Digital Communications and Networks最新文献_第5页

Decentralized snapshot selection via trust game for robust DOA estimation with FMCW radar in static scenarios 基于信任博弈的FMCW雷达静态场景鲁棒DOA估计分散快照选择

IF 6.3 2区计算机科学

Digital Communications and Networks Pub Date : 2026-06-01 Epub Date: 2026-03-01 DOI: 10.1016/j.dcan.2026.02.008

Jingran Cheng, Caixia Xie, Weixiao Zhang, Huaqing Li, Yukun Huang, Denghao Li

{"title":"Decentralized snapshot selection via trust game for robust DOA estimation with FMCW radar in static scenarios","authors":"Jingran Cheng, Caixia Xie, Weixiao Zhang, Huaqing Li, Yukun Huang, Denghao Li","doi":"10.1016/j.dcan.2026.02.008","DOIUrl":"10.1016/j.dcan.2026.02.008","url":null,"abstract":"<div><div>Direction Of Arrival (DOA) estimation in Frequency Modulated Continuous Wave (FMCW) radar systems is critical for structural health monitoring, but is often compromised by phase-corrupted snapshots caused by clock jitter or Phase-Locked Loop (PLL) drift. Existing robust DOA methods suffer from high computational complexity or sensitivity to outliers, limiting their real-time applicability. In this paper, we propose the first decentralized Trust Game (TG) mechanism for snapshot selection, which leverages inter-snapshot coherence to identify and exclude anomalies with provable complexity bounds. Combined with a Toeplitz-accelerated reiterative super-resolution estimator that exploits uniform linear array structure for near-linear computational cost, our approach achieves robust and high-resolution DOA estimation. Throughout this work, the anomalous snapshots are not caused by target motion but by hardware-induced data corruption (e.g., clock jitter and PLL drift) in an otherwise static scene. Experimental results demonstrate that the proposed method outperforms state-of-the-art techniques in both outlier robustness and execution speed, offering a practical solution for real-time monitoring under hardware constraints.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"12 6","pages":"Pages 937-945"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148530225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Mosaic-AM: multimodal sensors anomaly detection with inherent compensation for absent modalities 马赛克- am：多模态传感器异常检测与固有补偿缺失模态

IF 6.3 2区计算机科学

Digital Communications and Networks Pub Date : 2026-06-01 Epub Date: 2026-03-02 DOI: 10.1016/j.dcan.2026.02.005

Wesley O’Quinn, Ziqi Wang, Shiwen Mao

{"title":"Mosaic-AM: multimodal sensors anomaly detection with inherent compensation for absent modalities","authors":"Wesley O’Quinn, Ziqi Wang, Shiwen Mao","doi":"10.1016/j.dcan.2026.02.005","DOIUrl":"10.1016/j.dcan.2026.02.005","url":null,"abstract":"<div><div>Large scale deployment of the Internet of Things (IoT) has produced a disruptive effect in many fields in the recent past. Continuous connectivity combined with relatively low physical implementation cost has produced a Big Data paradigm shift, especially in industrial contexts. Unfortunately, the ability to process and adequately make use of this data has not kept pace with deployment. Specifically, machine learning models in use today lack the ability to perform well with data from a variety of sources. For instance, many models are trained using only one type of data. Even models trained on multimodal data lack the ability to predict on different combinations of this data. Sensor deployment on identical machines is often different depending on context, leading to the need for multiple models created for the same machine. The data in question has the ability to radically shift how equipment failure is predicted and when maintenance is completed, when processed correctly. The cost savings on large industrial machines and potential saved downtime could be enormous. This research investigates a new semi-supervised, technology agnostic anomaly detection framework that can be utilized on any combination of data modalities collected from sensors deployed on an equipment in a factory setting. This framework is then tested on a real-world anomaly dataset. Through testing, we demonstrate that the model maintains state of the art performance even in the face of multiple sensor failures.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"12 6","pages":"Pages 926-936"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148530641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Spatiotemporal correlation based self-adaptive pose estimation in complex scenes 基于时空相关的复杂场景自适应姿态估计

IF 6.3 2区计算机科学

Digital Communications and Networks Pub Date : 2026-06-01 Epub Date: 2024-03-20 DOI: 10.1016/j.dcan.2024.03.007

