Predictive Model of Solar Irradiance Using Artificial Intelligence

2021 ◽  
pp. 519-538
Author(s):  
Umang Soni ◽  
Saksham Gupta ◽  
Taranjeet Singh ◽  
Yash Vardhan ◽  
Vipul Jain
Keyword(s):  
Solar Irradiance ◽  
Solar Power ◽  
Indian Subcontinent ◽  
Meteorological Data ◽  
Ann Model ◽  
Financial Model ◽  
Factors Affecting ◽  
Svm Model ◽  
High Prediction ◽  
Set Up

Solar power in India is growing at a tremendous pace. India's solar power capacity is 20 GW and has grown 8-fold since 2014. Assessing the solar potential in India is thus the need of the hour. The objective of this study is to make an optimized prediction model of the monthly potential of solar irradiance of the Indian Subcontinent, by utilizing hour-wise unstructured voluminous (80 million line item) satellite-based data from 609 locations for 15 years. The variables chosen are temperature, pressure, relative humidity, month, year, latitude, longitude, altitude, DHI, DNI, and GHI. Combining predictive models using combinations of SVM, ANN, and RF for factors affecting solar irradiance. This model's performance has been evaluated by its accuracy. Accuracy for DHI, DNI, GHI values on testing data evaluated through the SVM model is 95.11%, 93.25%, and 96.88%, respectively, whereas accuracy evaluated through the ANN model is 94.18%, 91.60%, and 95.90%, respectively. The achieved high prediction accuracy makes the SVM, ANN, and RF model very robust. This model with a sustainable financial model can thus be used to identify major locations to set up solar farms in the present and future and the feasibility of its establishment, wherever local meteorological data measuring facilities are not available in India. Along with the air temperature, air pressure, and humidity predictive interrelation model created to aid the irradiance model this can be used for climate predictions in the Indian sub-continental region.

Predictive Model of Solar Irradiance Using Artificial Intelligence

2020 ◽  
Vol 10 (2) ◽  
pp. 81-98
Author(s):  
Umang Soni ◽  
Saksham Gupta ◽  
Taranjeet Singh ◽  
Yash Vardhan ◽  
Vipul Jain
Keyword(s):  
Solar Irradiance ◽  
Solar Power ◽  
Indian Subcontinent ◽  
Meteorological Data ◽  
Ann Model ◽  
Financial Model ◽  
Factors Affecting ◽  
Svm Model ◽  
High Prediction ◽  
Set Up

Solar power in India is growing at a tremendous pace. India's solar power capacity is 20 GW and has grown 8-fold since 2014. Assessing the solar potential in India is thus the need of the hour. The objective of this study is to make an optimized prediction model of the monthly potential of solar irradiance of the Indian Subcontinent, by utilizing hour-wise unstructured voluminous (80 million line item) satellite-based data from 609 locations for 15 years. The variables chosen are temperature, pressure, relative humidity, month, year, latitude, longitude, altitude, DHI, DNI, and GHI. Combining predictive models using combinations of SVM, ANN, and RF for factors affecting solar irradiance. This model's performance has been evaluated by its accuracy. Accuracy for DHI, DNI, GHI values on testing data evaluated through the SVM model is 95.11%, 93.25%, and 96.88%, respectively, whereas accuracy evaluated through the ANN model is 94.18%, 91.60%, and 95.90%, respectively. The achieved high prediction accuracy makes the SVM, ANN, and RF model very robust. This model with a sustainable financial model can thus be used to identify major locations to set up solar farms in the present and future and the feasibility of its establishment, wherever local meteorological data measuring facilities are not available in India. Along with the air temperature, air pressure, and humidity predictive interrelation model created to aid the irradiance model this can be used for climate predictions in the Indian sub-continental region.

The Spinning Quality Control Management Based on Decision Making by Data Mining Techniques

2018 ◽  
Vol 7 (1) ◽  
pp. 72
Author(s):  
Khalid AA Abakar ◽  
Chongwen Yu
Keyword(s):  
Data Mining ◽  
Kernel Functions ◽  
Support Vector ◽  
Ann Model ◽  
Data Mining Techniques ◽  
Yarn Quality ◽  
Yarn Properties ◽  
Svm Model ◽  
Rbf Kernel

This work demonstrated the possibility of using the data mining techniques such as artificial neural networks (ANN) and support vector machine (SVM) based model to predict the quality of the spinning yarn parameters. Three different kernel functions were used as SVM kernel functions which are Polynomial and Radial Basis Function (RBF) and Pearson VII Function-based Universal Kernel (PUK) and ANN model were used as data mining techniques to predict yarn properties. In this paper, it was found that the SVM model based on Person VII kernel function (PUK) have the same performance in prediction of spinning yarn quality in comparison with SVM based RBF kernel. The comparison with the ANN model showed that the two SVM models give a better prediction performance than an ANN model.

