Computers & Electrical Engineering最新文献

{"title":"An enhanced uncertainty and disturbance estimator based on Bi-LSTM-OTC-LADRC of grid-connected wind energy conversion system","authors":"AL-Wesabi Ibrahim ,&nbsp;Abdullrahman A. Al-Shamma’a ,&nbsp;Jiazhu Xu ,&nbsp;Imad Aboudrar ,&nbsp;Khaled Ameur ,&nbsp;Riadh Al Dawood ,&nbsp;Hassan M. Hussein Farh ,&nbsp;Grant Charles Mwakipunda","doi":"10.1016/j.compeleceng.2025.110534","DOIUrl":"10.1016/j.compeleceng.2025.110534","url":null,"abstract":"<div><div>Power restriction and load reduction are key challenges for large wind turbines in high wind speeds. Controller design is crucial to handle system nonlinearities and unpredictable wind for stable, eco-friendly power generation without oscillations. In this context, this study introduces both linear and nonlinear control algorithms that might be implemented on a grid-connected wind energy conversion system (G-CWECS) to optimize the extraction of the global maximum power point (GMPP) and improve active and reactive power regulation. The foundation of these strategies lies in linear active disturbance rejection control (LADRC), which is well-known for its capability to handle uncertainties and disturbances, relying on its observer. The current-based bidirectional LSTM (CBi-LSTM) and optimum torque control (OTC) MPPT method integrated with LADRC are employed to extract GMP from WECS. A powerful metaheuristic technique, named catch fish algorithm (CFA), is utilized to update the Bi-LSTM weights. The LADRC approach is applied to regulate both active and reactive power by controlling grid currents, ensuring a unity power factor. Matlab simulation and Hardware-In-the-Loop (HIL) experiment are carried out to verify the feasibility of the implementation. Comparing with well-known-MPPT methods, the output outcomes prove the efficiency of the recommended Bi-LSTM-OTC-LADRC regarding GMPP extraction during wind speed variation. Additionally, it's proved that the proposed LADRC approach is robustness in terms of managing the uncertainties and disturbances compared to PI, PID and SMC controllers.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"127 ","pages":"Article 110534"},"PeriodicalIF":4.0,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144632221","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}

{"title":"A review of machine learning and IoT-based energy management systems for AC microgrids","authors":"Hanane Tasmant ,&nbsp;Badre Bossoufi ,&nbsp;Chakib Alaoui ,&nbsp;Pierluigi Siano","doi":"10.1016/j.compeleceng.2025.110563","DOIUrl":"10.1016/j.compeleceng.2025.110563","url":null,"abstract":"<div><div>Global energy is in a disruptive shift into the demanded sustainable, efficient, and decentralized energy approach. Microgrids have emerged as key innovations as they can accommodate renewable energy sources, advanced storage solutions, and intelligent controls. This review provides insight into the critical role that Energy Management Systems (EMS) play in optimizing microgrid operation, providing stability, and improving energy use. This includes the added features of infusing new Technologies like Machine Learning (ML) and the Internet of Things (IoTs), which have changed the outlook for Energy Management Systems through predictive analytics, real-time optimization, and greater reliability. Key challenges of microgrid deployment are addressed - renewable energy variability, cybersecurity concerns-in addition to future trends like digital twins and blockchain applications. This thorough analysis will further reinforce that microgrids represent a point crucial in the solutions offered to the demands of the world in energy for resilient and sustainable power systems.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"127 ","pages":"Article 110563"},"PeriodicalIF":4.0,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144604477","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}

