Improve System Reliability Research Articles

AI-enhanced predictive maintenance systems for critical infrastructure: Cloud-native architectures approach

Critical infrastructure (CI), such as power grids, transportation systems, and telecommunications networks, is becoming increasingly complex, requiring sophisticated maintenance strategies and procedures to guarantee optimal performance and system durability. This paper examines the transformational potential of AI-driven predictive maintenance systems, highlighting their ability to prevent system failures, minimize downtime, and enhance resource efficiency. Integrating machine learning algorithms with real-time data analytics allows predictive maintenance frameworks to accurately foresee equipment failures, facilitating timely interventions that reduce the risk of catastrophic infrastructure breakdowns. This study primarily examines the development of cloud-native architectures, which include containers, microservices, and orchestration tools like Kubernetes, to facilitate the scalability, flexibility, and resilience required for contemporary CI maintenance systems. These designs facilitate the seamless integration of predictive maintenance solutions across geographically dispersed infrastructure, enabling effective administration of extensive datasets produced by Internet of Things (IoT) sensors, operational logs, and edge computing nodes. The document examines the essential function of intelligent data orchestration in facilitating the prompt gathering, processing, and analysis of operational data, which is vital for AI models to provide precise predictions. The amalgamation of AI-driven predictive maintenance with 5G and forthcoming 6G networks is poised to transform real-time system monitoring, diminishing latency and enhancing decision-making efficacy. Utilizing AI and cloud-native technologies substantially enhances system reliability, cost-effectiveness, and comprehensive infrastructure optimization. This article thoroughly analyses how AI, cloud-native platforms, and intelligent data orchestration may be utilized to tackle the changing maintenance issues of critical infrastructure by examining real-world case studies from sectors like power grids, telecommunications, and transportation. Integrating AI, cloud computing, and IoT in predictive maintenance improves system reliability and prepares critical infrastructure for future autonomous management and optimization developments. The study finishes by discussing new trends, such as the integration of digital twins and the synergies between AI and cloud-native solutions, which will enhance predictive maintenance capabilities.

AI-Driven Predictive Maintenance in Data Infrastructure: A Multi-Modal Framework for Enhanced System Reliability

This article presents a comprehensive framework for implementing artificial intelligence-driven predictive maintenance in modern data infrastructure environments. While traditional maintenance approaches have relied on reactive or scheduled interventions, the proposed framework leverages multiple AI technologies, including machine learning, natural language processing, and reinforcement learning, to create a proactive maintenance ecosystem. The methodology integrates diverse data streams from infrastructure components, including sensor data, system logs, and historical maintenance records, to predict potential failures and optimize maintenance schedules. The approach combines time series analysis for trend identification, natural language processing for unstructured data analysis, and reinforcement learning for dynamic schedule optimization. Implementation across multiple case studies, including cloud service providers and manufacturing environments, demonstrates significant improvements in system reliability, reduction in unplanned downtime, and optimization of maintenance resource allocation. The results indicate that AI-driven predictive maintenance substantially outperforms traditional approaches in both accuracy and cost-effectiveness. This article contributes to the growing field of intelligent infrastructure management and provides practical guidelines for organizations seeking to enhance their data infrastructure reliability through advanced predictive maintenance strategies.

Event-Driven Architecture: Harnessing Kafka and Spring Boot for Scalable, Real-Time Applications

This comprehensive article explores the transformative impact of Event-Driven Architecture (EDA) in modern financial services, focusing on its implementation using Apache Kafka and Spring Boot. The article examines how financial institutions have revolutionized their transaction processing capabilities through EDA adoption, achieving significant improvements in system performance, reliability, and customer experience. Through a detailed examination of real-world implementations, the analysis demonstrates how EDA has enabled banks to handle unprecedented transaction volumes while substantially reducing system latency and improving resource utilization. The integration of Kafka and Spring Boot has proven particularly effective, with major financial institutions leveraging these technologies to achieve superior performance metrics and system availability. The article further explores critical patterns, including event sourcing, CQRS, and saga patterns, alongside cloud-based best practices for monitoring, performance optimization, and security implementations. By examining various implementation strategies and their outcomes, this article provides a comprehensive framework for building scalable, resilient financial systems that meet the demanding requirements of modern banking operations while ensuring regulatory compliance and maintaining high security and reliability standards.

