With the widespread expansion of telecommunication networks, the increase in the number and complexity of base stations has led to an exponential growth in the volume of alarms. Traditional alarm prediction based on expert experience or rules has posed significant challenges due to the demand for engineers’ expertise and workload. It has become imperative to enhance efficiency by employing data-driven approaches for network alarm prognosis. In this paper, a data-driven alarm prediction model is proposed to support the alarm prognosis in base stations. To improve model performance, the proposed approach utilises ensemble deep learning methods to address the heterogeneity and highly imbalanced alarm dataset. The model is trained and validated using a dataset provided by British Telecom (BT) group. The validation results demonstrate that the proposed method achieves a top-5 accuracy of up to 90% in predicting alarms across 170 categories on the validation set.

The massive amounts of data generated by the Industrial Internet of Things (IIoT) require considerable processing power, which increases carbon emissions and energy usage, and we need sustainable solutions to enable flexible manufacturing. Serverless computing shows potential for meeting this requirement by scaling idle containers to zero energy-efficiency and cost, but this will lead to a cold start delay. Most solutions rely on idle containers, which necessitates dynamic request time forecasting and container execution monitoring. Furthermore, Artificial Intelligence of Things (AIoT) can provide autonomous and sustainable solutions by combining IIoT with artificial intelligence (AI) to solve this problem. Therefore, we develop a new testbed, CAPTAIN, to facilitate AI-based co-simulation of scalable and flexible serverless computing in IIoT environments. The AI module in the CAPTAIN framework employs random forest (RF) and light gradient-boosting machine (LightGBM) models to optimize cold start frequency and prevent cold starts based on their prediction results. The proxy module additionally monitors the client-server network and constantly updates the AI module training dataset via a message queue. Finally, we evaluated the proxy module’s performance using a predictive maintenance-based real-world IIoT application and the AI module’s performance in a realistic serverless environment using a Microsoft Azure dataset. The AI module of the CAPTAIN outperforms baselines in terms of cold start frequency, computational time with 0.5 ms, energy consumption with 1161.0 joules, and CO2 emissions with 32.25e-05 gCO2. The CAPTAIN testbed provides a co-simulation of sustainable and scalable serverless computing environments for AIoT-enabled predictive maintenance in Industry 4.0.

Semantic expertise remains a reliable foundation for industrial decision-making, while Large Language Models (LLMs) can augment the often limited empirical knowledge by generating domain-specific insights, though the quality of this generative knowledge is uncertain. Integrating LLMs with the collective wisdom of multiple stakeholders could enhance the quality and scale of knowledge, yet this integration might inadvertently raise privacy concerns for stakeholders. In response to this challenge, Federated Learning (FL) is harnessed to improve the knowledge base quality by cryptically leveraging other stakeholders’ knowledge, where knowledge base is represented in Knowledge Graph (KG) form. Initially, a multi-field hyperbolic (MFH) graph embedding method vectorizes entities, furnishing mathematical representations in lieu of solely semantic meanings. The FL framework subsequently encrypted identifies and fuses common entities, whereby the updated entities’ embedding can refine other private entities’ embedding locally, thus enhancing the overall KG quality. Finally, the KG complement method refines and clarifies triplets to improve the overall quality of the KG. An experiment assesses the proposed approach across different industrial KGs, confirming its effectiveness as a viable solution for collaborative KG creation, all while maintaining data security.

Maritime transport is an indispensable element of the global logistics network. Most maritime loading-unloading operations are supported by quay cranes, making their availability and condition critical to port operations. This work identifies discordant trends arising during the vibration-based condition monitoring of these quay cranes in one of the busiest container ports in the United Kingdom. This work proposes an unsupervised and constrained discord detection approach for irregular but near real-time time series data obtained from multi-modal IoT-based condition monitoring sensors installed on these cranes and transmitted over a 5G network. Due to the live nature of the seaport’s operations, the development of controlled anomaly signatures for a baseline reference was not possible. To address the challenges of incomplete asset health information, irregular and batched time-series sensor data, massive data volumes, and the lack of the assets’ vibration signature baselines, this paper proposes an unsupervised, robust, and fast discord detection mechanism that can rapidly highlight discordant time-series chunks in the received vibration data at a central server. A Support Vector Machine based One-Class Classifier (OCC-SVM) is used to identify the discordant vibration signatures in the time series data. During the development of this approach, the timestamped data chunks from the add-on IoT-based vibration sensors were clustered into two weight classes (loaded and unloaded) based on the crane’s default Programmable Logic Controller (PLC) sensors. The efficacy of this method is checked against the crane maintenance logs and data from a separate crane’s vibration and PLC data. Further, a method for generating synthetic noise-embedded vibration signatures to test the effectiveness of the discord detection method has been devised. Finally, the practicality of the proposed OCC-SVM approach for discord detection was inspected in a constrained environment setting.

