Solar Installations Research Articles

Cost-Effective Dust Detection on Solar PV Panels through Deep Learning: A Step towards Automated Maintenance Systems

Abstract: Accumulation of dust on solar panels impacts the overall efficiency and the amount of energy it produces. Detecting and mitigating dust accumulation is therefore crucial for optimizing solar energy production. While various techniques exist for detecting dust to schedule cleaning, many of these methods uses licensed software like MATLAB, which can be financially burdensome. This study proposes the use of modified pre-trained ResNet-50 model architecture with an adjusted fully connected layer for binary classification. An experimental setup was installed utilizing a single 75 Wp panel with an inclination maintained at 30-degree angle. The fine dirt particles were artificially introduced and datasets of images of clean and dusty panels were collected from five different sides were taken, to compensate for the surface reflectance from the PV panel due to camera angles. Those datasets were used to train and test the model and the accuracy achieved was 90%. The model's ability to detect dust with minimal false positives ensures more efficient maintenance scheduling. This research demonstrates the potential of AI-driven dust detection systems to enhance the operational efficiency of solar PV installations.

AI-driven predictive maintenance and optimization of renewable energy systems for enhanced operational efficiency and longevity

The rapid growth of renewable energy systems necessitates advanced strategies for maintenance and optimization to ensure long-term operational efficiency and sustainability. Traditional approaches often fall short in predicting failures and optimizing performance across diverse and dynamic renewable energy infrastructures. This study investigates the application of artificial intelligence (AI) techniques for predictive maintenance and optimization of renewable energy systems, with the aim of enhancing operational efficiency and extending system longevity. We employ a combination of machine learning algorithms, including deep neural networks and reinforcement learning, to develop predictive models and optimization strategies. These models are trained on large-scale datasets collected from operational wind farms, solar installations, and hydroelectric plants. Our results demonstrate that AI-driven approaches can predict equipment failures with 92% accuracy, reducing unplanned downtime by 35% compared to traditional methods. Moreover, AI-optimized operational parameters improved overall energy output by 8.5% across the studied systems. The proposed framework also showed adaptability to various environmental conditions and system configurations, suggesting broad applicability across the renewable energy sector. This research underscores the significant potential of AI in revolutionizing maintenance practices and operational strategies in renewable energy systems, paving the way for more reliable, efficient, and sustainable clean energy production.

Exploring rooftop solar potential through deep learning: a comparative case study of U-Net and Attention U-Net

Photovoltaic systems are increasingly gaining popularity for rooftop installations in urban areas. These devices contribute to the self-sufficiency of electricity supply and reduce greenhouse gas emissions in urban settings. In this study, we implement deep learning techniques and compare the U-Net and Attention U-Net architectures to detect rooftops in the city of Sidi Bel Abbes (North Africa) for the installation of solar panels. Contrary to trends observed in the literature and previous research, our results show that U-Net achieved a higher accuracy of 90.49%, while Attention U-Net achieved an accuracy of 89.96%. Using the U-Net method, we identified a 1.9-square-kilometer area of rooftops suitable for solar panel installation in the southern part of the town of Sidi Bel Abbes. This discovery represents a potential electrical capacity of 89 MVA, capable of largely satisfying the energy needs of the studied region. This work is a novelty, being the first study of its kind undertaken in Algeria.

VIABILIDADE DA ENERGIA FOTOVOLTAICA EM CARUARU

Renewable energy is an increasingly prominent topic due to the urgent need to reduce greenhouse gas emissions and combat global warming, which can lead to irreversible climate changes. In the state of Pernambuco, there is a growing popularity of solar energy, driven by its significant generation potential and ease of installation. Alongside these factors, there is an increase in the number of companies offering solar projects and installations for small consumers, enabling access to self-generated energy for both residences and businesses. However, despite these advantages, recent changes have raised questions about the viability of solar energy, particularly for the middle and lower classes. Thus, the purpose of this study is to analyze whether solar energy is feasible for residents of Caruaru or if further changes are needed to make it a realistic option.

