Solar Photovoltaic Power System Research Articles

Scientific Mapping of Machine Learning Methods in Predicting Power Output of Solar Photovoltaic Power Systems

Objective: This study aimed to conduct a scientometric mapping of the scientific literature on prediction models in photovoltaic solar energy generation, with a special focus on grid-connected photovoltaic systems (GCPV), aiming to provide important insights for researchers, policymakers, and professionals interested in advancing the integration of photovoltaic solar energy into the current energy distribution system. Theoretical Framework: In this section, the main concepts and theories underpinning the research are presented, focusing on prediction models in photovoltaic solar energy generation, as well as grid-connected photovoltaic systems (GCPV). Method: The methodology adopted comprised a bibliometric approach, analyzing publications indexed in the Scopus and Web of Science databases over the last decade, using the Biblioshiny software from RStudio. Results and Discussion: The results revealed a significant growth in academic production, identifying key authors, leading research countries, and influential journals in the field. Central and emerging themes were also mapped, along with research gaps and opportunities in the field of photovoltaic solar energy. Research Implications: The practical and theoretical implications of this research include insights into how the results may influence the integration of photovoltaic solar energy into the energy distribution system, impacting areas such as scientific research, policy development, and professional practice. Originality/Value: This study contributes to the literature by offering a comprehensive mapping of research on prediction models in photovoltaic solar energy generation, highlighting gaps and opportunities to advance the field, as well as providing valuable insights for various stakeholders interested in this area.

Hybrid Energy Holds Promise for Artificial Lift for Offshore Brazilian Fields

_ This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper OTC 32671, “Technical Evaluation of the Use of Hybrid Energy (Solar and Offshore Wind) To Supply Artificial Lift Pumps on an Oil Platform on the Equatorial Margin,” by W.K. Silva, Ana L.R. Cunha, SPE, and Ana C. Alves, Federal University of Pará, et al. The paper has not been peer reviewed. _ The complete paper investigates the relevance of wind and solar energy for the supply of artificial lift systems on offshore platforms in the Brazilian equatorial region. The scope of the authors’ study encompassed a detailed technical and environmental assessment, with an emphasis on the integration of a 10-MW floating solar photovoltaic (FSPV) power system to meet demand for 10 pumps. The results obtained highlight the high viability of the system in meeting the demand of these pumps and ensuring an adequate and sustainable energy supply. Area of Study The equatorial margin is an area in northern Brazil covering part of the sedimentary basins of the equatorial Atlantic. The region is home to important sedimentary basins such as the Amazon Basin, the Pará-Maranhão Basin, the Barreirinhas Basin, the Potiguar Basin, and the Ceará Basin, all known for their hydrocarbon reserves. Offshore oil-exploration activities in the equatorial margin involve the installation of drilling and production platforms that include artificial lift systems. To power these systems, a reliable and continuous power source is required. The use of green energies such as wind and solar can be advantageous in meeting this purpose. For the present study, the coastal city of Salinópolis in the state of Pará was selected because of its plentiful meteorological data and its location in the Pará-Maranhão Basin region. Methodology The methodology of the work consists of the evaluation of the energy required for artificial lifting systems with 10 pumps, using the nine steps developed by Baker Hughes’ Artificial Lift Research and Technology Center for the calculation of the power required to drive the pumps. Additionally, the study uses the System Advisor Model (SAM), November 2022 version, developed by the National Renewable Energy Laboratory to simulate the FSPV. Information related to wind potential was obtained through the measuring stations of the National Institute of Meteorology (INMET).

