Network Infrastructure Research Articles

Hybrid Intelligent Anomaly Detection System Using Attention based Deep Learning Approach for Cyber Attacks Prevention

Objectives: Network Intrusion Detection System (NIDS) plays an important role in finding and preventing cyber-attacks, which helps to improve the entire security posture of an organization’s network infrastructure. The development of Deep Learning (DL) techniques possess the ability of IDS to detect attacks without delay and protects from intrusions even in real-time environment. Methods: The present study proposes an improved IDS framework called Enhanced Gated Recurrent Unit Hyper-Model combined Attention Bidirectional Long-Short Term Memory (EGHAB) approach, to effectively address the detection of attacks with maximum accuracy and minimal error rate. The proposed model is enhanced by using methods like numericalization and normalisation for pre-processing the input data, Genetic Algorithm (GA) for extracting intricate features from the input data, and the EGHAB classifier, which works on the principles of both Gated Recurrent Unit (GRU) and Bidirectional Long-Short Term Memory (BiLSTM) models along with attention mechanism. Findings: The EGHAB model efficiently learns the abnormal behaviour of network and classified the attack and non-attack data using the publicly available NSL-KDD dataset and a generated real time data set, scapy. And it achieved 99.94% accuracy over NSL KDD dataset during multiclass classification and 93.3% on real time data set with reduced Error rate. Additionally, to examine the efficacy, the proposed approach is compared with other existing methods and proved its improved performance. Novelty: A combined ensemble classifier with GRU, BiLSTM and attention mechanism is designed to predict the attacks in earlier stage rather than due over. The model achieved better accuracy and reduced false assumption using anomaly prediction mechanism. Keywords: Cyber Attack, Anomaly Detection, Deep learning, Gated Recurrent Unit, Bi­ Directional Long­-Short Term Memory, Attention mechanism

Critical needs to close monitoring gaps in pan-tropical wetland CH4 emissions

Abstract Global wetlands are the largest and most uncertain natural source of atmospheric methane (CH4). The FLUXNET-CH4 synthesis initiative has established a global network of flux tower infrastructure, offering valuable data products and fostering a dedicated community for the measurement and analysis of methane flux data. Existing studies using the FLUXNET-CH4 Community Product v1.0 have provided invaluable insights into the drivers of ecosystem-to-regional spatial patterns and daily-to-decadal temporal dynamics in temperate, boreal, and Arctic climate regions. However, as the wetland CH4 monitoring network grows, there is a critical knowledge gap about where new monitoring infrastructure ought to be located to improve understanding of the global wetland CH4 budget. Here we address this gap with a spatial representativeness analysis at existing and hypothetical observation sites, using 16 process-based wetland biogeochemistry models and machine learning. We find that, in addition to eddy covariance monitoring sites, existing chamber sites are important complements, especially over high latitudes and the tropics. Furthermore, expanding the current monitoring network for wetland CH4 emissions should prioritize, first, tropical and second, sub-tropical semi-arid wetland regions. Considering those new hypothetical wetland sites from tropical and semi-arid climate zones could significantly improve global estimates of wetland CH4 emissions and reduce bias by 79% (from 76 to 16 TgCH4 y−1), compared with using solely existing monitoring networks. Our study thus demonstrates an approach for long-term strategic expansion of flux observations.

Research on energy saving effect of spatial correlation network of digital infrastructure: based on the analysis of network centrality.

Accurately portraying the spatially linked network characteristics of digital infrastructure and exploring its energy-saving effects are highly valuable for enhancing the synergy in digital infrastructure development and expanding its network spillover effects on energy conservation. This paper uses panel data at the city level in China and employs a modified gravity model to calculate the centrality of digital infrastructure spatial correlation network nodes. Based on this, an econometric model is constructed, incorporating variables such as digital infrastructure spatial correlation network node centrality and urban green total factor energy efficiency. The model is used to analyze the effects and transmission paths of digital infrastructure network node centrality on urban green total factor energy efficiency. The analysis yields the following conclusions: (1) Digital infrastructure spatial correlation network node centrality significantly improves urban green total factor energy efficiency, with considerable variability due to city geographic location, city scale, and city attributes. (2) Nonlinear testing results indicate that as digital infrastructure construction advances, its impact on urban green total factor energy efficiency shifts from inhibitory to promotional. (3) The impact mechanism shows that digital infrastructure node centrality enhances urban green total factor energy efficiency through green technology innovation. Additionally, it promotes advanced industrial structures and reduces capital mismatch, further influencing energy efficiency. (4) Digital infrastructure node centrality not only boosts urban green total factor energy efficiency but also facilitates regional convergence, increasing the convergence rate from 0.094 to 0.170%. The findings of the research offer policy guidance for the government on advancing digital transformation initiatives and enhancing energy efficiency.

