Shafiqur Rehman

Estimation of global solar radiation using artificial neural networks

This paper introduces a neural network technique for the estimation of global solar radiation. There are 41 radiation data collection stations spread all over the kingdom of Saudi Arabia where the radiation data and sunshine duration information are being collected since 1971. The available data from 31 locations is used for training the neural networks and the data from the other 10 locations is used for testing. The testing data was not used in the modeling to give an indication of the performance of the system in unknown locations. Results indicate the viability of this approach for spatial modeling of solar radiation.

A neural networks approach for wind speed prediction

This paper introduces neural networks technique for wind speed prediction and compares its performance with an autoregressive model. First, we studied the statistical characteristics of mean monthly and daily wind speed in Jeddah, Saudi Arabia. The autocorrelation coefficients are computed and the correlogram is found compatible with the real diurnal variation of mean wind speed. The stochastic time series analysis is found to be suitable for the description of autoregressive model that involves a time lag of one month for the mean monthly prediction and one day for the mean daily wind speed prediction. The results on a testing data indicate that the neural network approach outperforms the AR model as indicated by the prediction graph and by the root mean square errors.

USE OF RADIAL BASIS FUNCTIONS FOR ESTIMATING MONTHLY MEAN DAILY SOLAR RADIATION

The present study utilizes the radial basis functions technique for the estimation of monthly mean daily values of solar radiation falling on horizontal surfaces and compares its performance with that of the multilayer perceptrons network and a classical regression model. In this work, we use solar radiation data from 41 stations that are spread over the Kingdom of Saudi Arabia. The solar radiation data from 31 locations are used for training the neural networks and the data from the remaining 10 locations are used for testing the estimated values. However, the testing data were not used in the modeling or training of the networks to give an indication of the performance of the system at unknown locations. Results indicate the viability of the radial basis for this kind of problem.

Weibull parameters for wind speed distribution in Saudi Arabia

The shape and scale parameters of a Weibull density distribution function are calculated for 10 locations in Saudi Arabia. The daily mean wind speed data from 1970 to mid-1990 are used for this purpose. It is found that the numerical values of the shape parameter vary between 1.7 and 2.7, whereas the value of the scale parameter is found to vary between 3 and 6. It is also concluded from this study that wind data are very well represented by the Weibull distribution function.

Wind power cost assessment at twenty locations in the kingdom of Saudi Arabia

The Kingdom of Saudi Arabia has vast open land and hence has great potential of harnessing solar and wind energy sources for domestic and industrial use. This study proposes to assess wind power cost per kWh of electricity produced using three types of wind electric conversion systems at 20 locations within the Kingdom. These sites cover the eastern, central, and western regions. Hourly values of wind speed recorded for periods of 5.5–13 years (between 1970–1982, in most cases) were used for all 20 locations. Wind duration curves were developed and utilized to calculate the cost per kWh of electricity generated from three chosen wind-machines.

Application of neural networks for the prediction of hourly mean surface temperatures in Saudi Arabia

This paper utilizes artificial neural networks for the prediction of hourly mean values of ambient temperature 24 h in advance. Full year hourly values of ambient temperature are used to train a neural network model for a coastal location — Jeddah, Saudi Arabia. This neural network is trained off-line using back propagation and a batch learning scheme. The trained neural network is successfully tested on temperatures for years other than the one used for training. It requires only one temperature value as input to predict the temperature for the following day for the same hour. The predicted hourly temperature values are compared with the corresponding measured values. The mean percent deviation between the predicted and measured values is found to be 3.16, 4.17 and 2.83 for three different years. These results testify that the neural network can be a valuable tool for hourly temperature prediction in particular and other meteorological predictions in general.

Statistical characteristics of wind in Saudi Arabia

The statistical characteristics of wind at 10 locations in the Kingdom of Saudi Arabia are studied. The autocorrelation coefficients are computed and correlograms are found compatible with the real diurnal variation of mean wind speed for almost all the locations. The stochastic time series analysis is found to be suitable for the description of autoregressive models involving time lags of 1 and 24 h. The forecast wind values obtained from these autoregressive models are compared with the observed wind data for almost all the locations and are found to be in very good agreement.

