solution procedures

The Vehicle Routing Problem (VRP) is a well-known discrete optimization problem that has an impact on theoretical and practical applications. In this paper, a freight distribution model that includes a charging system located at the depot, making it feasible for real world-implementation, is proposed. Two different solution methods are proposed and compared: a genetic algorithm (GA) and a population-based simulated annealing (PBSA) with the number of moves increasing during the iterations. Among the variety of algorithm used to solve the VRP, population-based search methods are the most useful, due to the ability to update the memory at each iteration. To demonstrate the practical aspects of the proposed solution a case study is solved using travel time on a real network to evaluate the potentiality for a real-world application.

Insight into a new perspective on the complex propagation processes in networks: dynamic link equations

Insight into the spread of epidemics under different transmission mechanisms in networks has long been an important research question in the field of complex network dynamics. Currently, under simple transmission mechanisms, our analysis of the dynamic processes in networks starts only from the node level, considering the scale of infected nodes in the network. However, the information provided by this lowest-order approach to considering dynamic processes in networks is very limited. Most importantly, it is not applicable to the analysis of dynamic processes in networks under more common complex transmission mechanisms, as it neglects the interactions between nodes. Therefore, in this article, we propose a set of closed link dynamic equations to gain insight into complex propagation processes from a microscopic perspective. Fundamentally, we have developed a set of analytical tools for analyzing complex dynamic behaviors at the link level, enabling us to reexamine the complex dynamic processes on networks from a higher-order perspective. Additionally, we apply the proposed analytical framework to complex SIS epidemiological models on two real and synthetic networks, and extensive numerical simulation results demonstrate the feasibility and effectiveness of the proposed method.

A distance-based network activity correlation framework for defeating anonymization overlays

As the effectiveness of modern Internet-based anonymization infrastructures grows, law enforcement agencies are experiencing a progressive erosion of their surveillance capabilities. This can severely undermine their efforts to prevent and investigate various types of unlawful activities, potentially increasing the impunity of organized criminal networks. Balancing the legitimate privacy needs of individuals with the imperative to maintain public safety and combat criminal behavior in the digital world remains a complex tradeoff for both policymakers and technologists who need to find a systematic and reliable way to link the traffic traces associated with criminal activities to their anonymized origins. Accordingly, this paper presents a simple but very effective de-anonymization approach capable of associating traffic traces captured at the edge of the overlay infrastructures, in correspondence with the true origins, to those captured in correspondence with the destinations. The approach is based on determining the minimum-distance pairs within a complete bipartite graph in which the traffic traces are the nodes. Experiments with different distance functions, applied in varied ways, show that the resulting framework appears to be a promising solution that is scalable and easily deployable on real-life network equipment.

AI Fusion Hub: Advances in AI-Powered Communication Platforms

The "AI Fusion Hub" introduces a new network based on MERN that integrates advanced AI projects. The platform leverages natural language processing and machine learning models to revolutionize user communication, productivity and creativity. The front-end design using React.js provides excellent power and functionality, making the user experience seamless. On the backend, Node.js and Express.js support powerful external processing, while MongoDB handles data storage and retrieval efficiently. The platform is deployed on the Vercel cloud, ensuring capacity and reliability. Key features include scripting, sentence generation, AI-powered chatbot interactions, text-to-JavaScript code conversion, and a sci-fi generator. These features provide users with many tools for effective communication and content creation. The project not only demonstrates the alignment between the evolution of web technology and intelligence-driven capabilities, but also demonstrates future developments including multimedia support, mobile optimization, integration and security measures. Bridging the gap between artificial intelligence and real network structure, the "AI Fusion Hub" represents a major advance in intelligent communications

TrafficPro: A road speed prediction framework for urban signal-controlled road networks

In view of the problem that traditional deep learning models do not consider the active time-varying characteristics of traffic flow (signal control information) when predicting the speed of urban road networks, and have low prediction accuracy, this paper proposes a speed prediction framework based on generative adversarial networks and graph neural networks. In this framework, the generator network simultaneously encodes the road network traffic flow and signal control information through active and passive prediction modules to generate prediction results, and then uses the discriminator network to improve the generalization of the prediction results. This framework can obtain higher prediction accuracy than traditional time series models and deep learning models. In the real road network speed prediction scenario, this framework can reduce the prediction error compared to the best benchmark model 3%-4%.

