Event-Driven Architecture in Distributed Systems: Leveraging Azure Cloud Services for Scalable Applications

Modeling and fault diagnosis design for HVAC systems using recurrent neural networks

<div class="htmlview paragraph">The stochastic Fault Detection and Isolation (FDI) algorithm, known as the statistical local approach, is applied in a model-based framework to the diagnosis of component faults in the air-intake system of an automotive engine. The FDI scheme is first presented as a general methodology that permits the detection of faults in complex nonlinear systems without the need for building inverse models or numerous observers. Although sensor and actuator faults can be detected by this FDI methodology, component faults are generally more difficult to diagnose. Hence, this paper focuses on the detection and isolation of component faults for which the local approach is especially suitable. The challenge is to provide robust on-board diagnostics regardless of the inherent nonlinearities in a system and the random noise present. In particular, the local approach is shown to simplify and reduce the complicated FDI problem to the standard problem of detecting changes in the mean value of a Gaussian vector with a constant covariance matrix. In doing so, the least square score is implemented as our primary residual, and the statistical properties of the so-called improved residuals are used to detect changes in the parameters of a parametric model. Applying the local approach, in both offline and online configurations, to a mean-value model of a spark-ignition engine, component faults in the air-intake system, namely small abrupt changes in the volumetric efficiency coefficient <i>η<sub>o</sub></i> and the throttle discharge coefficient <i>C<sub>d</sub></i>, have been successfully detected and isolated. The FDI methodology shows robustness to modeling errors and noise, proving the fact that a perfect model is not required to monitor a given system. Since unknown plant parameters are usually determined by identification techniques, which never yield perfect results, modeling errors are indeed expected in practice. Consequently, the local approach sheds promises for robust on-board diagnostics in the face of the overall nonlinear powertrain problem.</div>

In this paper, we consider the fault Detection and isolation (FDI) problem for faulty linear parameter-varying (LPV) systems subject to disturbances and propose a observer-based solution by using multiobjective optimization techniques. To simply the design process, a general faulty LPV system will be constructed from standard LPV description by converting actuator/system component faults into sensor faults at first. Then a bank of LPV FDI filters will be designed to identify each fault. Each FDI filter could generate a residual signal to track individual fault with minimum error and suppressing the effects of disturbances and other fault signals. The design of FDI filters will be formulated as multiobjective optimization problems in terms of linear matrix inequalities (LMIs) and can be solved efficiently. Two numerical examples are also presented to demonstrate the proposed fault detection and isolation approach on both LPV and LTI systems.

Event-Driven Architecture (EDA) represents a transformative approach to retail system design, addressing the complex challenges of modern commerce through dynamic, responsive technological frameworks. By moving beyond traditional synchronous models, EDA enables real-time communication and instantaneous reaction to changing business conditions. The architecture fundamentally reimagines information flow, providing unprecedented capabilities to respond to market dynamics, customer behaviors, and operational challenges. Advanced event producers capture nuanced state changes, while intelligent event consumers transform raw data into strategic operational responses. Asynchronous communication emerges as a flexible backbone, allowing system components to operate independently and create more adaptable, scalable technological ecosystems.

In this paper, a new robust fault detection and isolation (FDI) methodology for an unmanned aerial vehicle (UAV) is proposed. The fault diagnosis scheme is constructed based on observer-based techniques according to fault models corresponding to each component (actuator, sensor, and structure). The proposed fault diagnosis method takes advantage of the structural perturbation of the UAV model due to the icing (the main structural fault in aircraft), sensor, and actuator faults to reduce the error of observers that are used in the FDI module in addition to distinguishing among faults in different components. Moreover, the accuracy of the FDI module is increased by considering the structural perturbation of the UAV linear model due to wind disturbances which is the major environmental disturbance affecting an aircraft. Our envisaged FDI strategy is capable of diagnosing recurrent faults through properly designed residuals with different responses to different types of faults. Simulation results are provided to illustrate and demonstrate the effectiveness of our proposed FDI approach due to faults in sensors, actuators, and structural components of unmanned aerial vehicles.

Serverless architecture has emerged as a revolutionary paradigm in cloud computing, offering developers a scalable and cost-effective approach to building and deploying applications. This article provides a comprehensive overview of serverless architecture, focusing on its key components, benefits, challenges, and future trends. We delve into core components such as Function as a Service (FaaS), Backend as a Service (BaaS), and event-driven architecture, highlighting their roles in enabling developers to build highly scalable and responsive applications. Furthermore, we explore the benefits of serverless architecture, including cost-effectiveness, scalability, and improved development velocity, while also addressing challenges such as cold start latency, vendor lock-in, and observability and debugging complexities. Looking ahead, we discuss future trends and considerations in serverless architecture, including advancements in technology, hybrid and multi-cloud deployments, and the importance of observability and DevOps practices. Finally, we encourage further exploration and adoption of serverless computing, emphasizing its potential to drive innovation and business success in the digital era.

