计算机科学最新文献

筛选
英文 中文
Performance Analysis of Mixed Beaulieu-Xie and M $mathcal {M}$ Dual-Hop Amplify-and-Forward Relay Systems 混合Beaulieu-Xie和M $mathcal {M}$双跳放大转发中继系统性能分析
IF 1.5 4区 计算机科学
IET Communications Pub Date : 2025-07-03 DOI: 10.1049/cmu2.12764
Jiashun Hu, Yuexiang Wu, Weiqiang Wu, Sunan Wang
{"title":"Performance Analysis of Mixed Beaulieu-Xie and \u0000 \u0000 M\u0000 $mathcal {M}$\u0000 Dual-Hop Amplify-and-Forward Relay Systems","authors":"Jiashun Hu,&nbsp;Yuexiang Wu,&nbsp;Weiqiang Wu,&nbsp;Sunan Wang","doi":"10.1049/cmu2.12764","DOIUrl":"https://doi.org/10.1049/cmu2.12764","url":null,"abstract":"<p>This work presents a comprehensive study on the performance of an asymmetric dual-hop radio frequency (RF)/free-space optical (FSO) transmission system that utilizes a fixed gain amplify-and-forward protocol. The RF path is characterized by the Beaulieu–Xie model, and the FSO link is affected by Málaga (<span></span><math>\u0000 <semantics>\u0000 <mi>M</mi>\u0000 <annotation>$mathcal {M}$</annotation>\u0000 </semantics></math>) turbulence in the presence of pointing errors. In this study, we introduce novel and precise analytical expressions for the probability density function, the cumulative distribution function (CDF), and the moment generating function (MGF) of the overall signal-to-noise ratio (SNR). Using the derived expressions, we proceed to obtain accurate infinite series representations for the outage probability (OP), the average bit-error rate (BER), and the ergodic capacity (EC). In addition, we conduct asymptotic analysis for the CDF, the MGF, the OP, the average BER, and the EC in the high SNR regime. Numerical results are compared with the Monte Carlo simulations to validate the accuracy of these derived expressions.</p>","PeriodicalId":55001,"journal":{"name":"IET Communications","volume":"19 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cmu2.12764","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Compact 18-Element Multiband MIMO Antenna With Metal Frames for 5G Mobile Devices 紧凑型18元多频段MIMO天线,金属框架,用于5G移动设备
IF 1.7 4区 计算机科学
International Journal of Communication Systems Pub Date : 2025-07-03 DOI: 10.1002/dac.70163
Naveen Jaglan, Ahmed A. Kishk
{"title":"Compact 18-Element Multiband MIMO Antenna With Metal Frames for 5G Mobile Devices","authors":"Naveen Jaglan,&nbsp;Ahmed A. Kishk","doi":"10.1002/dac.70163","DOIUrl":"https://doi.org/10.1002/dac.70163","url":null,"abstract":"<div>\u0000 \u0000 <p>An 18-element multiband massive MIMO antenna system is proposed for 5G-enabled smartphones. The radiating units are engineered to operate within the frequency ranges of 3.4–3.6 (LTE Band 42), 3.6–3.8 (LTE Band 43), and 5.15–5.925 GHz (LTE Band 46). A simple open-ended U-shaped slot radiator with metallic side frames is used. The metallic side frames improve the robustness of the handset. Open-ended slots integrated into the side frames help reduce mutual coupling between the radiating elements. Simulated and measurements show excellent envelope correlation coefficients (<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>&lt;</mo>\u0000 </mrow>\u0000 <annotation>$$ &lt; $$</annotation>\u0000 </semantics></math> 0.07) and total efficiency (<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>&gt;</mo>\u0000 </mrow>\u0000 <annotation>$$ &gt; $$</annotation>\u0000 </semantics></math> 87%) across the full operational bandwidth. The massive MIMO capabilities of the proposed design are evaluated through ergodic channel capacity analysis (&gt; 96 bps/Hz) using the Kronecker channel model. Furthermore, the influence of real-world factors such as human hand grip, LCD, and battery components is thoroughly examined.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"38 12","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144550886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
DualRT: A Qos-Aware Soft Real-Time Video Analytics Framework for Dual-Stage GPU-CPU Tasks on Edge DualRT:一种面向边缘双阶段GPU-CPU任务的qos感知软实时视频分析框架
IF 1.5 4区 计算机科学
Concurrency and Computation-Practice & Experience Pub Date : 2025-07-03 DOI: 10.1002/cpe.70174
Changhong Zhu, Haitao Zhang, Xingtao Xu
