scholarly journals Tree Search Fuzzy NARX Neural Network Fault Detection Technique for PV Systems with IoT Support

Electronics ◽  
2020 ◽  
Vol 9 (7) ◽  
pp. 1087
Author(s):  
Emad Natsheh ◽  
Sufyan Samara
Keyword(s):  
Solar Radiation ◽  
Energy Production ◽  
Alternative Energy ◽  
Pv System ◽  
Photovoltaic Panel ◽  
Pv Systems ◽  
Irregular Operations ◽  
Network Fault ◽  
Nonlinear Autoregressive ◽  
Main Factor

The photovoltaic (PV) panel’s output energy depends on many factors. As they are becoming the leading alternative energy source, it is essential to get the best out of them. Although the main factor for maximizing energy production is proportional to the amount of solar radiation reaching the photovoltaic panel surface, other factors, such as temperature and shading, influence them negatively. Moreover, being installed in a dynamic and frequently harsh environment causes a set of reasons for faults, defects, and irregular operations. Any irregular operation should be recognized and classified into faults that need attention and, therefore, maintenance or as being a regular operation due to changes in some surrounding factors, such as temperature or solar radiation. Besides, in case of faults, it would be helpful to identify the source and the cause of the problem. Hence, this study presented a novel methodology that modeled a PV system in a tree-like hierarchy, which allowed the use of a fuzzy nonlinear autoregressive network with exogenous inputs (NARX) to detect and classify faults in a PV system with customizable granularity. Moreover, the used methodology enabled the identification of the exact source of fault(s) in a fully automated way. The study was done on a string of eight PV panels; however, the paper discussed using the algorithm on a more extensive PV system. The used fuzzy NARX algorithm in this study was able to classify the faults that appeared in up to five out of the eight PV panels and to identify the faulty PV panels with high accuracy. The used hardware could be controlled and monitored through a Wi-Fi connection, which added support for Internet of Things applications.

Preliminary results on the determination of solar energy potential using LiDAR technology

2015 ◽  
Vol 6 (1) ◽  
pp. 11-17 ◽  
Author(s):  
G. Szabó ◽  
P. Enyedi ◽  
Gy. Szabó ◽  
I. Fazekas ◽  
T. Buday ◽  
...  
Keyword(s):  
Solar Radiation ◽  
Solar Energy ◽  
Energy Production ◽  
Alternative Energy ◽  
Surface Model ◽  
Solar Panels ◽  
Energy Potential ◽  
Potential Surfaces ◽  
Large Power ◽  
Automatic Data

According to the challenge of the reduction of greenhouse gases, the structure of energy production should be revised and the increase of the ratio of alternative energy sources can be a possible solution. Redistribution of the energy production to the private houses is an alternative of large power stations at least in a partial manner. Especially, the utilization of solar energy represents a real possibility to exploit the natural resources in a sustainable way. In this study we attempted to survey the roofs of the buildings with an automatic method as the potential surfaces of placing solar panels. A LiDAR survey was carried out with 12 points/m2 density as the most up-to-date method of surveys and automatic data collection techniques. Our primary goal was to extract the buildings with special regard to the roofs in a 1 km2 study area, in Debrecen. The 3D point cloud generated by the LiDAR was processed with MicroStation TerraScan software, using semi-automatic algorithms. Slopes, aspects and annual solar radiation income of roof planes were determined in ArcGIS10 environment from the digital surface model. Results showed that, generally, the outcome can be regarded as a roof cadaster of the buildings with correct geometry. Calculated solar radiation values revealed those roof planes where the investment for photovoltaic solar panels can be feasible.

scholarly journals Performance estimation of photovoltaic energy production

2020 ◽  
Vol 13 (3) ◽  
pp. 267-285
Author(s):  
Laura Casula ◽  
Guglielmo D’Amico ◽  
Giovanni Masala ◽  
Filippo Petroni
Keyword(s):  
Solar Radiation ◽  
Energy Production ◽  
Performance Estimation ◽  
Spot Price ◽  
Solar Panels ◽  
Pv System ◽  
Vector Autoregressive Models ◽  
Vector Autoregressive ◽  
Pv Panel ◽  
Payment Policies

AbstractThis article deals with the production of energy through photovoltaic (PV) panels. The efficiency and quantity of energy produced by a PV panel depend on both deterministic factors, mainly related to the technical characteristics of the panels, and stochastic factors, essentially the amount of incident solar radiation and some climatic variables that modify the efficiency of solar panels such as temperature and wind speed. The main objective of this work is to estimate the energy production of a PV system with fixed technical characteristics through the modeling of the stochastic factors listed above. Besides, we estimate the economic profitability of the plant, net of taxation or subsidiary payment policies, considered taking into account the hourly spot price curve of electricity and its correlation with solar radiation, via vector autoregressive models. Our investigation ends with a Monte Carlo simulation of the models introduced. We also propose the pricing of some quanto options that allow hedging both the price risk and the volumetric risk.

