Search Results (13,668)

This study explores advanced multivariate models that incorporate non-climatic exogenous variables for very short-term photovoltaic energy forecasting. By integrating historical energy data from multiple photovoltaic plants, the research aims to improve the prediction accuracy of a target plant while addressing critical challenges in electric power systems (EPS), such as frequency stability. Frequency stability becomes increasingly complex as renewable energy sources penetrate the grid because of their intermittent nature. To mitigate this challenge, precise forecasting of photovoltaic energy generation is essential for balancing supply and demand in real time. The performance of long short-term memory (LSTM) networks and bidirectional LSTM (BiLSTM) networks was compared over a 5 min horizon. Including energy generation data from neighboring plants significantly improved prediction accuracy compared to univariate models. Among the models, multivariate BiLSTM showed superior performance, achieving a lower root-mean-square error (RMSE) and higher correlation coefficients. Quantile regression applied to manage prediction uncertainty, providing robust confidence intervals. The results suggest that incorporating an exogenous power series effectively captures spatial correlations and enhances prediction accuracy. This approach offers practical benefits for optimizing grid management, reducing operational costs, improving the integration of renewable energy sources, and supporting frequency stability in power generation systems. Full article

The rapid growth of urban metro systems requires novel strategies to guarantee operational dependability and energy efficiency. This article describes a new way to use deep reinforcement learning (DRL) to help metro networks with predictive maintenance that adapts to changing conditions and energy optimization. We used real-world transit data from the General Transit Feed Specification (GTFS) to model the maintenance scheduling and energy management problem as a Markov Decision Process. This included important operational metrics like peak-hour demand, train arrival times, and station stop densities. A custom reinforcement learning environment mimics the changing conditions of metro operations. Deep Q-Networks (DQNs) and Proximal Policy Optimization (PPO) sophisticated deep reinforcement learning techniques were used to identify the optimal policies for decreasing energy consumption and downtime. The PPO hyperparameters were additionally optimized using Bayesian optimization by implementing Optuna, which produces a far greater performance than baseline DQNs and basic PPO. Comparative tests showed that our improved DRL-based method improves the accuracy of predictive maintenance and the efficiency of energy use, which lowers operational costs and raises the dependability of the service. These results show that advanced learning and optimization techniques could be added to public transportation systems in cities. This could lead to more sustainable and smart transportation management in big cities. Full article

The integration of large-scale distributed photovoltaics (DGPVs) and the generation of distributed photovoltaics (PVs) and loads with distinct characteristics in different transformer areas causes voltage problems in distribution networks, significantly compromising operational reliability and economy. To address this challenge, this study proposes the installation of a relocatable static var compensator (RSVC) to enhance the voltage regulation capability in addition to conventional voltage regulation methods. An RSVC can be deployed at critical nodes of distribution lines to provide continuous adjustable reactive power. RSVCs’ relocation capability in response to seasonal shifts in reactive power demand makes them an effective solution for spatiotemporal load disparities across transformer areas. A bi-level planning framework is established by first generating multiple typical scenarios based on load categories and their seasonal characteristics. The lower level achieves optimal operation in multiple scenarios through the coordination of active–reactive power regulation devices. The upper level employs a particle swarm optimization algorithm to determine the optimal siting and sizing of energy storage and the RSVC, iteratively invoking the lower-level model to minimize the total investment and operational costs. Validation was conducted on a modified IEEE 33-node test system. The results demonstrate that the proposed method effectively mitigates voltage violations caused by DGPVs and spatiotemporal load disparities while significantly enhancing the economic efficiency of distribution networks. Full article