Optimasi Jaringan Sensor Nirkabel untuk Monitoring Suhu dan Kelembaban

The development of Internet of Things (IoT) technology has provided new opportunities to improve monitoring through the integration of temperature and humidity sensors in wireless networks. This study aims to optimize a wireless sensor network for temperature and humidity monitoring. This study combines an experimental approach with network performance analysis and optimization methods. First, the selection of temperature and humidity sensors is carried out. Next, an efficient and reliable wireless sensor network architecture is designed to collect temperature and humidity data from various locations. The process of sending data from sensors to base stations and integration with IoT platforms are also studied. Furthermore, a series of experiments are conducted to test the performance of the wireless sensor network under real conditions. Analysis of the collected data is used to identify potential improvements in network performance and improve system reliability and responsiveness. The performance parameters evaluated include connection stability, data throughput, energy consumption, and communication latency. The results of this study contribute to the development of a monitoring system that is reliable, efficient, and easy to implement.

Defect Trends in Fire Alarm Systems: A Basis for Risk-Based Inspection (RBI) Approaches

This article presents a comprehensive statistical evaluation of defect frequency in fire alarm systems under real operating conditions, focusing on risk-based factors. The aim is not to introduce a complete RBI approach but rather to assess defect trends that can inform future RBI-based inspection strategies. The study categorizes and evaluates defects by frequency, particularly examining components such as cable and wire systems, acoustic signal devices, and the impact of detector contamination. These findings establish a foundation for developing tailored risk-based inspection and predictive maintenance strategies. A three-stage explanatory research design was employed, analyzing 4629 inspection reports with findings verified through expert surveys and cross-sample analysis. Results indicate that certain components, including acoustic devices and detectors, exhibit a significant increase in defects after 10 years, especially under challenging environmental conditions. Additionally, while ring bus technology supports less frequent functional testing, cable and wire systems require heightened attention in the early operational years. The study also identifies statistically significant trends and their potential for application to a broader system population, supporting enhanced RBI-based maintenance practices. These insights contribute to refining current maintenance approaches and offer practical recommendations for optimizing inspection routines based on risk factors. The article does not propose a system overhaul but lays essential groundwork for further research and improvement in fire alarm system reliability through targeted, risk-informed practices.

Enhancing High-Availability Database Systems: An AI-Driven Approach to Anomaly Detection

High-availability database systems are critical components in modern IT infrastructure, demanding robust mechanisms for ensuring continuous operation and data integrity. This article explores integrating artificial intelligence (AI) techniques into anomaly detection processes for such systems, addressing the limitations of traditional rule-based and statistical methods. We present a comprehensive analysis of machine learning and deep learning approaches, including supervised and unsupervised learning models, autoencoders, recurrent neural networks, and hybrid solutions that combine AI with conventional techniques. The article examines the challenges of implementing AI-powered anomaly detection in high-availability environments, such as scalability, real-time processing, and the balance between sensitivity and specificity. Through case studies in the financial and e-commerce sectors, we demonstrate these advanced detection methods' practical applications and benefits. Our findings indicate that AI-driven approaches significantly enhance the accuracy and efficiency of anomaly detection, leading to improved system reliability and performance. The article concludes by discussing emerging trends, including edge computing and explainable AI, and their potential impact on the future of database management and anomaly detection.

Orchestration Workflows in Distributed Systems: A Systematic Analysis of Efficiency Optimization and Service Coordination

This article presents a comprehensive analysis of orchestration workflows in modern software architectures, examining their role in optimizing service efficiency and coordination across distributed systems. Through a systematic investigation of implementation patterns and operational strategies, we demonstrate how orchestrated workflows enhance service integration, automate complex processes, and improve system reliability. The article employs a mixed-method approach, combining quantitative performance metrics from real-world implementations with qualitative analysis of architectural patterns across diverse enterprise environments. The findings reveal that organizations implementing robust orchestration workflows experienced a 47% reduction in service integration failures, 35% improvement in resource utilization, and 62% faster deployment cycles. The article also identifies critical success factors in orchestration implementation, including dynamic resource management, automated error handling, and comprehensive monitoring frameworks. Furthermore, The article proposes a novel framework for evaluating orchestration effectiveness in cloud-native environments, considering factors such as service mesh integration, container orchestration, and distributed tracing. This article contributes to the growing body of knowledge in service optimization by providing empirical evidence of orchestration benefits and offering practical guidelines for implementing scalable, resilient software systems through advanced workflow orchestration strategies.