Maintenance planning of networked multi-asset systems is a complex problem due to the inherent individual and collective asset constraints and dynamics as well as the size of the system and interdependencies among assets. Although multi-asset systems have been studied numerous times in the past decades, maintenance planning implications of the system’s network characteristics have been barely analysed. Likewise, solutions that consider the network perspective suffer from scalability issues as a network-wide observability is assumed. This paper proposes a network maintenance planning approach based on the decomposition of the multi-asset network into fixed-size localised subnetworks. The overall network maintenance plan is produced by aggregating the subnetwork maintenance plans, which are computed independently via a multi-agent deep reinforcement learning (MARL) algorithm. The results are evaluated against a network-wide approach as well as the commonly-used individual approach. The paper also introduces a systematic approach to integrate the MARL resulting policy in a multi-asset agent-based model. Simulation results of several random asset networks and a large nationwide network infrastructure show that, although a network-wide approach outperforms, on average, other approaches considered, the localised subnetworks approach, provides an acceptable alternative in networks with small-world properties, without the need of a network-wide view.

Serverless edge computing decreases unnecessary resource usage on end devices with limited processing power and storage capacity. Despite its benefits, serverless edge computing's zero scalability is the major source of the cold start delay, which is yet unsolved. This latency is unacceptable for time-sensitive Internet of Things (IoT) applications like autonomous cars. Most existing approaches need containers to idle and use extra computing resources. Edge devices have fewer resources than cloud-based systems, requiring new sustainable solutions. Therefore, we propose an AI-powered, sustainable resource management framework called ATOM for serverless edge computing. ATOM utilizes a deep reinforcement learning model to predict exactly when cold start latency will happen. We create a cold start dataset using a heart disease risk scenario and deploy using Google Cloud Functions. To demonstrate the superiority of ATOM, its performance is compared with two different baselines, which use the warm-start containers and a two-layer adaptive approach. The experimental results showed that although the ATOM required more calculation time of 118.76 seconds, it performed better in predicting cold start than baseline models with an RMSE ratio of 148.76. Additionally, the energy consumption and$CO_{2}$emission amount of these models are evaluated and compared for the training and prediction phases.

The physical assets within a critical infrastructure system are pivotal to its efficient performance and protection and that of other dependent systems. This is particularly the case for communication systems where network protection strategies usually involve asset redundancy. Although such redundancy is well-modelled in the literature, there is a gap in knowledge from a network science perspective in terms of its implications for network modelling and performance assessment. This paper presents a multilayer complex network framework that takes into account the heterogeneity of the redundant infrastructure for realistic network modelling and further analysis, a step change from using a single network model. Key performance indicators (KPIs) for communication networks (i.e., latency and jitter, bandwidth and throughput, queue depth and packet drops) are redefined to evaluate key important features of a long-haul backbone network such as network capacity and average use. In addition, these KPIs are adapted to deal with the aforementioned redundancy and so inform network managers with values defined over a model closer to the real system. The paper analyses the use case of a nationwide core and metro network infrastructure of one of the main UK internet service providers. The results of the analysis of KPIs showcase the advantage of the proposed multilayer complex network framework over the traditional single network model. Critical network elements within different dimensions of a communication network are identified based on their performance for prioritising network management measures.

