Network Infrastructure Research Articles

An efficient multi-objective UAV assisted RSU deployment (MOURD) scheme for VANET

A Roadside Unit (RSU) serves as essential infrastructure in Vehicular Ad Hoc Networks (VANETs) that supports the goals of Intelligent Transportation Systems (ITS) by providing safety services, shared storage, and enhanced internet connectivity to vehicular users, drivers, and pedestrians. Additionally, the efficiency of VANETs, concerning network service utility and latency, depends on the relative positioning of these RSUs within the network topology. Most existing RSU deployment approaches deal with a single objective, either enhancing network service utility or minimizing the latency. For instance, some studies suggest deploying RSUs in high-traffic road segments that enhance network service utility but lead to higher latency. Conversely, some suggest deploying the RSUs in low-traffic road segments that minimize the network latency, but there will be low network service utility. Hence, there exists a trade-off between these two conflicting objectives in VANETs, and none of the studies address both objectives simultaneously. To achieve the balance between these two objectives, this paper proposes a Multi-Objective UAV assisted RSU Deployment (MOURD) scheme that leverages the Unmanned Aerial Vehicles (UAVs) for VANET efficiency. The MOURD scheme statically places RSUs in high-traffic road segments and dynamically dispatches the UAVs in low-traffic road segments to facilitate seamless network coverage and minimize the overall network latency. The simulation results on the road network of Delhi, India, demonstrate the effectiveness of the proposed MOURD scheme compared to other benchmark RSU & UAV deployment approaches. MOURD scheme outperforms on an average of 17.42%, 13.29%, 15.67% and 6.23% in terms of vehicle connection time, packet delivery ratio, throughput, and latency, respectively.

Analysis of WiFi Reliability at 2.4 GHz and 5 GHz Frequencies in the Environment of STMIK Sinar Nusantara Surakarta

This research is expected to provide solutions to improve the performance and reliability of the WiFi network at STIMIK Sinar Nusantara, thus supporting teaching and learning activities and enhancing the quality of education. By comparing the quality of WiFi networks between 2.4 GHz and 5 GHz, it aims to shed light on the differences and advantages of each frequency band. Furthermore, the findings of this research can be beneficial for the design of future networks, helping network designers to better understand the importance of frequency management in network infrastructure planning. This research employs an experimental method by testing QoS parameters (throughput, delay, and packet loss) as well as reliability (connection and uptime) at both frequencies. The results of the research indicate that the 5 GHz frequency provides better QoS performance and reliability compared to 2.4 GHz. This research concludes that the 5 GHz frequency could be a solution to improve the WiFi network quality at STIMIK Sinar Nusantara

Optimalisasi Infrastruktur Jaringan dengan Teknologi Fiber Optic di PT. Sinar Nusantara Industries

PT. Sinar Nusantara Industries is a manufacturing company that produces famous building materials. One of the important divisions in the company's operations is the Information Technology (IT) division that is responsible for network infrastructure. Currently, the company uses UTP cables for the network, but the distant inter-building distance leads to connectivity instability. To address this problem, the study proposes replacing the UTP cable with fiber optics from the server room to the finished product warehouse (GPJ) to improve the network infrastructure at PT. Sinar Nusantara Industries. This research uses the PPDIOO method (Prepare, Plan, Design, Implement, Operate, Optimize) to ensure each step is done in a structured manner. Research results show that the use of fiber optic cables increases network speeds from 100 Mbps to 300-500 Mbps and improves the stability and reliability of remote connections. The implementation also utilizes fast connectors to facilitate connectivity without splicing, making it more effective. Thus, this move is expected to improve network performance and security in PT. Sinar Nusantara Industries