{"title":"DualRT: A Qos-Aware Soft Real-Time Video Analytics Framework for Dual-Stage GPU-CPU Tasks on Edge","authors":"Changhong Zhu,&nbsp;Haitao Zhang,&nbsp;Xingtao Xu","doi":"10.1002/cpe.70174","DOIUrl":"https://doi.org/10.1002/cpe.70174","url":null,"abstract":"<div>\u0000 \u0000 <p>Edge cameras are ubiquitous, together with the recent boom in computer vision technology, and a variety of video analytics tasks are being processed at the edge. It is challenging to support more complex video analytics tasks on edge servers with unpredictable request loads and limited resources. However, most of these works use only a single optimization approach, focusing only on the improvement of a certain performance metric in a single processing stage, ignoring the balance of other performance metrics, and the space available for optimization is often very limited. Especially when dealing with video analytics tasks that need to be divided into two GPU-CPU stages for completion, this unidirectional focus may lead to execution performance imbalance or even negative quality of service (QoS) optimization. In addition, to fully utilize the valuable resources on the edge servers, it is often necessary to schedule multiple types of video analytics tasks on the edge servers. However, most of the existing scheduling strategies only focus on how to allocate computational resources for end-to-end tasks. They lack the awareness and consideration of the execution of tasks in different execution stages, as well as the mutual interference among tasks. These scheduling strategies, lacking stage-sensitivity and interference-sensitivity, may cause performance conflicts in environments running multiple tasks involving GPU-CPU dual-stage processing, thus affecting the overall QoS. To address these challenges, we first evaluate the impact of batch processing, frame rate control, resolution selection, and CPU concurrency processing on throughput, latency, and accuracy when running dual-stage tasks on edge platforms. Then, we propose DualRT, a soft real-time video analytics framework for dual-stage tasks, to optimize the QoS of dual-stage tasks while avoiding request stacking on edge platforms. In the scheduling module of DualRT, we design a scheduling method using a multi-agent deep reinforcement learning algorithm and a variable time window approach to schedule multiple dual-stage tasks with joint control of batch size, resolution, frame rate, and CPU concurrency for each task. Our experimental results show that DualRT improves QoS by an average of 13.3% and maximum throughput by an average of 24.6% compared to state-of-the-art solutions.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 18-20","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144551205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Secure state and output estimation for accommodation of false data injection attacks in large-scale systems 大规模系统中适应假数据注入攻击的安全状态和输出估计
IF 4.8 2区 计算机科学
Automatica Pub Date : 2025-07-03 DOI: 10.1016/j.automatica.2025.112460
Hanieh Tabatabaei , Alexander J. Gallo , Ahmad W. Al-Dabbagh
{"title":"Secure state and output estimation for accommodation of false data injection attacks in large-scale systems","authors":"Hanieh Tabatabaei ,&nbsp;Alexander J. Gallo ,&nbsp;Ahmad W. Al-Dabbagh","doi":"10.1016/j.automatica.2025.112460","DOIUrl":"10.1016/j.automatica.2025.112460","url":null,"abstract":"<div><div>In this paper, we address the problem of secure estimation in networked systems, by focusing on false data injection attacks in large-scale systems, where malicious attackers alter the original transmitted data between subsystems. We propose a technique that ensures asymptotic secure estimation of the original transmitted data under two attack classes, termed stealthy and non-stealthy, while also providing detection and isolation capabilities. We give conditions under which asymptotic recovery of nominal performance is guaranteed, thus providing the large-scale system with resilience. Furthermore, we demonstrate the effectiveness of the proposed technique through a simulation-based case study.</div></div>","PeriodicalId":55413,"journal":{"name":"Automatica","volume":"180 ","pages":"Article 112460"},"PeriodicalIF":4.8,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144548521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Security in Metaverse Markets: Challenges and Solutions—A Comprehensive Review 元宇宙市场的安全:挑战与解决方案-全面回顾
IF 3 4区 计算机科学
Expert Systems Pub Date : 2025-07-03 DOI: 10.1111/exsy.70094
Mohammad Z. Aloudat, Mahmoud Barhamgi, Elias Yaacoub, Dani Aoun