Transformative Impact of AI and Cloud Technologies: A Comparative Analysis across Healthcare, Retail, and Mobile Financial Services

This article examines the transformative impact of artificial intelligence (AI) and cloud technologies across healthcare, retail, and mobile financial services sectors. Through a comprehensive analysis of industry-specific applications, we explore how these technologies are revolutionizing operational efficiency, customer experiences, and innovation in each domain. In healthcare, we investigate the role of CI/CD automation and scalable cloud infrastructure in improving system reliability and patient care. The retail sector analysis focuses on AI-driven customer insights and supply chain optimization. For mobile financial services, we examine AI applications in fraud detection and real-time analytics. The findings reveal significant improvements in operational efficiency, decision-making processes, and customer satisfaction across all three industries. However, we also identify unique challenges and opportunities specific to each sector. This article contributes to the growing body of literature on digital transformation and provides valuable insights for industry professionals and policymakers navigating the integration of AI and cloud technologies in their respective fields.

Comprehensive Analysis of Major Fault-to-Failure Mechanisms in Harmonic Drives

The present paper proposes a detailed Failure Mode, Effects, and Criticality Analysis (FMECA) on harmonic drives, focusing on their integration within the UR5 cobot. While harmonic drives are crucial for precision and efficiency in robotic manipulators, they are also prone to several failure modes that may affect the overall reliability of a system. This work provides a comprehensive analysis intended as a benchmark for advancements in predictive maintenance and condition-based monitoring. The results not only offer insights into improving the operational lifespan of harmonic drives, but also provide guidance for engineers working with similar systems across various robotic platforms. Robotic systems have advanced significantly; however, maintaining their reliability is essential, especially in industrial applications where even minor faults can lead to costly downtimes. This article examines the impact of harmonic drive degradation on industrial robots, with a focus on collaborative robotic arms. Condition-Based Maintenance (CBM) and Prognostics and Health Management (PHM) approaches are discussed, highlighting how digital twins and data-driven models can enhance fault detection. A case study using the UR5 collaborative robot illustrates the importance of fault diagnosis in harmonic drives. The analysis of fault-to-failure mechanisms, including wear, pitting, and crack propagation, shows how early detection strategies, such as vibration analysis and proactive maintenance approaches, can improve system reliability. The findings offer insights into failure mode identification, criticality analysis, and recommendations for improving fault tolerance in robotic systems.

Analisis Tingkat Kepuasan Pengguna Aplikasi Pengelolan Persediaan BMD di SMK Negeri 17 Jakarta Menggunakan Metode Service Quality

This study aims to analyze user satisfaction with the inventory management application for Regional-Owned Assets (BMD) at SMK Negeri 17 Jakarta using the SERVQUAL method. The application was implemented to enhance asset management efficiency, but challenges such as data inaccuracies and limited user skills hinder its effectiveness. The SERVQUAL method evaluates five service quality dimensions: tangibles, reliability, responsiveness, assurance, and empathy, by measuring the gap between user expectations and perceptions. The findings reveal that all service quality dimensions have negative GAP values, particularly in reliability and tangibles, indicating that the application has not fully met user expectations. Therefore, improvements in system reliability, application design, and technical training are essential to optimize the use of the application for effective asset management in the school.

