Network System Research Articles

Research on the Emergence and Development Trend of Software Defined Networks

With the rise and development of computer networks, more and more network architecture systems have emerged, and software defined networks have also emerged. As a new type of network architecture system, it is used to achieve flexible control of network traffic and make the network a resource that can be flexibly allocated according to its own needs. For traditional networks, the architecture of traditional networks will encounter many problems, and the traditional network structure system is complex in hierarchy and has a large number of business volumes, making it difficult to cope with the development of future network systems and solve the problems of future network architecture. This article mainly introduces the emergence and development trends of software defined networks, as well as the help that software defined networks can bring to future network systems.

Federated Learning of XAI Models in Healthcare: A Case Study on Parkinson’s Disease

Artificial intelligence (AI) systems are increasingly used in healthcare applications, although some challenges have not been completely overcome to make them fully trustworthy and compliant with modern regulations and societal needs. First of all, sensitive health data, essential to train AI systems, are typically stored and managed in several separate medical centers and cannot be shared due to privacy constraints, thus hindering the use of all available information in learning models. Further, transparency and explainability of such systems are becoming increasingly urgent, especially at a time when “opaque” or “black-box” models are commonly used. Recently, technological and algorithmic solutions to these challenges have been investigated: on the one hand, federated learning (FL) has been proposed as a paradigm for collaborative model training among multiple parties without any disclosure of private raw data; on the other hand, research on eXplainable AI (XAI) aims to enhance the explainability of AI systems, either through interpretable by-design approaches or post-hoc explanation techniques. In this paper, we focus on a healthcare case study, namely predicting the progression of Parkinson’s disease, and assume that raw data originate from different medical centers and data collection for centralized training is precluded due to privacy limitations. We aim to investigate how FL of XAI models can allow achieving a good level of accuracy and trustworthiness. Cognitive and biologically inspired approaches are adopted in our analysis: FL of an interpretable by-design fuzzy rule-based system and FL of a neural network explained using a federated version of the SHAP post-hoc explanation technique. We analyze accuracy, interpretability, and explainability of the two approaches, also varying the degree of heterogeneity across several data distribution scenarios. Although the neural network is generally more accurate, the results show that the fuzzy rule-based system achieves competitive performance in the federated setting and presents desirable properties in terms of interpretability and transparency.

Predefined-time synchronization of time-varying delay fractional-order Cohen–Grossberg neural network based on memristor

This paper delves into the synchronization dynamics of fractional-order memristor Cohen–Grossberg neural network systems with time-varying delays at predefined times (PTS-MFCGNNs). Firstly, leveraging the concept of predefined-time stability, we devise a fractional-order controller, establish sufficient conditions for predefined-time synchronization, and achieve synchronization within the Cohen–Grossberg drive–response system. Secondly, building upon these findings, we scrutinize the synchronization dynamics within the time domain of the PTS-MFCGNNs system. Finally, we validate our theoretical framework through numerical simulations and engage in a comprehensive discussion on predefined-time synchronization within the PTS-MFCGNNs system.

Distributed nonlinear fusion filtering for multi-sensor networked systems with random varying parameter matrix and missing measurements

This paper is concerned with the distributed fusion filtering algorithm design problem for multi-sensor nonlinear networked systems (MSNNSs) subject to multiplicative noises, random varying parameter matrix and missing measurements (MMs). In particular, we utilize the Bernoulli random variable with certain statistical features to describe and characterize the MMs phenomenon. By introduce a fictitious noise, the effects from process noise as well as random varying parameter matrix are addressed and a new nonlinear stochastic networked system is obtained. The primary purpose of this paper is to develop a novel fusion filtering scheme of the distributed way and provide the corresponding boundedness evaluation criterion. Firstly, specific upper bounds of filtering error covariance (FEC) are identified and locally minimized at each sampling instant. Subsequently, based on the obtained local filters, a distributed fusion filtering algorithm is designed via adopting the inverse covariance intersection (ICI) fusion idea. Furthermore, the analysis with respect to the upper bound of local FEC is discussed and examined by proposing a sufficient condition under certain constraints regarding the related parameters. Eventually, with the help of the simulation experiments, the usefulness of the proposed fusion filtering algorithm is illustrated.