Hydroxychloroquine (HCQ), a cornerstone therapeutic agent for autoimmune diseases, requires precise serum concentration monitoring due to its narrow therapeutic window. Current HCQ monitoring methods such as HPLC and LC-MS/MS are sensitive but costly and complex. While electrochemical sensors offer rapid, cost-effective detection, their large chambers and high sample consumption hinder point-of-care use. To address these challenges, we developed a microfluidic electrochemical sensing platform based on a screen-printed carbon electrode (SPCE) modified with a hierarchical nanocomposite of gold nanoparticles (AuNPs), copper-based metal–organic frameworks (Cu-MOFs), and multi-walled carbon nanotubes (MWCNTs). The Cu-MOF provided high porosity and analyte enrichment, MWCNTs established a 3D conductive network to enhance electron transfer, and AuNPs further optimized catalytic activity through localized plasmonic effects. Structural characterization (SEM, XRD, FT-IR) confirmed the successful integration of these components via π-π stacking and metal–carboxylate coordination. Electrochemical analyses (CV, EIS, DPV) revealed exceptional performance, with a wide linear range (0.05–50 μM), a low detection limit (19 nM, S/N = 3), and a rapid response time (<5 min). The sensor exhibited outstanding selectivity against common interferents, high reproducibility (RSD = 3.15%), and long-term stability (98% signal retention after 15 days). By integrating the nanocomposite-modified SPCE into a microfluidic chip, we achieved accurate HCQ detection in 50 μL of serum, with recovery rates of 95.0–103.0%, meeting FDA validation criteria. This portable platform combines the synergistic advantages of nanomaterials with microfluidic miniaturization, offering a robust and practical tool for real-time therapeutic drug monitoring in clinical settings. Full article

With the expansion of the scale of high-proportion wind and solar power grid connections, the problems of abandoned wind and solar power and insufficient peak shaving have become increasingly prominent. The electric–hydrogen coupling system has greater potential in flexible regulation, providing a new technological approach for the consumption of new energy. This paper proposes a two-layer optimization model for an electricity–hydrogen coupled distributed power generation system. The model is based on the collaborative regulation of flexible loads by electrolytic cells and fuel cells. Through the collaborative optimization of capacity configuration and operation scheduling, it breaks through the strong dependence of traditional systems on the distribution network and enhances the autonomous consumption capacity of new energy. The upper-level optimization model aims to minimize the total life-cycle cost of the system, and the lower-level optimization model aims to minimize the system’s operating cost. The capacity configuration of each module before and after the integration of flexible loads is compared. The simulation results show that the integration of flexible loads can not only effectively reduce the level of wind and solar power consumption in distributed power generation systems, but also play a role in load peak shaving and valley filling. At the same time, it can effectively reduce the system’s peak electricity purchase and sale cost and reduce the system’s dependence on the distribution network. Based on this, with the premise of meeting the load demand, the capacity configuration results of each module were compared when connecting electrolytic cells of different capacities. The results show that the simulated area has the best economic benefits when connected to a 4 MW electrolytic cell. This optimization model can increase the high wind and solar power consumption rate by 23%, reduce the peak purchase and sale cost of electricity by 40%, and achieve an economic benefit coefficient of up to 0.097. Full article

With the nationwide completion of China’s large-scale Poverty Alleviation Relocation (PAR) initiative in 2020, the government’s poverty alleviation efforts have officially entered the “post-poverty era”. However, many regions still lack well-established sustainable development mechanisms and face a potential risk of returning to poverty. To better stabilize the achievements of poverty alleviation, this study examines the potential risk of returning to poverty after the first Five-Year Transition Period (2021–2025) from a livelihood space perspective and proposes optimization directions for PAR policies in future poverty reduction efforts. Research findings indicate that simply altering geographical conditions is insufficient to achieve stable poverty alleviation. The production space of relocated populations is vulnerable to the stability and precision in resource supply, which may lead to recurring poverty due to policy discontinuities and administrative preferences. Meanwhile, improvements in living spaces are constrained by imbalances in household income and expenditure. This study also found that, on the one hand, changes in residential patterns break the original boundaries of administrative villages by incorporating migrants from different villages into concentrated communities, leading to the expansion of weak-tie networks while, on the other hand, the relocation process disrupts some of the migrants’ original strong-tie networks, and the concentration and clustering of impoverished groups in relocation communities further lead to the contraction of these networks. Additionally, the unique characteristics of relocation communities generate exorbitant governance costs and population management difficulties that far exceed the service provision and administrative capacities of community organizations. In the long run, this situation proves detrimental to normalized community governance and dynamic poverty relapse monitoring and interventions. Accordingly, this study proposes relevant policy recommendations from the following four aspects, i.e., strengthening endogenous development capacity, improving social security mechanisms, expanding social support networks, and enhancing organizational governance capabilities, aiming to provide both a theoretical basis and a decision-making reference for future poverty alleviation efforts. Full article