A Novelty Control Strategy for the Photovoltaic Supercapacitor and Battery Hybrids Storage System

2011 ◽  
Vol 301-303 ◽  
pp. 1522-1527
Author(s):  
Yi Yuan ◽  
Mohamed Machmoum ◽  
Salvy Bourguet ◽  
Nicolas Amelon
Keyword(s):  
Control Strategy ◽  
Storage System ◽  
Pv System ◽  
Photovoltaic Panel ◽  
Pv Systems ◽  
Power Product ◽  
Pv Panel ◽  
The Cost ◽  
Large Burst ◽  
Reasonable Energy

Most photovoltaic (PV) systems can supply continuous energy by using storage applications. Generally, the battery is employed for finishing this aim. The expense of the battery occupies a large part in the whole PV system. However, the constant variations of both photovoltaic panel power product and load power demand reduce the life of the battery. At the same time, for providing several large burst power demands generated by the motor based application startup, the sizing of battery should be enlarged. Both of them increase the cost of the PV system. Therefore, supercapacitor is integrated into this system. With a reasonable energy control strategy among the PV panel, supercapacitor and battery, the battery’s life could be prolonged and its size can be reduced. A PV system with hybrid storage applications is established in the Matlab/Simulink. Two different loads and weather situations are used to prove the efficiency of this control strategy.

scholarly journals Tailored Algorithms for Anomaly Detection in Photovoltaic Systems

Energies ◽  
2020 ◽  
Vol 13 (1) ◽  
pp. 225 ◽  
Author(s):  
Pedro Branco ◽  
Francisco Gonçalves ◽  
Ana Cristina Costa
Keyword(s):  
Time Series ◽  
Alternative Energy ◽  
Weather Conditions ◽  
Electricity Production ◽  
Pv System ◽  
Detection Algorithms ◽  
Pv Systems ◽  
Adverse Weather ◽  
Full Capacity ◽  
And Performance

The fastest-growing renewable source of energy is solar photovoltaic (PV) energy, which is likely to become the largest electricity source in the world by 2050. In order to be a viable alternative energy source, PV systems should maximise their efficiency and operate flawlessly. However, in practice, many PV systems do not operate at their full capacity due to several types of anomalies. We propose tailored algorithms for the detection of different PV system anomalies, including suboptimal orientation, daytime and sunrise/sunset shading, brief and sustained daytime zero-production, and low maximum production. Furthermore, we establish simple metrics to assess the severity of suboptimal orientation and daytime shading. The proposed detection algorithms were applied to a set of time-series of electricity production in Portugal, which are based on two periods with distinct weather conditions. Under favourable weather conditions, the algorithms successfully detected most of the time-series labelled with either daytime or sunrise/sunset shading, and with either sustained or brief daytime zero-production. There was a relatively low percentage of false positives, such that most of the anomaly detections were correct. As expected, the algorithms tend to be more robust under favourable rather than under adverse weather conditions. The proposed algorithms may prove to be useful not only to research specialists, but also to energy utilities and owners of small- and medium-sized PV systems, who may thereby effortlessly monitor their operation and performance.

scholarly journals Opera.DL: Deep Learning Modelling for Photovoltaic System Monitoring

Proceedings ◽  
2019 ◽  
Vol 31 (1) ◽  
pp. 50 ◽  
Author(s):  
G. Almonacid-Olleros ◽  
G. Almonacid ◽  
J. I. Fernandez-Carrasco ◽  
Javier Medina Quero
Keyword(s):  
Deep Learning ◽  
Environmental Conditions ◽  
Energy Production ◽  
Photovoltaic System ◽  
Analytical Models ◽  
Context Aware ◽  
Learning Models ◽  
Pv System ◽  
Pv Systems ◽  
The University

