Extreme Learning Machines for Solar Photovoltaic Power Predictions

Al‐Dahidi, Sameer; Ayadi, Osama; Adeeb, Jehad; Alrbai, Mohammad; Qawasmeh, Bashar R.

doi:10.3390/en11102725

Cited by 77 publications

(54 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite this novel research conducted using different hybrid AI models for estimating global solar radiation, there is still room for the improvement of these techniques [34]. Although employing a numerical weather model's estimation to feed machine learning techniques in global solar radiation estimation can enhance model accuracy, this approach has been applied for wind speed estimation [32].…”

Section: Introductionmentioning

confidence: 99%

Global Solar Radiation Prediction Using Hybrid Online Sequential Extreme Learning Machine Model

et al. 2018

View full text Add to dashboard Cite

Accurate global solar radiation prediction is highly essential for related research on renewable energy sources. The cost implication and measurement expertise of global solar radiation emphasize that intelligence prediction models need to be applied. On the basis of long-term measured daily solar radiation data, this study uses a novel regularized online sequential extreme learning machine, integrated with variable forgetting factor (FOS-ELM), to predict global solar radiation at Bur Dedougou, in the Burkina Faso region. Bayesian Information Criterion (BIC) is applied to build the seven input combinations based on speed (W speed ), maximum and minimum temperature (T max and T min ), maximum and minimum humidity (H max and H min ), evaporation (E o ) and vapor pressure deficiency (V PD ). For the difference input parameters magnitudes, seven models were developed and evaluated for the optimal input combination. Various statistical indicators were computed for the prediction accuracy examination. The experimental results of the applied FOS-ELM model demonstrated a reliable prediction accuracy against the classical extreme learning machine (ELM) model for daily global solar radiation simulation. In fact, compared to classical ELM, the FOS-ELM model reported an enhancement in the root mean square error (RMSE) and mean absolute error (MAE) by (68.8-79.8%). In summary, the results clearly confirm the effectiveness of the FOS-ELM model, owing to the fixed internal tuning parameters. Energies 2018, 11, 3415 2 of 19Moreover, several studies have investigated the relationship of the energy level of several countries to their levels of development [2]. Consequently, the findings of these studies have reported a positive relationship of energy utilization with living standards. The level of energy usage in the developed nations is lower. Advanced countries are significantly consuming the energy, which greatly affects the levels of development in backward and developing countries [3].Since energy is the main factor that drives all developmental processes, its effect on human, crops, plants, animals, and ecosystems depends on the form of energy employed [4,5]. Studies have reported two forms of available energy on Earth (renewable and non-renewable energies) [6]. The method employed in harnessing and applying these forms of energy for human use is very important in the way they affect humankind and the immediate environment. The uncontrolled utilization of the nonrenewable form of energy has been linked to several factors such as climate change, global warming, environmental pollution, and other economic and environmental hazards. Similarly, the renewable form of energy, which is globally available at varying levels, ought to be given attention. This form of energy can be obtained from natural processes, and therefore posits minimal or zero impact on humans and their immediate environment.Renewable energy sources have attracted much research interest in the 21st century due to the discoveries of the impact of non-renewable en...

show abstract

Section: Introductionmentioning

confidence: 99%

Global Solar Radiation Prediction Using Hybrid Online Sequential Extreme Learning Machine Model

et al. 2018

View full text Add to dashboard Cite

show abstract

“…It is worth mentioning that different steps are carried out a priori to process/correct the available dataset to effectively use it for the prediction task (Al-Dahidi et al, 2018;Alomari et al, 2018a;Das et al, 2018). For example, solar radiation and associated power production values are shown to be negative and missing in early and late days' hours, respectively.…”

Section: Asu Weather Stationmentioning

confidence: 99%

“…In practice, to further enhance the prediction performance of the ANN, additional neurons are added to the input (b h ) and hidden (b o ) layers which have a value of 1 (or other constant) for shifting the output of the activation functions left or right to assure that the weights' variations is sufficient to enhance the ANN prediction performance (Abuella and Chowdhury, 2015); • − → β h is the weights vector of the connections that connect the output of each h-th neuron to the output node, and • G 1 () and G 2 () are the hidden and output neuron activation functions, respectively. The former is usually a continuous non-polynomial function, whereas the latter is typically a linear function (Al-Dahidi et al, 2018). The "Log-Sigmoid" has been employed as a neuron activation function following an exhaustive search procedure carried out in Al-Dahidi et al (2018) on the same dataset of the ASU solar PV system.…”