Technology Focus: Artificial Lift (March 2024)

The industry is now in its second year beyond the COVID-19 pandemic, and the workforce has changed in many ways, but issues facing production performance remain. Major conferences saw 116 submissions from 28 countries, with 64% regarding electrical submersible pumps (ESPs), and 18% and 8% devoted to gas lift and rod lift, respectively. Many of the papers dealt with case history successes. That is all well and good, but it doesn’t necessarily drive reader interest if it can’t be applied to their asset. The top three papers were selected on the guidelines of clarity of the abstract in addressing the scope, methods/procedures/process, results/observations/conclusions, and novel or additive information. The papers described here focus on novel unconventional horizontal downhole pump card signatures, carbon reduction through alternative energy to pump wells, and predicting downhole-discharge pressure of ESPs. Paper SPE 214723 presents a discussion of the design, evaluation, and field testing of a new type of mechanical gas separator with what the authors term a “hydrohelical” design. The separator, in Permian Basin tests, almost doubled the flow capacity of conventional gas separators with a high level of efficiency. The authors draw particular attention to the improvement of ESP operations under multiphase conditions. Carbon reduction is a hot topic, and paper OTC 32671 does not disappoint as it looks at the use of a 10-MW floating solar photovoltaic power system to meet the energy needed for 10 ESP wells on an oil platform in the Brazil equatorial region. Collaboration with the National Renewable Energy Laboratory and its System Advisor Model was used with extensive meteorological and wind data to examine the sustainability of green energy use for the petroleum industry and offer valuable guidance for future renewable energy projects in regions with similar characteristics. Finally, paper SPE 216598 comes from Sudan and Saudia Arabia and focuses on digital solutions for the challenge of knowing the downhole-discharge pressure of an ESP system. Most ESP systems do not have downhole gauges, so an artificial neural network (ANN) approach is used to predict the ESP discharge pressure for performance optimization. Forty wells and more than 12,000 data points were reduced to 16 inputs plus one hidden layer of seven neurons to provide a high degree of accuracy in prediction of discharge pressure. The authors state that the ability to accurately predict discharge pressure can lead to the early detection of possible anomalies, which can prevent costly failures and reduce downtime. Artificial intelligence technology may improve the accuracy of ANNs, but, for now, ANNs are worth a look to obtain much-needed ESP discharge pressure. Other notable papers dealt with gas separation, ESP reliability, and the increasing challenges of low rates, low pressures, and high gas fractions. Recommended additional reading at OnePetro: www.onepetro.org. SPE 214913 Solved: ESP Shutdowns and Restart Issues—Novel Pump Protection and Active 3D Dispersion System Improve ESP Performance in Multiple Wells by A. Bhattacharjee, SLB, et al. SPE 215474 A New Artificial Lift Approach in Telisa Low-Productivity Reservoir: Utilized Very Low-Rate ESP by Agus Aryanto, Medco E&P Indonesia, et al. SPE 215170 A Comprehensive Study of a Novel Submersible Pump by Hattan Banjar, Saudi Aramco, et al. SPE 214722 Case Study: Predicting Electrical Submersible Pump Failures Using Artificial Intelligence and Physics-Based Hybrid Models by Shejuti Silvia, Baker Hughes, et al. SPE 214733 Gas-Flow-Management Technology Designed To Decrease Downtime and Improve ESP Efficiency by S. Fulwider, ConocoPhillips, et al.

Fuzzy Logic-based Power Optimizer for Solar Photovoltaic Power Systems

Solar photovoltaics has become the most popular renewable energy source due to its simplicity in installation and maintenance. However, the dependence on the availability of solar energy at the instant makes its operation non-linear. Various optimizing solutions are proposed to rule out this disadvantage. This paper dwells on a machine language approach to solve this problem. A maximal tracker for power points relies on fuzzy logic control. An embedded power optimizer is designed and tested under different environmental conditions through simulation. The results presented allow researchers to test various artificial intelligence techniques for renewable energy extraction processes.

