scholarly journals Small-Scale Solar Photovoltaic Power Prediction for Residential Load in Saudi Arabia Using Machine Learning

Energies ◽  
2021 ◽  
Vol 14 (20) ◽  
pp. 6759
Author(s):  
Mohamed Mohana ◽  
Abdelaziz Salah Saidi ◽  
Salem Alelyani ◽  
Mohammed J. Alshayeb ◽  
Suhail Basha ◽  
...  

Photovoltaic (PV) systems have become one of the most promising alternative energy sources, as they transform the sun’s energy into electricity. This can frequently be achieved without causing any potential harm to the environment. Although their usage in residential places and building sectors has notably increased, PV systems are regarded as unpredictable, changeable, and irregular power sources. This is because, in line with the system’s geographic region, the power output depends to a certain extent on the atmospheric environment, which can vary drastically. Therefore, artificial intelligence (AI)-based approaches are extensively employed to examine the effects of climate change on solar power. Then, the most optimal AI algorithm is used to predict the generated power. In this study, we used machine learning (ML)-based algorithms to predict the generated power of a PV system for residential buildings. Using a PV system, Pyranometers, and weather station data amassed from a station at King Khalid University, Abha (Saudi Arabia) with a residential setting, we conducted several experiments to evaluate the predictability of various well-known ML algorithms from the generated power. A backward feature-elimination technique was applied to find the most relevant set of features. Among all the ML prediction models used in the work, the deep-learning-based model provided the minimum errors with the minimum set of features (approximately seven features). When the feature set is greater than ten features, the polynomial regression model shows the best prediction, with minimal errors. Comparing all the prediction models, the highest errors were associated with the linear regression model. In general, it was observed that with a small number of features, the prediction models could minimize the generated power prediction’s mean squared error value to approximately 0.15.

2019 ◽  
Vol 8 (1) ◽  
pp. 34-52 ◽  
Author(s):  
M. Asif ◽  
Mohammad A. Hassanain ◽  
Kh Md Nahiduzzaman ◽  
Haitham Sawalha

Purpose The Kingdom of Saudi Arabia (KSA) is facing a rapid growth in energy demand mainly because of factors like burgeoning population, economic growth, modernization and infrastructure development. It is estimated that between 2000 and 2017 the power consumption has increased from 120 to 315 TWh. The building sector has an important role in this respect as it accounts for around 80 percent of the total electricity consumption. The situation is imposing significant energy, environmental and economic challenges for the country. To tackle these problems and curtail its dependence on oil-based energy infrastructure, KSA is aiming to develop 9.5 GW of renewable energy projects by 2030. The campus of the King Fahd University of Petroleum and Minerals (KFUPM) has been considered as a case study. In the wake of recently announced net-metering policy, the purpose of this paper is to investigate the prospects of rooftop application of PV in buildings. ArcGIS and PVsyst software have been used to determine the rooftop area and undertake PV system modeling respectively. Performance of PV system has been investigated for both horizontal and tilted installations. The study also investigates the economic feasibility of the PV application with the help of various economic parameters such as benefit cost ratio, simple payback period (SPP) and equity payback periods. An environmental analysis has also been carried out with the help of RETScreen software to determine the savings in greenhouse gas emissions as a result of PV system. Design/methodology/approach This study examines the buildings of the university campus for utilizable rooftop areas for PV application. Various types of structural, architectural and utilities-related features affecting the use of building roofs for PV have been investigated to determine the corrected area. To optimize the performance of the PV system as well as space utilization, modeling has been carried out for both horizontal and tilted applications of panels. Detailed economic and environmental assessments of the rooftop PV systems have also been investigated in detail. Modern software tools such as PVsyst, ArcGIS and RETScreen have also been used for system design calculations. Findings Saudi Arabia is embarking on a massive solar energy program as it plans to have over 200 GW of installed capacity by 2030. With solar energy being the most abundant of the available renewable resource for the country, PV is going to be one of the main technologies in achieving the set targets. The country has, however, unlike global trends, traditionally overlooked the small-scale and building-related application of solar PV, focusing mainly on larger projects. This study explores the prospects of utilization of solar PV on building roofs. Building rooftops are constrained in terms of PV application owing to wide ranging obstacles that can be classified into five types – structural, services, accessibility, maintenance and others. The total building rooftop area in the study zone, calculated through ArcGIS has been found to be 857,408 m2 of which 352,244 m2 is being used as car parking and hence is not available for PV application. The available roof area, 505,165 m2 is further hampered by construction and utilities related features including staircases, HVAC systems, skylights, water tanks and satellite dish antennas. Taking into account the relevant obstructive features, the net rooftop area covered by PV panels has been found to be in the range 25–41 percent depending upon the building typology, with residential buildings offering the least. To optimize both the system efficiency and space utilization, PV modeling has been carried out with the help of PVsyst software for both the tilted and horizontal installations. In terms of output, PV panels with tilt angle of 24° have been found to be 9 percent more efficient compared to the horizontally installed ones. Modeling results provide a net annual output 37,750 and 46,050 MWh from 21.44 and 28.51 MW of tilted and horizontal application of PV panels, sufficient to respectively meet 16 and 20 percent of the total campus electricity requirements. Findings of the economic analysis reveal the average SPP for horizontal and tilted applications of the PV to be 9.2 and 8.4 years, respectively. The benefit cost ratio for different types of buildings for horizontal and tilted application has been found to be ranging between 0.89 and 2.08 and 0.83 and 2.15, respectively. As electricity tariff in Saudi Arabia has been increased this year by as much as 45 percent and there are plans to remove $54bn of subsidy by 2020, the cost effectiveness of PV systems will be greatly helped. Application of PV in buildings can significantly improve their environmental performance as the findings of this study reveal that the annual greenhouse gas emission in the KFUPM campus can be reduced by as much as 40,199 tons carbon dioxide equivalent. Originality/value The PV application on building roof especially from economic perspective is an area which has not been addressed thus far. Khan et al. (2017) studied the power generation potential for PV application on residential buildings in KSA. Asif (2016) also investigated power output potential of PV system in different types of buildings. Dehwas et al. (2018) adopted a detailed approach to determine utilizability of PV on residential building roofs. None of these studies have covered the economics of PV systems. This study attempts to address the gap and contribute to the scholarship on the subject. It targets to determine the power output from different types of building in an urban environment by taking into account building roof conditions. It also provides detailed economic assessment of PV systems. Subsequent environmental savings are also calculated.


