Search Results (702)

In large wind farms, uneven voltage distribution caused by feeder impedance and turbine spacing may pose safety hazards and reduce operational efficiency. This paper proposes a two-layer voltage coordination optimal control method for wind farms that balances both grid-connection point voltage levels and turbine-end voltage safety. The outer layer tracks voltage commands issued by the AVC master station at the point of common coupling (PCC), while the inner layer establishes a global optimization model considering generator terminal voltage safety. The second-order cone relaxation method converts nonlinear constraints into solvable convex forms. Through a two-layer iterative solution, it achieves optimal allocation of active and reactive power between wind turbines and static var compensators (SVGs) within the field, thereby enhancing the active power output at the wind farm port and increasing the system’s reactive power margin. Simulation results demonstrate that compared to conventional unified power factor control, the proposed method effectively enhances terminal voltage security, increases wind farm power generation, and boosts system reactive power reserve capacity while stably tracking PCC voltage commands. Full article

Photovoltaic (PV) systems are vital to contemporary renewable energy generation systems. However, complex operating conditions, such as variable loads, grid uncertainty, and unstable sunlight, pose a serious threat to the stability of the power system integrated with PV generation. To maintain stable operation under such conditions, PV systems must dynamically regulate their power output through a boost converter, thereby preventing excessive DC bus voltage and power levels. This article first summarizes practical control requirements for PV systems under complex operating conditions and subsequently proposes a multi-objective control method for boost converters in PV applications to enhance system adaptability. The proposed strategy enables seamless transitions between operating modes, including DC-link voltage control, current control, power control, and maximum power point tracking (MPPT). The dynamic behavior of the control method during mode switching is theoretically analyzed. Simulation results verify the correctness of the analysis and demonstrate the effectiveness of the proposed method under challenging PV operating conditions. Full article

This paper addresses the limitations of conventional single-stage direct-control maximum power point tracking (MPPT) methods, such as the Perturb and Observe (P&O) algorithm. Fixed-step-size duty-cycle perturbations cause a trade-off between slow tracking with small oscillations and fast tracking with large oscillations, along with poor responsiveness to rapid weather variations and output voltage fluctuations. Two main contributions are presented. First, a fractional-order DC–DC boost converter (FOBC) is introduced, incorporating fractional-order dynamics to enhance system performance beyond improvements in control algorithms alone. Second, a novel indirect-control MPPT strategy based on a two-stage architecture is developed, where the P&O algorithm generates the optimal voltage reference and a fractional-order linear-quadratic-integral (FOLQI) controller—designed using a fractional-order small-signal model—regulates the PV module voltage to generate the FOBC duty cycle. Hardware-in-the-loop simulations confirm substantial performance improvements. The proposed FOLQI-based indirect-control approach with FOBC achieves a maximum MPPT efficiency of 99.26%. An alternative indirect method using a classical linear-quadratic-integral (LQI) controller with an integer-order boost converter reaches 98.38%, while the conventional direct-control P&O method achieves only 94.21%, demonstrating the superiority of the proposed fractional-order framework. Full article

Short-term load forecasting (STLF) underpins the efficient and secure operation of power systems. This study develops and evaluates a hybrid architecture that couples deep neural networks (DNNs) with support vector regression (SVR) for national-scale day-ahead STLF using Croatian load data from 2006 to 2022. The approach employs an hour-specific framework of 24 hybrid models: each DNN learns a compact nonlinear representation for a given hour, while an SVR trained on the penultimate layer activations performs the final regression. Gradient-boosting-based feature selection yields compact, informative inputs shared across all model variants. To overcome limitations of historical local measurements, the framework integrates global numerical weather prediction data from the TIGGE archive with load and local meteorological observations in an operationally realistic setup. In the held-out test year 2022, the proposed hybrid consistently reduced forecasting error relative to standalone DNN-, LSTM- and Transformer-based baselines, while preserving a reproducible pipeline. Beyond using SVR as an alternative output layer, the contributions are as follows: addressing a 17-year STLF task, proposing an hour-specific hybrid DNN–SVR framework, providing a systematic comparison with deep learning baselines under a unified protocol, and integrating global weather forecasts into a practical day-ahead STLF solution for a real power system. Full article

