J. Antonanzas

Estimation of solar global irradiation in remote areas

Solar global irradiation is barely recorded in remote areas around the world. The lack of access to an electricity grid in these areas presents an enormous opportunity for electrification through renewable energy sources and, specifically, with photovoltaic energy where great solar resources are available. Traditionally, solar resource estimation was performed using parametric-empirical models based on the relationship between solar irradiation and other atmospheric and commonly measured variables, such as temperatures, rainfall, sunshine duration, etc., achieving a relatively high level of certainty. The significant improvement in soft-computing techniques, applied extensively in many research fields, has led to improvements in solar global irradiation modeling. This study conducts a comparative assessment of four different soft-computing techniques (artificial neural networks, support vector regression, M5P regression trees, and extreme learning machines). The results were also compared with two well-kn...

Downscaling of global solar irradiation in complex areas in R

A methodology for downscaling solar irradiation from satellite-derived databases is described using R software. Different packages such as raster, parallel, solaR, gstat, sp, and rasterVis are considered in this study for improving solar resource estimation in areas with complex topography, in which downscaling is a very useful tool for reducing inherent deviations in satellite-derived irradiation databases, which lack of high global spatial resolution. A topographical analysis of horizon blocking and sky-view is developed with a digital elevation model to determine what fraction of hourly solar irradiation reaches the Earths surface. Eventually, kriging with external drift is applied for a better estimation of solar irradiation throughout the region analyzed including the use of local measurements. This methodology has been implemented as an example within the region of La Rioja in northern Spain. The mean absolute error found using the methodology proposed is 91.92 kW h/m2 vs. 172.62 kW h/m2 using the ...

Evaluation of a novel GA-based methodology for model structure selection: The GA-PARSIMONY

Abstract Most proposed metaheuristics for feature selection and model parameter optimization are based on a two-termed L o s s + P e n a l t y function. Their main drawback is the need of a manual set of the parameter that balances between the loss and the penalty term. In this paper, a novel methodology referred as the GA-PARSIMONY and specifically designed to overcome this issue is evaluated in detail in thirteen public databases with five regression techniques. It is a GA-based meta-heuristic that splits the classic two-termed minimization functions by making two consecutive ranks of individuals. The first rank is based solely on the generalization error, while the second (named ReRank) is based on the complexity of the models, giving a special weight to the complexity entailed by large number of inputs. For each database, models with lowest testing RMSE and without statistical difference among them were referred as winner models. Within this group, the number of features selected was below 50%, which proves an optimal balance between error minimization and parsimony. Particularly, the most complex algorithms (MLP and SVR) were mostly selected in the group of winner models, while using around40–45% of the available attributes. The most basic IBk, ridge regression (LIN) and M5P were only classified as winner models in the simpler databases, but using less number of features in those cases (up to a 20–25% of the initial inputs).

Estimation of Daily Global Horizontal Irradiation Using Extreme Gradient Boosting Machines

Empirical models are widely used to estimate solar radiation at locations where other more readily available meteorological variables are recorded. Within this group, soft computing techniques are the ones that provide more accurate results as they are able to relate all recorded variables with solar radiation. In this work, a new implementation of Gradient Boosting Machines (GBMs) named XGBoost is used to predict daily global horizontal irradiation at locations where no pyranometer records are available. The study is conducted with data from 38 ground stations in Castilla-La Mancha from 2001 to 2013.

Benchmark of algorithms for solar clear-sky detection

Nowadays, solar resource estimation via clear-sky models is widely accepted when correctly validated with on ground records. In the past, different approaches have been proposed in order to determine clear-sky periods of solar radiation on-ground records: visual inspection of registers, discretization via a threshold value of clear sky index, and correlation with estimated clear sky solar irradiation. However, due to the fact that the process must be automated and the need for universality, the search for clear-sky conditions presents a challenging feat. This study proposes a new algorithm based on the persistent value of the Linke turbidity in conjunction with a transitory filter. The determinant of the correlation matrix of estimated clear-sky solar irradiance and measured irradiance is calculated to distinguish between days under clear-sky conditions and cloudy or overcast days. The method was compared and proved superior against a review of other 10 commonly used techniques at 21 sites of the Baseline Surface Radiation Network, which includes diverse climates and terrain.