Energies ◽  
2019 ◽  
Vol 12 (16) ◽  
pp. 3158 ◽  
Author(s):  
Ngoc Thien Le ◽  
Watit Benjapolakul

Rooftop photovoltaics (PV) systems are attracting residential customers due to their renewable energy contribution to houses and to green cities. However, customers also need a comprehensive understanding of system design configuration and the related energy return from the system in order to support their PV investment. In this study, the rooftop PV systems from many high-volume installed PV systems countries and regions were collected to evaluate the lifetime energy yield of these systems based on machine learning techniques. Then, we obtained an association between the lifetime energy yield and technical configuration details of PV such as rated solar panel power, number of panels, rated inverter power, and number of inverters. Our findings reveal that the variability of PV lifetime energy is partly explained by the difference in PV system configuration. Indeed, our machine learning model can explain approximately 31 % ( 95 % confidence interval: 29–38%) of the variant energy efficiency of the PV system, given the configuration and components of the PV system. Our study has contributed useful knowledge to support the planning and design of a rooftop PV system such as PV financial modeling and PV investment decision.


Energies ◽  
2019 ◽  
Vol 12 (5) ◽  
pp. 790 ◽  
Author(s):  
Matej Žnidarec ◽  
Zvonimir Klaić ◽  
Damir Šljivac ◽  
Boris Dumnić

Expanding the number of photovoltaic (PV) systems integrated into a grid raises many concerns regarding protection, system safety, and power quality. In order to monitor the effects of the current harmonics generated by PV systems, this paper presents long-term current harmonic distortion prediction models. The proposed models use a multilayer perceptron neural network, a type of artificial neural network (ANN), with input parameters that are easy to measure in order to predict current harmonics. The models were trained with one-year worth of measurements of power quality at the point of common coupling of the PV system with the distribution network and the meteorological parameters measured at the test site. A total of six different models were developed, tested, and validated regarding a number of hidden layers and input parameters. The results show that the model with three input parameters and two hidden layers generates the best prediction performance.


2020 ◽  
Vol 173 ◽  
pp. 02005
Author(s):  
Amjad Ali ◽  
Muzafar Hussain ◽  
Fahad A. Al-Sulaiman ◽  
Shahbaz Tahir ◽  
Kashif Irshad ◽  
...  