Weina Fu, Zhe Luo, Shuai Liu, Jaime Lloret, Victor Hugo C. de Albuquerque, Abdul Khader Jilani Saudagar, Khan Muhammad

{"title":"Spatiotemporal correlation based self-adaptive pose estimation in complex scenes","authors":"Weina Fu, Zhe Luo, Shuai Liu, Jaime Lloret, Victor Hugo C. de Albuquerque, Abdul Khader Jilani Saudagar, Khan Muhammad","doi":"10.1016/j.dcan.2024.03.007","DOIUrl":"10.1016/j.dcan.2024.03.007","url":null,"abstract":"<div><div>In the current digital era, large-scale Artificial Intelligence (AI) models have fundamentally changed the landscape of the AI field. These models excel at extracting complex patterns and information from massive datasets, making them indispensable in a wide range of domains. With the advancement of large-scale AI models, pose estimation has achieved improved performance in managing large data sets and complex computations. However, most existing pose estimation methods suffer from the problem of inaccurate pose graph extraction in complex scenes. Moreover, the existing methods all focus on the message, ignoring the fact that it may not be optimal for the graph structure. This fixed graph structure is difficult to reflect the real dependency relationship between joint points. This study proposes a Character Redetection Model (CRM) to dynamically adjust the foreground extraction strategies to solve these problems. The CRM locates the target position based on the rich spatiotemporal information between the adjacent frames, effectively solving the problem of inaccurate foreground acquisition caused by occlusion and blur in complex scenes. In addition, an Uncertainty Graph Structure (UGS) is designed, which adaptively learns the topological structure of graphs with different Graph Convolutional Network (GCN) layers and skeleton samples in an end-to-end manner and mines the hidden space dependency between data to accurately model the different poses of the characters. The experimental results show that the proposed method achieves a superior performance compared to that of the State-Of-The-Art (SOTA) method, with a Percentage of Correct Keypoints (PCK) value of 94.6% at the Max Planck Institute for Informatics (MPII), along with the mean Average Precision (mAP) values of 83.3% and 82.1% on the PoseTrack2017 and classroom pose datasets, respectively.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"12 6","pages":"Pages 1003-1016"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148643498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Fully-dynamic and hardware-efficient analog architecture for terahertz wideband hybrid beamforming with multi-channel low-resolution phase shifters 具有多通道低分辨率移相器的太赫兹宽带混合波束形成的全动态和硬件高效模拟架构

IF 6.3 2区计算机科学

Digital Communications and Networks Pub Date : 2026-06-01 Epub Date: 2026-03-03 DOI: 10.1016/j.dcan.2026.02.009

Jun Shen, Hang Yuan, Xiaozheng Gao, Neng Ye, D.B. da Costa, Kai Yang

{"title":"Fully-dynamic and hardware-efficient analog architecture for terahertz wideband hybrid beamforming with multi-channel low-resolution phase shifters","authors":"Jun Shen, Hang Yuan, Xiaozheng Gao, Neng Ye, D.B. da Costa, Kai Yang","doi":"10.1016/j.dcan.2026.02.009","DOIUrl":"10.1016/j.dcan.2026.02.009","url":null,"abstract":"<div><div>We propose a fully dynamic analog architecture for Terahertz (THz) wideband Hybrid Beamforming (HBF), designed to support ultra-high data rate with low-resolution but multi-channel Phase Shifters (PSs). The proposed architecture employs multiple low-resolution PSs connected in a dynamically parallel configuration to emulate the performance of ideal infinite-resolution PSs. We first derive the minimum number of RF chains and PSs required to achieve performance comparable to fully digital beamforming. We then prove that each high-resolution PS can be effectively replaced by a small set of parallel low-resolution PSs with only marginal performance loss. To further enhance hardware efficiency, we exploit the multi-channel capability of THz PSs by combining multiple PSs with identical phase values. Moreover, an alternating minimization-based algorithm is developed to adaptively optimize the HBF matrices and switch network configurations in response to real-time channel conditions. Simulation results validate the effectiveness of the proposed architecture, demonstrating a substantial reduction in the number of PSs compared to existing schemes, while achieving superior spectral efficiency and energy efficiency. The work offers a hardware-efficient and scalable solution for future THz HBF systems.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"12 6","pages":"Pages 957-967"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148530638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Generative IoT: advancing IoT with generative AI and large language models 生成式物联网：利用生成式人工智能和大型语言模型推进物联网