{"title":"Improved Signcryption algorithm for cloud virtual machines","authors":"Yogesh Gurav ,&nbsp;Mukil Alagirisamy ,&nbsp;Sathish Kumar Selvaperumal ,&nbsp;Suresh Shirbahadurkar ,&nbsp;Bankat Patil","doi":"10.1016/j.compeleceng.2025.110499","DOIUrl":"10.1016/j.compeleceng.2025.110499","url":null,"abstract":"<div><div>Over the past few years, cloud computing has grown in popularity across all corporate sectors worldwide. However, security continues to be a major roadblock in the dependability of the cloud computing platform. As a result, tenant data security isolation is crucial for protecting sensitive tenant data. This paper's main goal is to present a new decentralized information flow control system for cloud virtual machines with multiple tenants. Three main elements make up the cloud computing environment: (a) Cloud Service Provider (CSP), (b) Data Store (DS), and (c) User. The Cloud Service Provider (CSP) is embedded with the newly proposed decentralized information flow control, and it enables the flow of control of data policies for regulating the flow of data between the cloud users within the cloud. The proposed technique involves three primary stages (i) data identification (ii) trust evaluation (iii) optimal key-based cipher-text information flow security. Initially, according to the security values, tactful information is derived from the input data, which is secured in the CA of CSP to safeguard the labels and keys authentically, subsequently, the decryption process takes place. Then the EP exhibit the flow of ciphertext data based on the proposed estimation of trust. The proposed improved Signcryption algorithm is employed to cipher the user's information and the optimal key is generated by using the proposed improved Sun Flow Optimization Algorithm, which ensures that data remains confidential and tamper-proof. Ultimately, based on the proposed trust value, a decryption key will be offered to users like direct users and indirect users, in which the direct users are the old users already having access rights whereas the indirect users are the new users. The proposed model is examined over various existing techniques, in which the cost function of the proposed work for the lung cancer dataset is 14.2%, 15.7%, 13.6%, 12.1%, 11.5% and 15.2% greater than the current methods like WOA, LA, SSA, ABC-GOA, FSO and SFO respectively. Therefore, the proposed ISFO has been proven to be very concurrent with the traditional optimization approaches, and this aids in increasing the security of the data.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"127 ","pages":"Article 110499"},"PeriodicalIF":4.0,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144604268","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}

{"title":"Stabilizing DC bus voltage using CEEMDAN-XGBoost based adaptive filtering technique in EV chargers","authors":"Gaurav Yadav,&nbsp;Poonam Dhaka","doi":"10.1016/j.compeleceng.2025.110547","DOIUrl":"10.1016/j.compeleceng.2025.110547","url":null,"abstract":"<div><div>The need for clean AC current, transient-free DC bus voltage, and reactive power support (RPS) in EV chargers has increased due to the widespread use of power electronics for current loads. Addressing these challenges, this manuscript proposes an adaptive filtering technique (AFT) that synergizes Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and XGBoost, an AI-driven framework, to stabilize DC-link voltage under nonlinear and dynamic load conditions. The CEEMDAN-XGBoost approach leverages CEEMDAN’s robust signal decomposition capability to isolate transient disturbances, while XGBoost’s machine learning prowess adaptively optimizes voltage regulation and transient response. This integration achieves enhanced grid stability and power quality, reducing total harmonic distortion (THD) to 2.44% in grid-to-vehicle (G2V) and 3.83% in vehicle-to-grid (V2G) modes. Further, a fourth-order Quadrature Signal Generator (QSG) filter is embedded within EV chargers to augment harmonic attenuation, suppress DC offsets, and accelerate settling times during abrupt load transitions. The efficacy of the proposed control strategy is rigorously validated through MATLAB/Simulink simulations and experimental testing on a laboratory-scale prototype. Results demonstrate superior DC bus voltage stabilization, improved dynamic performance, and compliance with power quality standards, underscoring the viability of CEEMDAN-XGBoost as a transformative solution for next-generation EV charging systems.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"127 ","pages":"Article 110547"},"PeriodicalIF":4.0,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144604478","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}

{"title":"Secure key agreement in IoT: A systematic literature review and taxonomy analysis","authors":"Rasoul Rasta ,&nbsp;Hamid Haj Seyyed Javadi ,&nbsp;Midida Reshadi","doi":"10.1016/j.compeleceng.2025.110480","DOIUrl":"10.1016/j.compeleceng.2025.110480","url":null,"abstract":"<div><div>The increasing reliance on smart systems and their remote management has led to the widespread adoption of the Internet of Things (IoT). Despite its benefits, IoT introduces significant communication security challenges due to its heterogeneous components. Key agreement techniques, which establish symmetric encryption keys between communicating parties, are crucial for secure communications. However, the diversity and resource constraints of IoT devices present ongoing challenges. Existing studies on key agreement often focus on devices with specific conditions and specialized communication models. Their broader applicability is limited by that reason. This study addresses this gap by identifying and compiling the necessary features and conditions for key agreement algorithms in IoT environments. We survey key agreement methods to understand the different approaches in IoT using the Systematic Literature Review (SLR) method. This paper aims to categorize, analytically and statistically, the current research techniques on key agreement approaches in IoT published from 2016 to 2024. We present three technical taxonomies for the key agreement approaches in IoT based on the content of current studies. Our findings reveal that crucial parameters such as communication models, essential resources, and required tools are often overlooked in current IoT key management approaches. Notably, only 2% of the reviewed algorithms are lightweight and suitable for device-to-device communication models without prerequisites. This highlights a significant gap, as over 98% of existing algorithms either fail to meet the current requirements of IoT devices or are not easily implementable in the desired environment.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"127 ","pages":"Article 110480"},"PeriodicalIF":4.0,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597099","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}

