Search Results (8,095)

Lightweight day-ahead photovoltaic (PV) forecasting models encounter a significant technical challenge: under resource-constrained deployment conditions, it is difficult to simultaneously address weather-regime heterogeneity, maintain model interpretability, and preserve adaptability as operating conditions evolve. To address this issue, we propose a multimodal short-term photovoltaic (PV) forecasting method that integrates weather-mode partitioning using the Clustering Using Representatives (CURE) algorithm with a self-updating Batch-Lasso model. First, the meteorological-PV dataset is partitioned along two dimensions by combining seasonal grouping with CURE clustering within each season, producing representative weather modes and enhancing the fidelity of weather pattern classification. Second, to extract informative predictors from high-dimensional meteorological inputs while maintaining interpretability, we formulate per-mode Lasso regression and adopt the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) to efficiently solve for the sparse regression coefficients. Third, we introduce a batch-based self-update and correction mechanism with rollback verification, enabling the mode-specific models to be refreshed as new historical data become available while preventing performance degradation. Compared with representative machine learning baselines, the proposed method maintains competitive accuracy with substantially lower computational and storage overhead, enabling high-frequency and energy-efficient inference on resource-constrained terminals, thereby reducing operational burdens and computational energy costs and better meeting the deployment needs of sustainable energy systems under heterogeneous weather conditions. Full article

Against the backdrop of the global energy transition toward deep electrification, the natural gas industry faces challenges, including increased load forecasting uncertainty and frequent extreme weather impacts. To enhance natural gas load forecasting accuracy and support system resilience planning, this study constructs a forecasting model based on quadratic decomposition and hybrid deep learning, incorporating an electricity substitution coefficient to characterize the coupling substitution effect between electricity and natural gas. Under the basic scenario, the VMD-WPD-TCN-BiGRU model is proposed. It employs variational mode decomposition and wavelet packet denoising for secondary signal denoising, combined with a time-series convolutional network and bidirectional gated recurrent unit to extract temporal features. Experiments demonstrate that, compared to mainstream methods such as CNN, BiLSTM, SVM, and XGBoost, this model achieves statistically significant reductions in MSE (11.11–96.21%), MAE (0.89–76.50%), and MAPE (4.10–67.94%), significantly improving forecasting accuracy. In the deep electrification scenario, the introduction of the electricity substitution coefficient further optimizes peak load forecasting for system pressure days under extreme low temperatures, elevating the overall R² to 0.9905 in the deep electrification scenario. Research indicates that the proposed model not only effectively improves the accuracy of short-term natural gas load forecasting but also provides quantitative support for enterprises to plan peak-shaving facilities, optimize pipeline networks, and respond to extreme weather emergencies in data silo environments. This contributes to strengthening the adaptability and long-term resilience of natural gas systems during the energy transition, thereby supporting the sustainable development of energy infrastructure. Full article

Electric vehicle(EV) diffusion exhibits nonlinear, path-dependent dynamics shaped by interacting economic, technological, and social constraints. This paper develops a unified hybrid systems framework that captures these complexities by integrating microfounded household choice, capacity-constrained firm behavior, local network spillovers, and multi-level policy intervention within a Filippov differential-inclusion structure. Households face heterogeneous preferences, liquidity limits, and network-mediated moral and informational influences; firms invest irreversibly under learning-by-doing and profitability thresholds; and national and local governments implement distinct financial and infrastructure policies subject to budget constraints. The resulting aggregate adoption dynamics feature endogenous switching, sliding modes at economic bottlenecks, network-amplified tipping, and hysteresis arising from irreversible investment. We establish conditions for the existence of Filippov solutions, derive network-dependent tipping thresholds, characterize sliding regimes at capacity and liquidity constraints, and show how network structure magnifies hysteresis and shapes the effectiveness of local versus national policy. Optimal-control analysis further demonstrates that national subsidies follow bang–bang patterns and that network-targeted local interventions minimize the fiscal cost of achieving regional tipping. Beyond theoretical characterization, the framework is structurally calibrated to match the order-of-magnitude effects reported in leading empirical and simulation-based studies, including network diffusion models, agent-based simulations, bass-type specifications, and fuel-price shock analyses. The hybrid formulation reproduces short-run percentage-point subsidy effects, long-run forecast dispersion under alternative network assumptions, and policy-induced equilibrium shifts observed in the applied literature while providing a unified geometric interpretation of these heterogeneous results through explicit basin boundaries and regime switching. The framework provides a complex systems perspective on sustainable mobility transitions and clarifies why identical national policies can generate asynchronous regional outcomes. These results offer theoretical foundations for designing coordinated, cost-effective, and network-aware EV transition strategies. Full article