IF 6.3 2区计算机科学

Digital Communications and Networks Pub Date : 2026-06-01 Epub Date: 2026-03-23 DOI: 10.1016/j.dcan.2026.03.010

Farshad Firouzi, Aritra Ray, Bahar Farahani, Mahmoud Daneshmand, Jaeseung Song, Shaoen Wu, Krishnendu Chakrabarty

{"title":"Generative IoT: advancing IoT with generative AI and large language models","authors":"Farshad Firouzi, Aritra Ray, Bahar Farahani, Mahmoud Daneshmand, Jaeseung Song, Shaoen Wu, Krishnendu Chakrabarty","doi":"10.1016/j.dcan.2026.03.010","DOIUrl":"10.1016/j.dcan.2026.03.010","url":null,"abstract":"<div><div>With the fusion of Generative AI–particularly large language models (LLMs), multi-modal language models (MLLMs) such as vision-language models (VLMs), and large action models (LAMs)–with the Artificial Intelligence of Things (AIoT), the Generative Internet of Things (GIoT) has emerged as an evolution of traditional IoT systems. The GIoT paradigm introduces advanced cognitive intelligence, automation, and sophisticated human-machine interaction, enhancing capabilities in sectors such as Industry 4.0, healthcare, and smart cities. While offering substantial potential for innovation and efficiency, GIoT remains in its early stages, facing challenges such as trust and security, efficient edge deployment, and the lack of tailored reasoning and architectural frameworks. This paper examines both the opportunities and challenges of GIoT, presenting a comparative analysis of representative architectures and assessing their implications for key performance metrics, including inference time, accuracy, scalability, and energy efficiency. Furthermore, it proposes an enhanced reasoning methodology that extends the widely adopted chain-of-thought (CoT) framework in LLMs to better address the dynamic and heterogeneous problem spaces inherent in GIoT applications. The capabilities of GIoT and the practical benefits of these contributions are illustrated through two case studies: (i) drone-based disaster management, demonstrating real-time situational awareness and decision support, and (ii) smart home systems, highlighting improved personalization, automation, and energy optimization. Collectively, these studies underscore GIoT’s transformative potential to advance operational capabilities and enrich user experiences across diverse domains.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"12 6","pages":"Pages 869-893"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148530615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Communication receiver design with pre-trained models based natural redundancy decoding 基于自然冗余解码的预训练模型通信接收机设计

IF 6.3 2区计算机科学

Digital Communications and Networks Pub Date : 2026-06-01 Epub Date: 2026-02-25 DOI: 10.1016/j.dcan.2026.02.006

Zhen-Yu Wang, Hong-Yi Yu, You-Zhen Yang

{"title":"Communication receiver design with pre-trained models based natural redundancy decoding","authors":"Zhen-Yu Wang, Hong-Yi Yu, You-Zhen Yang","doi":"10.1016/j.dcan.2026.02.006","DOIUrl":"10.1016/j.dcan.2026.02.006","url":null,"abstract":"<div><div>The current wireless communication system has higher demands for receivers’ performance. In this paper, Natural Redundancy (NR) which widely existed in the transmission sources is exploited to enhance the capability of current communication receivers in recovering information bit sequences from noisy measurements. To reveal the essential connotation of exploiting the NR in the sources to improve the performance of the communication receivers, we develop an NR coding and decoding theory by regarding the NR in the sources as a special kind of error-correcting code. Under this theory, we propose an effective “NR decoder + channel decoder” receiver structure. In addition, to sufficiently exploit the NR in the sources, we introduce the Pre-Trained Models (PTMs) into NR decoder design, which have a powerful capability to capture knowledge from massive data. Especially for uncompressed Chinese text sources, we design an efficient NR decoder based on Bidirectional Encoder Representation From Transformers (BERT) deep learning model in the Natural Language Processing (NLP) field. Comprehensive computer simulations were carried out and the results show that our proposed PTMs-based NR decoder has a significant effect on the performance improvement of the receiver and our designed receiver with the NR decoder can obtain over 2 dB performance gain compared with classical receiver on simplified Chinese edition Wiki-40B dataset.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"12 6","pages":"Pages 946-956"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148530636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Dynamic modeling and analysis of terahertz multiple-input multiple-output channels considering human presence in indoor environments 室内环境中考虑人类存在的太赫兹多输入多输出通道的动态建模与分析