Aviation hydrogen internal combustion engines represent a critical pathway for rapid decarbonization due to their reliability and compatibility with existing aircraft platforms. However, the significant reduction in air density at high altitudes causes severe power degradation in naturally aspirated port-fuel-injected hydrogen internal combustion engines, making turbocharging essential for maintaining propulsion capability. This study utilizes a combined experimental and simulation framework to investigate turbocharger matching for power recovery in a 1.4 L hydrogen engine. A simulation model was constructed and validated against experimental data within a 5% error margin to ensure technical accuracy. Theoretical compressor and turbine operating parameters were derived for altitudes ranging from 4 to 8 km, comparing two boost-pressure control strategies: variable geometry turbine and waste-gate turbine. The results demonstrate that both boosting strategies successfully restore sea-level power at altitudes up to 8 km, increasing high-altitude power output by approximately four-fold to five-fold compared to naturally aspirated conditions. Specifically, the variable of geometry turbine demonstrates superior overall performance, maintaining normalized turbine efficiencies between 78.4% and 96.3% while achieving lower pumping losses and improved brake thermal efficiency. These advantages arise from the variable geometry turbine’s ability to optimize exhaust-energy utilization across varying altitudes. This study establishes a quantitative methodology for turbocharger matching, providing essential guidance for developing efficient, high-altitude hydrogen propulsion systems. Full article

Background: The implementation of Large Language Models (LLMs) in software engineering has provided new and improved approaches to code synthesis, testing, and refactoring. However, even with these new approaches, the practical efficacy of LLMs is restricted due to their reliance on user-given prompts. The problem is that these prompts can vary a lot in quality and specificity, which results in inconsistent or suboptimal results for the LLM application. Methods: This research therefore aims to alleviate these issues by developing an LLM-based code assistance prototype with a framework based on Retrieval-Augmented Generation (RAG) that automates the prompt-generation process and improves the outputs of LLMs using contextually relevant external knowledge. Results: The tool aims to reduce dependence on the manual preparation of prompts and enhance accessibility and usability for developers of all experience levels. The tool achieved a Code Correctness Score (CCS) of 162.0 and an Average Code Correctness (ACC) score of 98.8% in the refactoring task. These results can be compared to those of the generated tests, which scored CCS 139.0 and ACC 85.3%, respectively. Conclusions: This research contributes to the growing list of Artificial Intelligence (AI)-powered development tools and offers new opportunities for boosting the productivity of developers. Full article

Background/Objectives: Subjective refraction is the clinical gold standard but is time-consuming and examiner-dependent. Most artificial intelligence (AI)-based approaches rely on specialized imaging or biometric data not routinely available. This study aimed to predict subjective refraction using only routine, non-cycloplegic autorefraction and keratometric data and to identify factors associated with reduced prediction accuracy. Methods: This retrospective study included 1856 eyes from 1006 patients. A multi-output histogram gradient-boosting model predicted subjective spherical equivalent, cylindrical power, and astigmatic axis. Performance was evaluated on an independent test dataset using R² and mean absolute error, with circular statistics for axis prediction. Prediction failure was assessed using clinically relevant tolerance thresholds (sphere/cylinder ≤ 0.50 D; axis ≤ 10°) and multivariable logistic regression. Results: The model achieved high accuracy for spherical and cylindrical prediction (R² = 0.987 and 0.933; MAE = 0.126 D and 0.137 D). Astigmatic axis prediction demonstrated strong circular agreement (ρ = 0.898), with a mean absolute angular error of 4.65° (median, 0.96°). Axis errors were higher in eyes with low cylinder magnitude (<0.75 D) and oblique astigmatism. In multivariable analysis, steeper keratometry (K2; OR = 7.25, 95% CI 1.62–32.46, p = 0.010) and greater objective cylindrical power (OR = 2.79, 95% CI 1.87–8.94, p = 0.032) were independently associated with poor prediction. Conclusions: A machine-learning model based solely on routine, non-cycloplegic autorefractor and keratometric measurements can accurately estimate subjective refraction, supporting AI as a complementary decision-support tool rather than a replacement for conventional subjective refraction. Full article

Accurate short-term forecasting of solar photovoltaic (PV) power output is essential for efficient grid integration and energy management, especially given the widespread global adoption of PV systems. To address this research gap, the present study introduces a scalable, interpretable ensemble learning model of PV power prediction with respect to a large PVOD v1.0 dataset, which encompasses more than 270,000 points representing ten PV stations. The proposed methodology involves data preprocessing, feature engineering, and a hybrid ensemble model consisting of Random Forest, XGBoost, and CatBoost. Temporal features, which included hour, day, and month, were created to reflect the diurnal and seasonal characteristics, whereas feature importance analysis identified global irradiance, temperature, and temporal indices as key indicators. The hybrid ensemble model presented has a high predictive power, with an R² = 0.993, a Mean Absolute Error (MAE) = 0.227 kW, and a Root Mean Squared Error (RMSE) = 0.628 kW when applied to the PVOD v1.0 dataset to predict short-term PV power. These findings were achieved on standardized, multi-station, open access data and thus are not in an entirely rigorous sense comparable to previous studies that may have used other datasets, forecasting horizons, or feature sets. Rather than asserting numerical dominance over other approaches, this paper focuses on the real utility of integrating well-known tree-based ensemble techniques with time-related feature engineering to derive real, interpretable, and computationally efficient PV power prediction models that can be used in smart grid applications. This paper shows that a mixture of conventional ensemble methods and extensive temporal feature engineering is effective in producing consistent accuracy in PV forecasting. The framework can be reproduced and run efficiently, which makes it applicable in the integration of smart grid applications. Full article