With the rapid development in data mining and learning analytics, integrating predictive analytics into educational data has become increasingly critical for supporting students’ learning trajectories. In many schooling systems, the academic tracks (such as Liberal Arts or Science) and the performance of junior high school students can substantially shape their subsequent university pathways and career planning. Despite the long-term impact of these decisions, academic track selections and the evaluation of students’ potential are often made without systematic and evidence-based guidance. Predictive computer applications can assist, but the training of accurate models and the selection of adequate features remain key challenges. This paper details our process of engineering such an application comprising two tasks based on 1357 real-world junior high school academic performance records. The first task applies a classification approach to predict students’ academic track orientation, while the second task employs a multi-output regression model to forecast students’ future academic performance in senior high school. Our approach shows that the stacking ensemble model achieved a classification accuracy of 85.76%, whereas the Bi-LSTM model with multi-head attention attained an overall R² exceeding 82% in performance forecasting; both models demonstrated strong and reliable predictive capability. Moreover, the proposed approach provides inherent interpretability by decomposing predictions at the subject level. Feature importance analysis reveals how different academic subjects contribute variably to both academic track decisions and future academic performance, offering actionable insights for academic counselling and future study planning. By bridging predictive modelling with students’ educational and career planning needs, this study advances the practical application of educational data mining and provides support for evidence-based academic guidance and future career choices in real-world contexts. Full article

Accurate energy forecasting is essential for maintaining power system reliability, integrating renewable generation, and ensuring market stability. Although machine learning has improved forecasting accuracy, its operational deployment depends on Machine Learning Operations (MLOps) platforms that automate and scale the entire lifecycle of energy data pipelines. However, the capabilities of existing MLOps platforms for energy forecasting have not been systematically compared. This study adopts a PRISMA-informed review process to identify relevant end-to-end MLOps platforms for energy forecasting and then maps their documented capabilities using an established energy forecasting pipeline lifecycle as the reference structure. A total of 256 records were screened across vendor documentation, open-source repositories, and academic literature, of which 13 MLOps platforms were selected for comparative capability analysis. Platform capabilities are organised and presented across an end-to-end lifecycle covering project setup and governance, data ingestion and management, model development and experimentation, deployment and serving, and monitoring and feedback. Commercial platforms such as Amazon SageMaker and Google Vertex AI generally provide stronger end-to-end integration and production readiness, while open-source platforms such as Kubeflow and ClearML offer modular flexibility that typically requires additional integration effort to achieve end-to-end operation. The mapping identifies four priority areas where platform support remains limited, namely (i) governance workflow automation, (ii) automated data quality validation, (iii) feature management, and (iv) deployment and monitoring support under nonstationary conditions. These findings indicate that platform selection for energy forecasting should be treated as a lifecycle capability decision, balancing end-to-end integration, operational assurance, and long-term flexibility. Full article

Building-Integrated and Building-Attached Photovoltaic (BIPV/BAPV) systems are increasingly being adopted in metropolitan areas worldwide, driven by international commitments to reduce greenhouse gas emissions and the declining cost of PV technology. A promising application involves the vertical integration of PV panels into building facades, which offers architectural and energy benefits, particularly in urban environments with limited roof space. This study experimentally evaluates the energy behavior of 12 vertically mounted 5 W PV panels (model SP005P) installed on university buildings in Ibarra, Ecuador, across four azimuth orientations (−135° SE, −45° NE, 45° NW, 135° SW). A continuous 8-month monitoring campaign was conducted using a custom-designed Arduino-based data logger, validated with multimeter measurements (error < 5%). The dataset was used to develop MATLAB version 2025b forecasting models based on Sum-of-Sine functions, achieving R² values between 0.83 and 0.98 and RMSE values between 0.024 and 0.082 W. The 45° (NW) orientation achieved the highest annual energy yield of 48% STC, reaching up to ≈440 kWh/kWp in the best-performing facade, while 135° (SW) also exhibited favorable performance compared with the northeast and southeast orientations. These findings provide significant evidence for facade-integrated PV design in equatorial latitudes, offering performance benchmarks and validated forecasting tools that can support architectural planning, BIPV feasibility analysis, and urban solar-energy strategies in regions with similar conditions. Full article