A Study of Pradhan Mantri Surya Ghar Yojna and Its Impact on Household Electricity Costs and Decreasing Dependency on Conventional Energy Sources

According to research, the Pradhan Mantri Surya Ghar Yojna has a significant impact on sustainable energy practices by lowering household electricity costs through rooftop solar installations and reducing India's dependency on foreign energy sources. The Yojna lessens the environmental effect of traditional energy usage by enabling homes to switch to greener options by promoting access to renewable energy. The program's subsidies and incentives increase access to solar energy, promoting its widespread adoption by both urban and rural families. In addition to lowering household power costs, its widespread adoption helps India meet its challenging targets for lowering carbon emissions and fostering environmental sustainability. Through the creation of chances for local manufacturers, skilled workers, and industries to engage in the solar energy value chain, the project also promotes socioeconomic development. The initiative supports India's larger sustainable energy aims by offering a framework for rooftop solar panel installations, guaranteeing long-term financial gains and promoting energy independence. There are difficulties, mostly associated with the initial high cost of installing solar panels and the difficulties in obtaining funding or subsidies, but they are gradually being resolved by means of incentives and policy changes from the government. Overall, by making solar energy more accessible, cheap, and appealing to Indian homes, the Pradhan Mantri Surya Ghar Yojna has played a significant role in defining sustainable energy habits and supporting the nation's wider economic and climatic goals.

Community Choice Electricity Aggregation and Solar Adoption: Evidence From Illinois

We explore whether municipalities voting on the community choice aggregation (CCA) model of electricity procurement relates to the adoption of small-scale distributed solar in the US state of Illinois. Municipalities that held a referendum for CCA were more likely to have small-scale solar installations compared to those that did not. Among municipalities with solar installations, those that held CCA referendums have lower per capita solar power generation than those without CCA referendums. The impacts of CCA referendums on small-scale solar adoption are mixed and should be combined with other strategies to promote broader solar adoption in the U.S. energy market.

Assessing the adoption level of Solar PV installations, on district scale of urban environment

This study addresses a research gap by implementing a novel methodology that combines GIS and MCDM techniques to evaluate photovoltaic (PV) potential at an urban scale, specifically within Riga, Latvia. Utilizing the AHP and MABAC methods, the research integrates technical, social, and economic criteria to rank urban districts based on their suitability for PV installations. 58 different districts were evaluated according to technical and socioeconomic criteria and were ranked through the MABAC MCDM methodology, from most preferable to less, on a PV adoption level. This comprehensive approach not only identifies the most promising areas for rooftop PV deployment but also emphasizes the importance of considering socioeconomic factors to enhance equity in renewable energy adoption. The findings provide valuable insights for urban planners and policymakers, demonstrating a systematic, data-driven method to promote sustainable energy initiatives in urban environments.

Deep Learning-Driven Thermal Imaging Hotspot Detection in Solar Photovoltaic Arrays Using YOLOv10

The effective management of solar photovoltaic (PV) arrays is vital to maximising energy generation and ensuring long-term performance reliability. The presence of faults, or partial shading, can give rise to hotspots in PV arrays, making their detection critical for timely maintenance and avoiding further impacts on their performance. This paper describes a new approach to the hotspot detection issue in thermal images of solar PV arrays by leveraging deep learning. This study employs the YOLOv10 (You Only Look Once, version 10) model to deliver very high accuracy and speed in identifying and localising hotspots under defined regions of interest (ROIs). The proposed method begins with taking thermal images from multiple solar PV installations while capturing a range of operational conditions and fault types. These images are annotated with hotspot regions to create a robust training dataset. Given YOLO's capability for real-time object detection with high precision and mean average precision (mAP), the YOLOv10 model is then implemented to train on this dataset. Multiple changes were made to the YOLOv10 hyperparameters to optimise them for detecting hotspots in thermal images. The experimental scenario of this paper demonstrates that this approach indeed performs significantly better than standard image processing methods as well as prior deep learning models for detecting both hotspot accuracy as well as speed of processing the images. The YOLOv10 method demonstrated the highest available classification performance with a mAP at intersection over union (IoU) of 0.5 accuracy of 0.91 with inference time suitable for real-time applications. The sample results demonstrated the model's continuous ability to detect hotspots and provide location data under various conditions, such as crossing through different times of day and weather. The results of this study demonstrate that YOLOv10 can be used for improved detection of hotspots in the explicably thermal imagery of solar PV arrays.

Propagation of expansion waves in a heat exchanger within a designated volume of the helioinstallation filler

This article considers a mathematical model of forced bifurcation oscillations of a three-mass chain system, when the measure of its dynamic susceptibility is incommensurable with the measures of forced bifurcation forces. The equivalent medium inside the allocated volume of the filler of the solar installation or filler, or its movement is reversible when turbulence occurs. Distributions of perturbations caused by the internal instability of the pre-central layer after abolishing conditions under a focused shear load in the zones of solidification, crystallization and cooling are obtained. The results of the comparison of the pre-central and central layers are presented.

