Computers & Electrical Engineering最新文献

{"title":"Discrete Ricci Flow: A powerful method for community detection in location-based social networks","authors":"Elahe Karampour ,&nbsp;Mohammad Reza Malek ,&nbsp;Marzieh Eidi","doi":"10.1016/j.compeleceng.2025.110302","DOIUrl":"10.1016/j.compeleceng.2025.110302","url":null,"abstract":"<div><div>Community detection is crucial to understanding behavioral patterns in location-based social networks (LBSNs) where user locations, media, and check-ins are involved. This hierarchical structure enables the formation of user communities, where a community represents a group of users sharing similar interests. In addition, selecting an appropriate community for a recommendation scenario is crucial and challenging. To address these issues, in this article, we propose a novel method to link LBSNs to the Discrete Ricci Flow (DRF) community detection algorithm. Then we use the communities formed by the Ricci curvature of the network to provide recommendations in a user-based collaborative filtering (CF) recommender system. Our evaluation method considers spatial–temporal features and user relationships. The evaluation encompasses unsupervised and supervised learning methodologies, employing the modularity evaluation index and the CF recommender system. Comparative analysis against traditional community detection algorithms, including Leiden, Infomap, Walktrap, and Fast Greedy, reveals the superior performance of our proposed method, as it achieves an impressive 0.5075% and 0.8486% modularity scores for Gowalla and Brightkite respectively that indicates the efficacy of the method in capturing the inherent structure of the data. Furthermore, when integrated into the CF recommender system, the proposed method based on DRF demonstrates superior performance compared to other community detection methods for different data sets such as Gowalla and Brightkite. In particular, for Gowalla it improves the performance of the Point Of Interest (POI) recommendation system by an average of 10.92% and 8.02% in Recall@15 and Recall@20, respectively.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110302"},"PeriodicalIF":4.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747245","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":"Intelligent assessment of power quality disturbances: A comprehensive review on machine learning and deep learning solutions","authors":"Shaurya Jain ,&nbsp;Amol Satsangi ,&nbsp;Rajat Kumar ,&nbsp;Divyani Panwar ,&nbsp;Mohammad Amir","doi":"10.1016/j.compeleceng.2025.110275","DOIUrl":"10.1016/j.compeleceng.2025.110275","url":null,"abstract":"<div><div>As the global focus on clean energy and smart grids intensifies, detecting power quality disturbances (PQDs), caused by energy instability, has become increasingly critical for achieving sustainable development goals by ensuring stable and reliable power quality. Power quality disturbances, such as voltage sags or harmonics, are disruptions in the electrical supply that can affect everything from household appliances to industrial machinery, making their detection and management essential for a stable power system. They can cause significant damage to power grid infrastructure, leading to energy inefficiency, restricted electricity generation and consumption, equipment malfunction, and industrial process failures. The incorporation of artificial intelligence (AI) has transformed PQD classification, providing substantial advancements in monitoring and managing electrical systems. This paper presents a systematic review of the existing literature, focusing on the integration of machine learning and deep learning techniques for PQD detection. It analyzes high-quality studies on PQDs detection and classification, categorizing them based on the AI techniques employed. Additionally, it emphasizes the role of digital signal processing (DSP) techniques in extracting features, with studies segregated based on the incorporation of DSP and non-DSP approaches. A case study demonstrates the practical application and effectiveness of AI techniques in real-world contexts, with the Bagged Trees classifier achieving the highest testing accuracy of 96.6 %. The insights provided aim to support researchers and practitioners in navigating the evolving landscape of power quality assessment, ultimately improving the reliability and accuracy of PQD detection systems.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110275"},"PeriodicalIF":4.0,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143734961","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":"Modeling the future: Mathematical insights for smart grid 3.0","authors":"Muhammad Adnan ,&nbsp;Muhammad Sajid Iqbal ,&nbsp;Sadia Jabeen Siddiqi ,&nbsp;Ijaz Ahmed ,&nbsp;Anwar Shah ,&nbsp;Inam Ullah ,&nbsp;Muhammad Tariq","doi":"10.1016/j.compeleceng.2025.110283","DOIUrl":"10.1016/j.compeleceng.2025.110283","url":null,"abstract":"<div><div>The synergistic integration of Metaverse, Digital Twin (DT), and Blockchain technologies is redefining the framework of smart grids (SGs) and establishing the foundation for the revolutionary phase of Smart Grid 3.0 (SG 3.0). This advancement offers unique opportunity to create robust convergence models that include the Metaverse, Digital Twins, and Blockchain, allowing an authentic depiction of the SG 3.0 environment in the complex interaction between customers and utilities. This advanced convergence model functions