Techno-economic analysis of hybrid renewable energy systems for cost reduction and reliability improvement using dwarf mongoose optimization algorithm

The global energy crisis, particularly in isolated and remote regions, has increased interest in renewable energy sources (RESs) to meet growing energy demands. Integrating RESs with energy storage systems offers a promising solution to mitigate fluctuations and intermittency, but concerns about cost and reliability remain. This study explores the optimal design of various microgrid configurations, combining photovoltaic (PV), wind turbine (WT), battery energy storage system (BESS), and diesel generator (DG) systems for Najran city, Saudi Arabia, via real-world meteorological and load demand data. The Dwarf Mongoose Optimization Algorithm (DMOA), alongside the salp swarm algorithm (SSA) and whale optimization algorithm (WOA), was applied to minimize the levelized cost of energy (LCOE) while improving system reliability. The results demonstrate that the PV/BESS configuration, although cost-effective with an LCOE of 0.038 USD/kWh, fail to meet reliability constraints with a loss of power supply probability (LPSP) of 0.679. In contrast, the PV, WT, BESS, and DG configurations achieved an LPSP of 1.9 × 10^--8% with an LCOE of 0.199 USD/kWh, offering a robust and reliable solution for the region's energy needs. This paper presents a novel application of the DMOA for optimizing hybrid renewable energy systems, demonstrating its effectiveness in achieving a balance between cost and reliability. This strategy provides a viable approach for sustainable energy planning in similar regions facing energy challenges.

Optimal scheduling of distributed generation in smart microgrids: A comprehensive model and efficient algorithm

Abstract This study proposes an optimal scheduling model for distributed generation (DG) within smart microgrids, incorporating various distributed energy resources (DERs) such as photovoltaic panels, wind turbines, biomass generators, and energy storage systems. To address the complexities of the scheduling problem, we design a hybrid optimization algorithm combining Genetic Algorithms (GA) and Particle Swarm Optimization (PSO). This hybrid algorithm leverages the global search capabilities of GA and the local search efficiency of PSO to achieve robust and efficient convergence to near-optimal solutions. A comprehensive case study based on a real-world smart microgrid system demonstrates the effectiveness of the proposed model and algorithm. The results indicate significant reductions in total operational costs, enhanced renewable energy utilization, reduced grid dependency, and improved system reliability. This research highlights the potential for broader implementation of the model, contributing to the advancement of smart grid technologies and the transition towards sustainable energy systems.

Reliability Assessment of Power Distribution Cyber–Physical Systems Considering the Impact of Wireless Access Networks

With the rapid increase in the number of various terminal devices in distribution systems, the important impact of communication networks on power supply reliability in cyber–physical distribution systems (CPDSs) is becoming increasingly prominent. The traditional wired communication method makes it difficult to meet the demand in some scenarios due to high cost and construction difficulty. For this reason, this study evaluated the reliability of power distribution cyber–physical systems, considering fifth-generation (5G) mobile communication technology wireless access conditions. First, a reliability model of a communication channel in a 5G communication network was established, and the indirect impact of information system failure on the power distribution system was analyzed. Secondly, a reliability assessment method based on the improved least path method was devised by combining switch action failure, self-healing processing, and load transfer. The simulation results show that 5G communication technology has significant advantages in improving system reliability, and the proposed method is closer to the development direction of future power distribution systems, which provides an effective reference basis for the optimized operation of power distribution cyber–physical systems.

Navigating the digital tax landscape: The impact of service quality factors on E-filing adoption among individual taxpayers in Jakarta

Tax administration digitization improves taxpayer experience through e-filing, supported by service quality, trust, and information technology. This study integrates electronic service quality to understand the decision to use E-filing, offering a comprehensive approach with the E-Filling model to create digital records that are easily accessible. This study analyzes the effect of quality factors on the use of E-filing, with mediation from perceived ease of use and perceived usefulness. The study design uses an explanatory with a causal approach to confirm the relationship between variables related to the use of e-filing by taxpayers in Jakarta. Samples were taken from 10,580,475 taxpayers, with 150 respondents based on certain criteria. Primary data were collected through an online survey using a Likert scale. The measurement model was tested for validity and reliability, as well as structural analysis to assess the relationship between variables using path coefficients and bootstrapping analysis for significance. The coefficient of determination (R²) and path analysis were also conducted to measure the impact of mediating variables. The study shows that of the various service quality factors, only responsiveness has a significant effect on the perception of e-filing usefulness with a T-statistic of 3.253 and a P value of 0.001. Meanwhile, the informativeness, reliability, and system availability factors do not show a significant effect on the perception of ease and usefulness, indicating the need for improvement in information delivery and system reliability. High responsiveness is very important in supporting positive perceptions of the usefulness of the e-filing system. Path analysis shows that neither perceived ease of use nor perceived usefulness affect the actual use of e-filing, with R Square only explaining 2.6% of the variation in use. Although the research model shows an adequate fit with an NFI of 0.786, improvements are still needed to increase e-filing adoption. Thus, focusing on improving responsiveness and optimizing other factors is needed to improve user experience. It is necessary to improve the responsiveness of the e-filing system and improve informativeness, reliability, and system availability to improve user perception. Future research is suggested to develop interventions for service factors that are not yet significant and explore other elements that influence e-filing adoption.

