4.5 Article Proceedings Paper

Artificial neural network modeling and sensitivity analysis for soiling effects on photovoltaic panels in Morocco

Journal

SUPERLATTICES AND MICROSTRUCTURES
Volume 127, Issue -, Pages 139-150

Publisher

ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD
DOI: 10.1016/j.spmi.2017.12.037

Keywords

Solar energy; Soiling effect; Solar PV glass; ANN application; PAWN sensitivity analysis

Funding

  1. Moroccan Research Institute IRESEN (Institut de Recherche en Energie Solaire et Energies Nouvelles)
  2. CONACYT-SENER project [254667]

Ask authors/readers for more resources

In the present work, an Artificial Neural Network (ANN) methodology for studying and modeling the soiling effect on solar photovoltaic (PV) glass is presented. To perform the study, a solar PV glazing was exposed outdoor at the home solar energy platform of Physic of Semi-conductors and Solar Energy research structure (PSES) at Mohammed V University in Rabat, Morocco. Regular measurements from April 20, to December 31, 2016, were carried out to monitor the soiling rate changes over time. Meteorological data were used as input variables for ANN modeling. The model performance was evaluated using a statistical comparison between experimental and simulated values. Results show that the implementation of Levenberg-Marquardt backpropagation algorithm, and the active functions Tansig, and Purline achieve the best estimations (R-2 = 0.928) in an ANN architecture 6-35-1. Additionally, a sensitivity analysis approach was employed to determine the effect of input parameters on model output and the behavior of the model with the variation of each input parameter. Sensitivity analysis results indicate that the most influential parameter for PV soiling rate was the relative humidity, followed by wind direction. The ANN model coupled with sensitivity analysis show be a promising framework for its application in smart sensors on cleaning systems for PV modules to improve their operational efficiency. (C) 2017 Elsevier Ltd. All rights reserved.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.5
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Energy & Fuels

Multivariate inverse artificial neural network to analyze and improve the mass transfer of ammonia in a Plate Heat Exchanger-Type Absorber with NH3/H2O for solar cooling applications

Oscar May Tzuc, Jorge J. Chan-Gonzalez, Ivan E. Castaneda-Robles, Francisco Lezama-Zarraga, Moises Moheno-Barrueta, Mario Jimenez Torres, Roberto Best

Summary: This study presents a numerical approach to optimize the absorption flux into a heat exchanger in absorption refrigeration systems. The researchers trained an artificial neural network to correlate the operational parameters and thermal properties with a high precision. They identified the variables that have the most impact on absorption flux optimization and proposed a method to improve mass transfer in the heat exchanger. The results obtained are highly important for the development of more competitive absorption cooling systems.

ENERGY EXPLORATION & EXPLOITATION (2022)

Article Engineering, Electrical & Electronic

Global sensitivity analysis for a real-time electricity market forecast by a machine learning approach: A case study of Mexico

E. Cruz May, A. Bassam, Luis J. Ricalde, M. A. Escalante Soberanis, O. Oubram, O. May Tzuc, Alma Y. Alanis, A. Livas-Garcia

Summary: This study combines global sensitivity analysis with data-driven techniques to evaluate the interaction of the Mexican electricity market and assess the impact of parameters on locational marginal prices. It compares three artificial intelligence techniques for predicting electricity prices under real-time market conditions. The results show that the impact of variables fluctuates depending on market and consumption conditions.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2022)

Article Chemistry, Multidisciplinary

Transient Differentiation Maximum Power Point Tracker (Td-MPPT) for Optimized Tracking under Very Fast-Changing Irradiance: A Theoretical Approach for Mobile PV Applications

Roberto I. Rico-Camacho, Luis J. Ricalde, Ali Bassam, Manuel I. Flota-Banuelos, Alma Y. Alanis

Summary: The paper proposes an algorithm for MPPT that accurately identifies power changes caused by irradiance changes and achieves maximum power point tracking through accurate judgment of the perturbation direction, resulting in better tracking performance compared to traditional algorithms.

APPLIED SCIENCES-BASEL (2022)

Article Green & Sustainable Science & Technology

Temperature dependence on hydrogen production from hydrolysis reaction of recycled aluminum

M. A. Escalante Soberanis, Caridad Vales-Pinzon, Emanuel Hernandez-Nunez, Manuel Flota-Banuelos, J. Medina, R. Quintal-Palomo, Liliana San-Pedro, Miguel Ruiz-Gomez

Summary: In this research, the effect of temperature on the hydrolysis reaction of recycled aluminum for hydrogen production was evaluated. The study found that the highest production of H-2 occurred at 50 degrees C, with a purity of 93.33%. However, at room temperature, the reaction efficiency was still high, with a production of 660 mL of H-2 in 268 s. The physicochemical characterization of the solid residues showed that they contained aluminum, sodium, and oxygen, with the main crystalline phases being aluminum hydroxide and sodium aluminum oxide hydrate. Overall, the production of H-2 from recycled aluminum at room temperature was found to be a viable option for clean power generation with lower energy consumption and financial costs compared to traditional technologies.

CLEAN TECHNOLOGIES AND ENVIRONMENTAL POLICY (2023)

Article Environmental Sciences

Waterless cleaning technique for photovoltaic panels on dual-axis tracker

Dounia Dahlioui, Soukaina Medaghri Alaoui, Bouchra Laarabi, Abdelfettah Barhdadi

Summary: This research investigated the adaptability of cleaning systems to solar trackers and found that automatic cleaning had similar efficiency to manual cleaning, reducing energy losses and increasing energy production. Economic analysis revealed that automatic cleaning had lower costs and faster payback time, making it suitable for highly polluted arid regions.