Background: Deep vein thrombosis (DVT) management remains challenging despite standard anticoagulation therapy. This study evaluated the comprehensive benefits of combining rivaroxaban with Aescuven (CAV) compared to rivaroxaban monotherapy (SAT) in DVT treatment. Methods: A retrospective analysis was conducted on DVT patients (2018–2023) using multi-method propensity score matching and ensemble weighting. Outcomes included improvement rate (IPR), daily improvement rate (DIR), cost-effectiveness ratio (CER), daily improvement cost (DIC), cost–LOS efficiency (CLE), and length of stay (LOS). Counterfactual analysis was implemented to estimate causal effects. Results: The CAV group demonstrated superior outcomes compared to SAT: IPR increased by 6.39 percentage points (95% CI: 5.61–7.39), DIC substantially reduced by 3323.38 CNY (95% CI: 2887.95–3758.81), and CLE improved by 136.97 CNY per day (95% CI: 122.31–151.64), with minimal LOS increase (0.15 days, 95% CI: 0.12–0.18). Network analysis revealed significant correlations between baseline coagulation parameters and treatment outcomes, particularly between APTT and economic benefits. Conclusions: The CAV regimen achieved significant clinical and economic advantages over standard monotherapy without substantially increasing resource utilization. These findings support integrating venoprotective agents into conventional anticoagulation strategies for optimized DVT management. Full article

The issue of pesticide and chemical residue in food has drawn increasing public attention, making effective control of plant pests and diseases a critical research focus in agriculture. Monitoring of pest populations is a key factor constraining the precision of pest management strategies. Low-cost and high-efficiency monitoring devices are highly desirable. To address these challenges, we focus on Cacopsylla chinensis and design a portable, AI-based detection device, along with an integrated online monitoring and forecasting system. First, to enhance the model’s capability for detecting small targets, we developed a backbone network based on the RepVit block and its variants. Additionally, we introduced a Dynamic Position Encoder module to improve feature position encoding. To further enhance detection performance, we adopt a Context Guide Fusion Module, which enables context-driven information guidance and adaptive feature adjustment. Second, a framework facilitates the development of an online monitoring system centered on Cacopsylla chinensis detection. The system incorporates a hybrid neural network model to establish the relationship between multiple environmental parameters and the Cacopsylla chinensis population, enabling trend prediction. We conduct feasibility validation experiments by comparing detection results with a manual survey. The experimental results show that the detection model achieves an accuracy of 87.4% for both test samples and edge devices. Furthermore, the population dynamics model yields a mean absolute error of 1.94% for the test dataset. These performance indicators fully meet the requirements of practical agricultural applications. Full article

Wind turbine wake modeling is critical for the design and optimization of wind farms. Traditional methods often struggle with the trade-off between accuracy and computational cost. Recently, data-driven neural networks have emerged as a promising solution, offering both high fidelity and fast inference speeds. To advance this field, a novel machine learning model has been developed to predict wind farm mean flow fields through an adaptive multi-fidelity framework. This model extends transfer-learning-based high-dimensional multi-fidelity modeling to scenarios where varying fidelity levels correspond to distinct physical models, rather than merely differing grid resolutions. Built upon a U-Net architecture and incorporating a wind farm parameter encoder, our framework integrates high-fidelity large-eddy simulation (LES) data with a low-fidelity engineering wake model. By directly predicting time-averaged velocity fields from wind farm parameters, our approach eliminates the need for computationally expensive simulations during inference, achieving real-time performance ($1.32\times {10}^{-5}$ GPU hours per instance with negligible CPU workload). Comparisons against field-measured data demonstrate that the model accurately approximates high-fidelity LES predictions, even when trained with limited high-fidelity data. Furthermore, its end-to-end extensible design allows full differentiability and seamless integration of multiple fidelity levels, providing a versatile and scalable solution for various downstream tasks, including wind farm control co-design. Full article

