IEEJ Transactions on Electrical and Electronic Engineering最新文献

筛选
英文 中文
Comparative Multiphysics Analysis of Ultra High Speed PMSM Rotor Designs 超高速永磁同步电机转子设计的多物理场对比分析
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-04-14 DOI: 10.1002/tee.70291
Ming Cheng, Zhiye Li, Yuxiao Li, Ruilin Pei
{"title":"Comparative Multiphysics Analysis of Ultra High Speed PMSM Rotor Designs","authors":"Ming Cheng,&nbsp;Zhiye Li,&nbsp;Yuxiao Li,&nbsp;Ruilin Pei","doi":"10.1002/tee.70291","DOIUrl":"https://doi.org/10.1002/tee.70291","url":null,"abstract":"<p>Solid permanent magnets are commonly used in the rotors of ultra-high-speed permanent magnet synchronous motors (PMSMs). However, standard rotor designs are subject to assembly difficulties and high manufacturing costs that are not conducive to large-scale production. The present work addresses this issue by proposing an integrated rotor structure composed of a retaining sleeve and ring-shaped permanent magnets with a rotor core that yields an ultra-high-speed PMSM operating at 95 krpm under 25 kW of power. Firstly, electromagnetic finite element analysis is conducted for rotor design schemes with different permanent magnet, sleeve, and rotor core materials to determine the optimal outer rotor core diameter based on the maximum current of the applied converter, and the electromagnetic performances of the schemes are compared. Secondly, the rotor design schemes are subjected to mechanical finite element analysis to obtain stress distributions under different temperatures. Finally, the rotor design scheme applying NdFeB permanent magnets, a carbon fiber sleeve, and a Ti-alloy rotor core is identified as providing optimal eddy current loss, temperature, tangential stress, and vibrational characteristics that surpass those of PMSMs applying conventional rotor designs. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1943-1954"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
DRL-Based Virtual Resource Allocation for Web 3-Tier Containers Using Low-Layer Metrics 基于drl的基于底层度量的Web三层容器虚拟资源分配
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-08-11 DOI: 10.1002/tee.70395
Shoma Kitagawa, Kimihiro Mizutani
{"title":"DRL-Based Virtual Resource Allocation for Web 3-Tier Containers Using Low-Layer Metrics","authors":"Shoma Kitagawa,&nbsp;Kimihiro Mizutani","doi":"10.1002/tee.70395","DOIUrl":"https://doi.org/10.1002/tee.70395","url":null,"abstract":"<p>Container-based virtualization is widely adopted as an execution substrate for cloud-native systems. However, when multiple containers share CPU and memory on a single host, workload imbalance can easily degrade tail latency. This paper proposes a dynamic resource allocation method for a Web 3-tier container system (Nginx/Flask/MySQL) using Deep Reinforcement Learning (DRL) with observations augmented by low-layer metrics. In experiments using a real hardware deployment, the policy improved p95 response time and showed reward convergence while maintaining throughput and avoiding excessive resource cost increase. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1961-1963"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Protection for Arc High-Resistance Grounding Faults in Active Distribution Networks With Low-Resistance Grounding 低阻接地有源配电网电弧高阻接地故障保护
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-04-06 DOI: 10.1002/tee.70307
Fengxian Zhao, Chunling Liu, Lin Yuan, Yingjia Sun, Yongqin Li
{"title":"Protection for Arc High-Resistance Grounding Faults in Active Distribution Networks With Low-Resistance Grounding","authors":"Fengxian Zhao,&nbsp;Chunling Liu,&nbsp;Lin Yuan,&nbsp;Yingjia Sun,&nbsp;Yongqin Li","doi":"10.1002/tee.70307","DOIUrl":"https://doi.org/10.1002/tee.70307","url":null,"abstract":"<p>Active distribution networks with low-resistance grounding face a significant challenge under the dual-carbon strategy. When a single-phase arcing high-resistance grounding fault occurs, the resulting zero-sequence current is weak and unstable. Consequently, existing protection schemes for such faults are rendered ineffective. Considering the neutral points of both the main power grid and the distributed generation (DG) using low-resistance grounding, the work established an arcing high-resistance grounding fault model for active distribution networks. The current in the faulty feeder was approximately 180° out of phase with the current at the neutral point due to the transient characteristics of the zero-sequence current in feeders and at the grid's neutral point. The phase difference between the zero-sequence current in the healthy feeder without DG and the zero-sequence current at the neutral point of the main power grid was approximately 90°. However, the phase of the zero-sequence current in the healthy feeder with DG was approximately in phase with that at the neutral point of the main power grid. A protection method for arc high-resistance grounding faults in active distribution networks with low-resistance grounding was proposed based on the waveform similarity of zero-sequence currents. The proposed protection principle was validated via PSCAD simulations. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1839-1847"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Enhancing Grayscale and Color Image Security: A Hybrid Encryption Method Utilizing 3D Henon Map and 3D Arnold Cat Map 增强灰度和彩色图像的安全性:利用3D Henon地图和3D Arnold猫地图的混合加密方法