This paper presents the economic, technical, and environmental performance of a GridConnected PV System (GCPVS) designed for a residential building consisting of 14 families for six major cities of Saudi Arabia. HOMER Pro was used in this study for the evaluation of the techno-economical & environmental performance of the GCPVS. Neom, which a newly developed city on the west coast of Saudi Arabia, which has never been investigated before for such conditions, is also considered among the selected cities in the current study and thus makes the work novel. This analysis demonstrates that CO2 emissions are considerably higher as compared to their counterparts in both; grid alone and grid + PV systems. The studies concluded that the grid + PV system was feasible for all cities. Parameters like Net Present Cost (NPC), Cost of Energy (COE), and excess electricity were proportional to the PV penetration, but with the increase of PV penetration, CO2 emissions decreased. For the grid + PV system, Neom was found to be the most economical as it demonstrated the lowest NPC ($80, 199) and CO2 emissions (63, 664 kg/yr), among others. Neom, as a rapidly developing city in the North-West of Saudi Arabia, possesses great potential for PV. The results of this study can be used to study further PV systems in different climate zones of Saudi Arabia.


Electronics ◽  
2019 ◽  
Vol 8 (12) ◽  
pp. 1443 ◽  
Author(s):  
Abdullah Alshahrani ◽  
Siddig Omer ◽  
Yuehong Su ◽  
Elamin Mohamed ◽  
Saleh Alotaibi

Decarbonisation, energy security and expanding energy access are the main driving forces behind the worldwide increasing attention in renewable energy. This paper focuses on the solar photovoltaic (PV) technology because, currently, it has the most attention in the energy sector due to the sharp drop in the solar PV system cost, which was one of the main barriers of PV large-scale deployment. Firstly, this paper extensively reviews the technical challenges, potential technical solutions and the research carried out in integrating high shares of small-scale PV systems into the distribution network of the grid in order to give a clearer picture of the impact since most of the PV systems installations were at small scales and connected into the distribution network. The paper reviews the localised technical challenges, grid stability challenges and technical solutions on integrating large-scale PV systems into the transmission network of the grid. In addition, the current practices for managing the variability of large-scale PV systems by the grid operators are discussed. Finally, this paper concludes by summarising the critical technical aspects facing the integration of the PV system depending on their size into the grid, in which it provides a strong point of reference and a useful framework for the researchers planning to exploit this field further on.


Author(s):  
Shakir Khan

<p>The World Health Organization (WHO) reported the COVID-19 epidemic a global health emergency on January 30 and confirmed its transformation into a pandemic on March 11. China has been the hardest hit since the virus's outbreak, which may date back to late November. Saudi Arabia realized the danger of the Coronavirus in March 2020, took the initiative to take a set of pre-emptive decisions that preceded many countries of the world, and worked to harness all capabilities to confront the outbreak of the epidemic. Several researchers are currently using various mathematical and machine learning-based prediction models to estimate this pandemic's future trend. In this work, the SEIR model was applied to predict the epidemic situation in Saudi Arabia and evaluate the effectiveness of some epidemic control measures, and finally, providing some advice on preventive measures.</p>


2021 ◽  
Vol 11 (19) ◽  
pp. 9318
Author(s):  
Mladen Bošnjaković ◽  
Ante Čikić ◽  
Boris Zlatunić

A large drop in prices of photovoltaic (PV) equipment, an increase in electricity prices, and increasing environmental pressure to use renewable energy sources that pollute the environment significantly less than the use of fossil fuels have led to a large increase in installed roof PV capacity in many parts of the world. In this context, this paper aims to analyze the cost-effectiveness of installing PV systems in the rural continental part of Croatia on existing family houses. A typical example is a house in Dragotin, Croatia with an annual consumption of 4211.70 kWh of electricity on which PV panels are placed facing south under the optimal slope. The calculation of the optimal size of a PV power plant with a capacity of 3.6 kW, without battery energy storage, was performed by the Homer program. The daily load curve was obtained by measuring the electricity consumption at the facility every hour during a characteristic day in the month of June. As most of the activities are related to electricity consumption, repeating during most days of the year, and taking into account seasonal activities, daily load curves were made for a characteristic day in each month of the year. Taking into account the insolation for the specified location, using the Internet platform Solargis Prospect, hourly data on the electricity production of selected PV modules for a characteristic day in each month were obtained. Based on the previous data, the electricity injected into the grid and taken from the grid was calculated. Taking into account the current tariffs for the sale and purchase of electricity, investment prices, and maintenance of equipment, the analysis shows that such a PV system can pay off in 10.5 years without government incentives.


2020 ◽  
Author(s):  
Yue Ruan ◽  
Alexis Bellot ◽  
Zuzana Moysova ◽  
Garry D. Tan ◽  
Alistair Lumb ◽  
...  

