Energy Science & Engineering最新文献

{"title":"Multidimensional Characterization of Formation Damage Mechanisms in Ancient Carbonate Reservoirs: Synergistic Effects of Inorganic-Organic Interactions","authors":"Jin Pang,&nbsp;Tongtong Wu,&nbsp;Xinan Yu,&nbsp;Hong Liu,&nbsp;Chunxi Zhou,&nbsp;Haotian Chen","doi":"10.1002/ese3.70059","DOIUrl":"https://doi.org/10.1002/ese3.70059","url":null,"abstract":"<p>Formation clogging in carbonate gas reservoirs is a significant challenge in natural gas extraction, particularly due to the complex mineral composition and physicochemical characteristics of carbonate rocks, which make clogging phenomena even more complex. This study aims to delve into the formation mechanisms of formation plugs in carbonate gas reservoirs by analyzing the chemical composition, mineral characteristics, and organic components of the clogging materials. Formation clogging usually results from multiple factors acting together, including the migration of rock particles, scaling of formation water, deposition of organic matter, and corrosion of downhole equipment. These clogging materials not only hinder gas flow but may also accelerate the corrosion of pipelines and other facilities, increasing maintenance costs, and in severe cases, leading to gas well failure. Although numerous studies have focused on formation clogging in carbonate gas reservoirs, a comprehensive understanding of their complex mechanisms of action is still lacking. This paper employs advanced analytical techniques such as X-ray diffraction (XRD), gas chromatography-mass spectrometry (GC-MS), and X-ray photoelectron spectroscopy (XPS) to analyze clogging materials from the Pengtan-1, which is part of the Ancient Carbonate Reservoirs, in the Sichuan Basin. The results indicate that the clogging materials are complex, consisting of a mixture of inorganic and organic substances, and multiple factors synergistically contribute to the formation of clogging. The study provides new insights into the formation mechanisms of clogging materials and offers a theoretical basis for developing more effective prevention and control strategies. This research provides significant support for improving the development efficiency, stability, and economic viability of carbonate gas reservoirs.</p>","PeriodicalId":11673,"journal":{"name":"Energy Science & Engineering","volume":"13 6","pages":"2663-2671"},"PeriodicalIF":3.5,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ese3.70059","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144244760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A DFT Investigation of Structural, Electronic, Optical, and Mechanical Properties of Lead-Free Novel InGeX3 (X = Cl, Br, and I) Perovskites for Potential Applications in Multijunctional Solar Cells","authors":"Md. Amran Sarker,&nbsp;Md. Mehedi Hasan,&nbsp;Sharmin Akhter Luna,&nbsp;Md. Imtiaz Hossain Chowdhury,&nbsp;Md. Rabbi Talukder,&nbsp;Md. Rasidul Islam,&nbsp;Sohail Ahmad","doi":"10.1002/ese3.70065","DOIUrl":"https://doi.org/10.1002/ese3.70065","url":null,"abstract":"<p>Conducting an inquiry into the structural, mechanical, electrical, and optical aspects of Ge-based InGeX₃ (Cl, Br, and I) halide perovskites using the density functional theory approach is the main objective of this study. The investigation reveals that substituting the bigger halogen atoms (Br and I) with the smaller halide (Cl) enhances the structural stability of the compound. The largest values of lattice constant and unit cell volumes are found for the InGeI₃ compound. Formation energy and born stability criteria are also calculated, which comprehend the compounds as chemically and mechanically stable. Elastic constants, mechanical properties, and anisotropy behavior of the compounds are also analyzed. The investigation explicitly demonstrates that InGeCl₃ has superior ductility, machinability, and hardness as well. The anisotropy nature of all our studied compounds has also been discussed and visualized through three-dimensional contour maps. Employing the GGA-PBE and HSE06 functional, the band gap energy of each InGeX₃ perovskite has been determined. In all our studied compounds, a direct band gap was observed at the high symmetrical point, <i>R</i>. The optical properties of the perovskites, including dielectric function, absorption coefficient, optical conductivity, reflectivity, refractive index, and extinction coefficient, have been analyzed. Overall, the results of the investigation conclude that InGeX₃ perovskite compounds are the preferred material choice for effective performance in multijunctional solar cells and optoelectronic devices.