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-04-09 DOI: 10.1002/tee.70295
RN Ramakant Parida, Binod Kumar Singh, Chittaranjan Pradhan
{"title":"Enhancing Grayscale and Color Image Security: A Hybrid Encryption Method Utilizing 3D Henon Map and 3D Arnold Cat Map","authors":"RN Ramakant Parida,&nbsp;Binod Kumar Singh,&nbsp;Chittaranjan Pradhan","doi":"10.1002/tee.70295","DOIUrl":"https://doi.org/10.1002/tee.70295","url":null,"abstract":"<p>Nowadays, a wide range of media, including pictures, are used to communicate vast volumes of information. Novel approach must employ cryptographic methods like encryption to guarantee data security and ownership. To improve data security, novel developed chaotic map method for image encryption by combining two chaotic map algorithms, which presented in this work. The two different approaches are the 3D Henon map and the 3D Arnold's Cat map. Both the encryption and decryption processes use them in tandem. Using a 3D Henon map first, then a 3D Arnold Cat map, the final encrypted picture for transmission in this work is produced. After the encrypted picture is created, it goes through a reverse process that first uses 3D Arnold's Cat to decode it, follow by 3D Henon map to recover the resulting image. This proposed solution has a high entropy value, and provides users with extra performance requirements for security and unpredictability. For every small change in pixels, the unified average changing intensity (UACI) and number of pixels change rate (NPCR) are employed to verify the efficacy of image encryption algorithms. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1915-1921"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Simple Estimation and Application of the Differential Resistance of a Photovoltaic Module at its Maximum Power Point 光伏组件最大功率点差分电阻的简单估算与应用
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-07-22 DOI: 10.1002/tee.70382
Yasuyuki Kobayashi, Hao Jiang, Tokuma Nagano
{"title":"Simple Estimation and Application of the Differential Resistance of a Photovoltaic Module at its Maximum Power Point","authors":"Yasuyuki Kobayashi,&nbsp;Hao Jiang,&nbsp;Tokuma Nagano","doi":"10.1002/tee.70382","DOIUrl":"https://doi.org/10.1002/tee.70382","url":null,"abstract":"<p>The modulating light irradiation method can estimate the target cell voltage in a working photovoltaic module without electrical contact. This method requires the differential resistances (DRs) of the target cell and module to quantitatively estimate the voltage. Generally, the DR of a module is calculated numerically from its I–V curve; however, the DR of an operating module at its maximum power point or any local maximum point is estimated as its load resistance. This simplifies the output relation of the modulating light irradiation method and can estimate the DR of the target cell without measuring the I–V curve in advance. © 2026 The Author(s). <i>IEEJ Transactions on Electrical and Electronic Engineering</i> published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1955-1957"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/tee.70382","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
3D Dynamic Obstacle Prediction and Obstacle Avoidance Method for Underwater Intelligent Robotic Fish Based on IMM-DWA Algorithm 基于IMM-DWA算法的水下智能机器鱼三维动态障碍物预测与避障方法
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-04-28 DOI: 10.1002/tee.70292
Huang Xuhong, Lin Jinghui, Chen Yuanhai, Zhang Yixin, Zhan Weixuan
