Search Results (3,788)

This review examined the latest advances in the modeling, analysis, and control of AC/DC power systems based on artificial intelligence (AI) in which renewable energy sources play a significant role. Integrating variable and intermittent renewable energy sources (such as sunlight and wind power) poses a major challenge in maintaining system stability, reliability, and optimal system performance. Traditional modeling and control methods are increasingly inadequate to capture the complex, nonlinear, and dynamic behavior of modern hybrid AC/DC systems. Specialized AI techniques, such as machine learning (ML) and deep learning (DL), and hybrid models, have become important tools to meet these challenges. This article presents a comprehensive overview of AI-based methodologies for system identification, fault diagnosis, predictive control, and real-time optimization. Particular attention is paid to the role of AI in increasing grid resilience, implementing adaptive control strategies, and supporting decision-making under uncertainty. The review also highlights key breakthroughs in AI algorithms, including federated learning, and physics-based neural networks, which offer scalable and interpretable solutions. Furthermore, the article examines current limitations and open research problems related to data quality, computational requirements, and model generalizability. Case studies of smart grids and comparative scenarios demonstrate the practical effectiveness of AI-based approaches in real-world energy system applications. Finally, it proposes future directions to narrow the gap between AI research and industrial application in next-generation smart grids. Full article

Accurate and up-to-date data on built-up areas are crucial for urban planning, disaster management, and sustainable development, yet Romania still lacks a unified, official database. In this study we integrated the three widely used global data sources—OpenStreetMap (OSM), Microsoft Building Footprints (MSBFs), and Global Human Settlement Layer Built-up surface (GHS)—onto a 10 m resolution raster grid and applied this consistently at the national scale across 3181 settlement polygons to produce a more accurate, unified ensemble model for Romania. The methodological basis was Triple Collocation Analysis (TCA), extended with ETC/CTC to estimate per-settlement scale factors, enabling the quantification and optimal weighting of the relative errors and accuracy in the absence of independent reference data. Weight patterns vary by settlement type: OSM receives relatively higher weights in smaller rural settlements with less redundant error; in municipalities the stronger OSM–MSBF correlation reduces both of their weights and increases the GHS share; cities exhibit a more balanced weighting. At cell level, the ensemble provides uncertainty quantification via confidence intervals that typically range from 2% to 14% at settlement scale. The resulting model—like any model—does not perfectly reflect reality; however, the ensemble improves the accuracy and timeliness of the available data. The resulting model is replicable and updatable with newer data, making it suitable for numerous practical applications, especially in spatial development and risk analysis. Full article

The emergence of mobile private networks (MPNs) has enabled tailored communication solutions for industries, enterprises, and specialized applications, fostering improved control, security, and flexibility. With the rapid advancements in software-defined radio (SDR) platforms, implementing MPNs using cost-effective and versatile hardware has become increasingly feasible. Analyzing the radio coverage of such networks is critical for optimizing performance, ensuring reliable connectivity, and addressing site-specific challenges in deployment. This paper investigates the radio coverage of a 4G MPN implemented using as radio front-end an SDR platform from the Universal Software Radio Peripheral (USRP) family and the srsRAN-4G open-source software suite. Using the HTZ Communication software as simulation tool and field-test measurements performed using an off-the-shelf mobile phone as user equipment (UE), an analysis is made to evaluate the accuracy of various propagation models in predicting network coverage, in several different frequency bands. The results provide valuable insights into the design and deployment of MPNs, highlighting the importance of accurate coverage estimation in achieving robust and efficient network operation. Full article

Event-Sourced Systems (ESSs) that adopt Domain-Driven Design (DDD) are becoming more popular because of their intuitive business process modeling and improved auditability, scalability, and flexibility. However, ensuring the correctness of domain models—particularly event-sourced aggregates (ESAs)—remains challenging. To address this, we propose root contracting, a novel, constrained, and lightweight adaptation of Design by Contract (DbC), specifying the precondition, postcondition, and class invariant exclusively at aggregate roots. Root contracting simplifies correctness enforcement by leveraging DDD principles aligned with DbC and the standardized ESA code structure. We offer uContract, a Java open-source utility that realizes root contracting, enabling automated verification of ESAs with configurable runtime overhead. Through performance evaluation and methodological discussion, we demonstrate that root contracting effectively bridges formal correctness with practical domain modeling. Our approach provides developers with a tool to streamline development workflows, potentially reducing testing overhead and supporting integration with methodologies like Behavior-Driven Development (BDD). Full article