{"title":"FuseNet: Attention-learning based MRI–PET slice fusion for Alzheimer’s diagnosis","authors":"Rahul Sharma ,&nbsp;Mujahed Al-Dhaifallah ,&nbsp;Adnan Shakoor","doi":"10.1016/j.compeleceng.2025.110556","DOIUrl":"10.1016/j.compeleceng.2025.110556","url":null,"abstract":"<div><div>In the quest for more effective diagnostic methodologies for Alzheimer’s disease (AD), the integration of multimodal imaging techniques with advanced machine learning models holds significant promise. This study introduces a novel diagnostic framework that combines Discrete Wavelet Transform (DWT)-based fusion of MRI and PET images with a deep learning architecture to enhance the accuracy of AD classification. Our model employs a 10-layer convolutional neural network (CNN) enhanced with channel-spatial attention mechanisms to extract and prioritize salient features from the fused images. For classification, an Ensemble Deep RVFL (edRVFL) is utilized, which leverages the strength of multiple RVFL networks to improve robustness and accuracy. We compare our model’s performance against traditional classifiers and other single-layer feedforward networks, demonstrating superior sensitivity, specificity, precision, and F1 scores. The results substantiate the efficacy of combining attention mechanisms with ensemble learning in a deep learning context, significantly outperforming existing state-of-the-art approaches in AD classification. The source code of the proposed model is available at <span><span>https://github.com/rsharma2612/Attentive-CNN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"127 ","pages":"Article 110556"},"PeriodicalIF":4.0,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144579888","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}

{"title":"A high-precision voltage sampling circuit for 14-series lithium-ion batteries utilizing an improved resistive level shifting technique","authors":"Zhongjie Guo,&nbsp;Yuyang Gao,&nbsp;Yina Bai,&nbsp;Jianfeng Dong","doi":"10.1016/j.compeleceng.2025.110560","DOIUrl":"10.1016/j.compeleceng.2025.110560","url":null,"abstract":"<div><div>In order to promote a low-carbon lifestyle, more and more electric bicycles are being put on the market. High-precision battery voltage sampling plays a vital role in the safe and reliable operation of electric bicycles. Based on improving the traditional resistive level shift circuit, this paper proposes a high-precision voltage sampling circuit for 14-series lithium battery packs. Voltage sampling is carried out by combining a High-Voltage Multiplexer (HV MUX) and a multiplexed resistive level shift circuit, and the current compensation circuit is designed to solve the problem of channel leakage current in the gate drive circuit when p-type and n-type Laterally Diffused Metal–Oxide–Semiconductor (LDMOS) are used as high-voltage switches. In addition, the influence of leakage current in the level shift circuit on battery voltage consistency and sampling accuracy is eliminated through the adaptive current compensation circuit, and the influence of operational amplifier mismatch on sampling accuracy is eliminated through chopper stabilization technique. Verify circuit performance based on 0.35<span><math><mi>μ</mi></math></span>m Bipolar-CMOS-DMOS (BCD) process, The results show that the maximum channel leakage current of HV MUX is 18.75nA, under the standard conditions of TT process angle and 27 °C, the maximum measurement error of the voltage sampling circuit is ±1.4 mV. Under comprehensive PVT verification, the maximum measurement error is 2.2 mV.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"127 ","pages":"Article 110560"},"PeriodicalIF":4.0,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144579887","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}

{"title":"Advanced Adaptive Control and Formal Stability Analysis of the N-Level Cascaded H-Bridge Multilevel Inverter fed Single-Stage Grid-Tied PV System Applications with an LCL Filter","authors":"Siham Chakiri ,&nbsp;Youssef Mchaouar ,&nbsp;Younes Abouelmahjoub ,&nbsp;Hassan Abouobaida ,&nbsp;Fouad Giri","doi":"10.1016/j.compeleceng.2025.110531","DOIUrl":"10.1016/j.compeleceng.2025.110531","url":null,"abstract":"<div><div>This paper deals with the control process of a single-stage grid-tied photovoltaic (PV) system, consisting of N separate PV panels, N cascaded H-bridge (CHB) inverters, and an LCL filter. The objective is to design a novel controller based on a new decoupling 5th order model to achieve threefold purposes: (i) power factor correction (PFC) by forcing the grid current tracking; (ii) providing maximum power from PV panels and controlling the sum of the squared capacitor voltages; (iii) power exchange balance by regulating the involved capacitor voltages. To fulfill the former objectives, an adaptive nonlinear controller composed of three-loops is synthesized: (i) the inner loop is designed using integral backstepping and Lyapunov approaches for the PFC objective; (ii) the outer loop is formulated using a filtered proportional-integral (PI) regulator for voltage regulation; (iii) the balance loop is designed using PI controllers for voltages balancing. Furthermore, the controller includes a sampled-data adaptive observer to provide online estimation of the grid state variables and the unknown impedance. The stability analysis of the closed loop system is formally proven involving the system averaging theory. The developed controller is evaluated in a 5-level CHB, through simulations in MATLAB/Simulink under different operating conditions. Hence, demonstrating the supremacy of the proposed approach over the PI-based controller.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110531"},"PeriodicalIF":4.0,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572523","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}