DELM: Deep Ensemble Learning Model for Anomaly Detection in Malicious Network Traffic-based Adaptive Feature Aggregation and Network Optimization

With the rapid advancements in internet technology, the complexity and sophistication of network traffic attacks are increasing, making it challenging for traditional anomaly detection systems to analyze and detect malicious network attacks. The increasing advancedness of cyber threats calls for innovative approaches to identify malicious patterns within network traffic precisely. The primary issue lies in the fact that these approaches do not focus on the essential adaptive features of network traffic. We proposed an effective anomaly detection system for malicious network traffic attacks called the Deep Ensemble Learning Model (DELM). We leverage the structure of the Feedforward Deep Neural Network (FDNN), and Deep Belief Network (DBN), incorporating multiple hidden layers with non-linear activation functions. Integrating Adaptive Feature Aggregation (AFA) with the FDNN algorithm dynamically adjusts the feature aggregation process based on incoming traffic characteristics to improve adaptability. The Conditional Generative Network was employed to enhance DELM for generating data for minority classes. To improve the model’s accuracy, we applied batch normalization and data augmentation techniques for preprocessing, utilized n-gram, one-hot encoding, and feature aggregation methods for effective feature extraction. This study significantly contributes to network security by enhancing systems for detecting malicious network traffic. With its interpretability and adaptability, our proposed model shows promise in addressing the evolving cyber threat and fortifying critical network infrastructure. The experimental results demonstrate that our model performs with higher stability than the existing state-of-the-art detection approaches, as reflected by its higher accuracy, precision, recall, F1-score, and AUC-ROC.

A Crucible of IoT Applications and Services and the Gambia Revenue Generation

The study investigated the relationship between Internet of Things (IoT) applications and services and The Gambia revenue generation, tax evasion and tax compliance respectively. It identified the challenges impeding the adoption and implementation of IoT applications and services in the revenue generation processes by the Gambia Revenue Authority (GRA). Both primary and secondary data were used in the study. Questionnaire and interview were used to generate the primary data. The study population (2188) comprised senior and mid-tier management personnel from the Ministry of Finance and Economic Affairs (MoFEA), staff members of The Gambia Revenue Authority, and the corporate taxpayers. The sampling approach used in this study was multistage. Personnel from the MoFEA and GRA were purposively selected, while corporate taxpayers were randomly selected. Their populations were then divided into various strata to ensure fair representation. Respondents were randomly picked from each stratum. To ensure an appropriate sample size, 327 individuals were selected. Data obtained were analysed using multiple regression, correlation coefficient, and simple regression analysis. Qualitative analyses were done on the interview responses. The study revealed that connectivity, networking, and data collection improve revenue generation, while increased IoT adoption and higher data utilisation and infrastructure investment reduce tax evasion and boost tax compliance. However, implementation of the IoT has encountered challenges in the form of technological barriers, financial constraints, and skill gaps. In view of these, investment must be made in enhancing connectivity and networking infrastructure, training staff in data analytics and cyber-security to optimise IoT data usage and boost IoT adoption through inducements and awareness programs. The study concluded that IOT applications and services are in the right direction to revolutionise The Gambia revenue generation.