{"title":"Security in Metaverse Markets: Challenges and Solutions—A Comprehensive Review","authors":"Mohammad Z. Aloudat,&nbsp;Mahmoud Barhamgi,&nbsp;Elias Yaacoub,&nbsp;Dani Aoun","doi":"10.1111/exsy.70094","DOIUrl":"https://doi.org/10.1111/exsy.70094","url":null,"abstract":"<p>This review paper provides a systematic overview of the metaverse markets security problems and solutions. The metaverse is an emerging digital space, bridging virtual, augmented and mixed reality environments. As the metaverse evolves, issues related to customer security have emerged, which include breaches of privacy, thefts of identity and cybercrimes, all of this compounded by insecurities in the decentralised structures. Through this systematic literature review, we analyse these challenges and assess current approaches to mitigate them, including encryption, decentralised identity and related regulatory frameworks, but highlight their limited capacity for dealing with immersive virtual spaces' unique risks. The review also explores some advanced solutions adopting artificial intelligence, blockchain and privacy enhancing technologies (PETs) for securing the metaverse and enhancing its privacy. Furthermore, the review also points out the gaps in the current literature, particularly a lack of customised customer protection structures and a poor analysis of the psychological effects. It also proposes future solutions such as quantum-resistant security and zero-trust architecture to fortify the security. This review highlights the necessity of partnership between the industries, as well as the setting of security protocols so as to safeguard customer trust and engagement in the growing digital space.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 8","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70094","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144550943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Realisation of an E-Plane Metal-Insert Filter at E-Band Based on Multi-Layer Waveguide With Pin Array Electromagnetic Band Gap 基于引脚阵列电磁带隙多层波导的e平面金属插入滤波器的实现
IF 1.1 4区 计算机科学
Iet Microwaves Antennas & Propagation Pub Date : 2025-07-03 DOI: 10.1049/mia2.70034
Morteza Rezaee, Abbas Vosoogh, Ali Mehrdadian
{"title":"Realisation of an E-Plane Metal-Insert Filter at E-Band Based on Multi-Layer Waveguide With Pin Array Electromagnetic Band Gap","authors":"Morteza Rezaee,&nbsp;Abbas Vosoogh,&nbsp;Ali Mehrdadian","doi":"10.1049/mia2.70034","DOIUrl":"https://doi.org/10.1049/mia2.70034","url":null,"abstract":"<p>In this paper, a multi-layer waveguide (MLW) bandpass filter is realised by stacking thin metal layers at E-band. In order to eliminate the leakage between layers, an electromagnetic band gap (EBG) pin array is utilised. The periodic pin texture is created by 3D chemical etching on the layers. The thickness of layers and height of pins are selected properly to provide a stopband at operating frequency band of interest. A thin metal layer at the middle of the waveguide channel is used to realise the cavities and coupling slits of the filter. A seventh order metal-insert E-plane filter with frequency pass band of 69.5–76 GHz is designed and fabricated. The designed MLW bandpass filter is fabricated in brass and copper metal sheets with insertion loss of around 1.5 and 1.1 dB, respectively. Several filter prototypes are fabricated and studied to verify the repeatability of the fabrication and assembly processes.</p>","PeriodicalId":13374,"journal":{"name":"Iet Microwaves Antennas & Propagation","volume":"19 1","pages":""},"PeriodicalIF":1.1,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/mia2.70034","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144550896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Improving the area-preserving parameterization of rational Bézier surfaces by rational bilinear transformation 利用有理双线性变换改进有理bsamzier曲面的保面积参数化
IF 2.5 4区 计算机科学
Graphical Models Pub Date : 2025-07-03 DOI: 10.1016/j.gmod.2025.101278
Xiaowei Li , Yingjie Wu , Yaohui Sun , Xin Chen , Yanru Chen , Yi-jun Yang
{"title":"Improving the area-preserving parameterization of rational Bézier surfaces by rational bilinear transformation","authors":"Xiaowei Li ,&nbsp;Yingjie Wu ,&nbsp;Yaohui Sun ,&nbsp;Xin Chen ,&nbsp;Yanru Chen ,&nbsp;Yi-jun Yang","doi":"10.1016/j.gmod.2025.101278","DOIUrl":"10.1016/j.gmod.2025.101278","url":null,"abstract":"<div><div>To improve the area-preserving parameterization quality of rational Bézier surfaces, an optimization algorithm using bilinear reparameterization is proposed. First, the rational Bézier surface is transformed using a rational bilinear transformation, which provides greater degrees of freedom compared to Möbius transformations, while preserving the rational Bézier representation. Then, the energy function is discretized using the composite Simpson’s rule, and its gradients are computed for optimization. Finally, the optimal rational bilinear transformation is determined using the L-BFGS method. Experimental results are presented to demonstrate the reparameterization effects through the circle-packing texture map, iso-parametric curve net, and color-coded images of APP energy in the proposed approach.