Event‐triggered tracking control for networked control systems under diversified attacks

AbstractThis paper mainly concerns on the tracking control problem for event‐triggered networked control systems (NCSs) with diversified cyber‐attacks. An event‐triggered mechanism (ETM) is exploited to decrease the amount of redundant transmissions, thus saving communication resources. In addition, a novel tracking error model for NCSs is built with consideration of ETM and diversified cyber‐attacks, which involves deception attacks and Denial‐of‐Service (DoS) attacks. On the basis of Lyapunov stability theory and linear matrix inequalities (LMIs), the stability criterion of the tracking error system is constructed, and the controller is designed to ensure the tracking performance of the system. In the end, simulation examples are provided to testify the validity of the proposed method.

A model of cement grout flow in a fracture network system

Understanding the mechanism of cement grout flow in fractured rocks is essential for controlling seepage in the construction of hydraulic projects. However, simulating grouting in fractured rocks is complex due to random fracture distribution and non-Newtonian grout flow. This study proposes a numerical model for simulating cement grout flow, considering the hydro-mechanical coupled process in a three-dimensional fracture network system based on the unified pipe-network method. A pipe-network equivalence method is used to derive equivalent pipes for the process of grouting displacement, and the flow field can be solved in unified pipe networks. The hydro-mechanical coupled process is achieved by incorporating an analytical solution for the stress distribution of the center borehole model on an infinitely large plane and a constitutive model for the estimation of the fracture aperture. The time-varying property of the cement grout flow is also considered in the simulation of grouting. The reliability of the numerical model is verified by comparing with analytical solutions for grout flow in a water-saturated fracture. Grouting experiments in fracture networks are also performed to demonstrate the applicability of the proposed method. The influence of various factors on the propagation of cement grout is further investigated in three-dimensional fracture network models.

Probing the timing of the onset of the modern-style plate tectonic regime in Earth's history

Following the Earth's formation about 4.6 Ga, its initial basaltic outer layer underwent differentiation, generating the oldest continental crust. However, how and when this differentiation took place and what processes led to the formation of early silicic continental crust are controversial topics, which are rooted in a bigger question of when modern-style plate tectonics started operating in Earth's history. In general, there is a well-accepted consensus that the Earth transitioned from single lid (squishy, stagnant, and/or sluggish lid?) to plate tectonics at some point, largely as a result of the establishment of the first subduction zone(s). Members of the geoscience community are divided in answering the question of the timing of the onset of plate tectonics, as reflected in the four perspective papers by different international research teams here. Using different proxies and datasets, the proposed models range from the Late Archean to Paleoproterozoic, and Neoproterozoic for the beginning of a plate tectonic convective regime. Another interpretation states that we do not know when plate tectonics might have started based on the extant observations and data. Although the beginning of plate tectonics is still a subject of debate, most researchers agree on the definition of plate tectonics as a globally networked system of laterally moving rigid plates riding on the aesthenosphere and mantle convection cells, which facilitated recycling of the top boundary layer through time. Testing the proposed models and concepts in these perspective papers with new data, observations and geodynamic modelling efforts will be critical to better understanding the Earth's thermal history and evolution since 4.4 Ga.

Training Artificial Neural Network with a Cultural Algorithm

Artificial neural networks are amongst the artificial intelligence techniques with their ability to provide machines with some functionalities such as decision making, comparison, and forecasting. They are known for having the capability of forecasting issues in real-world problems. Their acquired knowledge is stored in the interconnection strengths or weights of neurons through an optimization system known as learning. Several limitations have been identified with commonly used gradient-based optimization algorithms, including the risk of premature convergence, the sensitivity of initial parameters and positions, and the potential for getting trapped in local optima. Various meta-heuristics are proposed in the literature as alternative training algorithms to mitigate these limitations. Therefore, the primary aim of this study is to combine a feed-forward artificial neural network (ANN) with a cultural algorithm (CA) as a meta-heuristic, aiming to establish an efficient and dependable training system in comparison to existing methods. The proposed artificial neural network system (ANN-CA) evaluated its performance on classification tasks over nine benchmark datasets: Iris, Pima Indians Diabetes, Thyroid Disease, Breast Cancer Wisconsin, Credit Approval, Glass Identification, SPECT Heart, Wine and Balloon. The overall experimental results indicate that the proposed method outperforms other methods included in the comparative analysis by approximately 12% in terms of classification error and approximately 7% in terms of accuracy.