Insulator defect detection in power inspection tasks faces significant challenges due to the large variations in defect sizes and complex backgrounds, which hinder the accurate identification of both small and large defects. To overcome these issues, we propose a novel dual-branch YOLO-based algorithm (DB-YOLO), built upon the YOLOv11 architecture. The model introduces two dedicated branches, each tailored for detecting large and small defects, respectively, thereby enhancing robustness and precision across multiple scales. To further strengthen global feature representation, the Mamba mechanism is integrated, improving the detection of large defects in cluttered scenes. An adaptive weighted CIoU loss function, designed based on defect size, is employed to refine localization during training. Additionally, ShuffleNetV2 is embedded as a lightweight backbone to boost inference speed without compromising accuracy. We evaluate DB-YOLO on the following three datasets: the open source CPLID, a self-built insulator defect dataset, and GC-10. Experimental results demonstrate that DB-YOLO achieves superior performance in both accuracy and real-time efficiency compared to existing state-of-the-art methods. These findings suggest that the proposed approach offers strong potential for practical deployment in real-world power inspection applications. Full article

Background: Cryptococcosis, a systemic mycosis, remains a neglected disease in Brazil due to the absence of systematic national surveillance. This study developed an interactive dashboard to analyze cryptococcosis-related deaths (2000–2022) and forecast trends through regional ARIMA modeling. Methodology: The Cross-Industry Standard Process for Data Mining framework was employed to extract mortality data from the Brazilian Mortality Information System, utilizing the microdatasus package in R Studio software, with R version 3.4.0. The records were then filtered using the International Classification of Diseases, Tenth Revision codes (B45 series) to identify primary and associated causes of death. After data extraction, a series of data preprocessing steps was implemented, including deduplication, variable recoding, and the management of missing values. The Shiny framework was employed to construct an interactive dashboard, incorporating Plotly and DT packages, with time-series visualizations, demographic variables, and multilingual support (Portuguese/English). Results: Among 12,308 deaths (2227 primary; 10,081 associated causes), most occurred in males aged 21–60 years. Data completeness was high for age/residence (100%) but lower for education (82%). The dashboard enables dynamic exploration of trends, demographic patterns, and open-data downloads. Regional ARIMA models revealed heterogeneous forecasts, with the Southeast projecting a decline (193 deaths in 2025; 95% CI: 146–240) and the South showing stability (141 deaths; 95% CI: 109–173). Conclusions: This tool bridges a critical gap in cryptococcosis surveillance, enabling dynamic mortality trend analysis, identification of high-risk demographics, and regional forecasting to guide public health resource allocation. While the absence of HIV serostatus data limits etiological analysis, the dashboard’s open-source framework supports adaptation for other neglected diseases. Full article

With the large-scale integration of single-phase distributed photovoltaic systems into distribution grids, issues such as mismatched generation and load, overvoltage, and three-phase imbalance may arise in the distribution network. A multi-objective optimization method for flexible distribution networks incorporating a four-leg soft open point (F-SOP) is proposed based on fuzzy chance constraints. First, a mathematical model for the F-SOP’s loss characteristics and power control was established based on the three-phase four-arm topology. Considering the impact of source load uncertainty on voltage regulation, a multi-objective complementary voltage regulation architecture is proposed based on fuzzy chance constraint programming. This architecture integrates F-SOP with conventional reactive power compensation devices. Next, a multi-objective collaborative optimization model for distribution networks is constructed, with network losses, overall voltage deviation, and three-phase imbalance as objective functions. The proposed model is linearized using second-order cone programming. Finally, using an improved IEEE 33-node distribution network as a case study, the effectiveness of the proposed method was analyzed and validated. The results indicate that this method can reduce network losses by 30.17%, decrease voltage deviation by 46.32%, and lower three-phase imbalance by 57.86%. This method holds significant importance for the sustainable development of distribution networks. Full article