as an exact platform for technical experts, attracting growing interest from both academic and industrial sectors. In this swiftly advancing domain, it is essential to tackle the task of adaptively modifying the SG 3.0 architecture in response to multiple disruptions. The choice of an appropriate convergence model for specific type of disruptions is a critical research concern. Numerous convergence models have been developed in recent literature to address these problems. However, the extensive variety and characteristics of these mathematical models complicate the assessment of their realism and compliance with the SG 3.0 framework. This research presents an innovative mathematical modeling strategy to address these challenges, facilitating the evolution of the SG framework into SG 3.0. Our methodology integrates Metaverse, Digital Twin, and Blockchain technologies, providing a distinctive viewpoint that surpasses existing frameworks in the literature. Finally, this study addresses the essential requirement for clarity on the realism and attributes of mathematical models tailored for SG 3.0, hence pioneering new avenues and advancing knowledge and innovation in the growth of Smart Grids.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110283"},"PeriodicalIF":4.0,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725009","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":"Improving privacy in peer-to-peer energy-sharing systems: A data-centric architectural approach","authors":"Farhad Rahmanifard,&nbsp;Masoud Barati","doi":"10.1016/j.compeleceng.2025.110294","DOIUrl":"10.1016/j.compeleceng.2025.110294","url":null,"abstract":"<div><div>Energy-sharing systems increasingly leverage decentralized infrastructures and peer-to-peer networks to minimize transmission and distribution losses of renewable energy sources. In these systems, prosumers’ personal data may be shared with suppliers or subcontractors without their knowledge during energy transactions. Despite employing intelligent and tamper-proof technologies to enhance traceability of energy production and consumption, mechanisms for secure and transparent personal data management remain lacking—a core concept in privacy regulations. This problem includes the safe storage and transfer of data within the network and the absence of automated methods allowing consumers to control their personal information during the data processing life-cycle. To address these challenges, this paper proposes a new privacy-preserving platform designed to secure prosumers’ data collection and processing. A key component is a monitoring tool that enhances transparency by automatically logging and immutably recording all data accesses. This tool enables both prosumers and trusted arbiters to be informed about any access to personal data and to verify or detect privacy violations. The proposed platform offers fundamental privacy rights mandated by privacy regulations such as the General Data Protection Regulation (GDPR) in an adaptable design. Its performance and overhead are evaluated through a prototype implementation tested in a simulated energy-sharing system environment.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110294"},"PeriodicalIF":4.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725008","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":"IoT-based intrusion detection system using explainable multi-class deep learning approaches","authors":"Sapna Sadhwani,&nbsp;Ameya Navare,&nbsp;Alan Mohan,&nbsp;Raja Muthalagu,&nbsp;Pranav M. Pawar","doi":"10.1016/j.compeleceng.2025.110256","DOIUrl":"10.1016/j.compeleceng.2025.110256","url":null,"abstract":"<div><div>With the surge in Internet of Things (IoT) across various domains and the rise in security threats, researchers have developed Intrusion Detection Systems (IDS) attacks in networks. These Machine Learning (ML) and Deep Learning (DL) models are powerful in detecting and classifying attacks; however, they have a black-box nature and lack interpretability. Explainable Artificial Intelligence (XAI) works towards this and improves the model's transparency and trustworthiness with research in XAI increasing significantly. However, its application within cybersecurity and IoT Intrusion Detection, particularly, requires more work to interpret various IDS models and provide explanations on how various cyber-attacks occur. This work proposes various DL-based IDS trained on four datasets: NSL-KDD, UNSW-NB15, TON-IoT and X-IIoTID and applies XAI using Shapely Additive Explanations (SHAP) to interpret these models. Utilizing four datasets captures diverse network environments to thoroughly evaluate and interpret the model. Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) and Bidirectional LSTM (Bi-LSTM) based models were trained for multi-class classification. The best model (based on performance and training time) was chosen for each dataset and SHAP was applied to it. Furthermore, a novel set of 15 features, which impacted the model's decisions the most, were extracted using explanations generated from SHAP. The models trained on these reduced features required less training time without significant impact on training time and achieving a higher performance in comparison to peer models. This work achieves model accuracies of 98.21 % in NSL-KDD, 97.80 % in TON-IoT, 92.9 % in UNSW-NB15 and 98.09 % in X-IIoTID dataset using a CNN-based model, CNN-X and using a subset of only 15 features in each dataset. This work achieves high model performances, while improving the efficiency and interpretability of IDS.