7 research outputs found
Nonparametric Bayesian-based recognition of solar irradiance conditions: Application to the generation of high temporal resolution synthetic solar irradiance data
No full textHigh resolution synthetic irradiance is of interest for theoretical studies such as grid integration of solar PV and battery storage analysis. Access to site-specific data is often limited to inadequate temporal resolutions for such application. A new model for producing synthetic solar global horizontal irradiance (GHI) time-series at up to 1-min resolution is presented as derived from >10-min input data. Briefly, it is a clustered-based method for daily clearness index distributions using Dirichlet process Gaussian mixture model (DPGMM). DPGMM is a nonparametric Bayesian (NPB) model indexed with an infinite-dimensional space of parameters. The key benefit of the NPB paradigm is the automatic adaptation to the correct complexity level and model size, suggesting a local adaptation of the model to all climatic conditions. A posterior inference using Markov chain Monte Carlo algorithm (namely Gibbs sampling) is applied. The model only requires a valid number of intraday data to construct daily distributions, then it can be applied worldwide. The synthetic GHI time series are validated against observed 1-min GHI data for four locations distributed throughout the world with different climatic conditions and significant geographic separation. Moreover, the presented method can generate data based on similar climatic conditions. A good fit between real and generated data is observed. We present an nRMSE ≤ 4% and nMBE < ±4% between generated and measured means at both daily and monthly scales for all sites. The agreement between the real and generated cumulative density distributions of six comparative variability metrics (defined in text) at four different sites is measured using the overlapping and the Kullback-Leibler coefficients, which are ≥ 75% and ≤ 10% respectively, in all cases. To ensure the reproducibility of the research presented in this paper, the methodology is freely available as an R-package downloadable from SolarClusGnr
Identifying small decentralized solar systems in aerial images using deep learning
No full textStatistics on installed solar energy systems (SES) play a crucial role in the solar energy industry, providing valuable information for a wide range of stakeholders, such as policy makers, authorities, and financial evaluators. For example, grid operators rely on accurate data on photovoltaic penetration levels to ensure the quality and stability of the power supply. In this research, we present an automatic approach helping generate these statistics using deep learning and image processing techniques. Our proposed model is a machine learning approach that utilizes a specific architecture of convolutional neural networks (CNN) called the "U-net'' to detect SES from aerial images. We experimented different network settings to enhance the SES identification performance.In this study, the model was evaluated using two datasets from different locations, one from Sweden and one from Germany. Additionally, the model was trained and tested on a combination of both datasets. The impact of image resolution was also examined. The experimental results show that this architecture performs better than many recent CNN models that have been proposed in the literature for the task of SES identification from aerial images. To make it easy for others to replicate our findings, We have shared all the scripts, software, and dependencies required for running the model in this paper, along with instructions on how to use it in Appendix A
Experimental and Modeling Dynamic Study of the Indirect Solar Water Heater: Application to Rabat Morocco
No full textThe Indirect Solar Water Heater System (SWHS) with Forced Circulation is modeled by proposing a theoretical dynamic multi-node model. The SWHS, which works with a 1,91 m2 PFC and 300 L storage tank, and it is equipped with available forced circulation scale system fitted with an automated sub-system that controlled hot water, is what the experimental setup consisted of. The system, which 100% heated water by only using solar energy.
The experimental weather conditions are measured every one minute.
The experiments validation steps were performed for two periods, the first one concern the cloudy days in December, the second for the sunny days in May; the average deviations between the predicted and the experimental values is 2 %, 5 % for the water temperature output and for the useful energy are 4 %, 9 % respectively for the both typical days, which is very satisfied. The thermal efficiency was determined experimentally and theoretically and shown to agree well with the EN12975 standard for the flow rate between 0,02 kg/s and 0,2kg/s
Biological pre-hydrolysis and thermal pretreatment applied for anaerobic digestion improvement : Kinetic study and statistical variable selection
No full textIn the present study, two pretreatment methods (thermal pretreatment and biological pre-hydrolysis) were suggested for food waste (FW) with the aim to enhance biomass conversion and biogas production by anaerobic. The effects of thermal pretreatment (TP), including TP at 60°C and 80°C for 60 min, and TP at 100°C, 120°C and 140°C for 30 min, well as biological pre-hydrolysis (BPH) at 37°C, 55°C, 37°C followed by 55°C and 55°C followed by 37°C for 40 hour on anaerobic digestion performance of FW were evaluated in batch tests. Results were compared with untreated FW. The BPH and TP caused an increase in the soluble chemical oxygen demand and hydrolysis efficiency. The methane yield (MY) increased from 371.17 ml CH4/g VS for untreated FW to 471.95 ml CH4/ g VS. The maximal MY was recorded for BPH at 37°C for 20 h followed by 55°C for 20 h. The pretreatments increased the biogas production rate and reduced the lag phase. The most influential variables on the methane yield were investigated using three statistical methods: Principal component analysis, Mutual Information and R-squared. The results allowed a good modeling of the methane yield and minimized the overfitting effect. For reproduction and solid contribution to the field, we have attached to our article all the necessary material to reproduce the same statistical work as in the paper body
Nonparametric Bayesian-based recognition of solar irradiance conditions: Application to the generation of high temporal resolution synthetic solar irradiance data
No full textHigh resolution synthetic irradiance is of interest for theoretical studies such as grid integration of solar PV and battery storage analysis. Access to site-specific data is often limited to inadequate temporal resolutions for such application. A new model for producing synthetic solar global horizontal irradiance (GHI) time-series at up to 1-min resolution is presented as derived from >10-min input data. Briefly, it is a clustered-based method for daily clearness index distributions using Dirichlet process Gaussian mixture model (DPGMM). DPGMM is a nonparametric Bayesian (NPB) model indexed with an infinite-dimensional space of parameters. The key benefit of the NPB paradigm is the automatic adaptation to the correct complexity level and model size, suggesting a local adaptation of the model to all climatic conditions. A posterior inference using Markov chain Monte Carlo algorithm (namely Gibbs sampling) is applied. The model only requires a valid number of intraday data to construct daily distributions, then it can be applied worldwide. The synthetic GHI time series are validated against observed 1-min GHI data for four locations distributed throughout the world with different climatic conditions and significant geographic separation. Moreover, the presented method can generate data based on similar climatic conditions. A good fit between real and generated data is observed. We present an nRMSE ≤ 4% and nMBE < ±4% between generated and measured means at both daily and monthly scales for all sites. The agreement between the real and generated cumulative density distributions of six comparative variability metrics (defined in text) at four different sites is measured using the overlapping and the Kullback-Leibler coefficients, which are ≥ 75% and ≤ 10% respectively, in all cases. To ensure the reproducibility of the research presented in this paper, the methodology is freely available as an R-package downloadable from SolarClusGnr
Dirichlet downscaling model for synthetic solar irradiance time series
No full text10.1063/5.0028267Journal of Renewable and Sustainable Energy126063702-06370