Softwarized and containerized microservices-based network management analysis with MSN

Microservice architecture is a service-oriented paradigm that enables the decomposition of cumbersome monolithic-based software systems. Using microservice design principles, it is possible to develop flexible, scalable, reusable, and loosely coupled software that could be containerized and deployed in a distributed edge/cloud environment. The flexible deployment of microservices in an edge environment increases system performance in terms due to dynamic service function placement and chaining possibly resulting in latency reduction, fault tolerance, scalability, efficient resource utilization, cost reduction, and energy consumption reduction. On the other hand, virtualization and containerization of microservices add processing and communication overheads. Therefore, to evaluate end-to-end microservices-based system performance, we need to have an end-to-end mathematical formulation of the overall microservice-based network system. Incorporating the virtualization overhead, here we provide end-to-end mathematical formulation considering system parameters: latency, throughput, computational resource usage, and energy consumption. We then evaluate the formulation in a testbed environment with the Microservice-based SDN (MSN) framework that decomposes the Software-defined Networking (SDN) controller in microservices with Docker Container. The final result validates the presented mathematical modeling of the system’s dynamic behavior which can be used to design a microservice-based system.

Reliability–flexibility integrated optimal sizing of second‐life battery energy storage systems in distribution networks

AbstractSecond‐life batteries (SLBs), which are batteries retired from electric vehicles (EVs), can be used as energy storage systems to enhance the performance of distribution networks. Two issues should be addressed particularly for the optimal sizing of SLBs. Compared with fresh batteries, the failure rate of SLBs is relatively high, and timely and preventive replacement is needed. In addition, the flexibility introduced by EVs and installed SLBs should be coordinated to achieve optimal economic benefits. This paper focuses on the efficient utilization of SLBs by highlighting reliability‐flexibility concerns in optimal sizing. The model is formulated as a bi‐level model. On the upper‐level, considering the operational reliability constraints of SLBs, decisions regarding the investment and replacement of SLBs are optimized. Distribution network operations are improved on the lowerlevel, with an effective spatiotemporal flexible dispatch strategy for EVs. Finally, a linearized process for the optimal sizing of SLBs is presented and efficiently implemented. The Sioux Falls network and IEEE 69‐node distribution network are coupled as the test system. According to the simulation results, when the state of health of the SLBs decreased to 70%, the conditions were unreliable. The differences in the optimal SLB size and costs considering reliability and flexibility are highlighted.

FedAvg-P: Performance-Based Hierarchical Federated Learning-Based Anomaly Detection System Aggregation Strategy for Advanced Metering Infrastructure.

Advanced metering infrastructures (AMIs) aim to enhance the efficiency, reliability, and stability of electrical systems while offering advanced functionality. However, an AMI collects copious volumes of data and information, making the entire system sensitive and vulnerable to malicious attacks that may cause substantial damage, such as a deficit in national security, a disturbance of public order, or significant economic harm. As a result, it is critical to guarantee a steady and dependable supply of information and electricity. Furthermore, storing massive quantities of data in one central entity leads to compromised data privacy. As such, it is imperative to engineer decentralized, federated learning (FL) solutions. In this context, the performance of participating clients has a significant impact on global performance. Moreover, FL models have the potential for a Single Point of Failure (SPoF). These limitations contribute to system failure and performance degradation. This work aims to develop a performance-based hierarchical federated learning (HFL) anomaly detection system for an AMI through (1) developing a deep learning model that detects attacks against this critical infrastructure; (2) developing a novel aggregation strategy, FedAvg-P, to enhance global performance; and (3) proposing a peer-to-peer architecture guarding against a SPoF. The proposed system was employed in experiments on the CIC-IDS2017 dataset. The experimental results demonstrate that the proposed system can be used to develop a reliable anomaly detection system for AMI networks.

Network anomaly detection and security defense technology based on machine learning: A review

Robust solutions are essential for protecting complex network systems in the constantly changing cybersecurity scenario. This investigation examines the role of machine learning (ML) in improving the safety of digital infrastructure by examining network anomaly detection and security defense. We evaluate the effectiveness of key ML techniques, including deep learning (DL), ensemble methods, and supervised and unsupervised learning, in recognizing abnormalities and reducing dangers. Real-time monitoring and adaptive reactions are emphasized in the analysis of ML-based systems integration into comprehensive security frameworks. This section also addresses challenges like interpretability, harmful assaults, and model resilience. Real-world case examples emphasize the importance of ML in the advancement of network security. The paper continues with a discussion of ML's future role in the optimization of security measures and the mitigation of emergent threats.