{"title":"3D Dynamic Obstacle Prediction and Obstacle Avoidance Method for Underwater Intelligent Robotic Fish Based on IMM-DWA Algorithm","authors":"Huang Xuhong,&nbsp;Lin Jinghui,&nbsp;Chen Yuanhai,&nbsp;Zhang Yixin,&nbsp;Zhan Weixuan","doi":"10.1002/tee.70292","DOIUrl":"https://doi.org/10.1002/tee.70292","url":null,"abstract":"<p>Aiming at the problems of 3D spatial navigation, dynamic obstacle interaction, and limited computing resources when the Dynamic Window Approach (DWA) algorithm is applied to obstacle avoidance for small underwater devices such as intelligent robotic fish in complex underwater environments, this paper proposes a dynamic obstacle prediction and obstacle avoidance control method based on the fusion of Interacting Multiple Model - Dynamic Window Approach (IMM-DWA). First, a <i>Z</i>-axis Proportion Integration Differential (PID) height control mechanism is introduced to extend the 2D kinematic model of the basic DWA algorithm. Second, by simplifying the IMM algorithm model, a Constant Velocity-Constant Turn Rate and Velocity (CV-CTRV) hybrid obstacle prediction model with adaptive weights is designed to improve the trajectory prediction of dynamic obstacles. Meanwhile, the velocity sampling space is optimized into spherical coordinate layered sampling to enhance sampling efficiency. Finally, the evaluation function is optimized to improve decision-making quality. Simulation experiments show that the proposed IMM-DWA algorithm significantly outperforms the basic DWA algorithm in terms of path length and running time, with smoother paths and reduced obstacle collision risk. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1935-1942"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149312368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Energy-Efficient Federated Learning via Reinforcement Learning-Based Dynamic Epoch Control 基于强化学习的动态历元控制节能联邦学习
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-05-28 DOI: 10.1002/tee.70324
So Tamaki, Kimihiro Mizutani
{"title":"Energy-Efficient Federated Learning via Reinforcement Learning-Based Dynamic Epoch Control","authors":"So Tamaki,&nbsp;Kimihiro Mizutani","doi":"10.1002/tee.70324","DOIUrl":"https://doi.org/10.1002/tee.70324","url":null,"abstract":"<p>Federated learning enables collaborative model training across distributed clients while preserving data privacy. However, conventional approaches use fixed local epochs on the client side, leading to unnecessary computation when models converge. This study proposes a reinforcement learning (RL)-based scheme that dynamically controls each client's local epoch count to reduce unnecessary training iterations while maintaining model accuracy. The RL agent learns to avoid assigning redundant epochs as the global model converges, thereby improving training efficiency. Experiments on the Wine Quality dataset with non-IID data distribution demonstrate that our scheme reduces total local epochs by approximately 60% compared to fixed-epoch baselines while achieving comparable accuracy, even in the presence of heterogeneous clients. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1964-1966"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149312468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Quantum Computing Resistant Secure Communication Over Modified Nakagami- q $$ q $$ Fading Wireless Channel 基于改进Nakagami- q $$ q $$衰落无线信道的抗量子计算安全通信
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-04-05 DOI: 10.1002/tee.70308
Md. Sohidul Islam, Yosuke Sugiura, Tetsuya Shimamura
{"title":"Quantum Computing Resistant Secure Communication Over Modified Nakagami-\u0000 \u0000 \u0000 q\u0000 \u0000 $$ q $$\u0000 Fading Wireless Channel","authors":"Md. Sohidul Islam,&nbsp;Yosuke Sugiura,&nbsp;Tetsuya Shimamura","doi":"10.1002/tee.70308","DOIUrl":"https://doi.org/10.1002/tee.70308","url":null,"abstract":"<p>Quantum computing threatens traditional encryption methods like RSA and ECC, as quantum algorithms such as Shor's algorithm can break them efficiently. Physical Layer Security (PLS) offers a resilient alternative by leveraging the inherent properties of communication channels, making it immune to quantum advancements. This paper investigates the secrecy capacity of modified Nakagami-<i>q</i> fading channels in the presence of a multi-antenna eavesdropper. The multiple antennas at the receivers are assumed to be independent and identically distributed (i.i.d.). We apply a small limit argument approximation (SLAA) to the zeroth-order modified Bessel function of the first kind within the conventional Nakagami-<i>q</i> probability density function. This modification eliminates the mathematical intractability associated with the Bessel function, enabling the derivation of novel, simple, and closed-form analytical expressions for key secrecy metrics. Specifically, we derive and analyze the probability of positive secrecy capacity, secure outage probability, and ergodic secrecy capacity. The validity of the proposed approximation is confirmed through high-fidelity Monte Carlo simulations (<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>5</mn>\u0000 <mo>×</mo>\u0000 <msup>\u0000 <mn>10</mn>\u0000 <mn>6</mn>\u0000 </msup>\u0000 </mrow>\u0000 <annotation>$$ 5times {10}^6 $$</annotation>\u0000 </semantics></math> samples), which