Design and Development of a Micro Inverter Power Monitoring System to Enhance Photovoltaic System Performance by Integrating LoRaWAN and IoT

This research examines the significance of utilizing Photovoltaic Solar Power Systems (PVSPS) with Micro Inverters and Internet of Things (IoT) technology, particularly LoRaWAN, in addressing challenges related to efficiency and power management. PVSPS has emerged as a leading solution to tackle the increasing global energy consumption and the adverse effects of greenhouse gas emissions. The rapid growth of the PVSPS industry underscores its relevance. This study explores the impact of shading on solar panels connected in series and parallel configurations, emphasizing the importance of proper placement. The results indicate that shading significantly reduces energy production, especially in panels connected in series. Micro Inverters play a crucial role in maintaining stable output voltage, even under shading conditions. However, attention must be paid to their influence on output current. Efficient monitoring and management of PVSPS through IoT technology such as LoRaWAN are key in supporting the transition to sustainable energy. This data underscores the importance of continuous monitoring to identify issues and optimize PVSPS performance, in the face of environmental challenges and climate change.

Design methodology and implementation of stand-alone solar photovoltaic power system for daily energy consumption of 9.16 kWh

This stand-alone solar photovoltaic power system was designed to power a daily energy consumption of 9.16 kWh reliably, by means of photovoltaic only. The design involves different components whose capacities depend on 9.16 kWh daily energy consumption and 1-day autonomy, including several factors that determine the choice of selection. After implementation, the system was put to the test for two days to ascertain the design validity and check if it would be able to sustain the daily load demand for 24 h without failure. The results reveal that the design methodology employed for the stand-alone system in this study is accurate and reliable because the system was able to power the load interminably for 34 h, with a resulting 0.6% DoD at the end of the test. This was due to the complete energy balance that the design methodology offers. Day 1 shows that the overall PV array power was 208% higher than the daytime load power and 61.2% higher than the overall daily load power. While Day-2 shows the overall PV array power to be 130% higher than the daytime load power and 56.3% higher than the overall daily load power, The energy balance between PV array, battery, and load size was completely and sufficiently achieved on both days, as the highest depth of discharge recorded during the test was 48.7%. The study reveals that through a complete energy balance between PV, battery, and load size, a standalone PV system can reliably sustain daily energy demand. It aims to design a stand-alone PV system capable of reliably sustaining daily energy demand without the need for long days of autonomy, so as to help prevent failures in solar PV projects that come as a result of inappropriate sizing, planning, and a lack of technical know-how.

Data analytics for prediction of solar PV power generation and system performance: A real case of Bui Solar Generating Station, Ghana

The grid-connected solar power generated by the Bui Power Authority is sold to Ghana Grid Company Limited (GRIDCo) and other customers through bilateral contracts. However, there have been challenges in meeting the supply commitments due to the stochastic nature of solar energy. Fluctuating weather and climatic conditions make it difficult for operators to predict the output of the solar photovoltaic (PV) plant in advance. This has the tendency of leading to anticipated power loss or excess power not being managed effectively. In this study, the random forest and gradient boosting regressor algorithms were used to produce deterministic and probabilistic predictions of solar power generation by using data collected over an eleven-month span. Some of the findings show that the random forest model that produced probabilistic predictions performed better than the other compared models in terms of its accuracy. It produces reliable predictions with a normalized mean absolute error of 1.18%. This is deemed acceptable for operational purposes in the sphere of renewable energy prediction. As a result, these predictions are efficient enough to be used by utility companies as input to numerous decision-making problems during operations which consequently leads to the grid being managed effectively. It may also help them to choose the appropriate modelling approach for predicting solar PV power. Overall, this study supports the generation of clean and reliable energy through improved solar power prediction which directly contributes to African Union's agenda 2063 goals especially, in creating environmentally sustainable and climate resilient economies and communities. This is directly linked to the 7th and 13th UN sustainable developmental goals in ensuring access to affordable, reliable, sustainable, and modern energy for all and, combating climate change and its impacts.