IF 6.3 2区计算机科学

Digital Communications and Networks Pub Date : 2026-06-01 Epub Date: 2026-03-02 DOI: 10.1016/j.dcan.2026.02.003

Jian Song, Miao Zhang, Yebo Gu, Tao Shen

{"title":"Dynamic modeling and analysis of terahertz multiple-input multiple-output channels considering human presence in indoor environments","authors":"Jian Song, Miao Zhang, Yebo Gu, Tao Shen","doi":"10.1016/j.dcan.2026.02.003","DOIUrl":"10.1016/j.dcan.2026.02.003","url":null,"abstract":"<div><div>Terahertz (THz) technology is considered a critical enabler of ultra-high-speed wireless communication in future wireless networks. Achieving reliable THz communication performance in indoor environments requires careful analysis of channel characteristics influenced by human presence. This study presents a dynamic multiple-input multiple-output channel model for assessing human-induced occlusion in THz office scenarios. The ray-tracing method was employed to simulate key channel parameters, including path loss, capacity, and Root Mean Square (RMS) delay spread. Simulations revealed that human presence increases path loss, while capacity and RMS delay spread exhibit nonlinear variation with posture and density. Simulations were also conducted across scenarios including personnel in varying motion states, with results confirming the model’s ability to accurately capture these dynamics effects. The model was further employed to analyze data from previous literature, achieving high fitting accuracy and demonstrating robust generalizability.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"12 6","pages":"Pages 968-976"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148530637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Large language model empowered next-generation MIMO networks: fundamentals, challenges, and visions 支持下一代MIMO网络的大型语言模型：基础、挑战和愿景

IF 6.3 2区计算机科学

Digital Communications and Networks Pub Date : 2026-06-01 Epub Date: 2026-01-03 DOI: 10.1016/j.dcan.2025.12.005

Zhe Wang, Jiayi Zhang, Hongyang Du, Ruichen Zhang, Dusit Niyato, Bo Ai, Khaled B. Letaief

{"title":"Large language model empowered next-generation MIMO networks: fundamentals, challenges, and visions","authors":"Zhe Wang, Jiayi Zhang, Hongyang Du, Ruichen Zhang, Dusit Niyato, Bo Ai, Khaled B. Letaief","doi":"10.1016/j.dcan.2025.12.005","DOIUrl":"10.1016/j.dcan.2025.12.005","url":null,"abstract":"<div><div>Next-generation Multiple-Input Multiple-Output (MIMO) is expected to be intelligent and scalable. In this paper, we study Large Language Model (LLM)-enabled next-generation MIMO networks. Firstly, we provide an overview of the development, fundamentals, and challenges of the next-generation MIMO. Then, we propose the concept of the generative AI agent, which is capable of generating tailored and specialized contents with the aid of LLM and Retrieval Augmented Generation (RAG). Next, we comprehensively discuss the features and advantages of the generative AI agent framework. More importantly, to tackle existing challenges of next-generation MIMO, we discuss generative AI agent-enabled next-generation MIMO networks from the perspective of performance analysis, signal processing, and resource allocation. Furthermore, we present two compelling case studies that demonstrate the effectiveness of leveraging the generative AI agent for performance analysis in complex configuration scenarios. These examples highlight how the integration of generative AI agents can significantly enhance the analysis and design of next-generation MIMO systems. Finally, we discuss important potential research future directions.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"12 6","pages":"Pages 894-902"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148530642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Large language model-driven probabilistic trajectory prediction in the Internet of things using spatio-temporal encoding and normalizing flows 物联网中使用时空编码和规范化流的大型语言模型驱动的概率轨迹预测