{"title":"Hybrid Mamba-MoE model for non-invasive blood glucose prediction","authors":"Ümit Şentürk ,&nbsp;Gökhan Adıgüzel ,&nbsp;Kemal Polat","doi":"10.1016/j.compeleceng.2025.110549","DOIUrl":"10.1016/j.compeleceng.2025.110549","url":null,"abstract":"<div><div>Diabetes is a growing global health concern, necessitating accurate and non-invasive blood glucose monitoring solutions. Traditional glucose measurement methods, such as finger-prick tests and continuous glucose monitoring (CGM) systems, pose challenges related to patient adherence, discomfort, and cost, highlighting the need for advanced AI-driven alternatives. This study proposes a hybrid Mamba-MoE model, integrating State Space Models (SSM) and Mixture of Experts (MoE) architectures, to enhance the accuracy, robustness, and real-time feasibility of Photoplethysmography (PPG)-based blood glucose prediction. The methodology involves PPG data acquisition, preprocessing, synthetic signal generation, and model optimization. Wavelet denoising and moving average smoothing techniques were employed to mitigate motion artifacts and noise. At the same time, segmentation, normalization, and temporal feature extraction enhanced the quality and consistency of the PPG signals. A synthetic PPG signal augmentation framework was implemented to address data scarcity and imbalance, utilizing temporal epoch shifting and regression-based glucose interpolation. The Mamba-MoE model was trained and validated using a 5-fold cross-validation approach, ensuring robust performance across diverse patient profiles. Experimental results demonstrate that Mamba-MoE significantly outperforms traditional machine learning and deep learning models, achieving Zone A accuracy of 98.16% and a low RMSE of 7.99, making it a strong candidate for real-time, wearable glucose monitoring applications. The study underscores the potential of AI-driven hybrid models in improving non-invasive diabetes management while addressing clinical reliability, scalability, and computational efficiency. Future research should focus on expanding dataset diversity, integrating multimodal physiological signals, and optimizing computational efficiency for real-world deployment. By advancing AI-powered non-invasive glucose monitoring, this study paves the way for a more accessible, accurate, and patient-friendly approach to diabetes management.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"127 ","pages":"Article 110549"},"PeriodicalIF":4.0,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144564045","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}

{"title":"A systematic review of QoS enhancement techniques in microservices architecture","authors":"Neha Kaushik ,&nbsp;Harish Kumar ,&nbsp;Vinay Raj","doi":"10.1016/j.compeleceng.2025.110550","DOIUrl":"10.1016/j.compeleceng.2025.110550","url":null,"abstract":"<div><div>Microservices architecture (MSA) has emerged as a dominant paradigm for developing scalable, flexible, and independently deployable applications. This approach improves the maintainability and scalability of applications by decomposing them into smaller and self-contained services. However, ensuring high Quality of Service (QoS) in dynamic environments remains a persistent challenge due to the distributed nature, complexity, and continuously changing user requirements. The main goal of this study is to thoroughly examine the key quality attributes that greatly affect the QoS of microservices applications, including performance, reliability, maintainability, and fault tolerance. It also provides deep insights into how machine learning (ML) can be used to improve these quality attributes. Additionally, this survey identifies major challenges and limitations in enhancing the QoS of microservices and explores potential future research directions. It emphasizes the need to focus on quality attributes like security, testability, fault prediction, and reliability. The study also suggests investigating alternative deployment environments, such as edge and fog computing, to address related challenges. These advancements will contribute to more robust, reliable, and user-friendly microservices applications, ultimately better meeting the evolving demands of users and businesses.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"127 ","pages":"Article 110550"},"PeriodicalIF":4.0,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144548898","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}