In this paper, a generic computational framework, based on the generalized-mode approach, is developed for the fully coupled time-domain aero-hydro-servo-elastic analysis of Hybrid Offshore Wind and Wave Energy Systems (HOWiWaESs), consisting of a Floating Offshore Wind Turbine (FOWT) and several wave energy converters (WECs) mechanically connected to it. The FOWT’s platform and the WECs of the HOWiWaES are modeled as a single floating body with conventional rigid-body modes, while the motions of the WECs relative to the FOWT are described as additional generalized modes of motion. A numerical tool is established by appropriately modifying/extending the OpenFAST source code. The frequency-dependent exciting forces and hydrodynamic coefficients, as well as hydrostatic stiffness terms, are obtained using the traditional boundary integral equation method, whilst the generalized-mode shapes are determined by developing appropriate 3D vector shape functions. The tool is applied for a 5 MW FOWT with a spar-type floating platform and a conic WEC buoy hinged on it via a mechanical arm, and results are compared with those of other investigators utilizing the multi-body approach. Two distinctive cases of a pitching and a heaving WEC are considered. A quite good agreement is established, indicating the potential of the developed tool to model floating HOWiWaESs efficiently. Full article

To accurately assess the seismic risk of bridges, this study systematically conducted probabilistic seismic hazard–fragility–risk assessments using a reinforced concrete continuous girder bridge as a case study. First, the CPSHA method from China’s fifth-generation seismic zoning framework was employed to calculate the Peak Ground Acceleration (PGA) with 2%, 10%, and 63% exceedance probabilities over 50 years as 171.16 gal, 98.10 gal, and 28.61 gal, respectively, classifying the site as being with 0.10 g zone (basic intensity VII). Second, by innovatively integrating the Response Surface Method with Monte Carlo simulation, the study efficiently quantified the coupled effects of structural parameter and ground motion uncertainties, a finite element model was established based on OpenSees, and the seismic fragility curves were plotted. Finally, the risk probability of seismic damage was calculated based on the seismic hazard curve method. The results demonstrate that the study area encompasses 46 potential seismic sources according to China’s fifth-generation zoning. The seismic fragility curves clearly show that side piers and their bearings are generally more susceptible to damage than middle piers and their bearings. Over 50 years, the pier risk probabilities for the intact, slight, moderate, severe damage, and collapse are 68.90%, 6.22%, 15.75%, 7.86%, and 1.27%, while the corresponding probabilities of bearing are 3.54%, 44.11%, 25.64%, 7.74%, and 18.97%, indicating significantly higher bearing risks at the moderate damage and collapse levels. The method proposed in this study is applicable to various types of bridges and has high promotion and application value. Full article

Network traffic analysis is crucial for understanding network behavior and identifying underlying applications, protocols, and service groups. The increasing complexity of network environments, driven by the evolution of the Internet, poses significant challenges to traditional analytical approaches. Graph Neural Networks (GNNs) have recently garnered considerable attention in network traffic analysis due to their ability to model complex relationships within network flows and between communicating entities. This scoping review systematically surveys major academic databases, employing predefined eligibility criteria to identify and synthesize key research in the field, following the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) methodology. We present a comprehensive overview of a generalized architecture for GNN-based traffic analysis and categorize recent methods into three primary types: node prediction, edge prediction, and graph prediction. We discuss challenges in network traffic analysis, summarize solutions from various methods, and provide practical recommendations for model selection. This review also compiles publicly available datasets and open-source code, serving as valuable resources for further research. Finally, we outline future research directions to advance this field. This work offers an updated understanding of GNN applications in network traffic analysis and provides practical guidance for researchers and practitioners. Full article

The intelligence of sustainable design is reflected in the demands for accurate and real-time environmental impact assessments; traditional LCA methods are slow and static. In this paper, we propose a novel deep learning framework that serially links Shuffle-GhostNet (a lightweight convolutional neural network employing a combination of Ghost and Shuffle modules) improved by an enhanced version of Hippopotamus Optimizer (EHHO) for hyperparameter tuning and enhanced convergence. Upon testing the model on the Ecoinvent and OpenLCA Nexus datasets, pronounced advantages in predicting CO₂ emissions, energy use, and other sustainability indicators were found. Coupling the integration of multi-source sensor data and optimizing the architecture via metaheuristic search enables rapid and reliable decision support on eco-design. Final results are significantly better than the baseline models, achieving an R² of up to 0.943 with actual performance gains. AI-driven modeling integrated with LCA constitutes a pathway toward dynamic and scalable sustainability assessment in Industry 4.0 and circular economy applications. Full article