A bio-based soy wood adhesive modified by dual-crosslinking strategy with excellent mechanical strength and water-resistance

Soy-based adhesives have garnered significant attention owing to their distinctive environmentally sustainable characteristics and low cost. However, they exhibit inadequate bonding strength and water-resistance, which can be attributed to the presence of polar groups in soy flours. Herein, a simple and eco-friendly dual-crosslinking strategy was proposed to manufacture a soy-based adhesive (SF/IO4/CA adhesive) with excellent mechanical properties and good water-resistance. Specifically, soy flours were treated with sodium periodate (NaIO4) for oxidization, which facilitated the soy flours' self-crosslinking process by converting carbohydrates into components having the cross-linking action (internal cross-linking agents). Then, incorporating the citric acid (CA) would promote to the carboxyl groups (-COOH) of CA to react with the hydrophilic hydroxyl groups (-OH) present in soy flours by esterification reaction. The findings demonstrated that a high-performance plywood using SF/IO4/CA adhesive was successfully produced, which shear strength of cold-water (20 °C for 24 h), hot-water (63 °C for 3 h), and boiling-water (93 °C for 3 h) reached 1.69 MPa, 1.68 MPa, 1.72 MPa, and 1.47 MPa, respectively. The soy-based adhesive has excellent mechanical strength and water-resistance due to its dual-crosslinking network system, which has significant promise for application use in the wood-based panels industry.

Land price dynamics in response to high-speed rail network characteristics: An empirical analysis

High-speed railway (HSR) has become the backbone of China's rapid and comprehensive urban transportation network system. However, the impact of the network characteristics of HSR on urban land prices has not been studied in sufficient detail. To fill this gap, this study focuses on both the Yangtze River Delta urban agglomeration and the Beijing-Tianjin-Hebei urban agglomeration and explores the linkage relationship between the HSR network and urban land prices. For this analysis, social network analysis and fixed effects model are used. The results show that the overall HSR network density of these two urban agglomerations still has room for improvement. Affected by regional proximity and the direction of HSR lines, HSR presents a spatial pattern of a multi-center–multi-tier network. The “siphon effect” is the main effect of the HSR network characteristics on land prices. However, the weakening degree of spatial spillover effect on siphon effect of the HSR network in the Yangtze River Delta urban agglomeration is stronger than that in the Beijing-Tianjin-Hebei urban agglomeration. Local governments should fully utilize the spatial effects of HSR and enhance the level of coordinated development among urban agglomerations.

Guest editorial: Resilient fuzzy control synthesis of non‐linear networked systems against various cyber‐attacks

Guest editorial: Resilient fuzzy control synthesis of non‐linear networked systems against various cyber‐attacks

Distribution network line loss analysis method based on improved clustering algorithm and isolated forest algorithm

The long-term loss of distribution network in the process of distribution network development is caused by the backward management mode of distribution network. The traditional analysis and calculation methods of distribution network loss can not adapt to the current development environment of distribution network. To improve the accuracy of filling missing values in power load data, particle swarm optimization algorithm is proposed to optimize the clustering center of the clustering algorithm. Furthermore, the original isolated forest anomaly recognition algorithm can be used to detect outliers in the load data, and the coefficient of variation of the load data is used to improve the recognition accuracy of the algorithm. Finally, this paper introduces a breadth-first-based method for calculating line loss in the context of big data. An example is provided using the distribution network system of Yuxi City in Yunnan Province, and a simulation experiment is carried out. And the findings revealed that the error of the enhanced fuzzy C-mean clustering algorithm was on average − 6.35, with a standard deviation of 4.015 in the situation of partially missing data. The area under the characteristic curve of the improved isolated forest algorithm subjects in the case of the abnormal sample fuzzy situation was 0.8586, with the smallest decrease, based on the coefficient of variation, and through the refinement of the analysis, it was discovered that the feeder line loss rate is 7.62%. It is confirmed that the suggested technique can carry out distribution network line loss analysis fast and accurately and can serve as a guide for managing distribution network line loss.

Transfer learning-based nonstationary traffic flow prediction using AdaRNN and DCORAL

Traffic flow prediction is an integral part of an intelligent transportation system (ITS) for proactive transportation planning and management in public transit network systems. However, due to the influence of passengers’ travel modes and the difficulty of data collection, some traffic flow datasets are not only nonstationary in temporal distribution but also insufficient in data size, leading to inaccurate prediction results. Therefore, a transfer learning-based method is proposed to predict nonstationary traffic flow with inadequate data in the public transit system. In the proposed model, a novel approach named AdaRNN-DCORAL is presented to achieve accurate traffic flow prediction in the temporal dimension. Specifically, AdaRNN is an adaptive prediction network for nonstationary traffic flow data, while DCORAL performs domain adaptation between the source and target domain in the public transit system. First, two domains of traffic flow datasets in two public transit modes are established, which are the target domain with insufficient data and the source domain with sufficient data. Subsequently, the traffic flow datasets are divided into weekday and holiday time series based on their distribution characteristics. On this basis, AdaRNN-DCORAL is trained on the constructed datasets, thus achieving the precise nonstationary prediction of data scarcity in the target domain. Finally, the experiments demonstrate the improved performance of the proposed method over that of state-of-the-art models in terms of prediction accuracy and computation time.