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"140 ","pages":"Article 101278"},"PeriodicalIF":2.5,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144534220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A novel fragmentation metric and fragmentation-aware adaptive routing and spectrum allocation algorithm in elastic optical network 弹性光网络中一种新的碎片度量和碎片感知自适应路由和频谱分配算法
IF 2.6 3区 计算机科学
Optical Fiber Technology Pub Date : 2025-07-03 DOI: 10.1016/j.yofte.2025.104318
Ruchi Srivastava , Yatindra Nath Singh
{"title":"A novel fragmentation metric and fragmentation-aware adaptive routing and spectrum allocation algorithm in elastic optical network","authors":"Ruchi Srivastava ,&nbsp;Yatindra Nath Singh","doi":"10.1016/j.yofte.2025.104318","DOIUrl":"10.1016/j.yofte.2025.104318","url":null,"abstract":"<div><div>Next-generation elastic optical networks are being developed to accommodate the increasing demands of heterogeneous traffic for 5G/6G communication. The arrival and departure of this real-time traffic are inherently dynamic. Such dynamic traffic requests, combined with varying bandwidth requirements, lead to spectral fragmentation within the links. Link fragmentation refers to the presence of non-contiguous available spectrum slices within these links. An increase in the number of link fragments diminishes the width of the available frequency slots, which may not meet spectrum constraints, thereby resulting in higher blocking rates within the network. Consequently, it is essential to assess link spectral fragmentation to implement an effective spectrum management strategy. Various metrics for measuring fragmentation in links have been proposed in the literature, including external fragmentation metric (EFM), entropy-based fragmentation metric (EBFM), root mean square fragmentation metric (RMSFM), and golden fragmentation metric (GFM). This paper highlights the limitations of these existing metrics and introduces a novel spectrum slice-based fragmentation metric (SSFM). To evaluate the effectiveness of SSFM, in comparison to EFM, EBFM, RMSFM and GFM, a fragmentation status aware adaptive routing and spectrum allocation (FSA-RSA) algorithm has been developed. Simulations are conducted on German, USNET and Telecom Italia (TI) network topologies. To evaluate the effectiveness of SSFM in relation to other fragmentation metrics, we have employed the following measures: Execution Time (ET), Computational Overhead Ratio (COR), Memory Overhead (MO) and we have evaluated the following performance metrics as a quantitative tool for measuring the effectiveness of the proposed FSA-RSA (SSFM) algorithm against benchmark algorithms: throughput, Request Blocking Probability (RBP), Fractional Spectrum Utilization (FSU), and Link Fragmentation Metric (LFM). Among these, throughput and execution time are regarded as the primary performance metrics. The findings suggest that the FSA-RSA (SSFM) algorithm enhances network performance, yielding an average minimum throughput increase of 3.5%, 0.12% and 108% when compared to the FSA-RSA (EBFM), FSA-RSA (EFM) and FSA-RSA (GFM) algorithms, respectively. However, it exhibits a throughput that is 0.0049% lower than that of the FSA-RSA (RMSFM) algorithm, a shortfall that can be offset by the reduced execution time and memory overhead associated with SSFM in comparison to RMSFM.</div></div>","PeriodicalId":19663,"journal":{"name":"Optical Fiber Technology","volume":"94 ","pages":"Article 104318"},"PeriodicalIF":2.6,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144548394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Security Frame Towards 6G Networks for Isolating False Data Using Artificial Intelligence Algorithm 利用人工智能算法隔离虚假数据的6G网络安全框架
IF 1.5 4区 计算机科学
Concurrency and Computation-Practice & Experience Pub Date : 2025-07-03 DOI: 10.1002/cpe.70182
Hariprasath Manoharan, Gayathri Devi P