Heart disease is one of the leading causes of death worldwide, and with early detection, mortality rates can be reduced. Well-known studies have shown that the latest artificial intelligence (AI) can be used to determine the risk of heart disease. However, existing studies did not consider dynamic scalability to get the best performance from these AI models in case of an increasing number of users. To solve this problem, we proposed an AI-powered smart healthcare framework called HealthFaaS, using the Internet of Things (IoT) and a Serverless Computing environment to reduce heart disease-related deaths and prevent financial losses by reducing misdiagnoses. HealthFaaS framework collects health data from users via IoT devices and sends it to AI models deployed on a Google Cloud Platform (GCP)-based serverless computing environment due to its advantages, such as dynamic scalability, less operational complexity, and a pay-as-you-go pricing model. The performance of five different AI models for heart disease risk detection is evaluated and compared based on key parameters, such as accuracy, precision, recall,$F$-Score, and AUC. Experimental results demonstrate that the light gradient boosting machine model gives the highest success in detecting heart diseases with an accuracy rate of 91.80%. Further, we have tested the performance of the HealthFaaS framework in terms of Quality-of-Service (QoS) parameters, such as throughput and latency against the increasing number of users and compared it with a non-serverless platform. In addition, we have also evaluated the cold start latency using a serverless platform which determined that the amount of memory and the software language makes a direct impact on the cold start latency.

This article presents a ubiquitous domain adaptation (UDA) and generalizability technique for vibration-based automated machine status monitoring at the edge. The method significantly reduces the effects of signal noise artifacts and device/usage-specific vibration signatures using basic time-frequency domain signal operations and a lightweight ensemble of data-driven classifiers, allowing the method to be used for reliable domain-invariant status monitoring of motorized equipment. An experimental setup using vibration data from an air-cooled electric blender motor (source domain) is used to train an automated machine state identification classifier that can identify the operating states of an eccentric rotating mass vibration motor (target domain). Initial deployment of this method on target-domain motorized devices resulted in a machine status monitoring accuracy of at least 81.6% and a maximum training accuracy of almost 99% on known data of the source domain and 91.49% for unseen data in the target domain within an acceptable time frame. The performance of the proposed method is also comparable across platforms ranging from resource-constrained edge to a resource-rich cloud. This approach facilitates the use of noisy or uncalibrated sensor data in data-driven machine status monitoring tasks, therefore allowing for the development of reusable, low-cost monitoring systems that require meagre developmental effort, resulting in accelerated deployment times.

The assets in Industry 4.0 are categorized into physical, virtual, and human. The innovation and popularization of ubiquitous computing enhance the usage of smart devices: RFID tags, QR codes, LoRa tags, etc., for asset identification and tracking. The generated data from the Industrial Internet of Things (IIoT) ease information visibility and process automation in Industry 4.0. Virtual assets include the data produced from IIoT. One of the applications of the industrial big data is to predict the failure of the manufacturing equipment. Predictive maintenance enables the business owner to decide, such as repairing or replacing the component before an actual failure that affects the whole production line. Therefore, Industry 4.0 requires an effective asset management to optimize the task distributions and predictive maintenance model. This article presents the genetic algorithm (GA)-based resource management integrating with machine learning for predictive maintenance in fog computing. The time, cost, and energy performance of GA along with MinMin, MaxMin, FCFS, and RoundRobin are simulated in the FogWorkflowsim. The predictive maintenance model is built in two-class logistic regression using real-time data sets. The results demonstrate that the proposed technique outperforms MinMin, MaxMin, FCFS, RoundRobin in execution time, cost, and energy usage. The execution time is 0.48% faster, 5.43% lower cost and energy usage is 28.10% lower in comparison with second-best results. The training and testing accuracy of the prediction model is 95.1% and 94.5%, respectively.

Abstract Weibull time-to-event recurrent neural networks (WTTE-RNN) is a simple and versatile prognosis algorithm that works by optimising a Weibull survival function using a recurrent neural network. It offers the combined benefits of the sequential nature of the recurrent neural network, and the ability of the Weibull loss function to incorporate censored data. The goal of this paper is to present the first industrial use case of WTTE-RNN for prognosis. Prognosis of turbocharger conditions in a fleet of heavy-duty trucks is presented here, where the condition data used in the case study were recorded as a time series of sparsely sampled histograms. The experiments include comparison of the prediction models trained using data from the entire fleet of trucks vs data from clustered sub-fleets, where it is concluded that clustering is only beneficial as long as the training dataset is large enough for the model to not overfit. Moreover, the censored data from assets that did not fail are also shown to be incorporated while optimising the Weibull loss function and improve prediction performance. Overall, this paper concludes that WTTE-RNN-based failure predictions enable predictive maintenance policies, which are enhanced by identifying the sub-fleets of similar trucks.