PenGym: Realistic training environment for reinforcement learning pentesting agents

Penetration testing, or pentesting, refers to assessing network system security by trying to identify and exploit any existing vulnerabilities. Reinforcement Learning (RL) has recently become an effective method for creating autonomous pentesting agents. However, RL agents are typically trained in a simulated network environment. This can be challenging when deploying them in a real network infrastructure due to the lack of realism of the simulation-trained agents.In this paper, we present PenGym, a framework for training pentesting RL agents in realistic network environments. The most significant features of PenGym are its support for real pentesting actions, full automation of the network environment creation, and good execution performance. The results of our experiments demonstrated the advantages and effectiveness of using PenGym as a realistic training environment in comparison with a simulation approach (NASim). For the largest scenario, agents trained in the original NASim environment behaved poorly when tested in a real environment, having a high failure rate. In contrast, agents trained in PenGym successfully reached the pentesting goal in all our trials. Even after fixing logical modeling issues in simulation to create the revised version NASim(rev.), experiment results with the largest scenario indicated that agents trained in PenGym slightly outperformed, and were more stable, than those trained in NASim(rev.). Thus, the average number of steps required to reach the pentesting goal was 1.4 to 8 steps better for PenGym. Consequently, PenGym provides a reliable and realistic training environment for pentesting RL agents, eliminating the need to model agent actions via simulation.

Standardization Trends and Military Communication Applications of Core Technologies of 5G NR

5G New Radio(NR) technology, with its focus on high speed, low latency, and connectivity, introduces crucial advancements like MIMO for enhanced reliability and transmission rates, edge computing for reduced latency, and IAB for extended coverage. However, military communication networks face challenges such as limited capacity, unpredictable mobility and communication dead zones. This paper delves into the trends of the above 5G NR technologies outlined by the 3GPP standard, exploring their potential applications within military infrastructure networks. Our aim is to underscore the benefits of harnessing these technologies in military settings. Additionally, through simulation, we forecast the advantages associated with integrating these core 5G NR technologies, thereby paving the way for enhanced military communication capabilities.

Low Network Power Challenges in IoT-Based Applications in Smart Cities

The emergence of Internet of Things (IoT) technologies has led to the development of smart cities, potentially improving urban life through efficient and effective use of resources. The success of IoT-based applications in smart cities is contingent on several factors, including network power challenges. Deploying IoT-based applications in smart cities requires a reliable and efficient network infrastructure to ensure smooth and uninterrupted data communication. One of the significant challenges faced in this regard is low network power, which can significantly impact the performance of IoT devices and, consequently, the entire smart city system. This article addresses the issue of low network power in IoT-based applications in smart cities. It investigates the causes of this problem and the potential solutions that can be adopted to mitigate its impact. The article also highlights the importance of network power management in the context of IoT-based applications in smart cities. By implementing effective network power management techniques, it is possible to optimize the performance of IoT devices and extend their battery life, thus ensuring the overall efficiency and sustainability of the smart city system. The article concludes by emphasizing the need for continuous research and development to overcome the challenges of low network power and further enhance IoT technology's capabilities in smart cities.

Photo-voltaic system with battery employing parallel converters operation for charging stations and distributed loads amidst anomalous grid

In this work, solar photovoltaic array-based generation unit is connected to non-ideal distribution network and powering plug-in electric vehicle (PEV) charging infrastructure and other local loads connected to AC common bus while ensuring reliable operation of parallel connected voltage source converters under dynamics. A photovoltaic array connected via voltage source inverter, which feeds power to loads and battery is used to act as power management entity and provides reactive power and harmonic power support via converter. In context of widespread incorporation of PEVs and renewable energy sources (RES) into grid, inherent intermittency and dynamic behavior pose significant challenges in establishing a resilient and flexible control framework. Consequently, a solution is proposed that employs dual low pass filter integrated along an adaptive noise elimination filtering algorithm, serving as a primary processing stage. Additionally, integrator-based frequency locked loop control strategy is implemented in conjunction to mitigate power quality concerns, regulate voltage levels, and correct power factor discrepancies. Furthermore, system ensures continuous operation, providing uninterrupted power to local loads even during fluctuating conditions while simultaneously functioning as a seamless PEV charging station. Additionally, a comparative analysis of controller performance is summarized in a tabular format, alongside a power quality assessment. The analysis includes the evaluation of total harmonic distortion (THD) for both grid currents and grid voltages, which are measured at 2.36 % and 3.60 %, respectively. These values are well within the limits established by IEEE 519 standard, demonstrating compliance with the required power quality criteria. This RES based charging structure topology is tested using a hardware prototype under dynamics and impactful performance is observed through obtained results.