Ceramic matrix composites for corrosion-resistant next-generation nuclear reactor systems: A conceptual review of enhancements in durability against molten salt attack

Ceramic matrix composites (CMCs) are emerging as a key material class for enhancing corrosion resistance in next-generation nuclear reactor systems, particularly in high-temperature molten salt environments. These environments, critical for advanced nuclear reactors such as molten salt reactors (MSRs), present severe challenges, including aggressive chemical attacks that degrade traditional structural materials over time. This conceptual review explores the development and application of CMCs to improve the durability and corrosion resistance of nuclear reactors exposed to molten salt attacks. CMCs, which consist of ceramic fibers embedded in a ceramic matrix, offer significant advantages, such as high thermal stability, mechanical strength, and improved corrosion resistance compared to conventional materials. This review examines how CMCs can be tailored to withstand harsh operational conditions, with a focus on the selection of ceramic phases, fiber-matrix interactions, and innovative fabrication techniques that enhance their protective capabilities. Key challenges addressed include the optimization of composite design to resist molten salt corrosion, the effects of temperature on the material properties, and the long-term stability of CMCs under extreme conditions. Advances in surface treatments, coatings, and the development of hybrid CMC systems are also discussed, highlighting their potential to further enhance durability. The review outlines the use of advanced characterization techniques, such as high-temperature corrosion testing and in situ microscopy, to evaluate CMC performance in molten salt environments. Additionally, it identifies knowledge gaps in current research, emphasizing the need for long-term studies on CMC behavior under realistic reactor conditions. This review concludes by proposing future research directions and technological advancements required to integrate CMCs into next-generation nuclear reactor designs, aiming to improve system reliability and operational safety.

From Monitoring to Observability: A Paradigm Shift in IT Operations

This article explores the paradigm shift from traditional monitoring to observability in IT operations, driven by the increasing complexity of modern distributed systems, data overload, evolving cybersecurity threats, and the need for proactive problem-solving. Observability platforms, built on the four pillars of events, metrics, traces, and logs, provide comprehensive insights into system behavior and performance. Adopting observability practices offers numerous benefits, including automated discovery of system components, dependency mapping, topology visualization, correlative intelligence, faster root cause diagnosis, and more accurate anomaly detection through auto-baselining. Organizations that embrace observability report significant improvements in incident response times, system reliability, and overall operational efficiency. The article guides successfully transitioning to an observability-focused approach by embracing automation, fostering a culture of observability, implementing the right tools, and leveraging AI and machine learning for advanced analytics and insights.

Power substation load forecasting using interpretable transformer-based temporal fusion neural networks

Demand forecasting is one of the biggest challenges facing the power system, given that anticipating future consumption is fundamental to guarantee an adequate supply, without wasting resources or overloading the power grid. Despite numerous techniques developed for this purpose, the unstable nature of historical data makes electricity demand time series highly complex, making forecasting a critical and challenging problem. This work develops and explores the predictive potential of the temporal fusion transformer (TFT), an innovative approach capable of performing temporal fusions and forecasts over different time horizons. This architecture features interpretability capabilities, allowing the understanding of which variables and patterns are most relevant to predictions. It can help identify problems, provide insights and improve system reliability. The efficiency of the proposed model is assessed using historical data on the overall load of the New Zealand Electrical Company, which is made up of two thermoelectric power stations and seven substations. The results highlight the TFT as a promising approach since it shows significant indicators in the forecasts, including the mean absolute percentage error of less than 1.5% along 48 h in advance. The obtained performance metrics underscore the accuracy and robustness of the TFT architecture.