In this paper we present Deep Learning (DL) modelling to forecast the behaviour and energy production of a photovoltaic (PV) system. Using deep learning models rather than following the classical way (analytical models of PV systems) presents an outstanding advantage: context-aware learning for PV systems, which is independent of the deployment and configuration parameters of the PV system, its location and environmental conditions. These deep learning models were developed within the Ópera Digital Platform using the data of the UniVer Project, which is a standard PV system that was in place for the last twenty years in the Campus of the University of Jaén (Spain). From the obtained results, we conclude that the combination of CNN and LSTM is an encouraging model to forecast the behaviour of PV systems, even improving the results from the standard analytical model.

Performance Analysis of PV Systems: Case study of Palestine Technical University (PTUK) PV Plant

2021 ◽  
Vol 9 (1) ◽  
pp. 10-21
Author(s):  
Mahmoud Ismail
Keyword(s):  
Performance Analysis ◽  
Energy Production ◽  
The Other ◽  
Performance Ratio ◽  
Solar Irradiation ◽  
Pv System ◽  
Pv Systems ◽  
Science Building ◽  
University Buildings

Performance ratio is one of the indicators used to describe the effectiveness of the PV systems. The sustainability of the PV system year after year as well as its reliability can be checked by measuring the performance ratio each year. This indicator will also enable us to carry out a comparison between the performances of different PV systems. In this paper, the performance ratios for five PV systems installed on the roof tops of some of PTUK university buildings have been calculated on monthly and yearly basis. The analysis has been carried out using the available data (energy production and solar irradiation) for the year 2019. It was found that the performance ratio has higher values for May and September in comparison with other months. On the other hand, its lowest values were obtained in winter months. This trend can be observed for all of the PV clusters on the five buildings.  When taking into account the overall system, the highest value for the performance ratio was 0.89, which was for September, whereas its lowest value of 0.70 was obtained in January. The performance ratio, which was calculated on yearly basis for the overall system, was found to be 0.80. When considering each building separately, the lowest value was 0.44 for the “Services” building whereas the highest value was 0.94 for the Science building.

scholarly journals Nowcasting the Output Power of PV Systems

2018 ◽  
Vol 61 ◽  
pp. 00010 ◽  
Author(s):  
Marius Paulescu ◽  
Oana Mares ◽  
Ciprian Dughir ◽  
Eugenia Paulescu
Keyword(s):  
Output Power ◽  
Solar Irradiance ◽  
Energy Production ◽  
Ground Level ◽  
Measured Data ◽  
State Model ◽  
Clearness Index ◽  
Pv System ◽  
Pv Systems ◽  
Two State Model

This paper presents an innovative procedure for nowcasting the energy production of PV systems. The procedure is relayed on a new version of two-state model for forecasting solar irradiance at ground level and a simplified description of the PV system. The results of testing the proposed procedure against on field measured data are discussed. Generally, the proposed procedure demonstrates a better performance than the main competitor based on ARIMA forecasting of the clearness index.

scholarly journals Techno-economic analysis for the role of single end energy user in mitigating GHG emission

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Waqas Ahmed ◽  
Jamil Ahmed Sheikh ◽  
Muhammad Nouman ◽  
Mian Farhan Ullah ◽  
M. A. Parvez Mahmud
Keyword(s):  
Solar Radiation ◽  
Economic Analysis ◽  
Energy Production ◽  
Fossil Fuel ◽  
Meteorological Data ◽  
Green Energy ◽  
Pv System ◽  
Ghg Mitigation ◽  
Energy Demands

Abstract Background Households, as end energy users, consume grid electricity to meet their energy demands. However, grids across the globe for energy production are majorly based on fossil fuel technology and make the highest contributions to global warming and climate change due to greenhouse gases (GHG) emissions. This generic study aims to investigate the minute role of a single-end energy consumer in GHG mitigation by switching to a rooftop PV system to meet his energy demands and trading surplus energy to the grid through its techno-economic analysis. Method For the study impact, NASA Meteorological Data are used to select an ideal single energy user equipped with a 10-kW PV system based on annual average daily solar radiation and ambient temperature through MATLAB/Simulink, for 11 populous cities in Pakistan. Helioscope software is used to select tilt and azimuthal angles to maximize the solar radiation intercept. Afterward, RETScreen software is used for cost, financial and GHG analysis. Result and conclusion A single end energy user equipped with a 10-kW PV system switched to a green energy source from a fossil fuel-based grid has the potential to avoid the burning of 3570.6 L of gasoline by producing 16,832 kWh of green energy per annum, while financially recovering the 10-kW PV system’s 7337$ grid-tied investment in 5 years (equity) and in 9 years (equity) in a 9077$ stand-alone system over its 25-year life. This approach provides relief to end energy users from high priced grid electricity through environmental friendliness by mitigating 8.3 tons of CO2 equivalent emissions per annum from energy production, while providing relief to the main grid by grid stabilization through peak shaving, in the broad sense.

