Multi-Strategies Operational Regulation Investigations of the Pv/T Collectors Based on 3-Days Ahead Hourly Radiation Prediction

Published: Jan. 1, 2024

The PV/T collectors epitomize the advanced photovoltaic and photothermal integration technology, realizing full-spectrum utilization. energy profitability of not only depends on sophisticated equipment but also correlates significantly with operational regulation. 3-days-ahead hourly prediction model for horizontal global solar radiation is proposed examined three classical regression seven deep learning models. SARIMAX LSTM-Attention emerge as most outstanding models weighted mean R2 96.8% 94.0%, respectively. R2_train and, training dataset being 15 days data. An optimal timestep 12 identified, recommended upper limit 20. Variable inclination strategy, variable ground reflectivity reflector strategies, muti-strategies optimization are analyzed based WOA algorithm. monthly variation a compromise due to 1.5 MJ/m2 improvement compared weekly variation. 5% addition leads 0.45% average incident radiation. can achieve relative 11.53% 12.52% in thermal electrical gain, which contribution from individually occupy nearly 10%.

Language: Английский

---

Integrating Fy-4a Satellite Data into Active Fire Detection Fusion System to Improve Estimation of Crop Residue Open Burning Emissions

Published: Jan. 1, 2024

Language: Английский

---

Multi-Dimensional Coupled Evaluation and Prediction Of Solar Energy Utilization Indicators on Building Surfaces

Published: Jan. 1, 2024

The evaluation of solar energy utilization potential urban building surfaces currently faces the dilemma high complexity large-scale-high-precision-multidimensional coupled computation. This study introduces a more comprehensive method for clusters splitting and type identification, uses geometric morphology to extract multi-dimensional feature indicators clusters. A sky module technology coupling temporal dimension radiation type, dynamic identification surface orientation, high-performance computational framework metrics parsing have been developed. Further, variety machine learning algorithms were examined, finally XGB model, which balances predictive performance (R2>0.95 MSE<0.10) prevents overfitting, was selected predict multidimensional existing buildings in non-enriched areas. found that: (a) geographic location clusters, types can better characterize variability be used build high-precision prediction models. (b) shading typical varies across orientations, with roofs distributed between 3.45% 6.98%, façades 34.70 50.71%. (c)The is significant both different directions time dimensions, e.g., winter accounts about 38% summer Chengdu only 30% Chongqing. In this study, we further captured nonlinear relationship thresholds effective potentials under orientations constructed models bi-directional gains explaining science advancing applications.

Language: Английский

---

Spatio-Temporal Correlation-Based Surface Solar Irradiance Retrieval Approach Using Satellite Data Under Different Weather Conditions

Published: Jan. 1, 2024

Wide-area, high temporal-spatial resolution surface solar irradiance data (SSI) is critical for energy resource assessment, PV power station site selection, and forecasting. However, it evidently impractical to obtain the aforementioned by deploying a large number of high-density observation devices on ground. Satellite remote sensing, with global coverage spatio-temporal resolution, provides detailed information, widely applied in retrieval meteorological parameters studies. Currently, most satellite data-based SSI studies only consider cloud images as representation cover, without fully utilizing multi-channel spectral information from satellite. Furthermore, these not overlook impact image spatial scale under different weather conditions but also neglect correlation between pixels images. To solve above problems, this study proposes correlation-based approach using conditions. The mainly consists three parts: classification feature based single-pixel data, correlation. experiments confirm feasibility proposed validate necessity considering types establishing correlations retrieval.

Language: Английский

---

Joint Retrieval of PM2.5 Concentration and Aerosol Optical Depth over China Using Multi-Task Learning on FY-4A AGRI

Advances in Atmospheric Sciences, Journal Year: 2024, Volume and Issue: 42(1), P. 94 - 110

Published: Dec. 9, 2024

Language: Английский

---