In classical reliability engineering, failure is a probabilistic structural failure based on lifetime distributions of Weibull models. However, in the control-critical mechanical systems, it is possible that functional failure of the system happens before material failure occurs as a result of control power loss. This paper proposes a Controllability–Reliability Coupling (CRC) model, which redefines the concept of reliability as the stabilizability in the face of progressive degradation. The actuators’ deterioration is modeled using the time-varying input effectiveness factor $\alpha \left(t\right)$, and the actuator is said to be in failure when the minimum singular value of the finite-horizon controllability Gramian becomes less than a stabilizability threshold $\epsilon$. The performance of the simulation indicates that the functional failure is a precursor of structural failure in several degradation conditions. A baseline comparison shows that the CRC metric forecasts loss of controllability at $T_{CRC}=17.0$ s, but the classical Weibull reliability never attains the structural failure threshold even in the time horizon of 20 s. The system retains margins of Lyapunov stability and H infinity robustness are not lost, and it is still stable and attenuates disturbances even when control authority is lost. In practical degradation scenarios, the forecasted CRC failure times are 21.5 s (linear wear), 13.1 s (accelerated fatigue), 23.7 s (intermittent faults), and 24.4 s (shock damage), whereas maintenance recovery abated functional failure completely. In a case study of an industrial robotic joint, at 27.0 s, functional collapse occurred, and at the same time, structural reliability was still above the failure threshold. The findings support the hypothesis that structural survival and functional controllability are distinct concepts. The proposed CRC framework is an approach to control-conscious reliability measure, which can detect early failures and offer proactive maintenance advice in the context of a cyber–physical system. Full article

This study addresses the low operational efficiency and high energy storage cost of wind–solar hybrid energy storage systems due to the strong volatility and intermittency of wind and photovoltaic power. Instead, the authors propose a dual-layer optimization model based on convolutional neural network–long short-term memory–attention mechanism (CNN-LSTM-AM) forecasting. First, a CNN-LSTM-AM forecasting model is constructed based on convolutional neural networks and long short-term memory networks. Then, the model is applied to wind and solar power forecasting to dynamically optimize the output power ratio of renewable sources and batteries based on predicted power, thereby reducing the start–stop frequency of compressed air energy storage (CAES) and improving operational efficiency. For lower-layer optimization, a weight evaluation model based on AHP is constructed and subsequently used to optimize the capacity configuration of the hybrid energy storage system to achieve overall system optimality. Case studies indicate that after upper-layer optimization, the number of CAES start–stop cycles decreases from 25 to 17, and further declines to 14 after optimization of the lower-layer capacity configuration, while the energy storage cost is reduced by 5.43% and the curtailment rate decreases by 0.15%. This validates the effectiveness of the proposed model in improving the economic performance and stability of renewable hybrid energy storage systems. Full article