</p>","PeriodicalId":11673,"journal":{"name":"Energy Science & Engineering","volume":"13 6","pages":"2757-2771"},"PeriodicalIF":3.5,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ese3.70065","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144244750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Numerical Prediction of the Influence of Particle Properties on the Hydraulic Performance and Wear of a Self-Priming Pump","authors":"Ying-Yu Ji,&nbsp;Ze-Zhou Yang,&nbsp;Yu-Liang Zhang,&nbsp;Kai-Yuan Zhang","doi":"10.1002/ese3.70060","DOIUrl":"https://doi.org/10.1002/ese3.70060","url":null,"abstract":"<p>In addressing the complexities associated with the conveyance of solid–liquid two-phase flow by a self-priming pump in field irrigation and drainage, this study numerically investigates the impact of three typical solid phase properties on the hydraulic performance of the pump, employing the Mixture multiphase flow model. Concurrently, utilizing the discrete phase model (DPM), the influence of operational speed and working condition flow rate on the wear of the flow passage components' walls is also numerically examined. The findings indicate that the order of significance for the impact on the hydraulic performance of the self-priming pump is as follows: the volume fraction of the solid phase, the hydraulic diameter of the particles, and the density of the solid particles. As these parameters increase, the corresponding relative decreases in head are 43.232%, 7.132%, and 5.541%, respectively, while the relative reductions in efficiency are 61.199%, 2.930%, and 9.805%, respectively. An increase in these parameters leads to a general trend of decline in the pump's hydraulic performance. Notably, while the volume fraction of the solid phase and the hydraulic diameter of the particles exhibit an enhancement in pressure capability, the density of the particles shows an inverse relationship with respect to pressure capacity. Additionally, it is observed that an increase in both rotational speed and flow rate at working conditions exacerbates the wear on the walls of all flow passage components. The degree of wear on the pressure side of the blades is markedly higher than that on the suction side. Furthermore, the wear on the pressure side of the blades is predominantly localized toward the middle-front section, specifically within 0 to 0.6 times the relative length of the blade, with the most severe wear concentrated at approximately 0.3 times the relative length of the blade, whereas the wear on the suction side is more pronounced in the middle-rear section, ranging from 0.4 to 1.0 times the relative length of the blade. This study represents the first investigation into the impact of solid particle properties in solid–liquid two-phase flows on the wear and hydraulic performance degradation of self-priming pumps during their operation. It provides theoretical guidance for the optimized design of self-priming pumps.</p>","PeriodicalId":11673,"journal":{"name":"Energy Science & Engineering","volume":"13 6","pages":"2672-2694"},"PeriodicalIF":3.5,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ese3.70060","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144244761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mechanical Behavior and Response Characteristics of Overlying Strata in Remining Longwall Top-Coal Caving Working Face","authors":"Defu Zhu,&nbsp;Zhanguo Cheng,&nbsp;Huibo Xia,&nbsp;Yujiang Zhang","doi":"10.1002/ese3.70067","DOIUrl":"https://doi.org/10.1002/ese3.70067","url":null,"abstract":"<p>In the remining working face of thick coal seams, the instability of coal pillars near abandoned roadways can lead to advance fractures in the main roof, posing a significant threat to production safety. This study classifies roof collapse characteristics into four types and analyses the pillar instability mechanism using the Bieniawski formula and load estimation methods. A structural mechanics model is developed to predict the fracture location of the main roof based on bending moment distribution, influenced by factors such as pillar width, static load, cantilever length of the goaf, stress concentration, and abandoned roadway width. The fracture line is determined by the location of the maximum bending moment, and a mechanical model is developed to compute the hydraulic supports' working resistance. Theoretical calculations for three coal mines—Shiku, Hanzui, and Shenghua—yield maximum support resistances of 8757.25, 7810.09, and 10,034.46 kN, respectively, aligning well with measured mine pressure data. Results indicate that increased cantilever length and roadway width reduce pillar stability, shifting the maximum bending moment farther from the coal wall. This study provides a basis for selecting hydraulic supports and ensuring safe remining operations, offering theoretical guidance for addressing roof fractures and mine pressure management.