Progressive advancements in the global economy and technology have propelled human civilization forward; however, they have also inflicted significant harm on the global ecological environment. In the present era, electric vehicle (EV) technology is playing a vital role due to its environmentally friendly technological advances. However, widespread adoption of EVs has been hindered by their limited travel range, inadequate charging infrastructure, and high costs. This can be closely observed when we assess the adoption of electric vehicles (EVs) among motorcycle taxi drivers, commonly called ‘pilots,’ in Goa, India. Motorcycle taxis are crucial in Goa’s transportation network, providing affordable, efficient, and door-to-door services, especially in regions with limited public transport options. However, the rising costs of petrol and vehicle maintenance have adversely affected the income of these pilots, prompting concerns about their willingness to adopt EVs. This study aims to analyze the factors prompting the behavioral intention to adopt EVs by motorcycle taxi pilots in Goa, India, focusing on six key determinants: charging infrastructure, effort expectancy, performance expectancy, price value, social influence, and satisfaction with incentive policies. A quantitative approach was employed, utilizing stratified proportionate random sampling techniques to collect data from 242 motorcycle taxi pilots registered with the Goa State Government Transport Department. It was analyzed using partial least squares-structural equation modeling (PLS-SEM) through Smart-PLS 4.0 software. The research highlights that performance expectancy and price value are the potential motivators for the adoption of electric vehicles. These findings suggest that pilots are more likely to embrace EVs when they perceive tangible benefits in performance and find the cost reasonable in relation to the value offered. The results offer actionable insights for policymakers, manufacturers, and other stakeholders. These insights can guide strategic decisions and policy frameworks aimed at fostering a sustainable and user-centric transportation ecosystem. Full article

The spine is the most affected region, which compromises functionality and generates absenteeism, increased health care costs, and disability retirement rates. Based on the biopsychosocial model, it is believed that chronic back problems are the result of a complex network of factors, both individual and contextual. A cross-sectional study was developed with data from the 2013 National Health Survey, the United Nations Development Programme, and the National Register of Health Establishments (state level) for the second and third levels of aggregation, respectively. Multilevel Poisson regression was performed at three levels. The prevalence of chronic back problems was 18.5% (95% CI 17.8; 19.1), with a higher prevalence in females (RP = 1.23; 95% CI 1.15; 1.30), those aged above 49 years (RP = 1.75; 95% CI 1.61; 1.90), those performing heavy activities at work (RP = 1.37; 95% CI 1.28; 1.46), those with depressive days (RP = 1.70; 95% CI 1.50; 1.94), those who were smokers (RP = 1.37; 95% CI 1.27; 1.48), and those in states with a higher coefficient of Family Health Support Team per 100,000 inhabitants (PR = 1.28; 95% CI 1.07; 1.54). Chronic spine problems were associated with biological and behavioral factors and were more strongly associated with the coefficient of Family Health Support Team in Brazilian municipalities. Full article

The escalating scale and sophistication of cyber threats compel enterprises to urgently adopt data-driven security analytics. This systematic literature review, adhering to the PRISMA protocol, rigorously synthesizes current knowledge by analyzing 65 peer-reviewed studies (2013–2023) from six major databases on enterprise-level cybersecurity analytics. Our findings reveal a significant industry-wide transition from traditional signature-based tools towards advanced cloud-enabled, big-data and artificial intelligence-powered techniques, where machine learning and graph-based models are increasingly prominent in recent works. While large organizations in finance, Information and Communication Technology, and critical utilities spearhead adoption, dedicated research focusing on small and medium-sized enterprises (SMEs) remains notably limited. Ten thematic observations encapsulate key adoption drivers, an evolving preference for proactive and predictive security strategies, the critical role of heterogeneous log and network data, and persistent implementation challenges-notably data integration, skills shortages, and cost. Furthermore, this review identifies crucial open research avenues, including the development of real-time scalable analytics, unified policy languages, and critically needed SME-oriented solutions. Collectively, these insights provide a robust evidence base to inform future research trajectories and guide the practical deployment of effective cybersecurity analytics in diverse enterprise settings. Full article