scholarly journals The features of the coastal fronts in the Eastern Guangdong coastal waters during the downwelling-favorable wind period

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Chaoyu Yang ◽  
Haibin Ye
Keyword(s):  
Coastal Waters ◽  
Meteorological Data ◽  
Pearson Correlation ◽  
Ocean Model ◽  
Ekman Pumping ◽  
Zonal Distribution ◽  
Factors Affecting ◽  
China Sea ◽  
Hybrid Coordinate Ocean Model ◽  
The Mean

AbstractA coastal front was detected in the eastern Guangdong (EGD) coastal waters during a downwelling-favorable wind period by using the diffuse attenuation coefficient at 490 nm (Kd(490)). Long-term satellite data, meteorological data and hydrographic data collected from 2003 to 2017 were jointly utilized to analyze the environmental factors affecting coastal fronts. The intensities of the coastal fronts were found to be associated with the downwelling intensity. The monthly mean Kd(490) anomalies in shallow coastal waters less than 25 m deep along the EGD coast and the monthly mean Ekman pumping velocities retrieved by the ERA5 dataset were negatively correlated, with a Pearson correlation of − 0.71. The fronts started in October, became weaker and gradually disappeared after January, extending southwestward from the southeastern coast of Guangdong Province to the Wanshan Archipelago in the South China Sea (SCS). The cross-frontal differences in the mean Kd(490) values could reach 3.7 m−1. Noticeable peaks were found in the meridional distribution of the mean Kd(490) values at 22.5°N and 22.2°N and in the zonal distribution of the mean Kd(490) values at 114.7°E and 114.4°E. The peaks tended to narrow as the latitude increased. The average coastal surface currents obtained from the global Hybrid Coordinate Ocean Model (HYCOM) showed that waters with high nutrient and sediment contents in the Fujian and Zhejiang coastal areas in the southern part of the East China Sea could flow into the SCS. The directions and lengths of the fronts were found to be associated with the flow advection.

scholarly journals Cancer Discrimination Using Fourier Transform Near-Infrared Spectroscopy with Chemometric Models

2015 ◽  
Vol 2015 ◽  
pp. 1-8 ◽  
Author(s):  
Hui Chen ◽  
Zan Lin ◽  
Chao Tan
Keyword(s):  
Cancer Diagnosis ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Principal Component ◽  
Classification Model ◽  
Support Vector ◽  
Biomedical Analysis ◽  
First Derivative ◽  
Svm Model ◽  
High Prediction

Near-infrared (NIR) spectroscopy technique offers many potential advantages as tool for biomedical analysis since it enables the subtle biochemical signatures related to pathology to be detected and extracted. In conjunction with advanced chemometrics, NIR spectroscopy opens the possibility of their use in cancer diagnosis. The study focuses on the application of near-infrared (NIR) spectroscopy and classification models for discriminating colorectal cancer. A total of 107 surgical specimens and a corresponding NIR diffuse reflection spectral dataset were prepared. Three preprocessing methods were attempted and least-squares support vector machine (LS-SVM) was used to build a classification model. The hybrid preprocessing of first derivative and principal component analysis (PCA) resulted in the best LS-SVM model with the sensitivity and specificity of 0.96 and 0.96 for the training and 0.94 and 0.96 for test sets, respectively. The similarity performance on both subsets indicated that overfitting did not occur, assuring the robustness and reliability of the developed LS-SVM model. The area of receiver operating characteristic (ROC) curve was 0.99, demonstrating once again the high prediction power of the model. The result confirms the applicability of the combination of NIR spectroscopy, LS-SVM, PCA, and first derivative preprocessing for cancer diagnosis.

Ticket Income Distribution of Urban Rail Transit in Network Operating Condition

2011 ◽  
Vol 243-249 ◽  
pp. 4375-4380
Author(s):  
Yuan Chun Huang ◽  
Jian Li ◽  
Haize Pan
Keyword(s):  
Income Distribution ◽  
Urban Rail Transit ◽  
Ratio Method ◽  
Rail Transit ◽  
Matching Algorithm ◽  
Factors Affecting ◽  
Urban Rail ◽  
Set Up ◽  
Urban Rail Transit Network ◽  
Factor Matching

Through analyzing the factors affecting passengers’ path-choice, the corresponding principles and rules of the ticket income distribution are put forward and the new model of the Urban Rail Transit Network in Beijing is set up in the paper. Through the deformation of the urban rail transit and the simplification of the lines, the topology of the urban rail transit lines is abstracted into an undirected connection graph. Breadth-priority optimization algorithm is applied to search the effective paths between the OD and the flow-matching ratio is acquired by calculating based on multi-factor matching algorithm, in which many relevant numerical examples are analyzed to verify the feasibility of the dual-ratio method and to summarize the characteristics of the project.