Solar radiation over Saudi Arabia and comparisons with empirical models

We present a comparison between models developed by the present authors and 16 other models for different geographical and varied meteorological conditions. The comparisons are made using the mean bias error (MBE), root mean square error (RMSE), mean percentage error (MPE), and mean absolute bias error (MABE). These errors are calculated using monthly-mean, measured daily and estimated values of total solar radiation for 41 locations in Saudi Arabia. We find that our latitude, longitude, altitude, and sunshine-duration-dependent model given in Eq. (1)produced the best estimates for global solar radiation. The second- and third-best estimates were obtained from our linear model and other models given in Eq. (2)and Eq. (11), respectively.

Spatial estimation of global solar radiation using geostatistics

The number of radiation data collection stations is limited due to economic reasons. Hence, there is a need for the spatially continuous mapping of solar radiation by estimation. This paper utilizes a geostatistical technique for the estimation of solar radiation in Saudi Arabia. This technique includes five steps: (i) data collection, (ii) univariate analysis, (iii) experimental variogram calculations and model fitting, (iv) estimation using kriging, and (v) plotting contour maps. Variogram models are fitted to measured variograms for each month of the year. Estimates were obtained at 1500 grid points (30 × 50) between a longitude of 36.58°E and 50.00°E, and latitude of 17.17°N and 31.33°N for a grid resolution of 55 × 33 km. These values were used to plot the contour maps of solar radiation for each month of the year. To test the performance of the technique, estimates were obtained at the 41 known locations by systematically excluding one of these points from the known data. The error analysis showed a maximum mean deviation between measured and estimated values of 0.0037 (January) and a minimum of 0.0013 (March and October). The mean percent errors were found to vary between a minimum of 0.5% and a maximum of 1.7%. This technique may be expanded for the spatial estimation of solar radiation on regional and continental scales.

Techno-Economic Potential of Retrofitting Diesel Power Systems with Hybrid Wind-Photovoltaic-Diesel Systems for Off-Grid Electrification of Remote Villages of Saudi Arabia

Recent climatic anomalies such as hot summers, cold winters, hurricanes, and cyclones are all reflections of global warming due to burning of fossil fuels. To combat unprecedented global warming and to mitigate future energy challenges, there is worldwide interest in utilization of renewable sources of energy such as solar-photovoltaic (solar-PV) and wind energy. Other driving forces paving avenue for renewable energy include rapid escalation in oil prices, growing concerns regarding depletion of oil/gas reserves, etc. Retrofitting of diesel systems with hybrid wind-PV-diesel systems is being widely disseminated to reduce diesel fuel consumption and to minimize atmospheric degradation. One of the potential market for deployment of hybrid systems is in remote locations which are driven by diesel generators. The Kingdom of Saudi Arabia (KSA) has a number of remote villages scattered all over the Kingdom. The aim of this study is to analyze wind speed and solar radiation data of Rafha, KSA, and to assess the technical and economic potential of hybrid wind-PV-diesel power systems to meet the load requirements of a typical remote village Rawdhat Bin Habbas (RBH) with annual electrical energy demand of 15,943 MWh. Rafha is located near RBH. The monthly average wind speeds range from 2.99 m/s to 4.84 m/s at 10 m height. The monthly average daily global solar radiation ranges from 3.04 to 7.3 kWh/sq.m. The hybrid systems simulated consist of different combinations of 600 kW wind machines, PV panels, supplemented by diesel generators. National Renewable Energy Laboratorys (NREL) Hybrid Optimization Model for Electric Renewables (HOMER) software has been used to perform the techno-economic study. The simulation results indicate that for a hybrid system comprising of 1.2 MW wind farm capacity (two 600 kW units, 50 m hub-height) and 1.2 MW of PV capacity together with 4.5 MW diesel system (three 1.5 MW units), the renewable energy fraction with 0% annual capacity shortage is 24% (10% wind + 14% PV). The cost of generating energy (COE) from this hybrid wind-PV-diesel system has been found to be 0.118