On the use of niching genetic algorithms for variable selection in solar radiation estimation

Will, Adrián; Bustos, J.; Bocco, Mónica; Gotay, J.; Lamelas, C.

doi:10.1016/j.renene.2012.06.039

Cited by 46 publications

(24 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The RMSE is found to be 6.0%. Will A et al [18] used Niching Genetic Algorithms (NGA) to select most significant input parameters for estimation of solar radiation in El Colmenar (Tucum an, Argentina). The NGA involves codification of problem, assigning limit to each variable, finding out distance function in the search space, crossover operators and application ratios of crossover operators, initial population size and number of generations.…”

Section: Overview Of Most Influencing Input Parameters For Ann Based mentioning

confidence: 99%

Solar energy potential assessment of western Himalayan Indian state of Himachal Pradesh using J48 algorithm of WEKA in ANN based prediction model

Yadav

Chandel

2015

Renewable Energy

View full text Add to dashboard Cite

a b s t r a c tSolar potential of western Himalayan Indian state of Himachal Pradesh is assessed using Artificial Neural Network (ANN) based global solar radiation (GSR) prediction model. J48 algorithm in Waikato Environment for Knowledge Analysis (WEKA)is used for the selection of input parameters for ANN model for predicting GSR. Most relevant input parameters are found to be temperature, altitude and sunshine hours whereas latitude, longitude, clearness index and extraterrestrial radiation are found to be least influencing variables. The usefulness of J48 algorithm in variable selection is checked by developing five ANN models: ANN-1, ANN-2, ANN-3, ANN-4 and ANN-5. The maximum mean absolute percentage error (MAPE) for ANN-1, ANN-2, ANN-3, ANN-4 and ANN-5 are found to be 16.91%, 16.89%, 16.38%, 6.89% and 9.04% respectively. ANN-5 model is used to develop the solar maps of Himachal Pradesh. The estimated GSR varies from 3.59 to 5.38 kWh/m 2 /day indicating good solar potential for solar energy applications. A correlation is developed between NASA satellite data and ground measured GSR data to find values close to ground measured GSR for different locations. The correlation coefficient is found to be 0.97. Models developed can be used to assess solar potential of any location worldwide.

show abstract

Section: Overview Of Most Influencing Input Parameters For Ann Based mentioning

confidence: 99%

Solar energy potential assessment of western Himalayan Indian state of Himachal Pradesh using J48 algorithm of WEKA in ANN based prediction model

Yadav

Chandel

2015

Renewable Energy

View full text Add to dashboard Cite

show abstract

“…Argentina's Solarimetric Network underwent a continuous decrease in the number of operational stations, in view of this situation, different alternatives were gradually considered in order to improve the available solar radiation data [12]. This situation was also observed by Will et al [13], who stated that in Argentina there are many agricultural regions which lack on radiation data. For this country, diagnostic applications to characterize homogeneous regions of monthly average solar radiation were developed, with GOES-E satellite data.…”

Section: Introductionmentioning

confidence: 93%

Estimation of daily global solar radiation from measured temperatures at Cañada de Luque, Córdoba, Argentina

2013

View full text Add to dashboard Cite

a b s t r a c tSolar radiation is the most important source of renewable energy in the planet; it's important to solar engineers, designers and architects, and it's also fundamental for efficiently determining irrigation water needs and potential yield of crops, among others. Complete and accurate solar radiation data at a specific region are indispensable. For locations where measured values are not available, several models have been developed to estimate solar radiation. The objective of this paper was to calibrate, validate and compare five representative models to predict global solar radiation, adjusting the empirical coefficients to increase the local applicability and to develop a linear model. All models were based on easily available meteorological variables, without sunshine hours as input, and were used to estimate the daily solar radiation at Cañada de Luque (Córdoba, Argentina).As validation, measured and estimated solar radiation data were analyzed using several statistic coefficients. The results showed that all the analyzed models were robust and accurate (R 2 and RMSE values between 0.87 to 0.89 and 2.05 to 2.14, respectively), so global radiation can be estimated properly with easily available meteorological variables when only temperature data are available.Hargreaves-Samani, Allen and Bristow-Campbell models could be used with typical values to estimate solar radiation while Samani and Almorox models should be applied with calibrated coefficients. Although a new linear model presented the smallest R 2 value (R 2 ¼ 0.87), it could be considered useful for its easy application. The daily global solar radiation values produced for these models can be used to estimate missing daily values, when only temperature data are available, and in hydrologic or agricultural applications.

show abstract

“…Niching mechanism is introduced to improve the information exploitation among neighbors of monkeys. The niching method is based upon the natural Ecosystem [33]. As in an ecosystem with different niches having diverse species, niches are applied in NMA.…”

Section: G Niching Monkey Algorithmmentioning

confidence: 99%

Monkey Behavior Based Algorithms - A Survey

Devi¹,

Sathya²

2017

IJISA

View full text Add to dashboard Cite

Abstract-Swarm intelligence algorithms (SIA) are bioinspired techniques based on the intelligent behavior of various animals, birds, and insects. SIA are problemindependent and are efficient in solving real world complex optimization problems to arrive at the optimal solutions. Monkey behavior based algorithms are one among the SIAs first proposed in 2007. Since then, several variants such as Monkey search, Monkey algorithm, and Spider Monkey optimization algorithms have been proposed. These algorithms are based on the tree or mountain climbing and food searching behavior of monkeys either individually or in groups. They were designed with various representations, covering different behaviors of monkeys and hybridizing with the efficient operators and features of other SIAs and Genetic algorithm. They were explored for applications in several fields including bioinformatics, civil engineering, electrical engineering, networking, data mining etc. In this survey, we provide a comprehensive overview of monkey behavior based algorithms and their related literatures and discuss useful research directions to provide better insights for swarm intelligence researchers.

show abstract

On the use of niching genetic algorithms for variable selection in solar radiation estimation

Cited by 46 publications

References 13 publications

Solar energy potential assessment of western Himalayan Indian state of Himachal Pradesh using J48 algorithm of WEKA in ANN based prediction model

Solar energy potential assessment of western Himalayan Indian state of Himachal Pradesh using J48 algorithm of WEKA in ANN based prediction model

Estimation of daily global solar radiation from measured temperatures at Cañada de Luque, Córdoba, Argentina

Monkey Behavior Based Algorithms - A Survey

Contact Info

Product

Resources

About