Lane Line and Object Detection Using Yolo v3

In the contemporary age, creating autonomous vehi- cles is a crucial starting point for the advancement of intelligent transportation systems that rely on sophisticated telecommu- nications network infrastructure, including the upcoming 6g networks. The paper discusses two significant issues, namely, lane detection and obstacle detection (such as road signs, traffic lights, vehicles ahead, etc.) using image processing algorithms. To address issues like low accuracy in traditional image processing methods and slow real-time performance of deep learning-based methods, barriers for smart traffic lane and object detection algorithms are proposed. We initially rectify the distorted image resulting from the camera and then employ a threshold algorithm for the lane detection algorithm. The image is obtained by extracting a specific region of interest and applying an inverse perspective transform to obtain a top-down view. Finally, we apply the sliding window technique to identify pixels that belong to each lane and modify it to fit a quadratic equation. The Yolo algorithm is well-suited for identifying various types of obstacles, making it a valuable tool for solving identification problems. Finally, we utilize real-time videos and a straightforward dataset to conduct simulations for the proposed algorithm. The simula- tion outcomes indicate that the accuracy of the proposed method for lane detection is 97.91% and the processing time is 0.0021 seconds. The proposal for detecting obstacles has an accuracy rate of 81.90% and takes only 0.022 seconds to process. Compared to the conventional image processing technique, the proposed method achieves an average accuracy of 89.90% and execution time of 0.024 seconds, demonstrating a robust capability against noise. The findings demonstrate that the suggested algorithm can be implemented in self-driving car systems, allowing for efficient and fast processing of the advanced network.

Investigating stronger tolerant network against cascading failures in focusing on changing degree distributions.

Many real-world networks with Scale-Free structure are significantly vulnerable against both intentional attacks and catastrophic cascading failures. On the other hand, it has been shown that networks with narrower degree distributions have strong robustness of connectivity by enhancing loops. This paper numerically reveals that such networks are also tolerant against cascading failures. Our findings will be useful in designing stronger tolerant network infrastructures.

Real Time Anomaly Detection in Network Traffic: A Comparative Analysis of Machine Learning Algorithms

In the constantly changing field of cybersecurity, real-time intrusion detection using machine learning algorithms has become crucial for protecting network infrastructures. This paper presents a comprehensive literature survey focusing on the comparative study of diverse machine learning algorithms employed for anomaly detection in network traffic. The objective is to critically evaluate the effectiveness of various algorithms in identifying and mitigating threats in real-time scenarios. The study delves into the nuances of prominent machine learning models, including Decision Trees, Random Forests, Support Vector Machines, Neural Networks, and ensemble methods, as they apply to the domain of anomaly detection. Each algorithm is scrutinized based on its ability to adapt to dynamic network behaviors, handle imbalanced datasets, and provide accurate real-time threat assessments. Throughout the survey, key research contributions are analyzed, encompassing methodologies, datasets, and performance metrics. Comparative insights are provided to emphasize the strengths and weaknesses of each algorithm, elucidating their appropriateness for real-time intrusion detection in network traffic. Notably, the examination extends beyond traditional approaches, exploring recent advancements such as deep learning and ensemble techniques. The findings from this comparative study aim to provide practitioners and researchers with valuable insights into selecting the most suitable machine learning algorithm for real-time anomaly detection in the context of network security. By understanding the comparative performance of these algorithms, organizations can make informed decisions to enhance their cybersecurity posture and fortify their defenses against emerging threats.

Optimization Algorithms in SDN: Routing, Load Balancing, and Delay Optimization

Software-Defined Networking is today a mature technology, which is developed in many networks and also embedded in novel architectures like 5G and 6G. The SDN control centralization concept brings significant advantages for management and control in SDN together with the programmability of the data plane. SDN represents a paradigm shift towards agile, efficient, and secure network infrastructures, moving away from traditional, hardware-centric models to embrace dynamic, software-driven paradigms. SDN is compliant also with the virtualization architecture defined in the Network Function Virtualization framework. However, SDN should cooperate seamlessly for some years with the distributed TCP/IP control developed during the years all over the world. Among others, the traditional tasks of routing, forwarding, load balancing, QoS assurance, security, and privacy should be solved. The SDN native centralization brings also some new challenges and problems which are different from the traditional distributed control IP networks. The algorithms and protocols usable in SDN should meet requirements like scalability, convergence, redundancy assurance, sustainability, and good real-time response, and allow orchestrated automation in enhancing network resilience and adaptability. This work presents a theoretical review of state-of-the-art SDN optimization techniques, offering a critical and comparative discussion of various algorithms having tasks such as routing (including dynamic ones), forwarding, load balancing and traffic optimization, and forwarding delay minimization. Attention is pointed to general algorithms which can offer pragmatic solutions for large systems or multiple metric routing.