Long-term performance analysis of a large-scale photoVoltaic plant in extreme desert conditions

This study comprehensively evaluates the performance and operational challenges of a 9 MW grid-connected photovoltaic (PV) system in Timmimoun, southern Algeria, after eight years of operation. We identified a significant linear correlation (R2 = 0.73) between increased ambient temperatures and decreased PV module efficiency, underscoring the need for effective thermal management strategies. The investigation also examines potential solutions, such as cooling mechanisms, optimization of panel orientation and tilt angles, and development of temperature-resistant materials. Adhering to the International Energy Agency IEC 61724 standard, our analysis reveals a yield factor of 5.04 h/day, a yield ratio of 7.04 h/day, a performance ratio of 73 %, and a capacity factor of 21 % in 2023. Over its operational lifespan, the system has generated 133.43 GW h of energy, mitigating 1.01 105 tons of CO2 emissions. This long-term study provides critical insights into the performance and reliability of PV systems in hot desert climates, offering valuable guidance for future large-scale solar installations and contributing to the transition towards a sustainable energy future.

Integrating Technological Environmental Design and Energy Interventions in the Residential Building Stock: The Pilot Case of the Small Island Procida

The next decade will see severe environmental and technological risks, pushing our adaptive capacity to its limits. The EPBD Case Green directive, to counter this phenomenon, emphasizes accelerating building renovations, reducing GHG emissions and energy consumption, and promoting renewable energy installations. Additionally, it calls for deadlines to phase out fossil fuels and mandates solar system installations. This research provides a comprehensive perspective on the opportunities for and challenges of incorporating renewable energy into the built environment. It focuses on the 2961 residential buildings on Procida, a small island located south of Italy, to efficiently utilize energy resources and lay the groundwork for sustainability. Beginning with an analysis of the territorial, urban, historical–conservation, structural, and geological context, in addition to environmental assessments, the research develops a classification and archetypalization system using in-house software. This system aggregates data on the island’s residential buildings, analyzes their current state, and formulates various intervention scenarios. These scenarios demonstrate how integrating technological–environmental design interventions, such as upgrading the building envelope and enhancing bioclimatic behavior, with energy retrofitting measures, such as replacing mechanical systems and installing solar panels, can improve the overall performance of the existing building stock and achieve energy self-sufficiency.

Rapid assessment of solar PV micro-system energy generation in Poland based on freely pvlib-python library

Abstract Poland has experienced a remarkable growth in renewable energy adoption, notably in photovoltaic (PV) solar systems. The majority of installations are prosumer PV micro-installations, exceeding predicted capacity targets outlined in the Energy Policy of Poland until 2040. Despite the significant growth in installed PV capacity, there is still a lack of comprehensive research focusing on fast assessment of energy generation capacity for solar PV micro-systems. This study aims to address this gap by providing a comprehensive analysis of energy production potential across different configurations and locations in Poland. Using geocoding techniques, solar irradiation data from PVGIS database and pvlib-python library, a methodology was developed to rapidly estimate energy generation from 1 kWp solar PV systems . Results reveal spatial disparities in energy yield from solar PV micro installations in Poland, influenced by factors such as geographical location and panel orientation and inclination. Recognizing that the presented energy indicators provide valuable initial parameters for determining solar PV system power output, this data can serve as a critical reference point for stakeholders, assisting them in estimating potential energy generation capacities in different regions of Poland.

Transient modeling of stratified thermal storage tanks: Comparison of 1D models and the Advanced Flowrate Distribution method

Thermal energy storage (TES) is one of the key technologies for enabling a higher deployment of renewable energy. In this context, the present study analyzes the modeling strategies of one of the most common TES systems: stratified thermal storage tanks. These systems are essential to many solar thermal installations and heat pumps, among other clean energy technologies. Three different one-dimensional tank models are compared by their computing speed and resilience to long time steps. Two of the models analyzed are numerical, one being explicit and the other one implicit, and the other is analytical. The models are validated against data from experiments carried out considering small-scale stratified tanks, showing that their performance can be improved by using the Advanced Flowrate Distribution (AFD) method. The results show that the analytical model maintains its accuracy with longer time steps and is robust against divergence. Conversely, the numerical models show equivalent performance for short time steps, while the computation time is reduced. Although the AFD method shows promising results by achieving an improvement of 43% in terms of Dynamic Time Warping, its parameter optimization must be generalized for different tank designs, flow rates, and temperatures.