In this article, the problem of fault isolation is studied for linear stochastic time-varying systems. Different from the existing results about fault isolation, the system in this article suffers from strong noise, which increases the difficulty of distinguishing different fault components since the difference in measurement distributions caused by different fault components is small. To handle this problem, a novel fault isolation scheme comprising a set of residuals, a set of evaluation functions, and a decision logic is proposed. First, based on the hypothesis testing method, two performance indices reflecting the probability of two classes of false isolation induced by noise are introduced to quantitatively evaluate the influence of strong noise on residuals. Under a given threshold, the existence of the optimal residual with two minimal performance indices is proved in this article, which minimizes the effect of noise on residuals. Subsequently, a suboptimal recursive residual whose parameter gradually tends to the parameter of the optimal residual is designed. Following this, by employing the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\chi ^{2}$ </tex-math></inline-formula> test and the predesigned decision logic, fault isolation can be realized. Finally, two illustrative examples are provided to show the effectiveness of the proposed method.

Fintech modernization is a ground-up shift from traditional batch-processing infrastructure to event-driven real-time architectures that redefine financial service delivery and social mechanisms of trust. Modern financial institutions draw on advanced stream processing technologies, API-first integration, and distributed computing to support transaction throughput rates in millions of operations per second with sub-millisecond latencies for key financial transactions. Occasion-driven architectures (also known as event-driven architecture) provide instantaneous affirmation of transactions, real-time detection of fraud, and clear audit trails through immutable event recording structures that ensure end-to-end transaction traceability for regulatory purposes. Mobile-first design patterns and modern web-based packages boost access to finance for the underprivileged through offline-enabled interfaces that function across diverse device specifications and network connectivity eventualities. Advanced cryptographic algorithms, which include homomorphic encryption and zero-knowledge proofs, facilitate privacy-enhancing analytics that reconcile customized financial offerings in opposition to people’s privacy protection. Regulatory technology embedding using compliance-by-design architectures in regulatory technology help automate policy application and reporting while advanced trust protocols using biometric authentication, behavior analysis, and machine learning algorithms prevent fraud while ensuring frictionless user experiences. The intersection of distributed architectures, privacy-retaining technologies, and inclusive design styles generates financial structures that cater to various populations even as adhering to demanding safety and regulatory compliance in diverse jurisdictions.

Effective fault detection and isolation can improve the safety, reliability and efficiency of the district heating system. In order to detect and locate the sensor, actuator and component faults in the district heating system with faster response speed and higher accuracy, a two-level fault detection and isolation scheme, consisting of upper-level classifier for system faults and lower-level classifier for sub-faults, is developed based on convolutional neural networks. In consideration of the difficulty of obtaining the operation data of a real district heating system under various faulty states, a test benchmark model of an integrated energy based district heating system is built from the system level, which contains the renewable energy based water boilers, transmission networks, and heat load substations to examine the effectiveness of the proposed scheme. To improve the model reality, the dynamics of sensors and actuators, models of heat exchangers, and thermal inertia are considered in the district heating system, and Gaussian noises are added in the raw data signals. Nine kinds of system faults including sensor, actuator, component faults, along with three sub-fault types of bias, drift, complete failure, are investigated in the benchmark system. The performance of the proposed two-level fault detection and isolation scheme is evaluated under different data windows and Gaussian noises in the district heating system, and is compared with other data-driven methods including k-nearest neighbor, random forest and back propagation neural networks. Experimental results show that the two-level fault detection and isolation scheme can detect the faults in the district heating system accurately and robustly, and the proposed scheme has the potential to become an effective solution to real-time monitoring of faults in the district heating system.

The electrification of the mobility sector comes with multiple challenges such as the lack of information on when, where, how long and how fast charging processes of electric vehicles will take place. In order to keep up with increasing power demand of charging processes, besides better predictions also the active control of charging processes will be necessary to minimize infrastructure costs. This work deals with a real-time mechanism for supporting the Power Quality (PQ) in electric distribution grids in terms of congestion and voltage management. In the paper, we propose a distributed smart charging approach that considers real-time conditions of the distribution grid provided by an event-driven architecture that collects data from different points in the grid. Our approach adopts the traffic light model, which allows smooth changing of the charging power to avoid drastic changes of the grid state. In order to be ready for real-world application, the algorithm is validated by a series of experiments on two setups: Pure software (co-)simulation and Power Hardware In the Loop (PHIL) where physical charging stations and electric cars are controlled in a laboratory setup.

This article comprehensively analyzes event-driven data pipelines in cloud computing environments, examining their architecture, implementation considerations, and real-world applications. The article explores the fundamental components of event-driven systems, from event sources and message brokers to processing layers, while evaluating their performance characteristics and reliability mechanisms. Through detailed analysis of system architectures, we investigate the integration of various cloud services and their role in enabling scalable, real-time data processing. The article demonstrates how modern event-driven architectures achieve sub-millisecond processing times and handle millions of events per second while maintaining system resilience. Our findings reveal significant improvements in operational efficiency across various industries, including financial services, marketing automation, and IoT monitoring solutions. The article also addresses critical implementation aspects, including security frameworks, integration protocols, and best practices for system optimization. These insights provide valuable guidance for organizations leveraging event-driven architectures in their digital transformation initiatives. The article concludes that event-driven data pipelines represent a crucial advancement in data processing technology, offering unprecedented capabilities in handling real-time data streams while maintaining scalability, reliability, and cost-effectiveness.