Assessing Africa’s position in the development of AI-enabled ECG devices

Background The integration of Artificial Intelligence (AI) in electrocardiographic (ECG) devices has become a pivotal area of research, particularly during the COVID-19 pandemic. These technologies are essential for enhancing cardiac diagnosis and monitoring. Methods This study assesses current trends, key contributors, and collaborative networks in the field of AI-enhanced ECG devices. We utilized a comprehensive analysis, using the Biblioshiny library from Bibliometrix for data exploration of data extracted from the Scopus database and VOSViewer for creating and visualizing maps. These tools were played an important role in conducting an in-depth analysis of the relationships and developments within the field. Results The analysis shows a significant increase in publications related to AI-enhanced ECG devices, with a marked surge during the COVID-19 pandemic. Despite the growing interest and technological advancements, the study exposes a notable disparity in the geographical distribution of research contributions, highlighting substantial under-representation of African researchers. This gap is attributed to infrastructural, financial constraints, and limited collaborative networks within the continent. Conclusion The rapid evolution and increasing importance of AI in ECG devices underscore the need for more inclusive research practices. There is a critical need to integrate and promote contributions from under-represented regions, particularly Africa, to ensure a globally diverse perspective in tackling health challenges. This study calls for enhanced participation and support for African researchers to bridge the existing research gap and foster global health equity.

Optimization of Division and Reconfiguration Locations of the Medium-Voltage Power Grid Based on Forecasting the Level of Load and Generation from Renewable Energy Sources

The article addresses challenges in optimizing the operation of medium voltage networks, emphasizing optimizing network division points and selecting the best network configuration for minimizing power and energy losses. It critically reviews recent research on the issue of network configuration optimization. The optimization of the medium voltage power grid reconfiguration process was carried out using known optimization tools. The novelty lies in the inclusion of a probabilistic approach in the decision-making process in forecasting loads and generation from renewable energy sources (RES). Optimization studies utilizing heuristic optimization methods were completed, and an algorithm was developed for forecasting load and power generated from RES based on historical data and current weather data obtained from weather API. The solution proposed in the article allows multiple applications, including optimizing network division points’ locations (which decreases financial costs of modernizing network infrastructure) as well as improving the reconfiguration process, resulting in lower power losses while maintaining voltage requirements.

Optimal resilience-based restoration plan for disrupted interdependent infrastructure networks under uncertainty

The functioning of vital services in a society depends heavily on the proper and continuous operation of critical infrastructure networks, including water, transportation, power, natural gas, and telecommunication. Such networks are essential for maintaining the economy, security, and overall quality of life. However, since these critical networks are interdependent; hence, they are susceptible to various types of disruptions caused by natural disasters, failures, or malicious activities, leading to varying degrees of performance impacts that could directly affect people's daily lives. Thus, a disruption to one network can quickly spread to others, resulting in significant impacts on daily life. Therefore, restoring such disrupted networks in a timely manner is crucial to ensure a prompt recovery and minimize the impact on daily life. In this work, we consider the problem of restoring a set of interdependent infrastructure networks following a disruptive event. We study two essential factors that can accelerate the recovery process: (i) the restoration facilities location, which are considered as dispatching points for restoration crews, and (ii) the routes of the restoration crews within the interdependent networks. Accordingly, we formulate two optimization models using mixed integer programming. The first model, restoration facility location model, finds the optimal location for restoration facilities within interdependent infrastructure networks considering uncertainty in disruptions. The second model, restoration crew routing model, determine the optimal routes for restoration crews within the interdependent infrastructure networks considering: (i) travelled distance, (ii) restoration time required for disrupted network components, and (iii) different importance of network components. The two optimization models are solved through generated interdependent power and water networks to demonstrate their effectiveness.