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH (2023)

Article Environmental Sciences

Characterization of dust particles in South India and investigation on soiling image analysis for photovoltaic application

Bouchra Laarabi, Natarajan Rajasekar, Nikhil Pattath Gopi, Abdelfettah Barhdadi

Summary: The present study characterizes dust particles in South India through image analysis, focusing on factors influencing the accuracy of the analysis. Results show that the shape and size of dust particles vary with the tilt angle of the samples. Moreover, using three images produces more precise and representative results.

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH (2023)

Article Environmental Sciences

Evaluating the distribution of soil particle size on glass samples by a new generation of optical microscopy for solar PV applications

Hajar Chamali, Abdelouahed Dahrouch, Bouchra Laarabi, El Houssaine Fathi, Abdelfettah Barhdadi

Summary: This study proposes an image analysis technique that combines a new generation optical microscope and image processing software for studying dirt particles on PV modules in three different regions. The method provides an accurate assessment of particle size distribution and shows that only three images are needed to represent the entire sample area.

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH (2023)

Article Energy & Fuels

Experimental Study of an Inverter Control for Reactive Power Compensation in a Grid-Connected Solar Photovoltaic System Using Sliding Mode Control

Manuel Flota-Banuelos, Maria Espinosa-Trujillo, Jose Cruz-Chan, Tariq Kamal

Summary: In photovoltaic systems, inverters play a crucial role in providing an energy supply. However, when there is insufficient or no renewable power generation, the inverter remains inactive, leading to decreased performance. This paper presents a control scheme that allows the inverter to operate as a VAR compensator, generating reactive power in the absence of renewable sources to improve power factor and overall efficiency.

ENERGIES (2023)

Article Green & Sustainable Science & Technology

Assessment of climate change's impact on energy demand in Mexican buildings: Projection in single-family houses based on Representative Concentration Pathways

M. Jimenez Torres, David Bienvenido-Huertas, O. May Tzuc, A. Bassam, Luis J. Ricalde Castellanos, M. Flota-Banuelos

Summary: Insufficient thermal performance of buildings in Mexico leads to intensive energy use. This research examines the energy demand required to meet the country's cooling needs using weather-based technical indexes. The study analyzes 2440 municipalities in Mexico and considers climate change projections. The results show a significant increase in air conditioning energy demand, with over 50% of the country requiring high levels of air conditioning. The study also identified the time frames with the highest operating requirements and the regions with similar patterns in air conditioning.

ENERGY FOR SUSTAINABLE DEVELOPMENT (2023)

Article Mathematics

Neural Network Based Control of Four-Bar Mechanism with Variable Input Velocity

R. Peon-Escalante, Manuel Flota-Banuelos, Roberto Quintal-Palomo, Luis J. Ricalde, F. Penunuri, B. Cruz Jimenez, J. Aviles Vinas

Summary: This paper proposes controlling the variable velocity of the drive crank of a four-bar mechanism to achieve desired output motions. A neural network is trained using data from the kinematic model to estimate the reference trajectory for the crank velocity. The control law is designed using feedback linearization and a Proportional-Integral-Derivative (PID) controller. Simulation results validate the effectiveness of the proposed scheme for three variable speed profiles.

MATHEMATICS (2023)

Article Green & Sustainable Science & Technology

Using artificial intelligence for global solar radiation modeling from meteorological variables

Salma Zaim, Mohamed El Ibrahimi, Asmae Arbaoui, Abderrahim Samaouali, Mouhaydine Tlemcani, Abdelfettah Barhdadi

Summary: This study proposes the use of artificial neural networks and XGBoost algorithm for modeling hourly global solar radiation in a humid climate. Important meteorological data are selected and validated, and two ANN models and one XGBoost model are chosen with similar performances, with coefficient of determination values of 98% and 97% respectively. Statistical indicators prove to be effective in assessing the accuracy and fidelity of each model. The intent of the modeling in terms of accuracy, simplicity, and fidelity is a crucial factor in selecting the model algorithm to adopt.

RENEWABLE ENERGY (2023)

Article Environmental Sciences

Electronic structure and optical properties of Br- and Cl-doped rutile TiO2 for application in self-cleaning and photovoltaic panel's coatings: first-principle calculations

Badr Akharkhach, Abdelfettah Barhdadi

Summary: Development of novel self-cleaning technologies, especially those based on semiconductor photocatalysis system, is one of the most important research problems in environmental cleanup. This study explores the influence of specific doping configurations, such as Br or Cl doping at an O site, on the electronic structure and charge density distribution within rutile TiO2 using first-principle calculations based on density functional theory. Furthermore, the optical properties of the material as a self-cleaning coating on photovoltaic panels have been examined.

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH (2023)

Article Construction & Building Technology

Analysis of Energy and Environmental Indicators for Sustainable Operation of Mexican Hotels in Tropical Climate Aided by Artificial Intelligence

S. G. Mengual Torres, O. May Tzuc, K. M. Aguilar-Castro, Margarita Castillo Tellez, J. Ovando Sierra, Andrea Del Rosario Cruz-Y Cruz, Francisco Javier Barrera-Lao

Summary: This study assessed the energy-use index and carbon-footprint performance of medium-category Mexican hotels and found that it is possible to reduce energy consumption through partial replacement of energy-consuming devices without full equipment replacement.

BUILDINGS (2022)

No Data Available