Section: Solar Pv Power Prediction Modelingmentioning

confidence: 99%

“…Results showed that GA-SVM model performs better than the standard SVM model. Al-Dahidi et al (2018) investigated the capability of ELM in providing as accurate as possible 1 day-ahead power production predictions of a solar PV system. To this aim, the ELM architecture has been firstly optimized in terms of number of hidden neurons, number of historical (i.e., embedding dimension) ambient temperatures and global solar radiations, and neuron activation functions, then it has been used to predict the solar PV power.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Assessment of Artificial Neural Networks Learning Algorithms and Training Datasets for Solar Photovoltaic Power Production Prediction

et al. 2019

Self Cite

View full text Add to dashboard Cite

The capability of accurately predicting the Solar Photovoltaic (PV) power productions is crucial to effectively control and manage the electrical grid. In this regard, the objective of this work is to propose an efficient Artificial Neural Network (ANN) model in which 10 different learning algorithms (i.e., different in the way in which the adjustment on the ANN internal parameters is formulated to effectively map the inputs to the outputs) and 23 different training datasets (i.e., different combinations of the real-time weather variables and the PV power production data) are investigated for accurate 1 day-ahead power production predictions with short computational time. In particular, the correlations between different combinations of the historical wind speed, ambient temperature, global solar radiation, PV power productions, and the time stamp of the year are examined for developing an efficient solar PV power production prediction model. The investigation is carried out on a 231 kW ac grid-connected solar PV system located in Jordan. An ANN that receives in input the whole historical weather variables and PV power productions, and the time stamp of the year accompanied with Levenberg-Marquardt (LM) learning algorithm is found to provide the most accurate predictions with less computational efforts. Specifically, an enhancement reaches up to 15, 1, and 5% for the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R 2) performance metrics, respectively, compared to the Persistence prediction model of literature.

show abstract

“…Al-Kouz et al [13] proposed a computational model to investigate the effects of dust and temperature on the performance of a photovoltaic system using Artificial Neural Network (ANN) [14] and Extreme Learning Machine (ELM) [15] models. They found that the optimized model predicts a conversion efficiency yielding an R 2 of 91.4%.…”

Section: Introductionmentioning

confidence: 99%

Assessment of Existing Photovoltaic System with Cooling and Cleaning System: Case Study at Al-Khobar City

2019

Self Cite

View full text Add to dashboard Cite

There is no denial that renewable energy is considered to be the most cost-competitive source of clean power in many parts of the world. Saudi Arabia’s vision 2030 aims at achieving the best by using different sources of renewable energy such as solar energy, wind energy, and others. The use of solar energy in particular for power generation will decrease the dependency on oil, and thus, decrease the greenhouse gasses. Solar panels efficiency tends to decrease with the accumulation of dust on their surface. Thus, a cleaning process requires assigning and employing labor, which increases the cost of running as well as high cost of machinery. The current study focuses on assessing and designing a simple auto self-cleaning system in order to improve the efficiency of the solar panel. The results showed that for the Al-Khobar region, Eastern Province, Kingdom of Saudi Arabia, the efficiency of the solar panels after cleaning was increased from 6% to an average of 12% at nominal temperature of 27 °C. In addition, the average power output was increased by 35% during the day time. In addition, the normal efficiency of the solar panels before cooling was between 10% to 15% at 42 °C. After cooling, the temperature of solar cells decreased to 20 °C and the efficiency increased by 7%. Moreover, the output power was increased by 31% with maximum efficiency of 32% at noon time.

show abstract

Extreme Learning Machines for Solar Photovoltaic Power Predictions

Cited by 77 publications

References 34 publications

Global Solar Radiation Prediction Using Hybrid Online Sequential Extreme Learning Machine Model

Global Solar Radiation Prediction Using Hybrid Online Sequential Extreme Learning Machine Model

Assessment of Artificial Neural Networks Learning Algorithms and Training Datasets for Solar Photovoltaic Power Production Prediction

Assessment of Existing Photovoltaic System with Cooling and Cleaning System: Case Study at Al-Khobar City

Contact Info

Product

Resources

About