Load Frequency Control With Renewable Energy Sources Using Practical Swarm Optimization Based On PID

Future competitive solutions for the production of electricity may be provided by emerging renewable energy sources (RESs) technologies as wind, solar photovoltaic, and solar thermal power systems. In this study, simulation tests have been conducted on autonomous hybrid generating systems(HGSs) made up of diesel engine generators (Degs), fuel cells (FCs), wind turbine generators (Wpg), solar photovoltaic generators (Pvpg), battery energy storage systems (Bess), and flywheels (Fess). The abrupt fluctuations in load, generation, or both cause the power system's frequency to vary. PID controller tuning using particle swarm optimization (PSO) is used for the optimization of controllers’ gains of the proposed hybrid systems. The proposed method is compared with a genetic algorithm (GA) and a traditional PID controller. To test the proposed controller, three different scenarios were used: first, changing the load's value with a fixed value over a set period of time; second, changing the load's value with variable values; and third, changing the load's value with a variable value while changing the system parameters. The simulation results reveal that the suggested controller performs better and is more resilient against load and generational disruptions by reducing the maximum overshoot value and settling time by 70% and 65%, respectively, and by 14.2% and 5% when compared to a GA-PID control.

A Novel Adaptive Power Smoothing Approach for PV Power Plant with Hybrid Energy Storage System

Clouds passing over solar photovoltaic (PV) power system causes power fluctuations, which contributes to power quality issues. Power fluctuations are usually compensated by an energy storage system (ESS) integrated with a filtering or smoothing controller. However, there is a great burden to tune and determine the filtering time constant (TF) that leads to better alleviation of PV power fluctuations because the irradiance variability varies from day to day. Lack of cloud information leads to incorrect selection of TF values which leads to poor smoothing performance when setting low values on cloudy days, or to unnecessary ESS operation when setting high values on clear days. This paper introduces a novel power smoothing framework to avoid the arbitrary selection of TF values and reduce the stress on ESS based on predictive and adaptive smoothing mechanisms. The proposed controller contains two layers, the first layer predicts the next day's irradiance profile and uses a clear sky model to identify the cloud class. Next, the controller sets the initial values of the filter time constants for cloudy, moderate, and mild days, and disables smoothing on clear and overcast days. The second layer adaptively adjusts the initial filter time constant based on the current power ramp rate and shares power for a hybrid energy storage system (HESS). The performance of the proposed controller is tested against the forecasting errors and compared to fixed time constant-based smoothing techniques and ramp rate control in a range of scenarios, including smoothing, ramp rate reduction, and battery degradation assessment.

MPPT control technology based on the GWO-VINC algorithm

It is a challenging task to accurately track the global maximum power point (GMPP) in a changing environment in widely used photovoltaic (PV) systems. So far, a variety of maximum power point (MPP) tracking algorithms have been used in solar PV power systems. The classical algorithm is simple and fast to track the speed effectively in a constant environment, but it can get stuck at an extreme point in a variable environment. In this paper, the variable-step incremental conductance (VINC) method is combined with the gray wolf optimization (GWO) algorithm. Firstly, GWO conducts a global search. When the search reaches the area near GMPP, the next step of the search process is carried out based on the iteration number conditions of GWO. Enter the search process of VINC and determine whether the current search process is on the left or right side of the vertex based on the current search value. And adjust the duty cycle during the VINC search process using different variable step size methods based on the left and right sides, and finally accurately locate the GMPP value. To verify the robustness of the proposed algorithm, simulation, and experimental comparisons were conducted between the proposed method in the article and GWO and VINC. The tracking efficiency of static shadows, simulated dynamic shadows, and experimental static and dynamic shadows is 99.80%, 98.82%, 99.43%, and 98.51%, respectively. The tracking time of simulation and experiment is 46.49% and 89.34% faster than GWO and VINC technologies, respectively. The results show that compared with the GWO and VINC methods, the proposed method has improved tracking speed and efficiency. Moreover, compared with the method that combines the two intelligent algorithms, this method has fewer algorithm parameters, a simple calculation process, lower complexity, lower hardware requirements, and better actual implementation performance.

Why Does the PV Solar Power Plant Operate Ineffectively?