Within this work, the challenge of developing maintenance planning solutions for networked assets is considered. This is challenging due to the very nature of these systems which are often heterogeneous, distributed and have complex co-dependencies between the constituent components for effective operation. We develop a Multi-Agent Reinforcement Learning (MARL) solution for this domain and apply it to a simulated Radio Access Network (RAN) comprising of nine Base Stations (BS). Through empirical evaluation we show that our model outperforms fixed corrective and preventive maintenance policies in terms of network availability whilst generally utilizing less than or equal amounts of maintenance resource.

Traditional maintenance planning problems usually presume that preventive maintenance (PM) policies will be executed exactly as planned. In reality, however, maintainers often deviate from the intended PM policy, resulting in unpunctual PM executions that may reduce maintenance effectiveness. This article studies two imperfect PM policies with unpunctual executions for infinite and finite planning horizons, respectively. Under the former policy, imperfect PM actions are periodically performed and the system is preventively replaced at the last PM instant. The objective is to determine the optimal number of PM actions and associated PM interval so as to minimize the long-run average cost rate. However, the latter policy specifies that a system is subject to periodic PM activities within a finite planning horizon and there is no PM activity at the end of the horizon. The aim is then to identify the optimal number of PM activities to minimize the expected total maintenance cost. In this article, we discuss the modeling and optimization of the two unpunctual PM policies and then explore the impact of unpunctual executions on the optimal PM decisions and corresponding maintenance expenses in an analytical or numerical way. The resulting insights are helpful for practitioners to adjust their PM plans when unpunctual executions are anticipated.

Complex industrial assets such as power transformers are subject to accelerated deterioration when one of its constituent component malfunctions, affecting the condition of other components, which is a phenomenon called fault propagation. In this paper, we present a novel approach for optimizing condition-based maintenance policies for such assets by modelling their deterioration as a multiple dependent deterioration path process. The aim of the policy is to replace the malfunctioned component and mitigate accelerated deterioration at minimal impact to the business. The maintenance model provides guidance on determining inspection and maintenance strategies to optimize asset availability and operational cost.

A critical factor that prevents optimal scheduling of maintenance interventions is the uncertainty regarding the current condition of the asset under consideration, as well as the rate at which deterioration takes place. However, current maintenance modeling and optimization techniques assume that the condition of the asset is either known, or assumed to have an exponential deterioration rate. In this paper, we present a novel approach to maintenance modeling that removes such assumptions. Here, we employ a Partially Observable Semi-Markov Decision Process (POSMDP) for optimizing maintenance decisions, where the condition of the asset is not fully observable, and decision epochs occur at times following any other type of distribution. This method enables a more realistic way of modeling asset deterioration and optimizing maintenance schedules.

This paper presents a model for optimizing maintenance plans for an industrial system consisting of a number of assets with degradation and performance interaction between them. In particular, we consider an asset system with M identical non-critical machines feeding their output to a critical machine. A common repair team performs maintenance on all the machines. All the machines deteriorate over time stochastically independently. In addition to the stochastically independent degradation, the degradation of the non-critical machines also affects the performance of the critical machine. We develop a mathematical model to represent these interactions and performance of the asset system. We also provide a simulation-based numerical solution to optimize the maintenance plan for the system outlining the maintenance intervals for each of the machines.

Developments in Micro-Electro-Mechanical Systems (MEMS), wireless communication systems and ad-hoc networking have created new dimensions to improve asset management not only during the operational phase but throughout an asset's lifecycle based on using improved quality of information obtained with respect to two key aspects of an asset: its location and condition. In this paper, we present our experience as well as lessons learnt from building a prototype condition monitoring platform to demonstrate and to evaluate the use of COTS wireless sensor networks to develop a prototype condition monitoring platform with the aim of improving asset management by providing accurate and real-time information.

In order for engineering organisations to maximise revenue they have to utilise assets in an effective and efficient way. The success of an enterprise often depends on its ability to utilise assets efficiently. This paper explores challenges in managing engineering assets throughout their lifecycle. We examine the role of asset information management in improving the effectiveness with which complex engineering assets are utilised. Furthermore, the importance of quantifying the value of information in asset management is underlined, specifically discussing the issue of information quality in asset management.