Maximum entropy-based modeling of community-level hazard responses for civil infrastructures

Perturbed by natural hazards, community-level infrastructure networks operate like many-body systems, with behaviors emerging from coupling individual component dynamics with group correlations and interactions. It follows that we can borrow methods from statistical physics to study the response of infrastructure systems to natural disasters. This study aims to construct a joint probability distribution model to describe the post-hazard state of infrastructure networks and propose an efficient surrogate model of the joint distribution for large-scale systems. Specifically, we present maximum entropy modeling of the regional impact of natural hazards on civil infrastructures. Provided with the current state of knowledge, the principle of maximum entropy yields the “most unbiased“ joint distribution model for the performances of infrastructures. In the general form, the model can handle multivariate performance states and higher-order correlations. In a particular yet typical scenario of binary performance state variables with knowledge of their mean and pairwise correlation, the joint distribution reduces to the Ising model in statistical physics. In this context, we propose using a dichotomized Gaussian model as an efficient surrogate for the maximum entropy model, facilitating the application to large systems. Using the proposed method, we investigate the seismic collective behavior of a large-scale road network (with 8,694 nodes and 26,964 links) in San Francisco, showcasing the non-trivial collective behaviors of infrastructure systems.

Keamanan siber sebagai fondasi pengembangan aplikasi keuangan mobile: Studi literatur mengenai cybercrime dan mitigasinya

This study examines the importance of cybersecurity in mobile financial applications, particularly in the face of rising cybercrime threats. The aim of this research is to provide deeper insights into the significance of cybersecurity in mobile financial apps and to develop approaches that financial companies can adopt to protect their users' data and information. The research employs a qualitative descriptive method using a systematic literature review (SLR) approach. Meta-synthesis analysis is applied to synthesize data from 26 journal articles published between 2019 and 2024. The findings reveal that cybercrime in the financial and FinTech industries is driven by internal factors such as weak security systems, lack of system updates, limited human resource competencies, and careless user behavior. External factors include malware attacks, unclear regulations, and the use of advanced technology. To counter these, it is necessary to implement technologies such as firewalls and blockchain, strong risk management, enhanced network infrastructure, the establishment of cybersecurity teams, the development of clear regulations, and user education to raise awareness and improve cybersecurity. Therefore, the implementation of a comprehensive cybersecurity strategy is crucial in maintaining the integrity and trust of users in mobile financial applications.

An adaptive multistage intrusion detection and prevention system in software defined networking environment

The advancements made in Software-Defined Networking (SDN) technology seem quite promising, with potential wide application in managing and controlling the latest network infrastructures. SDN technology decouples the control plane from the data plane, enabling effective and flexible network management. However, this dynamic phenomenon brings new security challenges. With the increasing dynamism and programmable nature of networks, conventional security protocols may not sufficient to protect against advanced and sophisticated attacks. Although Intrusion Detection Systems (IDSs) have been extensively applied for identifying and preventing security threats in traditional network environments, IDS models designed specifically for traditional network requirements may not be adequate for SDN environments. These issues may stem from the static nature of conventional networks, contrasting with the dynamicity of advanced SDN networks, and the traditional IDS’s inability to adapt to the dynamic nature of SDN. To address these challenges, the current research proposes a novel Deep Hybrid IDS model to enhance network security in SDN environments and prevent attacks using Scapy. The proposed model detects signature-based attacks by integrating Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM) for real-time simulated datasets, achieving an accuracy of 97.8%, which is comparatively better than existing models.

Mobility–Multihoming Duality

In modern Internet-based communication, especially mobile systems, a mobile node (MN) will commonly have more than one possibility for Internet Protocol (IP) connectivity. For example, an MN such as a smartphone may be associated with an IEEE 802.11 network at a site while also connected to a cellular base station for 5G. In such a scenario, the smartphone might only be able to utilise the IEEE 802.11 network, not making use of the cellular connectivity simultaneously. Currently, IP does not allow applications and devices to easily utilise multiple IP connectivity opportunities—multihoming for the MN—without implementing special mechanisms to manage them. We demonstrate how the use of the Identifier Locator Network Protocol (ILNP), realised as an extension to IPv6, can enable mobility with multihoming using a duality mechanism that treats mobility and multihoming as the same logical concept. We present a network layer solution that does not require any modification to transport protocols, can be implemented using existing application programming interfaces (APIs), and can work for any application. We have evaluated our approach using an implementation in Linux and a testbed. The testbed consisted of commercial equipment to demonstrate that our approach can be used over existing network infrastructure requiring only normal unicast routing for IPv6.

Digital economy and green transformation of regional industries: New insights from sustainability.

