Kasra Mohammadi

Extreme learning machine based prediction of daily dew point temperature

An ELM-based model is proposed to predict daily dew point temperature.Weather data for two Iranian stations with different climate conditions were used.ELM model enjoys much greater predictions capability than SVM and ANN.Application of the proposed ELM model would be highly promising and appealing. The dew point temperature is a significant element particularly required in various hydrological, climatological and agronomical related researches. This study proposes an extreme learning machine (ELM)-based model for prediction of daily dew point temperature. As case studies, daily averaged measured weather data collected for two Iranian stations of Bandar Abass and Tabass, which enjoy different climate conditions, were used. The merit of the ELM model is evaluated against support vector machine (SVM) and artificial neural network (ANN) techniques. The findings from this research work demonstrate that the proposed ELM model enjoys much greater prediction capability than the SVM and ANN models so that it is capable of predicting daily dew point temperature with very favorable accuracy. For Tabass station, the mean absolute bias error (MABE), root mean square error (RMSE) and correlation coefficient (R) achieved for the ELM model are 0.3240?C, 0.5662?C and 0.9933, respectively, while for the SVM model the values are 0.7561?C, 1.0086?C and 0.9784, respectively and for the ANN model are 1.0324?C, 1.2589?C and 0.9663, respectively. For Bandar Abass station, the MABE, RMSE and R for the ELM model are 0.5203?C, 0.6709?C and 0.9877, respectively whereas for the SVM model the values are 1.0413?C, 1.2105?C and 0.9733, and for the ANN model are 1.3205?C, 1.5530?C and 0.9617, respectively. The study results convincingly advocate that ELM can be employed as an efficient method to predict daily dew point temperature with much higher precision than the SVM and ANN techniques.

Using self-adaptive evolutionary algorithm to improve the performance of an extreme learning machine for estimating soil temperature

Self-adaptive evolutionary (SaE) algorithm.To estimate daily soil temperature at 6 different depths.Tmin, Tmax and Tavg are considered as final inputs. In this study, the self-adaptive evolutionary (SaE) agent is employed to structure the contributing elements to process the management of extreme learning machine (ELM) architecture based on a logical procedure. In fact, the SaE algorithm is utilized for possibility of enhancing the performance of the ELM to estimate daily soil temperature (ST) at 6 different depths of 5, 10, 20, 30, 50 and 100cm. In the developed SaE-ELM model, the network hidden node parameters of the ELM are optimized using SaE algorithm. The precision of the SaE-ELM is then compared with the ELM model. Daily weather data sets including minimum, maximum and average air temperatures (Tmin, Tmax and Tavg), atmospheric pressure (P) and global solar radiation (RS) collected for two Iranian stations of Bandar Abbas and Kerman with different climate conditions have been utilized. After primary evaluation, Tmin, Tmax and Tavg are considered as final inputs for the ELM and SaE-ELM models due to their high correlations with ST at all depths. The achieved results for both stations reveal that both ELM and SaE-ELM models offer desirable performance to estimate daily ST at all depths; nevertheless, a slightly more precision can be obtained by the SaE-ELM model. The performance of the ELM and SaE-ELM models are verified against genetic programming (GP) and artificial neural network (ANN) models developed in this study. For Bandar Abbass station, the obtained mean absolute bias error (MABE) and correlation coefficient (R) for the ELM model at different depths are in the range of 0.9116-1.5988?C and 0.9023-0.9840, respectively while for the SaE-ELM model they are in the range of 0.8660-1.5338?C and 0.9084-0.9893, respectively. In addition, for Kerman Station the attained MABE and RMSE for the ELM model vary from 1.6567 to 2.4233?C and 0.8661 to 0.9789, respectively while for the SaE-ELM model they vary from 1.5818 to 2.3422?C and 0.8736 to 0.9831, respectively.

Modelling thermal comfort of visitors at urban squares in hot and arid climate using NN-ARX soft computing method

Visitors utilize the urban space based on their thermal perception and thermal environment. The thermal adaptation engages the user’s behavioural, physiological and psychological aspects. These aspects play critical roles in user’s ability to assess the thermal environments. Previous studies have rarely addressed the effects of identified factors such as gender, age and locality on outdoor thermal comfort, particularly in hot, dry climate. This study investigated the thermal comfort of visitors at two city squares in Iran based on their demographics as well as the role of thermal environment. Assessing the thermal comfort required taking physical measurement and questionnaire survey. In this study, a non-linear model known as the neural network autoregressive with exogenous input (NN-ARX) was employed. Five indices of physiological equivalent temperature (PET), predicted mean vote (PMV), standard effective temperature (SET), thermal sensation votes (TSVs) and mean radiant temperature (Tmrt) were trained and tested using the NN-ARX. Then, the results were compared to the artificial neural network (ANN) and the adaptive neuro-fuzzy inference system (ANFIS). The findings showed the superiority of the NN-ARX over the ANN and the ANFIS. For the NN-ARX model, the statistical indicators of the root mean square error (RMSE) and the mean absolute error (MAE) were 0.53 and 0.36 for the PET, 1.28 and 0.71 for the PMV, 2.59 and 1.99 for the SET, 0.29 and 0.08 for the TSV and finally 0.19 and 0.04 for the Tmrt.