</p>","PeriodicalId":11673,"journal":{"name":"Energy Science & Engineering","volume":"13 6","pages":"2788-2801"},"PeriodicalIF":3.5,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ese3.70067","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144244762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-Perspective Behavioural Investigations on Coolant of Battery Thermal Management Systems in Electrical Vehicles Using Computational Fluid Dynamics","authors":"Laxana Sourirajan,&nbsp;Mohankumar Subramanian,&nbsp;Beena Stanislaus Arputharaj,&nbsp;Parvathy Rajendran,&nbsp;Pradesh Sakthivel,&nbsp;Vijayanandh Raja,&nbsp;Arunkumar Karuppasamy,&nbsp;C. Ahamed Saleel,&nbsp;Nasim Hasan","doi":"10.1002/ese3.70044","DOIUrl":"https://doi.org/10.1002/ese3.70044","url":null,"abstract":"<p>Battery thermal management system (BTMS) is a very important field that is currently being focused on by the thermal and energy departments all around the world. This work primarily emphasizes channel design for BTMS and the utilization of modern computational fluid dynamics (CFD) investigations in BTMS. Enhancing the fluid-battery heat transfer interaction is the aim of the proposed channel design. A reliable CFD study and better wall treatment confirmed the thermal performance of the identical channel design. Secondly, this study focuses on finding a suitable velocity at which a coolant can perform its best efficiently, that is, by absorbing most of the heat present in the battery system. Six coolant fluids were chosen to achieve the goal of finding the best velocity at three different heat generation rates (HGR). These HGRs include 5318, 19,452 and 42,400 W/m³ describing the C Ratings 1C, 2C and 3C, respectively. Six coolants were Ethylene Glycol, Propylene Glycol, Glycerine, Ethyl Alcohol, Water liquid and Water Glycol. It is concerning that even after choosing the required coolant for heat absorption, it becomes necessary that the velocity at which it can be allowed to flow through the battery system determines the effectiveness of the coolants. It was concluded that the coolant fluids better perform at 1 m/s. This lets us know that, when the flow of the coolant is at its lowest velocity, it can efficiently absorb the heat while it stays at that particular instant. The coolant's temperature was measured to be higher at the outlet (after it has flowed through the entire battery system) compared to the intake temperature. This indicates that the coolant has absorbed heat through molecular interaction. The input temperature was recorded at 29.85°C. It was also noted that Ethyl Alcohol and Propylene Glycol work the best at the HGR of 5318 W/m³, and the other coolants work the best at 19,452 W/m³ at 1 m/s. Using low-velocity fluids in liquid BTMS has been found to enhance thermal management by improving heat transfer efficiency, ensuring structural integrity, extending the duration of heat exchange, enhancing temperature uniformity and reducing energy consumption. These factors collectively contribute to making lithium-ion batteries safer and more effective for a range of applications.</p>","PeriodicalId":11673,"journal":{"name":"Energy Science & Engineering","volume":"13 5","pages":"2455-2479"},"PeriodicalIF":3.5,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ese3.70044","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143920006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hydrocarbon Generation Characteristics and Geological Significance of Deep Organic-Rich Shales in the Gulong Fault Depression, Songliao Basin, Northeastern China","authors":"Bo Hu,&nbsp;Xiaomei Li,&nbsp;Jiajun Liu,&nbsp;Zhuang Cai,&nbsp;Hongyan Liu,&nbsp;Yan Xu,&nbsp;Fangwen Chen","doi":"10.1002/ese3.70063","DOIUrl":"https://doi.org/10.1002/ese3.70063","url":null,"abstract":"<p>To evaluate the hydrocarbon generation characteristics and geological significance of deep-source rocks in the Gulong Sag of the Songliao Basin and to identify the next exploration targets in the study area, this study focuses on the organic-rich mudstones and shales from the deep formations of the Gulong Sag. Organic geochemical characteristics, such as organic matter (OM) abundance, type, and maturity, were analyzed for shale samples from the Shahezi, Yingcheng, and Denglouku formations. Thermal simulation experiments on moderately mature source rock samples were conducted to assess the hydrocarbon conversion rates, hydrocarbon generation potential, and hydrocarbon generation phases using chemical kinetic methods. The results show that hydrocarbon generation from organic-rich deep mudstones and shales in the Gulong Sag begins at burial depths of 1,000–2,000 m, with the maximum oil generation rate occurring at burial depths of 2,500–3,200 m, corresponding to an oil conversion rate of 28%. At burial depths exceeding 3,300 m, the rate of gas generation surpasses that of oil, marking a transition