Accurate yaw alignment is critical for maximizing power capture in horizontal-axis wind turbines, as even moderate yaw misalignment leads to significant aerodynamic losses, increased actuator usage, and accelerated mechanical wear. This research paper proposes a hybrid smart yaw control system for small-scale wind turbines that combines real-time measurements with short-term wind direction prediction to improve alignment accuracy, operational reliability, and energy efficiency under realistic operating conditions. The system integrates four wind direction information sources, such as physical wind vane sensing, live online weather data, forecast data, and a data-driven prediction module within a structured priority framework (VANE → LIVE → FORECAST → AI), to ensure continuous yaw control during sensor or communication unavailability. The prediction module is based on a long short-term memory (LSTM) neural network trained in MATLAB using live data from an online platform, with sine–cosine encoding employed to address the circular nature of directional data. The yaw controller incorporates a ±15° deadband, dwell-time logic, shortest-path rotation, and cable-safe constraints to reduce unnecessary actuation while maintaining effective alignment. The proposed system is validated through MATLAB/Simulink simulations and real-time microcontroller-based experiments using a stepper motor-driven nacelle. Compared with conventional vane-based yaw control, the hybrid AI-assisted approach reduces the average yaw error by approximately 35–45%, maintains a yaw error within ±15° for more than 90% of the operating time, increases average electrical power output by 3–5%, and reduces yaw motor energy consumption by 10–15%, while decreasing corrective yaw actuation events by 30–40%. These results demonstrate that integrating an LSTM-based wind direction predictor with multi-source wind data provides a robust, low-cost, and practically deployable yaw control solution that enhances energy capture and mechanical durability in small-scale wind turbines. Full article

Greenhouse cultivation enables year-round vegetable production and high yields through precise environmental regulation. Yet, the same stable microclimate that promotes crop growth also favors the proliferation of pests and diseases. This review synthesizes current knowledge on how greenhouse climate variables govern pest and disease epidemiology in tomato, cucumber, and sweet pepper. Only greenhouse-based studies were included to ensure direct relevance to protected horticulture. Microclimatic stability determines infection probability, vector behavior, and host susceptibility. Warm, humid conditions promote fungal and bacterial pathogens, whereas dry, high vapor pressure deficit (VPD) environments favor mites and thrips and enhance virus transmission. Species-specific traits further modulate vulnerability. Tomato is dominated by virus–bacterium complexes and foliar/stem fungal diseases, cucumber by phytopathogenic fungi favored by high relative humidity (RH) and soilborne pathogens, and sweet pepper by virus–vector systems and long-cycle fungal infections. Temperature exerts the strongest influence, while RH and VPD jointly regulate surface moisture and vector activity. Light intensity and spectral composition also affect pest orientation and fungal sporulation. Integrating environmental sensing, biological control, and adaptive climate regulation offers a pathway toward preventive, climate-smart Integrated Pest Management (IPM). The review highlights the emerging role of climate-informed decision-support systems (DSSs) and the need for greenhouse-specific datasets to improve pest and disease forecasting. Full article

Short-term forecasting of solar radiation is essential for the efficient operation of solar energy systems. This study presents a neural network-based approach for short-term solar radiation forecasting using a hybrid framework that integrates temporal characteristics with weather-based features. The proposed model combines a Gated Recurrent Unit (GRU) to capture short-term temporal dynamics, a Transformer Encoder, and a Multilayer Perceptron (MLP) to integrate these representations for final prediction. Key meteorological variables, including temperature, humidity, and wind speed, are incorporated along with engineered time-related features such as lagged values, rolling statistics, and cyclical time-of-day encodings. The results demonstrate that the hybrid model effectively integrates sequential learning and feature interaction, leading to improved forecasting accuracy. The proposed approach achieves a test Mean Absolute Error (MAE) of 0.056, Root Mean Square Error (RMSE) of 0.086, and coefficient of determination (R²) of 0.92, outperforming benchmark models such as AutoRegressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), GRU, and Extreme Gradient Boosting (XGBoost). The model maintains stable performance across cross-validation folds, multiple forecasting horizons, and varying weather conditions. These findings indicate that the proposed framework provides a reliable and practical solution for accurate short-term solar radiation forecasting, supporting real-time solar energy management and renewable energy system optimization. Full article