</div><div>© 2017 Elsevier Inc. All rights reserved.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110256"},"PeriodicalIF":4.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725176","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":"Smart offloading for IoT application: Building a fog-cloud based context aware offloading framework and exploring potential for integration with blockchain","authors":"Karan Bajaj ,&nbsp;Shaily Jain ,&nbsp;Raman Singh ,&nbsp;Chander Prabha ,&nbsp;Md. Mehedi Hassan ,&nbsp;Anupam Kumar Bairagi ,&nbsp;Sheikh Mohammed Shariful Islam","doi":"10.1016/j.compeleceng.2025.110292","DOIUrl":"10.1016/j.compeleceng.2025.110292","url":null,"abstract":"<div><div>In the world of interconnected devices also referred to as the Internet of Things (IoT) in the modern era, it's important to ensure that computing resources are allocated efficiently to nearby devices such as edge, fog, or cloud systems to meet resource needs. However, problems such as delays in data transmission, high energy consumption, and slow response times can negatively impact the performance of time-sensitive applications in cloud-based environments.</div><div>This paper presents the Context-Aware Offloading Framework (CAOF) for resource-constrained IoT applications. CAOF leverages contextual information to identify scenarios where offloading tasks to the cloud or to the local instances are beneficial. The framework aims to make optimal offloading decisions to improve system performance and minimize energy consumption. The effectiveness of CAOF is evaluated through simulations, comparing its performance against established offloading frameworks. CAOF is implemented as a middleware solution within an Amazon Web Services (AWS) ecosystem. This middleware integrates a Greengrass intelligent gateway that dynamically determines how to handle incoming data based on contextual information. The intelligent gateway can either process the data on local Elastic Cloud Compute (EC2) instances, effectively creating a fog layer, or send it directly to the cloud for further processing.</div><div>Experimental results demonstrate that CAOF achieves an energy consumption of 0.0011 joules approximately, with an memory utilization of 3.46 MB calculated as and average over all the EC2 machines. The framework execution time, averaging 4.07 s on edge, 5.41 s on cloud, and only 0.56 s when leveraging EC2 instances specifically, including an 80.4% accuracy in multi-class classification tasks. The CAOF systematically selects the most suitable alternatives for each offloading scenario to optimize efficiency in terms of time, memory, CPU, and energy consumption. The proposed smart gateway framework utilizes a hybrid approach to make optimal offloading decisions by considering contextual data. The research concludes with the design and development of an edge or fog-based framework that uses smart computing to make decisions using machine learning reasoning. The proposed framework architecture incorporates feature selection, classification, and hybrid logistic regression-based learning for the most effective offloading solution.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110292"},"PeriodicalIF":4.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143714543","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":"Novel cascaded tilt fractional-order integral derivative with a proportional integral for harmonics mitigation in 31-level multi-level inverter","authors":"P V V Raghava Sharma ,&nbsp;Neelshetty K","doi":"10.1016/j.compeleceng.2025.110280","DOIUrl":"10.1016/j.compeleceng.2025.110280","url":null,"abstract":"<div><div>Alternate current (AC) motor drives and distributed power generation systems often use inverters, which are also known as DC-to-AC power converters. Multi-Level Inverters (MLIs) have emerged as the preferred inverter technology due to their benefits of lower switching losses and improved harmonic profile. In this article, an innovative controller topology for reducing total harmonic distortion (THD) in the 31-level MLI is proposed. A cascaded controller consisting of tilt fractional order integral derivative with proportional integral controller (C-TFOID-PI) is proposed for optimizing the switching angles of the MLI. Green anaconda optimization algorithm (GAOA) is included in this work to select the optimal gain parameters in the novel controller with minimum error. A single-phase 31-level asymmetrical cascaded MLI is utilized in this work to validate the proposed controller with the optimization method. By simulating the entire procedure with MATLAB/Simulink, the control performance of the proposed system is verified. In order to demonstrate the superior performance of the proposed C-TFOID-PI controller and optimization method, its performance is contrasted with that of other controllers. The proposed controller topology effectively lowers the THD to 0.41 %, which is 2 % better than a fuzzy logic controller. Also, the proposed inverter topology improves efficiency by 3.9 % and reduces losses by 1.02 % when compared with other controllers.