Real-time payment processing has become a critical infrastructure component in modern financial systems, requiring architectures capable of handling millions of transactions per second with sub-second latency guarantees. This review examines the evolution and current state of event-driven architectures (EDA) for payment processing, focusing on latency optimization techniques and scalability challenges. Event-driven systems leverage asynchronous message passing and distributed computing paradigms to achieve the performance requirements of contemporary payment networks. The adoption of microservices architecture (MSA) combined with event streaming platforms has enabled financial institutions to process transactions with latencies below 100 milliseconds while maintaining consistency and reliability. This paper synthesizes research on architectural patterns including Command Query Responsibility Segregation (CQRS), event sourcing, and saga patterns that address the complexities of distributed payment processing. We analyze optimization strategies encompassing network topology design, data partitioning schemes, caching mechanisms, and consensus protocols. The review also examines scalability solutions including horizontal scaling approaches, load balancing algorithms, and database sharding techniques. Key findings indicate that hybrid architectures combining synchronous and asynchronous processing, coupled with intelligent caching and optimized serialization protocols, can achieve throughput exceeding ten million transactions per second while maintaining ACID properties. The paper concludes by identifying emerging trends in quantum-resistant cryptography integration, machine learning-based fraud detection, and cross-border payment harmonization that will shape future payment processing architectures.

Gas path fault diagnosis in high-performance gas turbines is often challenged by insufficient sensor availability, leading to underdetermined problems where fault isolation is easily confused with degradation in other components. In such cases, isolation results become unreliable when the number of sensors is smaller than the number of estimated health parameters, and multiple feasible solutions arise. To alleviate this issue, this paper introduces an isolability indicator for gas path faults under simultaneous unknown degradations, along with a sensor selection algorithm that maximizes isolability. The isolability of a component fault is defined as the probability of distinguishing it from faults in other components, and a sensor configuration performance metric is constructed from the isolabilities of all faults. Since calculating isolability through Monte Carlo simulations imposes a heavy computational burden, an approximation method based on clustering to reduce Monte Carlo simulations is developed. A simplified indicator is designed to infer the change of isolability. And they can be classified by the geometric features of the fault symptoms sets. Building on this, an algorithm is proposed to determine the necessary Monte Carlo simulations, further estimating the remained isolability and reducing computational cost. The approach is validated on a high-bypass ratio turbofan engine model through digital simulations. Results demonstrate that the proposed indicator effectively characterizes component fault isolability, and that appropriate sensor selection enhances the fault isolability in the presence of unknown degradation. Moreover, the algorithm successfully identifies optimal or near-optimal sensor configurations across different scenarios.

This article addresses a robust fault detection and isolation procedure which is applicable for a hybrid system undergoing discrete mode changes. Global analytical redundancy relations, which may undergo change in their structure depending on the switched mode, are derived from the diagnostic hybrid bond graph model of the system. For fault detection and isolation analysis, the residuals, evaluated at every instant from the global analytical redundancy relations, are tested against adaptive thresholds which are changed with mode shift and variation of states, but not changed due to any fault. The parametric uncertainties are included in the diagnostic hybrid bond graph through the linear fractional transformation approach and the adaptive thresholds are obtained from the modified diagnostic hybrid bond graph model. The residuals are made robust in a sense that these would always remain within the upper and lower threshold bound for any perturbation except fault occurrence. For application of the robust fault detection and isolation analysis, a hybrid thermo-fluid system is selected whose behavioural evolution combines both discrete as well as continuous changes of states. It is shown through simulation that with parameter uncertainties in a hybrid system subject to frequent mode shift, robust fault detection and isolation is successfully achieved using the passive approach. The novelty of this work lies in the integration of the model-based diagnosis principle for hybrid systems with the approach for robust residual threshold generation for systems having uncertain parameters.

In this paper the problem of fault diagnosis in an aircraft jet engine is investigated by using an intelligent-based methodology. The proposed fault detection and isolation (FDI) scheme is based on the multiple model approach and utilizes autoassociative neural networks (AANNs). This methodology consists of a bank of AANNs and provides a novel integrated solution to the problem of both sensor and component fault detection and isolation even though possibly both engine and sensor faults may occur concurrently. Moreover, the proposed algorithm can be used for sensor data validation and correction as the first step for health monitoring of jet engines. We have also presented a comparison between our proposed approach and another commonly used neural network scheme known as dynamic neural networks to demonstrate the advantages and capabilities of our approach. Various simulations are carried out to demonstrate the performance capabilities of our proposed fault detection and isolation scheme.