Field measurements of wind load effects in a photovoltaic single-axis tracker mounting rail

The demand for solar photovoltaic power installations has resulted in a highly competitive industry. Equipment suppliers are under pressure to reduce design margins for projects to be feasible. Single-axis trackers are widely used to increase yield and reduce the levelised cost of energy compared to fixed-tilt installations. Load coefficients on tracker arrays are usually quantified using model-scale studies conducted in atmospheric boundary layer wind tunnels. These dynamically sensitive structures have been known to suffer wind damage despite the use of modern design methods. Ongoing research into the support structure design is deemed important to ensure long-term reliability. The current study presents full-scale field data acquired over 109 days on an experimental one-in-portrait single-axis tracker facility located in the Western Cape, South Africa. The purpose of these measurements was to quantify wind load effects in two instrumented PV module mounting rails. Frequency domain data showed modal participation of both the torsional and bending modes of the torque tube. The effect of the bending mode was more pronounced for the rail furthest from a pile. Load coefficients calculated using experimental data were generally lower than those presented in ASCE 7-22. Fluctuating stresses at critical locations led to negligible fatigue damage.

IoT-Enabled energy conservation in residential Buildings: Machine learning models for analyzing annual solar power consumption

This study investigates enhancing the self-consumption of solar panels by integrating thermal and electrical energy storage using lithium-ion batteries in a duplex building over a year. Machine learning algorithms are applied to understand energy usage patterns. An IoT-connected model is introduced to reduce electricity expenses by boosting consumption with solar energy and extending solar panel lifespan through optimization. The model includes lithium-ion batteries for energy storage and a thermal cooling system to regulate panel temperatures. Data collected from sensors monitoring occupancy, temperature, humidity, energy, and thermostats are sent to a cloud-based platform via IoT. Results show peak monthly energy conservation measures of 41.6 kW and 28 kW during summer for the two residences. Winter witnesses a reduction of 13.9 % and 7 % in energy consumption, while autumn sees an 18 % decrease for one residence and stability for the other. Real-time IoT monitoring aids model training, with the Gaussian Probability model emerging as the most accurate. Optimization analysis underscores the thermal cooling system’s efficacy in improving solar panel performance and reducing electricity costs. Integration of machine learning and IoT curtails energy consumption to 22 kWh and 15.7 kWh for the respective residences, offering inhabitants free energy from renewable sources and ensuring swift recovery of solar panel installation costs.

Enhancing Urban Sustainability and Resilience: Employing Digital Twin Technologies for Integrated WEFE Nexus Management to Achieve SDGs

This research explores the application of digital twin technologies to progress the United Nations’ Sustainable Development Goals (SDGs) within the water-energy-food-environment (WEFE) nexus management in urban refugee areas. The study in Irbid Camp utilizes a detailed 3D Revit model combined with real-time data and community insights processed through advanced machine learning algorithms. An examination of 450 qualitative interviews indicates an 80% knowledge level of water conservation practices among the community but only 35% satisfaction with the current management of resources. Predictive analytics forecast a 25% increase in water scarcity and an 18% surge in energy demand within the next ten years, prompting the deployment of sustainable solutions such as solar energy installations and enhanced rainwater collection systems. By simulating resource allocation and environmental impacts, the digital twin framework helps in planning urban development in line with SDGs 6 (Clean Water and Sanitation), 7 (Affordable and Clean Energy), 11 (Sustainable Cities and Communities), and 12 (Responsible Consumption and Production). This investigation highlights the capacity of digital twin technology to improve resource management, increase community resilience, and support sustainable urban growth, suggesting its wider implementation in comparable environments.

Research on supply-demand balance in China’s five southern provinces amidst fluctuations in regional wind and solar power generation and transmission faults

To investigate the supply-demand balance of regional power systems under extreme scenarios, this study employs the high-resolution power optimization model SWITCH-China to simulate the regional heterogeneity and randomness of extreme weather events in detail. Focusing on the five southern provinces, this study explores various impacts on the power generation side and the grid side under scenarios of reduced wind and solar power output, transmission line failures, and combined scenarios, proposing strategies for constructing a new power system. The main conclusions are: the reduction in wind and solar power output significantly affects provinces with a high proportion of these installations, like Guizhou, necessitating other stable power generation forms to compensate. Transmission line failures notably impact provinces like Guangdong, which rely heavily on imported electricity, requiring increased investment in new wind and solar installations and more self-generated power to offset the reduction in imported electricity. The combination of these factors amplifies their individual impacts, leading to the highest carbon reduction and electricity costs. The simulation results of this study are valuable for China’s five southern provinces in coping with extreme scenarios. As these provinces work on building a new power system and gradually retire fossil fuel units, they should expand the number and capacity of inter-provincial high-voltage transmission lines while considering system economics. Additionally, accelerating the deployment of energy storage is crucial for maintaining power system stability.