A Straightforward Implementation of a GPU-accelerated ELM in R with NVIDIA Graphic Cards

General purpose computing on graphics processing units (GPGPU) is a promising technique to cope with nowadays arising computational challenges due to the suitability of GPUs for parallel processing. Several libraries and functions are being released to boost the use of GPUs in real world problems. However, many of these packages require a deep knowledge in GPUs’ architecture and in low-level programming. As a result, end users find trouble in exploiting GPGPU advantages. In this paper, we focus on the GPU-acceleration of a prediction technique specially designed to deal with big datasets: the extreme learning machine (ELM). The intent of this study is to develop a user-friendly library in the open source R language and subsequently release the code in https://github.com/maaliam/EDMANS-elmNN-GPU.git. Therefore R users can freely implement it with the only requirement of having a NVIDIA graphic card. The most computationally demanding operations were identified by performing a sensitivity analysis. As a result, only matrix multiplications were executed in the GPU as they take around 99 % of total execution time. A speedup rate up to 15 times was obtained with this GPU-accelerated ELM in the most computationally expensive scenarios. Moreover, the applicability of the GPU-accelerated ELM was also tested with a typical case of model selection, in which genetic algorithms were used to fine-tune an ELM and training thousands of models is required. In this case, still a speedup of 6 times was obtained.

Downscaling of Solar Irradiation from Satellite Estimates

Solar irradiation databases from satellite estimates are based on images taken from satellites with wide spatial resolution. The rising interest on solar energy technologies and climate change suppose the necessity of high spatial resolution data of solar irradiation. The downscaling of satellite estimates provides an alternative to dense pyranometers networks, which are very expensive to maintain. The methodology proposed is based on the shade impact analysed from a digital elevation model of high spatial resolution. This methodology is applied and validated with on-ground measurements in the Iregua river valley in the Spanish region of La Rioja. Eventually, it is generated a map of the annual sum of solar global irradiation for this valley.

An Algorithm Based on Satellite Observations to Quality Control Ground Solar Sensors: Analysis of Spanish Meteorological Networks

We present a hybrid quality control (QC) for identifying defects in ground sensors of solar radiation. The method combines a window function that flags potential defects in radiation time series with a visual decision support system that eases the detection of false alarms and the identification of the causes of the defects. The core of the algorithm is the window function that filters out groups of daily records where the errors of several radiation products, mainly satellite-based models, are greater than the typical values for that product, region and time of the year.

Stacking ensemble with parsimonious base models to improve generalization capability in the characterization of steel bolted components

Abstract This study presents a new soft computing method to create an accurate and reliable model capable of determining three key points of the comprehensive force–displacement curve of bolted components in steel structures. To this end, a database with the results of a set of finite element (FE) simulations, which represent real responses of bolted components, is utilized to create a stacking ensemble model that combines the predictions of different parsimonious base models. The innovative proposal of this study is using GA-PARSIMONY, a previously published GA-method which searches parsimonious models by optimizing feature selection and hyperparameter optimization processes. Therefore, parsimonious solutions created with a variety of machine learning methods are combined by means of a nested cross-validation scheme in a unique meta-learner in order to increase diversity and minimize the generalization error rate. The results reveal that efficiently combining parsimonious models provides more accurate and reliable predictions as compared to other methods. Thus, the informational model is able to replace costly FE simulations without significantly comprising accuracy and could be implemented in structural analysis software.

Single and Blended Models for Day-Ahead Photovoltaic Power Forecasting

Solar power forecasts are gaining continuous importance as the penetration of solar energy into the grid rises. The natural variability of the solar resource, joined to the difficulties of cloud movement modeling, endow solar power forecasts with a certain level of uncertainty. Important efforts have been carried out in the field to reduce as much as possible the errors. Various approaches have been followed, being the predominant nowadays the use of statistical techniques to model production.