<b><i>Objective </i></b> <p>We analyzed data from inpatients with diabetes admitted to a large university hospital to predict the risk of hypoglycemia through the use of machine learning algorithms.<i></i></p> <p><b><i>Research Design and Methods </i></b></p> <p>Four years of data was extracted from a hospital electronic health record system. This included laboratory and point-of-care blood glucose (BG) values to identify biochemical and clinically significant hypoglycaemic episodes (BG <u><</u> 3.9 and <u><</u> 2.9mmol/L respectively). We used patient demographics, administered medications, vital signs, laboratory results and procedures performed during the hospital stays to inform the model. Two iterations of the dataset included the doses of insulin administered and the past history of inpatient hypoglycaemia. Eighteen different prediction models were compared using the area under curve of the receiver operating characteristics (AUC_ROC) through a ten-fold cross validation.</p> <p><b><i>Results</i></b> </p> <p>We analyzed data obtained from 17,658 inpatients with diabetes who underwent 32,758 admissions between July 2014 and August 2018. The predictive factors from the logistic regression model included people undergoing procedures, weight, type of diabetes, oxygen saturation level, use of medications (insulin, sulfonylurea, metformin) and albumin levels. The machine learning model with the best performance was the XGBoost model (AUC_ROC 0.96. This outperformed the logistic regression model which had an AUC_ROC of 0.75 for the estimation of the risk of clinically significant hypoglycaemia.<b><i></i></b></p> <p><b><i>Conclusions</i></b></p> <p>Advanced machine learning models are superior to logistic regression models in predicting the risk of hypoglycemia in inpatients with diabetes. Trials of such models should be conducted in real time to evaluate their utility to reduce inpatient hypoglycaemia.</p>


2020 ◽  
Author(s):  
Yue Ruan ◽  
Alexis Bellot ◽  
Zuzana Moysova ◽  
Garry D. Tan ◽  
Alistair Lumb ◽  
...  

<b><i>Objective </i></b> <p>We analyzed data from inpatients with diabetes admitted to a large university hospital to predict the risk of hypoglycemia through the use of machine learning algorithms.<i></i></p> <p><b><i>Research Design and Methods </i></b></p> <p>Four years of data was extracted from a hospital electronic health record system. This included laboratory and point-of-care blood glucose (BG) values to identify biochemical and clinically significant hypoglycaemic episodes (BG <u><</u> 3.9 and <u><</u> 2.9mmol/L respectively). We used patient demographics, administered medications, vital signs, laboratory results and procedures performed during the hospital stays to inform the model. Two iterations of the dataset included the doses of insulin administered and the past history of inpatient hypoglycaemia. Eighteen different prediction models were compared using the area under curve of the receiver operating characteristics (AUC_ROC) through a ten-fold cross validation.</p> <p><b><i>Results</i></b> </p> <p>We analyzed data obtained from 17,658 inpatients with diabetes who underwent 32,758 admissions between July 2014 and August 2018. The predictive factors from the logistic regression model included people undergoing procedures, weight, type of diabetes, oxygen saturation level, use of medications (insulin, sulfonylurea, metformin) and albumin levels. The machine learning model with the best performance was the XGBoost model (AUC_ROC 0.96. This outperformed the logistic regression model which had an AUC_ROC of 0.75 for the estimation of the risk of clinically significant hypoglycaemia.<b><i></i></b></p> <p><b><i>Conclusions</i></b></p> <p>Advanced machine learning models are superior to logistic regression models in predicting the risk of hypoglycemia in inpatients with diabetes. Trials of such models should be conducted in real time to evaluate their utility to reduce inpatient hypoglycaemia.</p>


The local supply and supply scheme called micro grid will become a significant chance due to the latest development of small scale distributed generators such as OV on demand side. Renewable energy structure has been far reaching due to ecological demands. The essence of the structure for renewable energy is very efficient in using distributed generation within the structure of the power scheme. The low voltage DC distribution system is becoming essential as the amount of DC applications is increasing in our regular needs. Power provided through the AC distribution mechanism of low voltage requires both AC/DC converter to delivers the DC batteries. MGs would be fitted battery like energy storage devices. Since PVs and batteries primarily operates through DC, it is possible to emphasize the benefit of the DC distribution scheme over AC production. This article recommends an ideal MG layout including AC and DC distribution device choice. This article also describes qualitatively the benefit of micro grid with DC production, termed as DCMG through housing client studies assuming different kinds of home appliances.


Sign in / Sign up

Export Citation Format

Share Document