Quality, reliability, and durability are the key features of photovoltaic (PV) solar system design, production, and operation. They are considered when manufacturing every cell and designing the entire system. Achieving these key features ensures that the PV solar system performs satisfactorily and offers years of trouble-free operation, even in adverse conditions. In each cell, the quality of the raw material should meet the quality standards. The fulfillment of the quality management system requires every part that goes into the PV solar system to undergo extensive testing in laboratories and environments to ensure it meets expectations. Hence, every MWh of electricity generated by the PV solar system is counted, the losses should be examined, and the PV system’s returns should be maximized. There are many types of losses in the PV solar system; these losses are identified and quantified based on knowledge and experience. They can be classified into two major blocks: optical and electrical losses. The optical losses include, but are not limited to, partial shading losses, far shading losses, near shading losses, incident angle modifier (IAM) losses, soiling losses, potential induced degradation (PID) losses, temperature losses, light-induced degradation (LID) losses, PV yearly degradation losses, array mismatch losses, and module quality losses. In addition, there are cable losses inside the PV solar power system, inverter losses, transformer losses, and transmission line losses. Thus, this work reviews the losses in the PV solar system in general and the 103 MWp grid-tied Al Quweira PV power plant/Aqaba, mainly using PVsyst software. The annual performance ratio (PR) is 79.5%, and the efficiency (η) under standard test conditions (STC) is 16.49%. The normalized production is 4.64 kWh/kWp/day, the array loss is 1.69 kWh/kWp/day, and the system loss is 0.18 kWh/kWp/day. Understanding factors that impact the PV system production losses is the key to obtaining an accurate production estimation. It enhances the annual energy and yield generated from the power plant. This review benefits investors, energy professionals, manufacturers, installers, and project developers by allowing them to maximize energy generation from PV solar systems and increase the number of solar irradiation incidents on PV modules.

Heuristic Approach for Net-Zero Energy Residential Buildings in Arid Region Using Dual Renewable Energy Sources

Optimizing a net-zero energy (NZE) residential building using what renewable energy resources are available in desert environments and budgeted within the limits of a governmental construction project is proving to be increasingly challenging for many countries, including the Kingdom of Saudi Arabia (KSA). Buildings in such regions encounter significantly high annual energy consumption rates, especially in the cooling capacity across a project’s life cycle, which in turn impacts the investment value. Therefore, this study presents a heuristic approach that aimed to examine the feasibility of NZE residential buildings in the KSA using an arid campus case study within the period of 2021–2022 based on the dual renewable energy sources of a geothermal heat pump (GHP), which served as a cooling system, and photovoltaic thermal collectors (PVT) serving as a power generation system. This study adopted a numerical technical assessment in the case study, using HAP software to analyze heating/cooling systems, and PVsyst V7.1.0 software for the variable simulation of solar photovoltaic power systems. This heuristic approach, through two assessment stages, achieved significant outcomes for a sustainable bottom-line, and provide a practical approach for achieving an NZE residential building in the King Faisal University (KFU) case study, as well as a reduction in energy consumption as well as the maintenance cost, which has a positive consequence on the payback period. Our study’s results have implications for both sustainable and green buildings with similar characteristics to those we investigated, and our results could be used to develop installation guidelines for renewable energy systems. Furthermore, our results can provide decision makers with a basis for retrofitting existing buildings to enhance their energy efficiency, increase investment value, as well as prevent the indiscriminate installation of renewable energy sources to merely increase the renewable energy installation rate.

Automatic detection of photovoltaic facilities from Sentinel-2 observations by the enhanced U-Net method

With the enactment of supportive government policies and the increasing maturity of solar photovoltaic (PV) technologies, solar PV energy has become the most cost-effective new energy resource worldwide. Geospatial information on existing solar PV power systems is necessary to manage and optimize the deployment of new PV facilities. In this study, we propose a new deep-learning network, named the enhanced U-Net (E-UNET), to detect PV facilities from Sentinel-2 multi-spectral remote sensing data. Our E-UNET features an enhanced encoder–decoder structure that can efficiently extract spectral and spatial features simultaneously by combining a multi-spectral three-dimensional convolution path and a multi-scale pooling block. We compare the performance of the E-UNET with other semantic segmentation deep-learning networks and a pixel-based random forest classifier. The experimental results show that the E-UNET performs better than the other methods. It achieves an overall accuracy, Matthews correlation coefficient, F1, kappa coefficient, and recall of 0.989, 0.862, 0.869, 0.934, and 0.875, respectively. The experimental results also indicate that the E-UNET accurately detects PV facilities from various complex environments with high accuracy in terms of PV integrity and details.