demonstrate a negligible Root Mean Square Error (RMSE) of <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>4.64</mn>\u0000 <mo>×</mo>\u0000 <msup>\u0000 <mn>10</mn>\u0000 <mrow>\u0000 <mo>−</mo>\u0000 <mn>3</mn>\u0000 </mrow>\u0000 </msup>\u0000 </mrow>\u0000 <annotation>$$ 4.64times {10}^{-3} $$</annotation>\u0000 </semantics></math> from the conventional model. Results show that the system maintains positive secrecy capacity even when the eavesdropper has a higher SNR than the legitimate channel, particularly in low-SNR regions where eavesdropper antenna count has minimal impact. Special cases, such as Rayleigh fading with single-antenna setups, further validate these findings. This research highlights the robustness of PLS in protecting communications against quantum threats and provides a mathematically tractable framework for secrecy analysis in generalized fading environments. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1848-1858"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Mechanical Fault Identification of High Voltage Circuit Breaker Based on WOA-VMD and RF 基于WOA-VMD和RF的高压断路器机械故障识别
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-04-05 DOI: 10.1002/tee.70305
Pei Zhang, Li Ma, Fan Sun
{"title":"Mechanical Fault Identification of High Voltage Circuit Breaker Based on WOA-VMD and RF","authors":"Pei Zhang,&nbsp;Li Ma,&nbsp;Fan Sun","doi":"10.1002/tee.70305","DOIUrl":"https://doi.org/10.1002/tee.70305","url":null,"abstract":"<p>To solve the problem that it is difficult to effectively extract the mechanical fault features of high-voltage circuit breakers from vibration signals and the fault identification rate is not high, a fault diagnosis method combining whale optimization algorithm enhanced variational mode decomposition (WOA-VMD) with random forest (RF) is proposed. Initially, WOA is used to globally optimize the VMD parameters [<i>K</i>, <i>a</i>]. According to the optimization results, the mechanical vibration signals of the circuit breaker are decomposed to obtain a series of intrinsic mode functions (IMF) reflecting the mechanical state information of the circuit breaker. Then, the correlation coefficient is used to screen the modal components related to the original signal, and the sample entropy of the selected IMF is obtained as the feature vector, and the dataset is randomly divided into a training set and a test set. Finally, the training set is input into a random forest to train a classification model, and the trained model is used to classify the samples in the test set. Experimental results indicate that the vibration signal features extracted based on WOA-VMD-sample entropy are obvious, and the RF can accurately identify the mechanical fault of the circuit breaker. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1820-1827"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Adaptive Task Scheduling via Graph Convolutional Deep Q-Networks for Dynamic Dependency Modeling 基于图卷积深度q网络的动态依赖建模自适应任务调度
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-04-15 DOI: 10.1002/tee.70294
Jiamin Wang, Jiawei Yu, Wenjian Tao, Ying Wang
{"title":"Adaptive Task Scheduling via Graph Convolutional Deep Q-Networks for Dynamic Dependency Modeling","authors":"Jiamin Wang,&nbsp;Jiawei Yu,&nbsp;Wenjian Tao,&nbsp;Ying Wang","doi":"10.1002/tee.70294","DOIUrl":"https://doi.org/10.1002/tee.70294","url":null,"abstract":"<p>Task scheduling in dynamic environments poses substantial challenges due to the intricate interdependencies among tasks and the continuously evolving system states. In this paper, we introduce an ingenious Adaptive Graph-Convolutional Deep Q-Network (AGC-DQN) framework that seamlessly integrates Graph Neural Networks (GNNs) with the Deep Q-Networks (DQN) paradigm to effectively address these challenges. By representing task attributes and their dependencies as graph structures, our approach captures the complex relationships between tasks and adaptively computes feature interactions via graph convolution operations. This architecture enables the reinforcement learning agent to make more informed, context-aware scheduling decisions, enhancing its decision-making capabilities. We evaluate the AGC-DQN framework on the benchmark dataset and the dynamic scheduling scenario, demonstrating its superior performance in terms of task completion rate, system efficiency, and adaptability compared to traditional DQN-based methods. Our results underscore the potential of using graph-based representations to improve task scheduling in complex and dynamic environments. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1903-1914"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","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
小红书