to predominantly gas generation at this stage. The oil generation potential of source rocks from the Denglouku, Yingcheng, and Shahezi formations was 0.237, 0.194, and 0.175 mg/g, respectively, while their gas generation potentials were 0.285, 0.311, and 0.301 cm³/g, respectively. The primary oil generation periods correspond to the sedimentary phases of the Denglouku, Quantou, and Qingshankou formations, whereas the primary gas generation periods align with the sedimentary phases of the Quantou and Qingshankou formations. Deep-source rocks in the Gulong Sag initially exhibit predominantly oil generation, transitioning to gas generation in later stages, with total gas production exceeding oil production. Additionally, secondary cracking of oil into gas occurs during later stages, suggesting that the late-stage gas generation enhances the preservation potential for natural gas and indicates the potential for natural gas reservoir formation in the study area. Compared to Cretaceous marine source rocks in North America, the Gulong Sag source rocks exhibit lower OM abundance but higher maturity. This high maturity is more favorable for gas generation through source rock cracking. However, the structural complexity of the Songliao Basin results in smaller, unevenly distributed natural gas reservoirs. Consequently, gas reservoir exploration requires advanced geophysical techniques to improve accuracy. Additionally, stratified and segmented precision extraction methods should be employed to enhance recovery rates.</p>","PeriodicalId":11673,"journal":{"name":"Energy Science & Engineering","volume":"13 6","pages":"2707-2719"},"PeriodicalIF":3.5,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ese3.70063","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144244751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring Review of Advancements in Fast-Charging Techniques and Infrastructure for Electric Vehicles Revolution","authors":"Ahmed Zentani,&nbsp;A. M. Almaktoof,&nbsp;M. T. E. Kahn","doi":"10.1002/ese3.70051","DOIUrl":"https://doi.org/10.1002/ese3.70051","url":null,"abstract":"<p>The rapid growth of the electric vehicle (EV) industry has increased the demand for efficient and reliable fast-charging infrastructure. This paper comprehensively reviews advancements in fast-charging techniques, focusing on DC fast charging, evolving standards, and charging modes. A detailed analysis of on-board and off-board EV chargers is presented, including DC–DC conversion stages with a comparison of isolated and non-isolated topologies. Key control strategies, such as voltage and current regulation and AI-driven approaches, are examined to optimize performance and reliability. Thermal management strategies using advanced sensors to enhance safety and battery longevity are also discussed. This paper highlights recent research contributions and emerging challenges, with insights into infrastructure development, energy storage integration, and policy implications. Notably, projections indicate that global EV sales could rise to 35% by 2030, with fast-charging infrastructure supporting charging times as low as 15 min for 80% battery capacity. Advancements in bidirectional charging and AI-driven optimization are shaping the next generation of smart EV charging stations. This review serves as a valuable resource for researchers, engineers, and policymakers engaged in EV technology and infrastructure development.</p>","PeriodicalId":11673,"journal":{"name":"Energy Science & Engineering","volume":"13 6","pages":"3437-3447"},"PeriodicalIF":3.5,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ese3.70051","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144244999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experimental Study on Instability Mechanism of Red Shale Roadway Under Dynamic Disturbance","authors":"Xuewu Wu,&nbsp;Zhenqian Ma,&nbsp;Jinlian Zhou,&nbsp;Chunhng Mao,&nbsp;Jimin Zhang","doi":"10.1002/ese3.70043","DOIUrl":"https://doi.org/10.1002/ese3.70043","url":null,"abstract":"<p>To delve into the instability mechanism of the surrounding rock in red shale roadways, a bespoke device was chosen to fabricate a physical model, and a similar experiment was conducted with a blasting-induced disturbance. A meticulous examination was performed on the evolution of surface fractures and the macroscopic failure patterns of the surrounding rock in conjunction with the temperature data gathered via infrared thermal imaging. In accordance with the similarity principle, five perturbation sources were strategically positioned on either side of the roadway, at the haunches, and at a location three times the roadway diameter away from the roof, aiming to comprehensively investigate the root causes of instability under dynamic loading conditions. Simultaneously, a 