Robust reconfiguration strategies for maximum output power from large-scale photovoltaic arrays under partial shading conditions

Extraction of maximum power from large scale solar photovoltaic power systems is the most challenging and demanding research in the current scenario. Solar photovoltaic panels are highly susceptible to a phenomenon known as partial shading. Partial shading increases mismatch losses and reduces the output of the solar photovoltaic system The output reduction in the partially shaded array is proportional to the shaded area, shaded panel’s placement within the array, panel connections, shade geometry, etc. There are several approaches for reducing Partial shading effects in the literature. The most efficient approach to mitigating the mismatch losses due to Partial shading in large-scale solar photovoltaic systems is the reconfiguration technique, which distributes shaded panels more evenly and increases the maximum power output. The current work utilizes a set of reconfiguration rules for selecting the location of shaded panels within an array that allows for multiple reconfiguration options. The results show that the proposed reconfiguration has obtained an improved Performance enhancement ratio of 25% in one shading pattern i.e. short wide shading, Performance enhancement ratio of 6.4% in short narrow and centre shading and Performance enhancement ratio of 5.9% in long narrow shading. The proposed reconfiguration was found to be the most suitable, simple, and cost-effective solution for large size of solar photovoltaic system under all shading conditions.

Design and Simulation of a Floating Solar Photovoltaic System for an Offshore Aquaculture Site in Canada

This article presents the design and commercial feasibility of a floating solar photovoltaic (FSPV) power system for an offshore fish farm site located in the Newfoundland province of Canada. The offshore fish farms are energy-intensive units, and the fish feeding system is the primary energy consumer. Due to the remote location, the grid/utility power infrastructure does not exist, and diesel generators fulfill energy needs, which is expensive and detrimental to the environment. A FSPV power system is proposed as a replacement for the fossil fuel energy source. A comprehensive study is conducted to investigate the actual energy requirements of a site and an appropriate hybrid solar system is designed using Homer Pro software. The designed system’s techno-commercial feasibility is evaluated based on three different scenarios (base, ideal and worst). The obtained results show that the renewable energy penetration for all cases is very convincing and encouraging. The Levelized Cost of Energy (LCOE) computed by the software for all three cases is compared with the existing setup produced energy cost. It reveals that the designed FSPV produces significantly economical power. Overall, the outcomes of this investigation demonstrate the potential of FSPV systems as a viable and sustainable solution for powering fish farms and contributing to the sustainability of the aquaculture industry.

Techno-economic comparison of standalone solar PV and hybrid power systems for remote outdoor telecommunication sites in northern Ghana

Telecommunication services have continued to evolve to meet the ever-changing bandwidth demand requirements. The electricity grid network of Ghana is faced with challenges, including low voltages, a lack of quick fault response teams, and the proximity to specific locations. Using diesel generators to address the shortfall in grid supply is expensive and has implications for greenhouse gas emissions. This study evaluated the technical and economic benefits of using a standalone solar photovoltaic (PV) system, hybrid (Solar PV/diesel), conventional diesel generators (DG), and grid extension to power an off-grid outdoor telecommunication site. Power solutions configurations were simulated using hybrid optimization of multiple electric renewables (HOMER). The study found the optimum design to be a standalone solar PV/battery system with 56.3 kW solar PV array and Sixty (60) pieces of 12 V SAGM batteries of 135 Ah. The optimum design had a net present cost (NPC) of US$ 88,176.00 and a cost of energy (COE) of US$ 0.321/kWh. The COE and the NPC of the optimum system were approximately 50% less than the design with DG only, which could significantly impact service tariff and improve access to digital connectivity. The COE from the solar PV/battery system is not competitive with the grid power supply (COE = US$0.12). However, considering the electric distance limit or breakeven distance of 4.51km for grid extension, the solar PV/battery is preferred. Therefore, the stakeholders in providing power solutions to off-grid locations should consider solar PV technology.