AI-driven transcriptomic encoders: From explainable models to accurate, sample-independent cancer diagnostics

In the rapidly evolving domain of medical technology, the utilization of sophisticated algorithms for deciphering transcriptional data has emerged as a critical aspect, especially in the oncology sector. These algorithms, drawing upon methodologies from fields such as natural language processing and advanced image analysis, can significantly enhance the accuracy in predicting cancer-related molecular states. Notably, Transformer models, renowned for their proficiency in handling extensive datasets, are now being adapted for breakthroughs in medical diagnostics or in stratifying patients according to prognostic levels. Our study contributes to the field of precision medicine by integrating Transformer-based learning, exemplified by the Geneformer model, with explainable AI techniques. These techniques are employed to find out the input variables (genes resulting from genomic transcription) most correlated with the decisions of neural network systems. This insight, a key goal in genomic research, aims to select the most relevant gene subset for each specific task in which a neural network is employed. This selection approach has proven to be effective in two classification tasks: cell type classification and breast cancer type classification. Such effectiveness has been demonstrated even across various cohorts of patients. When applying Geneformer-like architecture analyses solely to the selected gene subsets, the outcomes either maintain their accuracy or significantly improve. This approach, aims not only to contribute to the identification of vital genetic markers in cancer genomics, but also to exemplify the adaptability of AI models to different datasets, marking a significant step towards the development of accurate and universally applicable diagnostic tools for precision medicine.

Asynchronous encoder-based event-triggered control of nonlinear networked control system under DoS attacks

This paper discusses the stability of a nonlinear networked control system with limited channels under denial-of-service (DoS) attacks. The transmitted signals in both plant-to-controller and controller-to-plant channels are asynchronous, and each channel is under the threat of DoS attacks. To overcome the negative effects raised by imperfect channels and DoS attacks, the relationship among encoder structure, DoS attacks and triggering characteristics is thoroughly analyzed and the asynchronous encoder-based event-triggered control mechanisms are novelly proposed. Moreover, both encoding and decoding schemes are designed to ensure the transmission efficiency. Furthermore, the QSR-dissipativity, finite-gain L2 stability and input-feedforward output-feedback passivity of the nonlinear system are analyzed. Finally, experiments are conducted to illustrate the validity and superiority of the proposed scheme.

Investigation of a model predictive control (MPC) strategy for seasonal thermochemical energy storage systems in district heating networks

This research investigates the integration of model predictive control (MPC) with seasonal thermochemical energy storage systems (STES) within district heating networks, focusing on the Nottingham district heating as a case study. The primary aim is to develop an MPC strategy that utilizes machine learning models for accurate heat load forecasting. This strategy optimizes the charging and discharging cycles of thermochemical energy storage systems to mitigate the mismatch between heating energy supply and demand by storing surplus heat during summer and utilizing it during winter. We employed and validated machine learning models, including support vector regression (SVR), regression trees, and long short-term memory (LSTM) networks, using historical heat load and meteorological data. A validated numerical model of the thermochemical energy storage system (TCES) was integrated into the MPC framework, formulated as a mixed-integer linear program to optimize the STES's operations. The performance of the MPC strategy was benchmarked against a rule-based control approach under varying supply capacities to evaluate scalability and robustness. Our findings reveal that each machine learning model achieved comparable performance, with CVRMSE values within the 9–11% range. The LSTM model, in particular, provided accurate multi-step forecasts essential for the MPC framework. Incorporating these models into the MPC strategy allowed for precise heat demand predictions, enhancing the management of energy storage and distribution. Results confirmed that MPC effectively shifts energy seasonally, reduces reliance on auxiliary heating during winter, and minimizes waste heat. The MPC strategy outperformed the rule-based control by storing a significantly higher percentage of waste heat and meeting a greater portion of the additional heat demand that was not covered by the auxiliary heat supply. The system demonstrated effective performance under varying supply capacities, with the MPC strategy efficiently utilizing stored heat to meet demand at 80% supply capacity, achieving a waste heat reduction to 4% and meeting most of the heat demand. However, performance declined at 60% capacity, indicating the need for careful consideration of supply capacities in system design. This study highlights the potential of integrating machine learning models with MPC to enhance the performance and adaptability of district heating systems with STES, minimizing waste heat and efficiently meeting energy demands.