Influence of introducing various meteorological parameters to the Angstrom-Prescott model for estimation of global solar radiation

AbstractThis study aims to recognize that whether introducing various meteorological parameters to the Angström–Prescott (A–P) model eventuates in enhancing the precision of monthly mean global solar radiation estimation in cities of Bandar Abbas and Jask, situated in the south coast of Iran. To identify the significance of the average, maximum and minimum ambient temperatures, average and maximum relative humidity as well as water vapor and sea level pressures, seven models have been chosen from the literature. Using the long-term measured data and via statistical regression technique, the new regression coefficients have been developed for the original A–P model and the other seven nominated models. The models’ performances have been appraised via commonly utilized statistical indicators. The results indicated that the new models provided only minor improvements over the traditional A–P model; therefore, as more complexity is associated with introducing different meteorological parameters, their applications are not appealing practically. Making comparisons with the existing models developed using PSO (particle swarm optimization) technique demonstrated the superiority of the new established A–P models of this study; consequently, even without any improvement, the simple A–P models are indeed qualified for accurate estimation of global solar radiation in cities of Bandar Abbas and Jask and their neighboring.

Horizontal global solar radiation estimation using hybrid SVM-firefly and SVM-wavelet algorithms: a case study

Nowadays, investigations are being performed to identify proper approaches for prediction of solar radiation in the absence of measured data. In this context, application of hybrid techniques has attracted many attentions since it offers some advantages by utilizing the specific nature of each technique to achieve more preciseness. This study aims at assessing the suitability of two hybrid approaches to predict monthly mean daily horizontal global solar radiation. For this aim, two hybrid approaches by integrating support vector machine (SVM) with firefly algorithm (FFA) and wavelet transform (WT) algorithm named, respectively, SVM-FFA and SVM-WT are developed. Then two different SVM-FFA and SVM-WT models are established by considering different meteorological parameters: (1) relative sunshine duration and (2) relative sunshine duration, air temperature difference, average air temperature and relative humidity. The results indicate that hybridizing the SVM with FFA and WT algorithms would be promising as both SVM-FFA and SVM-WT approaches show higher performance than single SVM. Also, model (2) of each hybrid approach provides more accuracy. Furthermore, the statistical results reveal the superiority of SVM-WT over SVM-FFA in terms of predictions accuracy.

Investigation of wind resources in Timimoun region, Algeria

This article presents an analysis of wind power resources in Timimoun region using the Wind Atlas Analysis and Application Program. This application takes in consideration the effects of sheltering obstacles, surface roughness changes, and the terrain variations on the wind speed variability and power output. The analysis part is composed of generating the wind speed and direction data for developing the wind atlas. Hourly wind data records over a period of 3 years from 2001 to 2003 were obtained from Société Nationale de l’Electricité et du Gaz R&D Office. The wind data measurements were made at an elevation of 17 m above the ground level. The mean values of wind speeds, wind power density, the predominant wind directions, the frequency distribution, and the Weibull distribution parameters (c and k) were determined. Finally, the energy yield was estimated using the VESTAS V90-2.0-MW wind turbine as the reference turbine in the southwestern region of Algeria, Timimoun. RETScreen model was also used to estimate the wind power potential employing the long-term annual mean wind speed data over a period of almost 22 years between 1984 and 2005.

Erratum to: Application of extreme learning machine for estimation of wind speed distribution

Unfortunately, the co-author affiliation Dalibor Petković has been incorrectly published in the original publication.

Wind-solar energy potentials for three free trade and industrial zones of Iran

This paper presents analysis of wind-solar potential for major three free trade and industrial zones in Iran. For this purpose, the available measured solar and wind data of the cities (Chabahar, Kish and Salafchegan) including horizontal global solar radiation, and wind speed data at 10 m elevation were analyzed. Also, key solar parameters like monthly mean global, beam and diffuse solar radiation as well as clearness index were investigated too. For analyzing the wind potentials, Weibull Distribution Function (WDF) was performed at different heights. The annual wind speeds and wind powers of locations at 20, 30 and 40 m heights were calculated. The study results clearly demonstrate that wind as a renewable energy source can supply a portion of the energy demands for Kish and Salafchegan with yearly wind powers of 111.28 W/m2 and 114.34 W/m2, respectively ranked in class 2 which are considered marginal for wind power development. It was also illustrated that all three locations had great potentials for utilizing different solar energy applications. In addition, the monthly, seasonal, seim-yearly and yearly optimum tilt angles of south facing solar collectors and panels were determined. For all locations adjusting the tilt angle twice a year or in other words, the semi-yearly tilt adjustment for two periods of warm and cold were suggested.

Feasibility of installing wind turbines for electricity generation in Jarandagh, Iran

In this study, the wind energy potential for the purpose of electricity generation in Jarandagh, Iran was investigated. The measured wind speed data collected between 2008 and 2009 at 40 m is utilized to analyze the wind energy potential and wind characteristics at 40 and 70m. According to the obtained results the annual mean wind speed at the heights of 40 and 70 were 7.74m/s and 8.73 m/s, respectively. Also, the annual mean power density vary from 324.70 to 1267.06 W/m2 and from 450.28 to 1661.62 W/m2, respectively. The results demonstrated that Jarandagh enjoys excellent potential for wind energy exploitation in 8 months of the year. The electricity production and economic evaluation of four large-scale wind turbine models for installation at 70m height were assessed. The energy cost estimation results showed that investing on wind farm construction using all nominated turbines is very profitable and among all turbines, Suzlon S66/1.25MW model with energy cost of 0.0357

A support vector machine–firefly algorithm-based model for global solar radiation prediction

/kWh is the best economic option.