A hierarchical optimization approach to maximize hosting capacity for electric vehicles and renewable energy sources through demand response and transmission expansion planning

Within the scope of sustainable development, integrating electric vehicles (EVs) and renewable energy sources (RESs) into power grids offers a number of benefits. These include reducing greenhouse gas emissions, diversifying energy sources, and promoting the use of green energy. Although the literature on hosting capacity (HC) models has grown, there is still a noticeable gap in the discussion of models that successfully handle transmission expansion planning (TEP), demand response (DR), and HC objectives simultaneously. Combining TEP, DR, and HC objectives in one model optimizes resource use, enhances grid stability, supports renewable and EV integration, and aligns with regulatory and market demands, resulting in a more efficient, reliable, and sustainable power system. This research presents an innovative two-layer HC model, including considerations for TEP and DR. The model determines the highest degree of load shifting appropriate for incorporation into power networks in the first layer. Meanwhile, the second layer focuses on augmenting the RES and EVs’ hosting capability and modernizing the network infrastructure. System operators can choose the best scenario to increase the penetration level of EVs and RESs with the aid of the proposed model. The proposed model, which is formulated as a multi-objective mixed-integer nonlinear optimization problem, uses a hierarchical optimization technique to identify effective solutions by combining the particle swarm optimization algorithm and the crayfish optimizer. When compared to traditional methods, the results obtained from implementing the proposed hierarchical optimization algorithm on the Garver network and the IEEE 24-bus system indicated how effective it is at solving the presented HC model. The case studies demonstrated that integrating DR into the HC problem reduced peak load by 10.4–23.25%. The findings also highlighted that DR did not impact the total energy consumed by EVs throughout the day, but it did reshape the timing of EV charging, creating more opportunities for integration during periods of high demand. Implementing DR reduced the number of projects needed and, in some cases, led to cost savings of up to 12.3%.

Pemasangan Jaringan Internet Berbasis WiFi Untuk Meningkatkan Akses Komunikasi Warga Di Desa Durian

Durian Village is a village located in Janapria District, Central Lombok Regency. Currently, there is an internet network available in Durian Village, but the speed and quality of the internet network in several places is not good. The condition of infrastructure in Durian Village is still very poor, especially internet access is still very limited, while communication needs are increasing. The aim of this community service program is to install a WiFi-based internet network to improve communication access for residents and the use of information and communication technology (ICT) for the people of Durian Village, Janapria District. Internet installation begins with preparing the device and planning the location of the device so that the signal coverage can be wider. Installation of internet network infrastructure where needed and wider coverage for residents. The implementation of the internet installation was also assisted by STMIK Lombok students. After installing the internet network, the internet network signal area is tested. Internet network testing is carried out by testing signal strength and internet speed which is found to be sufficient to meet internet access standards for communication access and running streaming media applications.

Transport SDN architecture for multi-layer transport slicing

The proposed architecture advances the concept of network slicing, crucial for beyond 5G services, by enabling dynamic resource allocation and customized partitioning in managed network infrastructures. This architecture addresses the challenges of provisioning end-to-end (E2E) slices across diverse network domains, which is complicated by technological heterogeneity and the variety of vendor solutions. By introducing a standardized transport network solution, we ensure seamless integration, equitable treatment of service requests, and the ability to meet diverse demands. The architecture is centered around a multi-layer transport network slicing architecture, which allows for the division of transport networks into virtual autonomous segments, each tailored for specific services or applications. This segmentation is essential for providing differentiated and personalized 5G services, optimizing network performance, and maximizing resource application. A key component of this architecture is the transport slice controller (TSC), which controls the provision and life-cycle management of transport slices, ensuring a standardized approach in the industry for the definition and realization of slices.

AIS-NIDS: An intelligent and self-sustaining network intrusion detection system

The ever-evolving landscape of network security is continually molded by the dynamic evolution of attack vectors and the relentless emergence of new, highly sophisticated attacks. Attackers consistently employ increasingly advanced techniques, rendering their actions elusive and formidable. In response to this ever-growing threat, the demand for intelligent and autonomous security systems has reached paramount importance. In this paper, we introduce AIS-NIDS (An Intelligent and Self-Sustaining Network Intrusion Detection System), an innovative network intrusion detection system (NIDS) that delves into the realm of packet-level analysis. By doing so, AIS-NIDS is capable of identifying threats with intricate payload-level details, a level of granularity that traditional NIDS relying solely on flow-level data may overlook. The defining feature of AIS-NIDS is its dual functionality, driven by autonomous and intelligent learning. It not only autonomously distinguishes between benign and unknown attacks using machine learning models but also conducts incremental learning, adapting to new attack classes. In essence, AIS-NIDS bridges the gap between traditional NIDS and the next generation of intelligent systems, endowing the system with the capacity for independent decision-making and real-time adaptability in the face of evolving threats. Our extensive experiments stand as a testament to AIS-NIDS’ ability to efficiently manage and identify new attack classes, thus establishing it as a valuable asset in the reinforcement of network infrastructures. Through our experimentation, we have demonstrated the practical efficacy of the proposed approach by simulating a real-world scenario in which certain attack classes are unknown. AIS-NIDS not only effectively identified these unknown threats but also autonomously learned to recognize them as it encountered them, enhancing the system’s capabilities for future encounters with these threats.