Reliability-constrained configuration optimization for integrated power and natural gas energy systems: A stochastic approach

With the escalating dependence on electricity and natural gas infrastructure, ensuring both reliability and economic efficiency becomes paramount. It necessitates reliability centric measures to mitigate disruptions that could cascade between these interconnected systems. To address this challenges, this paper introduces a reliability-constrained two-stage stochastic model to optimize power-to-gas (P2 G) and gas-to-power (G2P) unit placement and sizing, aiming to enhance the reliability of both systems under stochastic scenarios. The proposed model, employing Sequential Monte Carlo (SMC) within its optimization framework, seeks to minimize investment, operation, and reliability costs. By addressing temporal uncertainties in component outages for both systems and considering uncertainties in power and gas system loads with a high temporal resolution and annual load growth, the model provides a comprehensive reliability perspective. Furthermore, sensitivity analysis is conducted to explore the impact of varying Values of Lost Load (VOLL) on the planning results. Numerical evaluation, using two integrated energy systems including IEEE 14-bus-10-gas node, and large-scale energy systems including IEEE 118-bus-85-gas node integrated power-gas system (IPGS), demonstrates a significant 12.53 % improvement in overall system reliability. Furthermore, a 2.81 % reduction in operation costs and a substantial 26.3 % reduction in reliability costs, validating the effectiveness of the proposed model.

A two-layer strategy for sustainable energy management of microgrid clusters with embedded energy storage system and demand-side flexibility provision

The intermittent nature of renewable energy generation and the fluctuating demands pose persistent challenges in microgrid operations. In response, stakeholders and operators have turned to clustering the geographically adjacent microgrids as a solution. In this context, this paper introduces a novel two-layer energy management strategy for microgrid clusters, utilizing demand-side flexibility and the capabilities of shared battery energy storage (SBES) to minimize operational costs and emissions, while ensuring a spinning reserve within individual microgrids to prevent load-shedding. In the lower layer, the proposed approach devises optimal day-ahead operation policies, while the upper layer employs a cooperative strategy to further optimize the operational efficiency across the entire cluster. The energy management problem is accurately formulated as a mixed integer quadratic programming (MIQP) optimization, which incorporates linear terms in the problem's constraints. The formulation accounts for operational costs associated with SBES including expenses of charging/discharging and changes in operating states (CiOS). Real-world case studies with a cluster of three microgrids in Australia validate the effectiveness of this approach. Results show a reduction in operational costs for the base case scenario by 6.96 % compared to conventional microgrid management strategies. Sensitivity analyses further demonstrate the economic benefits of varying SBES capacity and flexibility pricing, with savings ranging from 6.5 % to 8.1 %. The proposed strategy also reduces CO2 emissions by up to 11.6 %, while improving system reliability. This strategy holds promise for integration into distributed energy systems with high renewable penetration and clustered local grids, offering significant advantages for utility operators and end-users through improved energy efficiency and reduced emissions.

The Calibrated Safety Constraints Optimal Power Flow for the Operation of Wind-Integrated Power Systems

As the penetration of renewable energy sources (RESs), particularly wind power, continues to rise, the uncertainty in power systems increases. This challenges traditional optimal power flow (OPF) methods. This paper proposes a Calibrated Safety Constraints Optimal Power Flow (CSCOPF) model that uses the Improved Acceleration Coefficient-Based Bee Swarm algorithm (IACBS) in combination with the equivalent current injection (ECI) model. The proposed method addresses key challenges in wind-integrated power systems by ensuring preventive safety scheduling and enabling effective power incident safety analysis (PISA). This improves system reliability and stability. This method incorporates mixed-integer programming, with continuous and discrete variables representing power outputs and control mechanisms. Detailed numerical simulations were conducted on the IEEE 30-bus test system, and the feasibility of the proposed method was further validated on the IEEE 118-bus test system. The results show that the IACBS algorithm outperforms the existing methods in both computational efficiency and robustness. It achieves lower generation costs and faster convergence times. Additionally, the CSCOPF model effectively prevents power grid disruptions during critical incidents, ensuring that wind farms remain operational within predefined safety limits, even in fault scenarios. These findings suggest that the CSCOPF model provides a reliable solution for optimizing power flow in renewable energy-integrated systems, significantly contributing to grid stability and operational safety.