IF 6.3 2区计算机科学

Digital Communications and Networks Pub Date : 2026-06-01 Epub Date: 2025-03-10 DOI: 10.1016/j.dcan.2025.03.004

Xiaoliang Wang, Liming Xu, Lian Zhou, Yuzhen Liu, Neal N. Xiong, Kuan-Ching Li

{"title":"Large language model-driven probabilistic trajectory prediction in the Internet of things using spatio-temporal encoding and normalizing flows","authors":"Xiaoliang Wang, Liming Xu, Lian Zhou, Yuzhen Liu, Neal N. Xiong, Kuan-Ching Li","doi":"10.1016/j.dcan.2025.03.004","DOIUrl":"10.1016/j.dcan.2025.03.004","url":null,"abstract":"<div><div>The convergence of the Internet of Things (IoT) and foundation models, particularly Large Language Models (LLMs), heralds a new era of intelligent and adaptive systems. This investigation explores the integration of LLMs and IoT for probabilistic vehicle trajectory prediction, a critical component in autonomous driving. Traditional deterministic models often fail to capture the complexity and uncertainty of real-world driving environments. To address these limitations, we propose an innovative approach that leverages LLM-driven spatio-temporal encoding and normalizing flows. The proposed method extracts latent motion patterns from historical trajectory data using LLMs, providing a nuanced understanding of vehicle dynamics. Advanced spatio-temporal encoders are employed for comprehensive feature extraction, capturing temporal dependencies and spatial relationships. Additionally, scaled dot-product attention is utilized for effective multimodal feature fusion, enhancing the integration of diverse data sources. The normalizing flows framework enhances the model's ability to capture complex, multimodal probability distributions of future trajectories by constructing an invertible transformation network. The network systematically maps simple base distributions to intricate target distributions through reversible transformations, significantly improving prediction accuracy. Evaluation of the nuScenes dataset demonstrates substantial improvements over existing methods. The results underscore the model's capability to generate diverse and realistic trajectory distributions, paving the way for safer and more efficient autonomous driving systems.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"12 6","pages":"Pages 903-915"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148530639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Adaptive task offloading and resource orchestration under spatiotemporal constraints in mobile edge computing 移动边缘计算时空约束下的自适应任务卸载与资源编排

IF 6.3 2区计算机科学

Digital Communications and Networks Pub Date : 2026-06-01 Epub Date: 2026-03-13 DOI: 10.1016/j.dcan.2026.03.002

Jishen Liang, Shichao Xia, Wantong Xin, Zhixiu Yao, Hongjiu Shan

{"title":"Adaptive task offloading and resource orchestration under spatiotemporal constraints in mobile edge computing","authors":"Jishen Liang, Shichao Xia, Wantong Xin, Zhixiu Yao, Hongjiu Shan","doi":"10.1016/j.dcan.2026.03.002","DOIUrl":"10.1016/j.dcan.2026.03.002","url":null,"abstract":"<div><div>With the rapid proliferation of mobile devices and network applications, user service demands exhibit significant spatiotemporal variability and differentiation, posing considerable challenges to efficient resource allocation in Mobile Edge Computing (MEC). To address the differentiated characteristics of user demands across spatial and temporal dimensions, this paper develops an integrated model explicitly embedding spatiotemporal features into task computation offloading and service caching. Considering user-specific constraints such as delay tolerance, we construct a joint multi-dimensional resource optimization model integrating latency constraints with resource allocation conditions. To effectively manage inherent spatiotemporal variability and deep uncertainty in MEC environments while minimizing task processing delays, we propose a spatiotemporal graph-attention-enhanced Multi-Agent Deep Reinforcement Learning (MADRL) approach for joint task offloading and service caching optimization. Specifically, the proposed method employs Graph Attention networks (GAT) to effectively capture node dependencies and spatial correlations in task offloading decisions, and utilizes Long Short-Term Memory (LSTM) modules to accurately model temporal dynamics of service demands, enabling autonomous learning and adaptive decision-making for task offloading, resource allocation, and service caching strategies. Extensive simulations demonstrate that the proposed method achieves superior convergence performance, significantly reduces latency, and improves efficiency compared to existing methods.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"12 6","pages":"Pages 994-1002"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148643496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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