Network Goodness Calculus Propositions

We coin the term “network goodness” for a value we define for a network embedded in a given environment as a metric that describes the suitability of that network for meeting a demand. Three formulas are proposed to calculate the metric from three variable values. The first variable considers parts of the environment gravitated by the network. For these parts of the environment, we define a value that measures user costs refusing them the use of the network. Last but not least, the network maintenance costs are considered. The results are obtained after focusing on infrastructure and transport networks, but can be used for other types of networks as well.

Модель интеграции педагогического вуза в региональную инновационную сетевую инфраструктуру

Раскрыты значение и особенности, представлена общая характеристика педагогической интеграции, рассмотрен перечень показателей, свидетельствующих об интегрированности современного педагогического вуза в инновационную инфраструктуру региональной системы образования. Дано описание авторской модели интеграции педагогического вуза в региональную инновационную сетевую инфраструктуру, построенной с учётом специфики системы образования Краснодарского края. Существенное внимание уделено характеристике формализованного и инициативного форматов интеграции. При описании модели актуализированы основные субъекты её реализации, направления взаимодействия и практические мероприятия, обеспечивающие интеграционные процессы, раскрыты возможности использования ресурсов педагогического вуза и инновационной инфраструктуры региональной системы образования. Указаны ожидаемые эффекты для современной системы образования от реализации авторской модели. The meaning, features and general characteristics of pedagogical integration are revealed, a list of indicators is considered that indicate the integration of a modern pedagogical university into the innovative infrastructure of the regional education system. A description of the author's model for integrating a pedagogical university into a regional innovative network infrastructure, built taking into account the specifics of the education system of the Krasnodar Territory, is given. Significant attention is paid to the characteristics of formalized and initiative formats of integration. When describing the model, the main subjects of its implementation, areas of interaction and practical measures that ensure integration processes are updated and the possibilities of using the resources of a pedagogical university and the innovative infrastructure of the regional education system are revealed. The expected effects for the modern education system from the implementation of the author's model are indicated.

Online Multi-Resource Allocation for Network Slicing in 5G with Distributed Algorithms

With the increasing scale of mobile cellular network applications, 5G mobile network infrastructure provides customizable services to users in the form of network slices. How to effectively allocate existing resources in real dynamic networks with time-varying network utility is a key issue that previous work did not consider. This paper first initializes the multi-resource allocation problem of network slicing in an online manner, where the utility function is set to change over time. Therefore, we propose Metis, an online network slicing resource allocation framework that combines the time-varying nature of the network utility function given bandwidth and processing power constraints with the requirement of virtual network function isolation. The goal is to maximize the cumulative network utility in the long term and specify multiple resource allocation problems by utilizing concave optimization methods. In addition, a distributed algorithm based on the online alternating direction method of multipliers with regret optimization has been developed to achieve optimal resource allocation. Our mathematical analysis proves that Metis can provably converge to the optimal solution and the result of experiments demonstrates a steady state behavior of Metis, which converges in dynamic network settings.

Building a searchable online corpus of Australian and New Zealand aligned speech

ABSTRACT Advances in automatic speech recognition technology, increases in bandwidth availability, and the widespread use of video streaming and sharing platforms have opened new horizons for corpus phonetics. CoANZSE Audio, a searchable online version of the Corpus of Australian and New Zealand Spoken English, provides access to over 195 million words of transcribed speech from transcripts of videos uploaded to YouTube by councils and other local government entities in Australia and New Zealand. Audio and forced alignment files are also available, making the resource suitable for the investigation of a range of research questions pertaining to morphosyntax, phonetics, and discourse. The resource, which is freely available via login through CLARIN, Europe’s main language resources infrastructure network, was created through the use of open-source tools and software: yt-dlp, a Python library for collecting data from video and streaming websites; the Montreal Forced Aligner, a recent neural network alignment suite; and Parselmouth-Praat, Python bindings for the Praat acoustic analysis software. The website is powered by BlackLab, which combines a powerful search engine based on Apache Lucene with an intuitive web frontend. CoANZSE Audio may be useful for the investigation of regional differentiation of language features, and with additional annotation, differences in feature use according to social or demographic groups. Recent applications have included studies of double modals, a rare syntactic feature, and apology sequences. The nature of the audio and alignment data may make the resource especially suitable for the study of regional phonetic variation. Furthermore, the methods used to create the resource may be of interest to researchers seeking to adopt a pipeline approach for the creation of specialized corpora from publicly available online content.