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110280"},"PeriodicalIF":4.0,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706389","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":"Blockchain-Based peer-to-peer energy trading: A decentralized and innovative approach for sustainable local markets","authors":"Tao Shen ,&nbsp;Xiufang Ou ,&nbsp;Bingbin Chen","doi":"10.1016/j.compeleceng.2025.110281","DOIUrl":"10.1016/j.compeleceng.2025.110281","url":null,"abstract":"<div><div>This study presents an innovative approach to local energy generation and peer-to-peer energy trading (P2PET) through the use of blockchain technology, with a focus on decentralization and trustlessness. The primary objectives are to reduce energy costs and address privacy concerns in P2PET transactions. To facilitate this, the paper proposes three key smart contracts: one for member registration and data storage, another for managing P2PET transactions, and a third for regulating customer interactions with the main energy network. The objectives of this study go beyond technical implementation, focusing on establishing an efficient energy trading market, reducing costs, and balancing load ratios. Simulation results indicate a potential monthly cost reduction of 514 Euros per consumer. The decentralized blockchain system offers both cost-effectiveness and flexibility, enhancing network sustainability and reliability. This research examines the integration of blockchain and smart contracts in transforming energy markets, highlighting their significant impact on local energy trading and broader environmental objectives.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110281"},"PeriodicalIF":4.0,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697619","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":"Short-term optimal operation of phase shifting soft open point with high accuracy loss model in unbalanced distribution networks","authors":"Amir Mohammad Ayazi ,&nbsp;Mahmoud Reza Shakarami ,&nbsp;Meysam Doostizadeh ,&nbsp;Farhad Namdari ,&nbsp;Mohammad Reza Nikzad","doi":"10.1016/j.compeleceng.2025.110284","DOIUrl":"10.1016/j.compeleceng.2025.110284","url":null,"abstract":"<div><div>This paper examines the issues associated with unbalanced operations in distribution networks (DNs), which arise from inconsistencies in loads, resources, and configurations. This is particularly relevant in the context of peer-to-peer (P2P) trading, which may introduce security vulnerabilities and exacerbate existing imbalances. To improve the secure and efficient operation of DNs, we propose a short-term optimal operation model that integrates P2P transactions and emphasizes the physical layer of trading. The study assesses the effectiveness of a developed phase shifting-soft open point (PS-SOP) in enhancing operational flexibility and quantifies the related losses, including conduction and switching losses associated with semiconductor switches. By employing a deep neural network (DNN), these losses are converted into linear constraints suitable for incorporation into the convex optimization framework. An AC optimal power flow model is constructed to identify optimal power transfer sequences, which is framed as a mixed-integer linear programming problem to evaluate the PS-SOP's influence on voltage imbalance reduction, loss minimization, and facilitation of P2P transactions. Numerical simulations are conducted on two IEEE test networks to validate the proposed method's efficacy. For scenarios involving multi-terminal PS-SOP, all P2P transactions are successfully executed in the IEEE 13-bus network, and a 97.55 % authorization rate is achieved in the IEEE 123-bus network. The SOP loss derived from the DNN exhibits a negligible discrepancy of 2.54 % compared to nonlinear loss formulations, underscoring the model's precision and dependability.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110284"},"PeriodicalIF":4.0,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706388","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":"Age of information-aware intelligent resource management in D2D-enabled social IoT networks","authors":"Saurabh Chandra ,&nbsp;Rajeev Arya ,&nbsp;Maheshwari Prasad Singh","doi":"10.1016/j.compeleceng.2025.110295","DOIUrl":"10.1016/j.compeleceng.2025.110295","url":null,"abstract":"<div><div>Due to the increasing number of time-sensitive Internet of Things (IoT) applications, effective time management is crucial for maintaining the freshness of information in dynamic and resource-constrained environments. The age of Information (AoI) metric is adopted to quantify timeliness in urban dynamic environments. Device-to-Device (D2D) communication enhances timely information freshness updates by enabling direct communication. This paper proposes a two-stage auction-based resource and power-driven mechanism for AoI and throughput optimization in Social IoT networks. The first stage employs a time-sensitive auction-based model to ensure efficient resource allocation. The second stage utilizes a fixed-point iteration-based power control scheme to enhance the network performance. Simulation results demonstrate proposed approach achieves an 18.03 % increment in throughput, a 69.69 % reduction in AoI, and a 66.41 % reduction in power consumption compared to benchmark schemes. The proposed algorithm may be utilized as a practical solution in disaster management systems, where timeliness and resource-efficient communication are paramount.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110295"},"PeriodicalIF":4.0,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706390","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}