Microbial fuel cells (MFCs) are a promising technology for simultaneously treating wastewater and recovering energy, yet scaling them from lab prototypes to practical systems poses persistent challenges. This review addresses the scale-up gap by systematically examining recent pilot-scale MFC studies from multiple perspectives, including reactor design configurations, materials innovations, treatment performance, energy recovery, and environmental impact. The findings show that pilot MFCs reliably achieve significant chemical oxygen demand (COD) removal (often 50–90%), but power densities remain modest (typically 0.1–10 W m⁻³)—far below levels needed for major energy generation. Key engineering advances have improved performance; modular stacking maintains higher power output, low-cost electrodes and membranes reduce costs (with some efficiency trade-offs), and power-management strategies mitigate issues like cell reversal. Life cycle assessments indicate that while MFC systems can outperform conventional treatment in specific scenarios, overall sustainability gains depend on boosting energy yields and optimizing materials. The findings highlight common trade-offs and emerging strategies. By consolidating recent insights, a roadmap of design principles and research directions to advance MFC technology toward sustainable, energy-positive wastewater treatment was outlined. Full article

Virtual synchronous machine (VSG) technology provides a robust framework for integrating electric vehicle energy storage into modern microgrids. Nonetheless, conventional VSG control often suffers from intense interaction between active and reactive power flows, which can trigger persistent steady-state errors, power fluctuations, and potential system collapse. This research addresses these challenges by developing a 5th-order electromagnetic dynamic model tailored for a two-stage cascaded bridge inverter. By synthesizing a 3rd-order power regulation loop with a 2nd-order output stage, the proposed model captures stability boundaries across an extensive parameter spectrum. Unlike traditional 3rd-order “quasi-steady-state” approaches—which overlook essential dynamics under weak-damping or low-inertia conditions—this study utilizes the 5th-order model to derive an adaptive dynamic virtual impedance decoupling technique. This strategy facilitates real-time compensation of the cross-coupling between active and reactive channels, significantly boosting the inverter’s damping ratio. Quantitative analysis confirms that this approach curtails overshoot by 85.6% and accelerates the stabilization process by 42%, markedly enhancing the overall dynamic performance of the grid-connected system. Full article

This study presents a pulley-buoy-accelerated linear wave power generation system and verifies its feasibility and effectiveness through experimental research. Compared with traditional wave power generation systems that rely on three-stage energy conversion, the proposed system eliminates intermediate energy transfer and conversion links, enabling direct extraction of electrical energy from wave-induced motion. Additionally, by incorporating a pulley assembly, the system amplifies the buoy’s motion speed. This enhancement boosts the power output of the linear generator and improves the system’s overall wave energy conversion efficiency. Under laboratory conditions, a small-scale prototype of the system and a swing-type wave generator were constructed. Experimental tests were conducted to examine how three key factors influence the system’s power generation performance: the number of stator coils, wave conditions (wave height and wavelength), and buoy size. The results indicate that three measures can effectively improve both the wave energy conversion efficiency and power generation performance of the pulley-buoy-accelerated system: increasing the number of stator coils, increasing wave height and wavelength, and moderately enlarging the buoy size. These findings offer valuable insights for the practical application and efficient operation of wave power generation systems. Full article

In this paper, a permanent-magnet-assisted synchronous reluctance motor (SYNRM) coupled with a newly built QDBC and a voltage-fed inverter (VFI) for a standalone PV water pumping system is suggested. Because power supply oscillations can result in short-term disruptions that affect drive performance in industrial applications involving these motors, a robust smooth control system is required to guarantee high efficiency and uninterrupted operation. According to the suggested architecture, a newly built quadratic boost regulator with a very high voltage gain, called a quadruple-diode boost converter (QDBC), is used to first elevate PV voltage to high levels. Additionally, to optimize the power output of the solar PV module, the perturbation and observation highest power point tracking approach (P&O) is implemented. To provide smooth synchronous motor starting, field-oriented control (FOC) of a voltage-fed inverter (VFI) is combined with hysteresis current control of the QDBC. The optimization algorithms discussed in this paper aim to enhance the efficiency of the SYNRM, particularly in operating a synchronous motor powered by variable energy sources such as solar PV. These algorithms function within a cybernetic system designed for water pumping, incorporating feedback loops and computational intelligence for improved performance. Afterward, the three-phase permanent-magnet synchronous motor that drives the mechanical load is fed by the resulting voltage via a voltage source inverter. Furthermore, a thorough hysteresis current control method implementation of the QDBC was suggested in order to attain optimal efficiency in both devices, which is crucial when off-grids are present. Even when the DC-link voltage dropped by up to 10% of the rated voltage, the suggested method was shown to maintain the required reference torque and rated speed. To verify the efficacy of the suggested method, a simulation setup according to the MATLAB 2022b/Simulink environment was employed. To gather and analyze the data, multiple scenarios with varying operating conditions and irradiance levels were taken into consideration. Finally, a working prototype was constructed in order to validate the mathematical analysis and simulation findings of the suggested framework, which includes a 1 kW motor, current sensor, voltage sensor, QDBC, and VCS inverter. Full article