Industrial Metaverse: A Comprehensive Review, Environmental Impact, and Challenges

The Industrial Metaverse paradigm can be broadly described as a virtual environment that integrates various technologies such as augmented reality and mixed reality to enhance business operations and processes. It aims to streamline workflows, reduce error rates, improve efficiency, and provide a more engaging experience for employees. The promise of the Industrial Metaverse to drive sustainability and resource efficiency is compelling. Using advanced technologies such as the Industrial Metaverse is vital in an endeavor to have a competitive edge in a rapidly evolving business environment. However, the environmental impact of the technologies underpinning the Industrial Metaverse, like data centers and network infrastructure, should not be overlooked. The ecological footprint of these technologies must be considered in the sustainability equation. Researchers have warned that, by 2025, without sustainable artificial intelligence (AI) practices, AI will consume more energy than the human workforce, significantly offsetting zero carbon gains. As the Metaverse persists in evolving and gaining momentum, it will be necessary for companies to prioritize sustainability and explore new ways to balance technological advancements with environmental stewardship. However, recent studies have conjectured that the Metaverse holds the potential to reduce carbon emissions, as digital replacements for physical goods become more prevalent and physical activities like mobility and construction are reduced. Moreover, the specific extent to which this substitution can alleviate environmental concerns remains an open issue, presenting a knowledge gap in understanding the real-world impact of digital replacements. Thus, the objective of this paper is to provide a comprehensive review of the Industrial Metaverse, as well as explore the environmental impact of the Industrial Metaverse. The integrative literature review design and methodological approach involved multiple sources from the Web of Science and databases such as the ACM library, IEEE Library, and Google Scholar, which were analyzed to provide a comprehensive understanding of the developments in the Industrial Metaverse. Firstly, by considering the Industrial Metaverse’s architecture, we elucidate the Industrial Metaverse concept and the associated enabling technologies. Secondly, we performed an exploration through a discussion of the prevalent use cases and the deployment of the emerging Industrial Metaverse. Thirdly, we explored the impact of the Industrial Metaverse on the environment. Lastly, we address novel security and privacy risks, as well as upcoming research challenges, keeping in mind that the Industrial Metaverse is based on a strong data fabric. The results point to the Industrial Metaverse as having both positive and negative environmental effects in terms of energy consumption, e-waste, and pollution. Research, however, indicates that most Industrial Metaverse applications have a positive environmental impact and subsequently trend toward sustainability. Finally, for sustainability in the Industrial Metaverse, enterprises may consider utilizing renewable energy sources and cloud services. Furthermore, we examined the effects of products on the environment, as well as in the creation of a circular economy.

An intelligent security mechanism in mobile Ad-Hoc networks using precision probability genetic algorithms (PPGA) and deep learning technique (Stacked LSTM)

The Mobile Ad-hoc Networks (MANETs) have gained a significant attention in the recent years due to their proliferation and huge application purposes. To defend from many types of modern cyber dangers like Distributed Denial of Service (DDoS) attacks, Advanced Persistent Threats (APTs), Insider Threats, Ransomware, Zero-Day Exploits, Social Engineering tactics, and etc is not easy when it comes to keeping MANETs security. These complex assaults focus on network infrastructure, take advantage of weaknesses in communication protocols and control user actions. Although there have been improvements in intrusion detection systems (IDS), it is still difficult to fully safeguard MANETs. The purpose of this research is to create advanced methods that can accurately find and decrease attacks inside MANETs. Applying Sensor-based Feature Extraction (SFE) to extract useful network features such as Received Signal Strength Indication (RSSI) and Time of Travel (TOT) from datasets NSL-KDD and CICIDS-2017. Utilizing the fresh method of Precise Probability Genetic Algorithm (PPGA) optimization for removing unrelated details, which enhances precision in detecting attacks. Predicting normal and attacking labels by applying Stacked Recurrent Long Short Term Memory (SRLSTM) method, fine-tuning classifier's parameters in every layer to improve outcomes. In order to authenticate and compare the suggested methods with current attack detection tactics, this study will make use of various evaluation measurements. The NSL-KDD, which is a benchmark dataset in network intrusion detection research, has a wide variety of network traffic data with instances that are labeled as normal and different attacks. CICIDS-2017 is similar because it contains an extensive dataset too - this includes real-world traces from network traffic where there's both regular activity and harmful actions. The purpose is to enhance the existing status of MANET security so as it can withstand more strongly against cyber dangers. According to the outcomes, it is analyzed that the attack detection accuracy has improved greatly 99 % when compared to other methods, as shown by the detailed assessment measurements. Better handling of big datasets with top detection accuracy reduces the time needed 8.9 s for training and testing models. Decrease in misclassification results and better ability to differentiate normal network actions from harmful intrusions. Improved resistance of MANETs to different cyber dangers, guaranteeing the safety and dependability of network communication in changing and non-centralized settings.