Traffic speed prediction of regional complex road network based on CapsNet and D-BiLSTM

Accurate and efficient short-term traffic prediction is of great significance in the study of regional traffic network. However, the complex and dynamic spatiotemporal correlation of traffic patterns makes the existing methods insufficient in learning traffic evolution in terms of structural depth and prediction scale. Therefore, this paper proposes a deep learning model combining capsule network (CapsNet) and deep bidirectional LSTM (D-BiLSTM). CapsNet is used to identify the spatial topological structure of the road network and extract spatial features, and D-BiLSTM network is integrated. The forward and backward dependencies of traffic states are considered at the same time, and the bidirectional temporal correlation of different historical periods is captured to predict the traffic of large-scale complex road networks in the target area. Experiments on real traffic network speed datasets show that the prediction accuracy of the proposed model is improved by more than 10% on average , which is better than other methods. It has high prediction accuracy and good robustness in traffic prediction of regional complex road networks.

Network mutual information measures for graph similarity

A wide range of tasks in network analysis, such as clustering network populations or identifying anomalies in temporal graph streams, require a measure of the similarity between two graphs. To provide a meaningful data summary for downstream scientific analyses, the graph similarity measures used for these tasks must be principled, interpretable, and capable of distinguishing meaningful overlapping network structure from statistical noise at different scales of interest. Here we derive a family of graph mutual information measures that satisfy these criteria and are constructed using only fundamental information theoretic principles. Our measures capture the information shared among networks according to different encodings of their structural information, with our mesoscale mutual information measure allowing for network comparison under any specified network coarse-graining. We test our measures in a range of applications on real and synthetic network data, finding that they effectively highlight intuitive aspects of network similarity across scales in a variety of systems.

Research on charging scheduling optimization of pure electric buses considering peak-valley time-of-use electricity prices and battery loss costs

In recent years, with the accelerated progress of pure electric buses in my country, the charging scheduling and operation plan of pure electric buses urgently needs to be rationalized and scientific. This study takes the charging scheduling operation in the daily operation of pure electric buses as the starting point, and effectively describes the battery loss cost function by analyzing the optimal fluctuation range of the state of charge of the power battery of pure electric buses. Combined with the analysis of the characteristics of peak and valley time-of-use electricity prices during the charging period, the problem is refined into a pure electric bus charging scheduling decision with controllable operation completion, and the parallel machine scheduling theory is used to characterize and solve the mathematical optimization model, with the aim of minimizing the operating cost of bus companies. At the same time, an immune optimization algorithm based on random key encoding and a greedy algorithm based on the idea of avoiding peaks and filling valleys are developed to solve large-scale problems. In addition, the effectiveness of the algorithm and the applicability of the method are verified through the real bus network in Shanghai.

PLC Honeypots: Enhancing Interaction-Level Assessment

The motivation for this work arose when noticing that definitions of honeypots’ interaction level are mainly based on the information technology environment and do not reflect operational technology even if several honeypot projects approach this field. Within operational technology, programmable logic controllers (PLCs) have a main role, resulting in several honeypot researchers choosing to mimic this device at a certain interaction level. However, searching for an interaction level definition that approaches PLCs results in few studies. In this context, this work aims to explore how to adapt the information technology definition of the interaction level in order to encompass PLCs and their specific features. The method chosen to obtain inputs was a literature review where, in attempting to keep the connection with information technology, the features were based in terms of honey system, honey service, and honey token. The findings of this review provide a means to translate these terms when developing a PLC honeypot for a desired interaction level, resulting in a metrics proposal for low and high interaction. Summarizing the proposed metrics, the system of a PLC can be considered as the vendor specific firmware, its unique device banner, and a realistic network topology. For services, a PLC honeypot reflects the tasks performed by the real device, thus resulting in industrial communication protocols, network management protocols, appropriate response times, code-related interactions, dynamic input and output data processing, physical process simulation, and web interface. Lastly, a PLC honey token can be approached with the PLC program file, MIB file, and software license, among other elements. Based on these metrics, researchers can better evaluate how to design a programmable logic controller honeypot or select tools that match their target interaction level.

Exploring the feasibility of high-capacity vehicle strategy on ridesharing service from the perspective of economic, social, and environmental sustainability

The emergence of ridesharing services is poised to significantly reshape the urban sustainability paradigm. With ever-growing demand, the adoption of high-capacity vehicles in shared mobility is becoming increasingly feasible. In this study, we present a high-capacity vehicle strategy to improve the economic, social, and environmental sustainability of the ridesharing system. To optimize the initial solution, deep reinforcement learning (DRL) is introduced into the framework of the NSGA-II algorithm. Based on the priority order, we apply lexicographic optimization to achieve the final solution. Ultimately, a case study is investigated to simulate the system performance on a realistic network of Chicago area. The results suggest that the high-capacity strategy with an incentive mechanism can substantially benefit all the stakeholders. Per-vehicle profit has drastically promoted from $82.50 to $95.00, meanwhile regret utility and carbon emissions decline to some extent. The best incentive discount for the high-capacity vehicle strategy is approximately 0.2. Overall, this study is significantly conducive to providing a new strategy to promote economic-social-environmental sustainability.