To ensure reliable and accurate short-term photovoltaic power generation prediction, this study introduces an integrated forecasting framework that combines the gradient boosting paradigm with a dendritic neural structure, termed Gradient Boosting Multi-Bias Dendritic Units Integrated in a Fully Connected Neural Network (GBMDF). The proposed GBMDF algorithm minimizes prediction deviations by progressively capturing the nonlinear mappings between residual predictions and environmental variables through an iterative error-correction process. Compared with traditional data-driven learning algorithms, GBMDF can comprehensively utilize multiple meteorological inputs while maintaining strong interpretability and analytical transparency. Furthermore, leveraging the flexibility of the GBMDF, the prediction accuracy of existing models is improved through a proposed compensation enhancement technique. Under this mechanism, GBMDF is trained to offset the residual differences in alternative predictors by examining the correlations between the error patterns of alternative predictors and weather attributes. This enhancement method features a simple concept and effective practical performance. Validation experiments confirm that GBMDF not only achieves higher accuracy in photovoltaic output prediction but also improves the overall efficiency of other forecasting methods. Full article

Fuel cell commercial vehicles are widely used in commercial transport for their high efficiency and long range. However, in mixed operating scenarios, their energy economy and fuel cell operational stability cannot be fully balanced. Traditional strategies lack adaptability in mixed operating scenarios. Therefore, based on the equivalent factor regulation formula of the Adaptive Equivalent Hydrogen Consumption Minimization Strategy (A-ECMS) and the improved Sparrow Search Algorithm-Long Short-Term Memory (SSA-LSTM) hybrid model, short-term speed prediction and three-stage speed interval division are embedded into the equivalent factor regulation logic. A dynamic equivalent factor regulation strategy integrating SOC deviation is constructed, and an improved Predictive Equivalent Hydrogen Consumption Minimization Strategy (P-ECMS) is finally derived. The SSA-LSTM algorithm is optimized via constrained hyperparameter tuning for short-term speed prediction. A time-decay weighting mechanism enhances recent speed data weight, with weighted results as inputs to boost accuracy. Moving Average Residual Correction (MARC) is used to verify the speed prediction model accuracy and correct residuals. Multi-scenario tests show that the SSA-LSTM model outperforms the Gated Recurrent Unit (GRU) model in prediction accuracy and generalization ability, providing reliable data support for segmented regulation. With battery SOC deviation and the SSA-LSTM-predicted speed trend as core inputs, combined with three-stage speed interval division, A-ECMS’s equivalent factor regulation formula is improved. The model adopts a segmented dynamic regulation logic to integrate dual factors into equivalent factor adjustment, and it reasonably adjusts the energy output ratio of fuel cells and power batteries according to speed intervals and operating condition changes. In scenarios with significant speed fluctuations and frequent operating condition transitions, power shocks are mitigated by the power battery’s peak-shaving and valley-filling function. Simulation results for C-WTVC and NREL2VAIL show that, compared with traditional A-ECMS, the improved P-ECMS has notable energy benefits, with equivalent hydrogen consumption reduced by 3.41% and 5.48%, respectively. The fuel cell’s state is significantly improved, with its high-efficiency share reaching 63%. The output power curve is smoother, start–stop losses are reduced, and the fuel cell’s service life is extended, balancing the energy economy and component durability. Full article

Cloud-based platforms form the backbone of smart city ecosystems, powering essential services such as transportation, energy management, and public safety. However, their operational complexity generates vast volumes of system logs, making manual anomaly detection infeasible and raising reliability concerns. This study addresses the challenge of data scarcity in log anomaly detection by leveraging Large Language Models (LLMs) to enhance domain-specific classification tasks. We empirically validate that domain-adapted classifiers preserve strong natural language understanding, and introduce a Proximal Policy Optimization (PPO)-based approach to align semantic patterns between LLM outputs and classifier preferences. Experiments were conducted using three Transformer-based baselines under few-shot conditions across four public datasets. Results indicate that integrating natural language analyses improves anomaly detection F1-Scores by 5–86% over the baselines, while iterative PPO refinement boosts classifier’s “confidence” in label prediction. This research pioneers a novel framework for few-shot log anomaly detection, establishing an innovative paradigm in resource-constrained diagnostic systems in smart city infrastructures. Full article