Prediction of Photovoltaic Panels Output Performance Using Artificial Neural Network

To ensure the safe and stable operation of solar photovoltaic system-based power systems, it is essential to predict the PV module output performance under varying operating conditions. In this paper, the interest is to develop an accurate model of a PV module in order to predict its electrical characteristics. For this purpose, an artificial neural network (ANN) based on the backpropagation algorithm is proposed for the performance prediction of a photovoltaic module. In this modeling approach, the temperature and illumination are taken as inputs and the current of the mathematical model as output for the learning of the ANN-PV-Panel. Simulation results showing the performance of the ANN model in obtaining the electrical properties of the chosen PV panel, including I–V curves and P–V curves, in comparison with the mathematical model performance are presented and discussed. The given results show that the error of the maximum power is very small while the current error is about 10-8, which means that the obtained model is able to predict accurately the outputs of the PV panel.

Effect of peak sun hour on energy productivity of solar photovoltaic power system

A solar cell is a type of renewable energy engineering technology that can convert photons coming from the sun to be converted into electrical energy. The amount of energy that can be converted by a solar cell is determined by the effective insolation time. Peak sun hours (PSH) are the focus of this research. This PSH analysis aims to determine the potential for solar energy obtained in geographical locations throughout the year. Geographical location and the position of the astronomical coordinates of a certain area affect PSH. Therefore, the orientation of solar panel installation, including the height, slope, and latitude of the solar panel surface needs to be considered in order to get maximum solar energy. The results of this study can be used by technicians in determining the orientation of solar panel development in an area.

A Machine Learning-Based Novel Energy Optimization Algorithm in a Photovoltaic Solar Power System

Performance, cost, and aesthetics are all difficult to beat in today’s expanding distributed rooftop solar sector, and flat-plate PV is no exception. Photovoltaics will be able to take advantage of some of their most significant advantages as a result of this marketplace, including the elimination of transmission losses and the generation of power at the point of sale. Concentrated photovoltaic (CPV) technology, on the other hand, represents a viable alternative in the quest for ever-lower normalised energy costs and ever-shorter energy payback times. Material, components, and manufacturing techniques from allied sectors, particularly the power electronics industry, have been adapted to lower system costs and time-to-market for the system under development. The LFR is less than 30 mm wide to maximise thermal efficiency, and a densely packed cell array has been used to maximise electrical output. The Matlab simulations show that the proposed machine learning-based LFR technique has a greater concentration rate than the present LFR method, as demonstrated by the results.

Comparative Review and Performance Evaluation of Various Solar PV System Reconfigurations

In the current context, the most challenging and demanding research is to obtain maximum power from solar photovoltaic (SPV) power systems. Partial shadowing (PS) is a prominent cause of solar photovoltaic panels output power loss. The output decreases proportionally to the shaded area, the placement of shaded panels within the array, panel interconnections, shade pattern, etc. Numerous static and dynamic approaches for reducing the PS effect have been reported in the literature. Of these, the most common is the reconfiguration technique based on the static method, which distributes shaded panels more consistently and increases maximum power generation. The current study investigates the performance of common existing reconfiguration techniques based on static methods, including TCT, Sudoku, odd even (OE), and Latin square (LS) on a 4×4 PV array. The five different shadow patterns: short narrow (SN), short wide (SW), long narrow (LN), long wide (LW), and centre (CN) are implemented in this work. The performance analysis is carried out by comparing the maximum power generated (PM) and the results of panel simulations, as well as their theoretical conclusions, to ensure that these strategies are effectively implemented in hardware configuration.