The transition to smart cities is accelerating distributed wind and solar deployment. However, their intermittency challenges grid operation, thereby making accurate machine-learning-based prediction of wind speed and global horizontal irradiance (GHI) crucial. This study presents a cost-effective approach that enhances prediction accuracy by extracting additional features from timestamp records for deep learning models used to forecast GHI and wind speed. Unlike conventional methods that require onsite meteorological measurements, the proposed approach uses only date and time information as inputs to multivariate deep neural networks, including recurrent neural networks, gated recurrent units, long short-term memory (LSTM), bidirectional LSTM, and convolutional neural networks. For wind speed prediction, the proposed configuration achieves R² up to 0.9987, with RMSE as low as 0.067 m/s for 3 d ahead forecasting, outperforming univariate baselines and matching models. For GHI forecasting, the time-based configuration attains R² values above 0.9994 in 12 h ahead predictions, with the RMSE reduced to approximately 4.47 W/m², representing a substantial improvement over univariate models. The proposed framework maintains strong performance, particularly under clear and sunny conditions. These results demonstrate that timestamp-engineered features can deliver forecasting accuracy comparable to conventional multivariate meteorological models while significantly reducing infrastructure requirements, making the approach well-suited for scalable smart city energy management. Full article

Viral and fungal diseases of greenhouse strawberries lead to significant crop losses, while traditional uniform spraying schemes do not account for the actual distribution of infection foci or changes in the microclimate. This paper proposes an integrated system for greenhouse farms that combines a stochastic SIRS model of the epidemic process with a microclimate-dependent infection coefficient β_eff(t), a computer vision module based on a lightweight YOLOv10n detector, and a mobile sprayer robot. For three sets of parameters corresponding to moderate infection, outbreak, and suppression scenarios, ensemble simulations are performed (100 realizations per scenario). The results show that the maximum number of infected plants reaches approximately 690 out of 1000 in the outbreak scenario and only about 28 out of 1000 in the suppression scenario, reflecting the effect of timely microclimate correction and local spraying. The YOLOv10n detector is used as a sensor to determine the proportion of affected plants I(0)/N and provides automatic formation of the initial conditions of the population model. The resulting forecasts then serve as the basis for selecting one of three operating modes for the spraying robot (observation, microclimate correction, local treatment). Unlike existing works that consider disease detection, epidemiological models, or robotic spraying separately, this paper proposes a unified closed-loop scheme of “computer vision—stochastic model—mobile robot,” linking detection quality with epidemic process forecasting and treatment strategy. In this study, the feasibility of the proposed system was examined through numerical simulations, detector-level performance evaluation, and offline image-based integrated validation of the detector-to-decision workflow. Full closed-loop experiments in a real greenhouse environment are planned for future work. Full article

Collaboration between humans and robots (HRC) is advancing rapidly due to the intersection of robotics and generative artificial intelligence (GenAI). The current paper includes a systematic review of 103 studies on the role of generative models, including Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), diffusion models, and Large Language Models (LLMs) in improving the safety, trust, and adaptability of collaborative robotics using a PRISMA-based systematic approach. The review recognizes four major themed areas of GenAI-based safety frameworks—namely, data-driven simulation to synthesize hazards, predictive reasoning to forecast human motion, adaptive control to reduce risks dynamically, and trust-aware cognition to explain human–robot interaction. Findings indicate that generative models transform robotic safety from a reactive mechanism to proactive, contextual and interpretable systems. Nevertheless, real-time performance, interpretability, standard benchmarking, and ethical assurance are still some of the challenges to be overcome. The paper proposes a taxonomy linking generative modeling layers and physical, cognitive and ethical aspects of HRC safety, and gives a roadmap of certifiable hybrid systems with generative foresight and deterministic control. This synthesis provides a foundation for developing transparent, adaptive, and trustworthy collaborative robotic systems. Full article

This modeling study investigates the impact of the 2023 Canadian wildfire aerosols (primarily black carbon and organic aerosol) on weather forecasts, concluding that incorporating real-time aerosol forcing improves model performance over using climatology. Experiments without real-time data severely underestimated aerosol optical depth (AOD), an error mitigated by including the forcing or using the coupled atmosphere–chemistry model. The aerosols exerted a strong direct radiative effect, reducing surface downward shortwave (SW) flux and generating corresponding surface cooling over the wildfire region. Furthermore, including aerosol–cloud interactions amplified this cooling and led to an increase in the overall cloud fraction and precipitation, illustrating complex indirect effects. While these physical improvements enhanced the representation of the atmosphere, the positive impact on overall medium-range forecasting performance (5–10 days) was modest, suggesting that the benefits of accurately representing wildfire feedback on the coupled Earth system are achieved through relatively slow processes, such as radiation feedback. Full article