To facilitate power system decarbonization, optimizing clean energy integration has emerged as a critical pathway for establishing sustainable power infrastructure. This study addresses the multi-timescale operational challenges inherent in power networks with high renewable penetration, proposing a novel stochastic dynamic programming framework that synergizes intraday microgrid dispatch with a multi-phase carbon cost calculation mechanism. A probabilistic carbon flux quantification model is developed, incorporating source–load carbon flow tracing and nonconvex carbon pricing dynamics to enhance environmental–economic co-optimization constraints. The spatiotemporally coupled multi-microgrid (MMG) coordination paradigm is reformulated as a continuous state-action Markov game process governed by stochastic differential Stackelberg game principles. A communication mechanism-enabled multi-agent twin-delayed deep deterministic policy gradient (CMMA-TD3) algorithm is implemented to achieve Pareto-optimal solutions through cyber–physical collaboration. Results of the measurements in the MMG containing three microgrids show that the proposed approach reduces operation costs by 61.59% and carbon emissions by 27.95% compared to the least effective benchmark solution. Full article

The gearbox, as an important transmission component in wind turbines, connects the blades to the generator and is responsible for converting wind energy into mechanical energy and transmitting it to the generator. Its ability to reduce vibrations directly affects the operational lifespan of the wind turbine. When designing the gearbox’s elastic support structure, it is essential to evaluate how the design parameters influence various performance metrics. Neural networks offer a powerful means of capturing and interpreting the intricate associations linking structural parameters with performance metrics. However, conventional neural networks are usually optimized for a single task, failing to fully account for task differences and shared information. This can lead to task conflicts or insufficient feature modeling, which in turn affects the learning efficiency of inter-task correlations. Furthermore, physical experiments are costly and provide limited training, making it difficult to meet the large-scale dataset requirements for neural network training. To address the high cost and limited scalability of traditional physical testing for gearbox rubber damping structures, in this study, we propose a low-cost performance prediction method that replaces expensive experiments with simulation-driven dataset generation. An optimal Latin hypercube sampling technique is employed to generate high-quality data at minimal cost. On this basis, a multi-task prediction model called multi-gate mixture-of-experts with LSTM (PLE-LSTM) is constructed. The adaptive gating mechanism, hierarchical nonlinear transformation, and effective capture of temporal dynamics in the LSTM significantly enhance the model’s ability to model complex nonlinear patterns. During training, a dynamic weighting strategy named GradNorm is utilized to counteract issues like the early stabilization in multi-task loss convergence and the uneven minimization of loss values. Finally, ablation experiments conducted on different datasets validate the effectiveness of this approach, with experimental results demonstrating its success. Full article

Urban rail transit, a crucial component of urban public transportation, often experiences increased operational costs and carbon emissions due to low-load operations being conducted during off-peak passenger flow periods. This study aims to develop an optimization method for the daily scheduling of rail train operations with the goal of carbon emission reduction, while comprehensively considering the built environment and travel demand. Firstly, the influence of the urban built environment on residents’ travel demand is analyzed using an XGBoost model. Secondly, a time convolutional travel demand prediction model, Built Environment-Weighted Temporal Convolutional Network (BE-TCN), weighted by built environment factors, is constructed. Finally, an optimization method for rail train operation schedules based on the built environment and travel demand is proposed, with the objective of carbon emission reduction. A case study is conducted using the Hangzhou urban rail transit system as an example. The results indicate that the optimization method proposed in this study can achieve monthly carbon emission reductions of 1524.58 tons, 1181.94 tons, and 520.84 tons for Lines 1, 2, and 4 of the Hangzhou urban rail transit system, respectively. The research findings contribute to enhancing the economic efficiency and environmental sustainability of urban rail transit systems. Full article