Application of extreme learning machine for estimating solar radiation from satellite data

Abstract

SUMMARYIn this paper, a simple and fast method based on extreme learning machine (ELM) for the estimation of solar radiation in Turkey was presented. To design the ELM model, satellite data of the National Oceanic and Atmospheric Administration advanced very high-resolution radiometer from 20 locations spread over Turkey were used. The satellite-based land surface temperature, altitude, latitude, longitude, month, and city were applied as input to the ELM, and the output variable is the solar radiation. To show the applicability of the ELM model, a performance comparison in terms of the estimation capability and the learning speed was made between the ELM model and conventional artificial neural network (ANN) model with backpropagation. The comparison results showed that the ELM model gave better estimation than the ANN model for the overall test locations. Moreover, the ELM model was about 23.5 times faster than the ANN model. The method could be used by researchers or scientists to design high-efficiency solar devices such as solar power plant and photovoltaic cell.

Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia

“…Consequently the ELM model has been widely used for the solution of estimation problems in many different fields and is now gaining attention within the climate research and applied engineering community (Acharya et al, 2013;Belayneh and Adamowski, 2012;Şahin et al, 2014). These investigations and others have demonstrated important advantages of the ELM model over the traditional neural network or vector classification schemes.…”

“…However a major challenge encountered by the ANN is the requirement of iterative tuning of model parameters, slow response of the gradient based learning algorithm used and the relatively low prediction accuracy compared to the more advanced ML algorithms (e.g. Acharya et al, 2013;Şahin et al, 2014). Therefore in this study we have adopted a much improved class of ML algorithm, known as extreme learning machine (ELM) as a statistical model in a problem of predicting the monthly Effective Drought Index (EDI) (Byun and Wilhite, 1999).…”

Estimation of monthly evaporative loss using relevance vector machine, extreme learning machine and multivariate adaptive regression spline models

“…The ELM model has been used widely in estimation problems in various fields including climate research (Acharya et al 2013;Belayneh and Adamowski 2012;Deo and Ş ahin 2015a, b;Ş ahin et al 2014). Its primary advantage has been the easiness of development and no requirement of the tuning of model parameters as with the case of ANN models, except the need to set up predefined network architecture.…”

“…These employ data-driven models that rely on the formulation of causal relationships from predictor datasets using linear, non-linear or a mixture both algorithms (e.g. (Deo and Ş ahin 2015a, b;Ş ahin 2012;Ş ahin et al 2014;Tiwari and Adamowski 2013)). Traditional models based on multilinear regression (MLR) and auto-regressive integrand moving average (ARMA) frameworks are common (Adamowski 2008;Goyal et al 2014;Raman and Sunilkumar 1995;Young 1999).…”

Water demand forecasting using extreme learning machines

“…The hidden layer learns patterns from distinct observations and therefore requires no parameter tuning, only a predefined network. The ELM is free from the complications faced by gradient-based algorithms (e.g., learning rate, learning epochs and local minima) [ACHARYA et al 2014;BELAYNEH, ADAMOWSKI 2014;ŞAHIN et al 2014]. Despite their widespread use, ANNs suffer from difficulty in training predictors and may not, therefore, produce a unique solution over various runs due to different weights [COULIBALY, EVORA 2007;KHAN, COULIBALY 2006].…”