A novel development of hybrid maximum power point tracking controller for solar pv systems with wide voltage gain DC-DC converter

Now, the present power generation and distribution companies are working on renewable energy systems because their features are low-level atmospheric pollution, producing less greenhouse pollutants, more reliability, good static performance, and high robustness. In this work, the sunlight Photovoltaic (PV) system is selected because of its advantages are easily available in the atmosphere, high flexibility, zero carbon footprint, easy to maintain, and less transportation cost. However, solar networks produce nonlinear I-V characteristics. Due to the non-linear nature of the solar system, the extraction of peak voltage from the PV module is a very tough task. So, in this article, a variable modified step grey wolf method is integrated with the adaptive-neuro-fuzzy-inference-system to improve the energy production of solar systems. The features of this proposed maximum power point tracking controller are fast identification of the solar system operating point, generating the less fluctuated oriented converter load power, providing more MPP tracking accuracy, less dependence on the solar system installation, and useful for all environmental bad weather conditions. Another problem of solar systems is less voltage production which is improved by introducing a wide voltage gain-boost converter circuit. The features of this converter circuit are less development cost because it does not require more power electronics switches. Here, the proposed IGWM with an AFLC-fed sunlight system is investigated by using MATLAB/Simulink.

Performance Analysis of a 50 MW Solar PV Installation at BUI Power Authority: A Comparative Study between Sunny and Overcast Days

Ghana, being blessed with abundant solar resources, has strategically invested in solar photovoltaic (PV) technologies to diversify its energy mix and reduce the environmental impacts of traditional energy technologies. The 50 MW solar PV installation by the Bui Power Authority (BPA) exemplifies the nation’s dedication to utilizing clean energy for sustainable growth. This study seeks to close the knowledge gap by providing a detailed analysis of the system’s performance under different weather conditions, particularly on days with abundant sunshine and those with cloudy skies. The research consists of one year’s worth of monitoring data for the climatic conditions at the facility and AC energy output fed into the grid. These data were used to analyze PV performance on each month’s sunniest and cloudiest days. The goal is to aid in predicting the system’s output over the next 365 days based on the system design and weather forecast and identify opportunities for system optimization to improve grid dependability. The results show that the total amount of AC energy output fed into the grid each month on the sunniest day varies between 229.3 MWh in December and 278.0 MWh in November, while the total amount of AC energy output fed into the grid each month on the cloudiest day varies between 16.1 MWh in August and 192.8 MWh in February. Also, the percentage variation in energy produced between the sunniest and cloudiest days within a month ranges from 16.9% (December) to 94.1% (August). The reference and system yield analyses showed that the PV plant has a high conversion efficiency of 91.3%; however, only the sunniest and overcast days had an efficiency of 38% and 92%, respectively. The BPA plant’s performance can be enhanced by using this analysis to identify erratic power generation on sunny days and schedule timely maintenance to keep the plant’s performance from deteriorating. Optimizing a solar PV system’s design, installation, and operation can significantly improve its AC energy output, performance ratio, and capacity factor on sunny and cloudy days. The study reveals the necessity of hydropower backup during cloudy days, enabling BPA to calculate the required hydropower for a consistent grid supply. Being able to predict the daily output of the system allows BPA to optimize dispatch strategies and determine the most efficient mix of solar and hydropower. It also assists BPA in identifying areas of the solar facility that require optimization to improve grid reliability.

LCZ-based city-wide solar radiation potential analysis by coupling physical modeling, machine learning, and 3D buildings

Addressing climate change and urban energy problems is a great challenge. Building Integrated Photovoltaics (BIPV) plays a pivotal role in energy conservation and carbon emission reduction. However, traditional approaches to assessing solar radiation on buildings with physical models are computing-intensive and time-consuming. This study presents a hybrid approach by integrating physical model-based solar radiation calculation and machine learning (ML) for city-wide building solar radiation potential (SRP) analysis. By considering urban morphology, land cover, and meteorological characteristics, local climate zones (LCZs) are classified. The SRP of representative LCZs is precisely evaluated using computing-intensive physical models integrated with 3D building models. A ML model is then developed to effectively predict the SRP of building roofs and facades throughout the city. An experiment was conducted in Shenzhen, China to validate the presented approach. The results demonstrate that Shenzhen has a total annual building solar radiation of 3.28∗1011kwh. Luohu District exhibits the highest SRP density. The LCZ-based analysis highlights that compact low-rise LCZs offer greater SRP for roofs, while compact high-rise LCZs do so for facades. Moreover, BIPV could cut CO2 emission by up to 41.85 million tons annually. Notably, solar PV installation only on rooftops in Shenzhen could meet 87.81% of the city's electricity department's carbon reduction goal. This study provides an alternative for city-wide SRP estimation by combining physical modeling and ML and offers valuable insights for data-driven and model-driven urban planning and management in low-carbon cities.