scholarly journals Fýsileiki virkjunar sólarorku á norðurslóðum: Reynsla af sólarpanelum IKEA á Íslandi

2019 ◽  
Vol 25 ◽  
pp. 1-19
Author(s):  
Sindri Þrastarson ◽  
Björn Marteinsson ◽  
Hrund Ólöf Andradóttir
Keyword(s):  
Energy Production ◽  
Production Capacity ◽  
Production Costs ◽  
Performance Ratio ◽  
Solar Irradiation ◽  
Specific Yield ◽  
Solar Pv ◽  
Solar Panels ◽  
Pv System ◽  
Pv Systems

The efficiency and production costs of solar panels have improved dramatically in the past decades. The Nordic countries have taken steps in instigating photovoltaic (PV) systems into energy production despite limited incoming solar radiation in winter. IKEA installed the first major PV system in Iceland with 65 solar panels with 17.55 kW of production capacity in the summer of 2018. The purpose of this research was to assess the feasibility of PV systems in Reykjavík based on solar irradiation measurements, energy production of a PV array located at IKEA and theory. Results suggests that net irradiation in Reykjavík (64°N, 21° V) was on average about 780 kWh/m2 per year (based on years 2008-2018), highest 140 kWh/m2 in July and lowest 1,8 kWh/m2 in December. Maximum annual solar power is generated by solar panels installed at a 40° fixed angle. PV panels at a lower angle produce more energy during summer. Conversely, higher angles maximize production in the winter. The PV system produced over 12 MWh over a one-year period and annual specific yield was 712 kWh/kW and performance ratio 69% which is about 10% lower than in similar studies in cold climates. That difference can be explained by snow cover, shadow falling on the panels and panels not being fixed at optimal slope. Payback time for the IKEA PV system was calculated 24 years which considers low electricity prices in Reykjavik and unforeseen high installation costs. Solar energy could be a feasible option in the future if production- and installation costs were to decrease and if the solar PV output could be sold to the electric grid in Iceland.

scholarly journals Thermal building upgrade with off-grid PV system: a Polish case

2021 ◽  
Vol 14 (7) ◽  
Author(s):  
Sylwia Wciślik ◽  
Dagmara Kotrys-Działak
Keyword(s):  
Solar Radiation ◽  
Alternative Energy ◽  
Net Present Value ◽  
Photovoltaic System ◽  
Solar Irradiation ◽  
Total Solar Radiation ◽  
Pv System ◽  
Alternative Energy Sources ◽  
High Investment ◽  
The Difference

AbstractNowadays, one of the basic requirements for thermally upgraded buildings involves limitation in CO2 emission even by over 90%. To fulfil these criteria, it is necessary to use alternative energy sources and photovoltaics constitutes a reasonable option for this. This paper addresses an analysis of the efficiency and profitability of a photovoltaic system located in the geometric center of Europe-Poland, where the intensity of solar irradiation is not very high compared to other European countries. The difference of total solar radiation density between Poland and Malta is 49.2%, from analysis based on SolarGIS base. The PV Lighthouse calculator was used for global power density and photon current examination for a Polish city and locations of the highest and the lowest solar radiation values, Malta and Finland, respectively. This case study concerns a thermally upgraded building; a gas boiler was replaced by a heat pump supported by an off-grid PV system. To achieve a reduction in CO2 emission of 90%, it is necessary to install 182 PV cells, which generates high investment costs. An investment is entirely profitable with 70% of funding with Simple Pay Back Time, SPBT~7 years although Net Present Value, NPV>0; Internal Rate of Return, IRR=10.6%.

Sign in / Sign up

Export Citation Format

Share Document