{"title":"Security Frame Towards 6G Networks for Isolating False Data Using Artificial Intelligence Algorithm","authors":"Hariprasath Manoharan,&nbsp;Gayathri Devi P","doi":"10.1002/cpe.70182","DOIUrl":"https://doi.org/10.1002/cpe.70182","url":null,"abstract":"<div>\u0000 \u0000 <p>This research aims to identify and explore the significance of security aspects in the transition to Sixth Generation (6G) networks. Due to the lack of security features and absence of a data discovery process in the current infrastructure, the proposed approach is being built to discover data under low latency conditions. Furthermore, data analysis is conducted using an artificial intelligence algorithm that incorporates distributed and various decision-making processes to monitor the outcomes. The analysis focuses on the impact of influential factors during data transmission units, employing normalizations to prevent unauthorized users from accessing such transmissions. In order to enhance the security of data in 6G networks, data pairing circumstances are assessed, resulting in increased delivery units at the receiver side and prevention of data drops. In order to conduct a thorough study, the parametric design is evaluated under four different scenarios. The performance analysis is then carried out using two case studies. The results show that the suggested method decreases data drops to 2%, whereas the previous methodology has a data drop rate of 10%.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 18-20","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144551204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A ground-based cloud image classification method for photovoltaic power prediction based on Convolutional Neural Networks and Vision Transformer 基于卷积神经网络和视觉变压器的光伏发电功率预测地基云图分类方法
IF 7.5 2区 计算机科学
Engineering Applications of Artificial Intelligence Pub Date : 2025-07-03 DOI: 10.1016/j.engappai.2025.111582
Chaojun Shi , Mengyu Zhang , Hongyin Xiang , Ke Zhang , Sihao Ju , Xiaoyun Zhang , Leile Han
{"title":"A ground-based cloud image classification method for photovoltaic power prediction based on Convolutional Neural Networks and Vision Transformer","authors":"Chaojun Shi ,&nbsp;Mengyu Zhang ,&nbsp;Hongyin Xiang ,&nbsp;Ke Zhang ,&nbsp;Sihao Ju ,&nbsp;Xiaoyun Zhang ,&nbsp;Leile Han","doi":"10.1016/j.engappai.2025.111582","DOIUrl":"10.1016/j.engappai.2025.111582","url":null,"abstract":"<div><div>Cloud image classification plays a crucial role in accurately predicting solar radiation attenuation, which significantly impacts ultra-short-term photovoltaic power predictions. Despite recent advancements in cloud image classification using Transformer and convolutional neural networks, challenges remain, particularly in handling rapidly evolving cumuliform clouds. To address this, we propose CloudMViT, an improved model derived from a model that combines Convolutional Neural Networks and Vision Transformer (MobileViT). CloudMViT introduces the CloudMobileNetV2 (CMV2) Block, building upon the Mobile Network architecture (MobileNetV2). This block incorporates a triple-branch inverted residual structure consisting of depthwise separable convolution, standard convolution, and shortcut branches, along with a New Multi-scale Channel Attention Module (NMS-CAM). Simultaneously, CloudMViT proposes the CloudMViT Block, which integrates adaptive convolution to enhance local feature representation. CloudMViT improves local and global feature extraction, boosting cloud image classification accuracy. The proposed model was evaluated through ablation studies and comparative experiments on the Tianjin-Normal-University-Ground-based-Cloud-Dataset (GCD) and Tianjin-Normal-University-Ground-based-Remote-Sensing-Cloud-Database (GRSCD). The ablation experiments demonstrate that the modules introduced in CloudMViT significantly improve cloud image classification accuracy. Comparative results show that CloudMViT achieves higher accuracy than other state-of-the-art methods, reaching 91.40% on GCD and 98.25% on GRSCD datasets. Finally, CloudMViT was validated through experiments in conjunction with a photovoltaic power prediction model, achieving a prediction accuracy of 96.70%, which surpasses that of the original model. This further demonstrates that utilizing CloudMViT cloud image classification results enhances the accuracy of photovoltaic power prediction. Moreover, it verifies that improving cloud image classification accuracy can effectively enhance the precision of photovoltaic power forecasting.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"159 ","pages":"Article 111582"},"PeriodicalIF":7.5,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144548785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信