Quantitative reliability evaluation is essential for optimizing control policies and maintenance strategies in complex industrial systems. While Reliability Block Diagrams (RBDs) are a natural formalism for modeling these hierarchical systems, modern applications require highly efficient, online reliability assessment on resource-constrained embedded hardware. This demand presents two fundamental challenges: developing algorithmically efficient RBD evaluation methods that can handle diverse custom distributions while preserving numerical accuracy, and ensuring platform-agnostic performance across diverse multicore architectures. This paper investigates these issues by developing a new version of the librbd open-source RBD library. This version includes advances in efficiency of evaluation algorithms, as well as restructured computation sequences, cache-aware data structures to minimize memory overhead, and an adaptive parallelization framework that scales automatically from embedded processors to high-performance systems. Comprehensive validation demonstrates that these advances significantly reduce computational complexity and improve performance over the original implementation, enabling real-time analysis of substantially larger systems. Full article

Adapting open-source large language models (LLMs) to specialized domains remains a critical challenge due to domain knowledge gaps, data scarcity, and reference hallucination. Existing approaches often neglect the structural characteristics of domain knowledge and fail to provide principled estimations of knowledge scope, resulting in data homogenization and suboptimal adaptation, while leaving reference hallucination unmitigated. This paper introduces BOLT(Building Open-source LLMs for your Target domain), a modular end-to-end framework that tailors open-source LLMs for domain-specific scenarios. BOLT systematically estimates domain scope, constructs structured hierarchical knowledge trees, distills diverse and semantically aligned training data from advanced teacher LLMs, and employs curriculum learning for progressive model optimization. To address reference hallucination, BOLT substitutes generative methods, which are susceptible to hallucinations, with a matching-based strategy, thereby alleviating the problem and significantly improving reference recommendation accuracy. Extensive experiments across diverse domains and models demonstrate that BOLT enables the efficient modeling of structured hierarchical domain knowledge and effectively enhances reference recommendation accuracy while preserving both training efficiency and robustness throughout the adaptation process. Full article

Water scarcity is a relevant issue whose impact can be mitigated through sustainable solutions. Humidification–dehumidification (HDH) cycles powered by photovoltaic thermal (PVT) modules enable pure water production in remote areas. In this study, models have been developed and validated for the main components of the system, the humidifier and the dehumidifier. A unique HDH-PVT prototype was built and experimentally tested at the SolarTech Lab of Politecnico di Milano in Milan, Italy. The experimental system is a Closed Air Closed Water—Water Heated (CACW-WH) that mimics a Closed Air Open Water—Water Heated (CAOW-WH) cycle through brine cooling, pure water mixing, and recirculation, avoiding a continuous waste of water. Tests were performed varying the mass flow ratio (MR) between 0.346 and 2.03 during summer and autumn in 2023 and 2024. The experimental results enabled the verification of the developed models. The optimal system performance was obtained for an MR close to 1 and a maximum cycle temperature of $44 °\mathrm{C}$, enabling a 0.51 gain output ratio (GOR) and 0.72% recovery ratio (RR). The electrical and thermal energy generation of the PVT modules satisfied the whole consumption of the system enabling pure water production exploiting only the solar resource available. The PVT-HDH system proved the viability of the proposed solution for a sustainable self-sufficient desalination system in remote areas, thus successfully addressing water scarcity issues exploiting a renewable energy source. Full article

There has been a growing demand for clean energy in recent years, with the advancement of the carbon neutrality vision. Wind power has occupied a significant percentage of clean energy sources. Usually deployed in open fields, on mountaintops, and in offshore areas, wind turbines are particularly vulnerable to lightning strikes due to their unique operational characteristics. Therefore, accurately evaluating the lightning strike risk of wind turbines is an important issue that should be addressed. Current IEC standards lack a physically grounded approach for calculating the equivalent collection area, leading to an overestimation of this value. This paper employs an upward leader initiation model to develop a novel calculation method for the equivalent collection area of wind turbines. By considering the impact of upward leader channel initiation and development, the model demonstrates accuracy through comparison with observational data (0.7761 strikes/year), showing only a −7.1% discrepancy. This study also examines the impact of various blade rotation angles, stepped leader speeds, and peak current of the return stroke on the equivalent collection area. Results indicate that the lightning strike distance specified in IEC standards underestimates the equivalent collection area due to neglecting the upward leader channel, resulting in significant differences compared to our approach, with a maximum deviation of up to 313.12%. Full article