scholarly journals Building the Sun4Cast System: Improvements in Solar Power Forecasting

2018 ◽  
Vol 99 (1) ◽  
pp. 121-136 ◽  
Author(s):  
Sue Ellen Haupt ◽  
Branko Kosović ◽  
Tara Jensen ◽  
Jeffrey K. Lazo ◽  
Jared A. Lee ◽  
...  
Keyword(s):  
Decision Making ◽  
Value Chain ◽  
Solar Irradiance ◽  
Collaborative Design ◽  
Solar Power ◽  
Spatial Scales ◽  
Weather Prediction ◽  
Solar Array ◽  
Solar Power Forecasting ◽  
Power Forecasting

Abstract As integration of solar power into the national electric grid rapidly increases, it becomes imperative to improve forecasting of this highly variable renewable resource. Thus, a team of researchers from the public, private, and academic sectors partnered to develop and assess a new solar power forecasting system, Sun4Cast. The partnership focused on improving decision-making for utilities and independent system operators, ultimately resulting in improved grid stability and cost savings for consumers. The project followed a value chain approach to determine key research and technology needs to reach desired results. Sun4Cast integrates various forecasting technologies across a spectrum of temporal and spatial scales to predict surface solar irradiance. Anchoring the system is WRF-Solar, a version of the Weather Research and Forecasting (WRF) numerical weather prediction (NWP) model optimized for solar irradiance prediction. Forecasts from multiple NWP models are blended via the Dynamic Integrated Forecast (DICast) System, which forms the basis of the system beyond about 6 h. For short-range (0–6 h) forecasts, Sun4Cast leverages several observation-based nowcasting technologies. These technologies are blended via the Nowcasting Expert System Integrator (NESI). The NESI and DICast systems are subsequently blended to produce short- to midterm irradiance forecasts for solar array locations. The irradiance forecasts are translated into power with uncertainties quantified using an analog ensemble approach and are provided to the industry partners for real-time decision-making. The Sun4Cast system ran operationally throughout 2015 and results were assessed. This paper analyzes the collaborative design process, discusses the project results, and provides recommendations for best-practice solar forecasting.

scholarly journals Simulating the Stress-Strain Relationship of Geomaterials by Support Vector Machine

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Hongbo Zhao ◽  
Zenghui Huang ◽  
Zhengsheng Zou
Keyword(s):  
Support Vector Machine ◽  
Constitutive Relationship ◽  
Support Vector ◽  
Nonlinear Relationship ◽  
Ann Model ◽  
Stress Strain ◽  
Svm Model ◽  
Strain Relationship ◽  
Artificial Neural Network Ann ◽  
Relationship Of

Stress-strain relationship of geomaterials is important to numerical analysis in geotechnical engineering. It is difficult to be represented by conventional constitutive model accurately. Artificial neural network (ANN) has been proposed as a more effective approach to represent this complex and nonlinear relationship, but ANN itself still has some limitations that restrict the applicability of the method. In this paper, an alternative method, support vector machine (SVM), is proposed to simulate this type of complex constitutive relationship. The SVM model can overcome the limitations of ANN model while still processing the advantages over the traditional model. The application examples show that it is an effective and accurate modeling approach for stress-strain relationship representation for geomaterials.

scholarly journals Experimental and artificial neural network approach for forecasting of traffic air pollution in urban areas: The case of Subotica

2010 ◽  
Vol 14 (suppl.) ◽  
pp. 79-87 ◽  
Author(s):  
Bogdana Vujic ◽  
Srdjan Vukmirovic ◽  
Goran Vujic ◽  
Nebojsa Jovicic ◽  
Gordana Jovicic ◽  
...  
Keyword(s):  
Air Pollution ◽  
Urban Areas ◽  
Meteorological Data ◽  
Model Development ◽  
Ambient Air ◽  
Ann Model ◽  
Statistical Parameters ◽  
Neural Network Approach ◽  
Starting Point ◽  
Artificial Neural

In the recent years, artificial neural networks (ANNs) have been used to predict the concentrations of various gaseous pollutants in ambient air, mainly to forecast mean daily particle concentrations. The data on traffic air pollution, irrespective of whether they are obtained by measuring or modelling, represent an important starting point for planning effective measures to improve air quality in urban areas. The aim of this study was to develop a mathematical model for predicting daily concentrations of air pollution caused by the traffic in urban areas. For the model development, experimental data have been collected for 10 months, covering all four seasons. The data about hourly concentration levels of suspended particles with aerodynamic diameter less than 10 ?m (PM10) and meteorological data (temperature, air humidity, speed and direction of wind), measured at the measuring station in the town of Subotica from June 2008 to March 2009, served as the basis for developing an ANN-based model for forecasting mean daily concentrations of PM10. The quality of the ANN model was assessed on the basis of the statistical parameters, such as RMSE, MAE, MAPE, and r.