30° inclined rock layer model was developed using numerical simulation techniques to contrast the alterations in stress, displacement, and other relevant aspects of the surrounding rock under both static and dynamic loads. External dynamic disturbances were then applied to probe the deformation behavior. The experimental results revealed that, subsequent to applying a dynamic load at the midpoint of the left rib of the model, the horizontal and vertical displacements of the surrounding rock augmented, whereas the displacement distribution pattern exhibited minimal alteration. Under static load conditions, the displacement of the left rib surged by 22.5%, that of the right rib climbed by 20.6%, the roof displacement expanded by 33%, and the floor displacement grew by 12.2%, with the peak acceleration at the left rib being the most prominent.</p>","PeriodicalId":11673,"journal":{"name":"Energy Science & Engineering","volume":"13 5","pages":"2440-2454"},"PeriodicalIF":3.5,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ese3.70043","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143919945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Blended Ensemble Learning for Robust Normal Behavior Modeling of Wind Turbines","authors":"Jianghao Zhu,&nbsp;Tingting Pei,&nbsp;Le Su,&nbsp;Bin Lan,&nbsp;Wei Chen","doi":"10.1002/ese3.70055","DOIUrl":"https://doi.org/10.1002/ese3.70055","url":null,"abstract":"<p>The increasing scale of wind farms demands more efficient approaches to turbine monitoring and maintenance. Here, we present an innovative framework that combines enhanced kernel principal component analysis (KPCA) with ensemble learning to revolutionize normal behavior modeling (NBM) of wind turbines. By integrating random kitchen sinks (RKS) algorithm with KPCA, we achieved a 25.21% reduction in computational time while maintaining model accuracy. Our mixed ensemble approach, synthesizing LightGBM, random forest, and decision tree algorithms, demonstrated exceptional performance across diverse operational conditions, achieving <i>R</i>² values of 0.9995 in primary testing. The framework reduced mean absolute error by 25.1% and mean absolute percentage error by 33.4% compared to conventional methods. Notably, when tested across three distinct operational environments, the model maintained robust performance (<i>R</i>² &gt; 0.97), demonstrating strong generalization capability. The system automatically detects anomalies using a 0.1% threshold, enabling real-time monitoring of 78 variables across 136,000+ operational records. This scalable approach integrates seamlessly with existing SCADA infrastructure, offering a practical solution for large-scale wind farm management. Our findings establish a new paradigm for wind turbine monitoring, combining computational efficiency with unprecedented accuracy in normal behavior prediction.</p>","PeriodicalId":11673,"journal":{"name":"Energy Science & Engineering","volume":"13 5","pages":"2565-2584"},"PeriodicalIF":3.5,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ese3.70055","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143919943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimation of Daily Photovoltaic Power One Day Ahead With Hybrid Deep Learning and Machine Learning Models","authors":"Tuba T. Ağır","doi":"10.1002/ese3.1994","DOIUrl":"https://doi.org/10.1002/ese3.1994","url":null,"abstract":"<p>In this study, hybrid LSTM-SVM and hybrid LSTM-KNN models were developed to predict hourly PV power one day ahead. The performances of these hybrid models were compared with K-nearest neighbors (KNN), long short-term memory (LSTM), and support vector machine (SVM) models. The input data of these models were pressure, cloudiness, humidity, temperature, and solar intensity, while the output data was the daily photovoltaic (PV) power one day ahead. The performances of the models were evaluated using mean square error (MSE), root mean square error (RMSE), normalized root mean square error (NRMSE), and peak signal-to-noise ratio (PSNR). The prediction accuracies of hybrid LSTM-KNN, LSTM, KNN, hybrid LSTM-SVM, and SVM were 98.72%, 95.8%, 90.25%, 76.3%, and 48.87%, respectively. Hybrid LSTM-KNN predicted the daily PV power of the day ahead with higher accuracy than LSTM, KNN, SVM, and hybrid LSTM-SVM. The effect of input variables on output variables was examined with sensitivity analysis. Sensitivity analyses showed that the most important meteorological data affecting the daily PV power one day ahead was solar intensity with a rate of 95%.</p>","PeriodicalId":11673,"journal":{"name":"Energy Science & Engineering","volume":"13 4","pages":"1478-1491"},"PeriodicalIF":3.5,"publicationDate":"2025-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ese3.1994","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}