Studying the impact of the digital economy on carbon emissions in the distribution industry is of great significance for realizing sustainable development goals and coping with climate change. This study finds that increasing the level of digital economy development can reduce the carbon emission intensity of the circulation industry through fixed-effects modeling. Moreover, the effect is different in different geographic regions, and the improvement of the digital economy development level in the east and central regions can significantly reduce the carbon emission intensity of the distribution industry. The digital economy can simultaneously reduce the carbon emission intensity of the circulation industry by reducing the degree of labor factor mismatch in the circulation industry and improving the regional green innovation capacity. Therefore, in order to promote the green development of the distribution industry, it is also necessary to make efforts to improve the construction of network infrastructure, accelerate the process of research and development and cultivation of green technology, and break down the barriers of cross-regional mobility of talents.

A systemic approach for assessing infrastructure component importance in hazard-prone communities

Investing in pre-event disaster mitigation interventions for physical infrastructure, such as structural retrofits and enhancements, can be costly due to limited resources. To prioritize investments, infrastructure components are ranked by their criticality within the overall system. To be effective in real-world deployment, this approach must account for the complex interactions between components, as failures can occur simultaneously across large geographical areas due to the hazard footprint. As a result, hazard-specific uncertainties and spatial correlations may lead to distinctive failure patterns. In this study, we propose a novel data-driven framework leveraging Monte Carlo simulation, that harnesses the individual realizations to capture and model realistic component damage patterns under a specified hazard scenario. This framework addresses a gap in literature by moving beyond traditional methods that often treat component failures as independent events. By capturing the interdependence between bridges, primarily through failure interactions, and system-wide effects, our method provides a more comprehensive criticality assessment. The simulation data provides a foundation for the framework, which applies to a wide variety of infrastructure networks and performance metrics. To demonstrate the method's effectiveness, a simplified transportation network from Shelby County, TN subjected to an earthquake event is analyzed. The proposed framework provides an effective approach for component ranking, suitable for decision-making where human intuition and simple methods are insufficient. Its broad applicability suggests a potential for large-scale and interdependent network problems.

Urban green streets and water management safety hubs in public schools lots

Abstract Green Stormwater Infrastructure (GSI) represents an effective approach to enhance urban resilience to climate change, contributing to runoff regulation and localized flood risk reduction. This study examines the potential for transforming open spaces in public schools into safety hubs for stormwater management in Mediterranean urban contexts, drawing on best practices from North America. Through a methodological analysis combining Research Through Design and an international literary scoping review, case studies of schools in the Metropolitan City of Naples are presented and compared with U.S. projects implementing GSI in school areas. The results highlight the importance of strategic coordination guidelines for local administrators, designers, and school principals, aimed at planning, designing, and managing highly performant green infrastructure networks. An integrated and shared metropolitan-level approach can maximize environmental benefits, transforming schools into community centers for urban resilience education and participatory management of risks related to extreme weather events.

Virtualized network functions resource allocation in network functions virtualization using mathematical programming

Network Functions Virtualization (NFV) revolutionizes network services by eliminating the need for dedicated hardware. This virtualization enables flexible and efficient deployment of various network functions like proxies, firewalls, and load balancers. Providing the service requested by the user in the network is done by a sequence of virtual network functions, which are known as service functions chain. One of the main challenges in the development of network functions virtualization architecture is the allocation of resources to the requested network services in network infrastructures, this challenge is called network function virtualization resource allocation problem. Therefore, this paper addresses the resource allocation problem in Network Functions Virtualization (NFV) architectures using mathematical programming techniques. A multi-objective mixed-integer linear programming (MILP) model is proposed to optimize resource allocation for virtual network functions (VNFs). The model incorporates constraints related to node and link resource capacities, as well as delay requirements. The objective functions focus on maximizing network throughput, minimizing node resource costs (CPU cores and memory), reducing capital and operational expenses, and ensuring efficient execution time. These constraints and objective functions are formally defined by mathematical functions. The proposed mathematical model is implemented and solved using the Cplex solver. To evaluate the effectiveness of the proposed mathematical model, various network topologies were evaluated under different parameters. These parameters included the length of Service Function Chains (SFCs), the number and length of flows, node resource capacities, the number of nodes and VNFs. The experimental results demonstrated the model’s ability to efficiently allocate resources to VNFs across these different scenarios.