scholarly journals A countrywide analysis of 27 solar power plants installed at different climates

2022 ◽  
Vol 12 (1) ◽  
Author(s):  
Talat Ozden
Keyword(s):  
Power Plant ◽  
Alternative Energy ◽  
Power Plants ◽  
Solar Power ◽  
Meteorological Data ◽  
Energy Sources ◽  
Climate Classification ◽  
Climate Type ◽  
Monthly Average ◽  
The World

AbstractThe world is still heavily using nonconventional energy sources, which are worryingly based on carbon. The step is now alternative energy sources hoping that they will be more environmentally friendly. One of the important energy conversion forms by using these sources is photovoltaic solar systems. These type of power plants is on the increase in everyday on the world. Before investment a solar power plant in a specified region, a techno-economic analyse is performed for that power plant by using several meteorological data like solar irradiance and ambient temperature. However, this analyses generally lacks evaluation on effects of climatic and geographical conditions. In this work, 5 years of data of 27 grid-connected photovoltaic power plants are investigated, which are installed on seven different climate types in Turkey. Firstly, the power plants are categorized considering the tilt angles and Köppen–Gieger climate classification. The performance evaluations of the plants are mainly conducted using monthly average efficiencies and specific yields. The monthly average efficiencies, which were classified using the tilts and climate types were from 12 to 17%, from 12 to 16% and from 13 to 15% for tilts 30°/10°, 25° and 20°, respectively. The variation in the specific yields decrease with elevation as y(x) =  − 0.068x + 1707.29 (kWh/kWp). As the performances of photovoltaic systems for some locations within the Csb climatic regions may relatively lower than some other regions with same climate type. Thus, techno-economic performance for PVPP located in this climate classification should be carefully treated.

scholarly journals Multivariate clustering of reindeer herding districts in Sweden according to range prerequisites for reindeer husbandry

Rangifer ◽  
2009 ◽  
Vol 27 (2) ◽  
pp. 107-119
Author(s):  
Henrik Lundqvist ◽  
Öje Danell
Keyword(s):  
Geographical Information Systems ◽  
Large Scale ◽  
Global Climate ◽  
Meteorological Data ◽  
Principal Component ◽  
Geographical Information ◽  
Reindeer Herding ◽  
Factors Affecting ◽  
Decision Tools ◽  
Forage Value

The 51 reindeer herding districts in Sweden vary in productivity and prerequisites for reindeer herding. In this study we characterize and group reindeer herding districts based on relevant factors affecting reindeer productivity, i.e. topography, vegetation, forage value, habitat fragmentation and reachability, as well as season lengths, snow fall, ice-crust probability, and insect harassment, totally quantified in 15 variables. The herding districts were grouped into seven main groups and three single outliers through cluster analyses. The largest group, consisting of 14 herding districts, was further divided into four subgroups. The range properties of herding districts and groups of districts were characterized through principal component analyses. By comparisons of the suggested grouping of herding districts with existing administrative divisions, these appeared not to coincide. A new division of herding districts into six administrative sets of districts was suggested in order to improve administrative planning and management of the reindeer herding industry. The results also give possibilities for projections of alterations caused by an upcoming global climate change. Large scale investigations using geographical information systems (GIS) and meteorological data would be helpful for administrative purposes, both nationally and internationally, as science-based decision tools in legislative, economical, ecological and structural assessments. Abstract in Swedish / Sammanfattning: Multivariat gruppering av svenska samebyar baserat på renbetesmarkernas grundförutsettningar Svenska renskötselområdet består av 51 samebyar som varierar i produktivitet och förutsättningar för renskötsel. Vi analyserade variationen mellan samebyar med avseende på 15 variabler som beskriver topografi, vegetation, betesvärde, fragmentering av betesmarker, klimat, skareförekomst och aktivitet av parasiterande insekter och vi föreslår en indelning av samebyar i tio grupper. Den största gruppen, som bestod av 14 samebyar, delades vidare in i 4 undergrupper. Klusteranalyser med 4 olika linkage-varianter användes till att gruppera samebyarna. Principalkomponentsanalys användes för att kartlägga undersökta variabler och de resulterande samebygruppernas karaktär. Samebygrupperna följde inte länsgränser och tre samebyar föll ut som enskilda grupper. Denna undersökning ger underlag för jämförelser mellan samebyar med beaktande av likheter och olikheter i fråga om produktivitet och funktionella särdrag istället för länsgränser och historik. Vi föreslår en ny administrativ indelning i sex områden som skulle kunna fungera som ett alternativt underlag för planering och beslut som rör produktionsaspekter i rennäringen. Resultaten ger också underlag för förutsägelser av förändringar i samebyars produktionsförutsättningar till följd av klimatförändringar.

Sign in / Sign up

Export Citation Format

Share Document