Utilising InSAR for monitoring infrastructure at national scales

Interferometric SAR (InSAR) is now a widely used tool for the monitoring of infrastructure, in particular mines, dams, and oil and gas facilities. The technology is also widely used for the monitoring of construction activities such as tunnelling. With the growth of globally available and continuously updated SAR datasets, the monitoring of entire regional and national infrastructure networks is now feasible. Here we show how continuously updated, network-wide, InSAR datasets can be used to proactively manage large infrastructure networks such as roads, railways, and water pipelines. In the UK continuously updated InSAR data (derived from Sentinel-1 SAR data) is being effectively used across the entire railway network to proactively monitor potential embankment failures, large-scale landslides, and potential hazards outside of the boundary fence. A challenge of using InSAR data in this way is the huge volume of data that is available, as such custom risk metrics and machine learning algorithms are applied to highlight some of the areas at heightened risk. InSAR is also being applied to tackle the issue of water pipe leakage caused by natural ground movements, such as soil shrink-swell. In this case, regularly updated InSAR data has been used in the UK and Australia to detect areas at elevated risk of pipeline failures based on ground movement patterns, and by combining historical movement data and known failure events it is possible to refine such models. With expanding global SAR constellations proactive, nationwide, monitoring of critical assets is now possible, with the challenge being how we derive insight from these very large datasets.

Comparison between acoustic emission sensors and piezoelectric patches for damage detection in concrete beams

Acoustic emission (AE) sensing is an established technique to monitor crack nucleation and propagation in different types of structural elements and for different damage scenarios. Although effective for crack monitoring in civil infrastructure, off-the-shelf AE sensors can be expensive, discouraging their installation in large numbers for assessing the global structural performance or monitoring multiple assets in the infrastructure network. For this reason, this paper explores the use of piezoelectric patches as an alternative low-cost solution to AE sensors. These patches are considerably cheaper, do not require external power supply and can be easily attached to existing structural elements or embedded into new structures. Moreover, thanks to the direct and inverse piezoelectric effect, the same set of patches can act both as sensors and actuators, meaning that they can be used to “passively” monitor crack propagation over time, as well as to locate and characterize damage in ageing structures at a certain time by using the patches as emitters and receivers of waves. In this framework, this paper proposes a comparison between traditional AE sensors and piezoelectric patches. The comparison is performed on a set of three concrete beams subjected to four-point bending loading, each equipped with two grids of sensors, i.e. 8 AE sensors and 8 patches. The beams are tested under increasing monotonic loading, from zero-load uncracked condition up to collapse.

Learning local cascading failure pattern from massive network failure data

Abstract This article proposes a novel multivariate point process regression model for a large-scale physically distributed network infrastructure with two failure modes, i.e. primary failures caused by the long-term usage and degradation of assets, and cascading failures triggered by primary failures in a short period. We exploit large-scale field pipe failure data from a UK-based water utility to support the rationale of considering the two failure modes. The two modes are not self-revealed in the data. To make the inference of the large-scale problem possible, we introduce a time window for cascading failures, based on which the likelihood of the pipe failure process can be decomposed into two parts, one for the primary failures and the other for the cascading failure processes modulated by the primary failure processes. The window length for cascading failures is treated as a tuning parameter, and determined through maximizing the likelihood based on all failure data. To illustrate the effectiveness of the model, two case studies are presented based on real data from the UK-based water utility. Interesting features of the cascading failures are identified from massive field pipe failure data. The results provide insights on advanced modelling and practical decision-making for both researchers and practitioners.