Ad Hoc Networks最新文献

英文中文

Predicting diverse QoS metrics in IoT: An adaptive deep learning cross-layer approach for performance balancing

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2025-01-24 DOI: 10.1016/j.adhoc.2025.103769

Yassin Eljakani , Abdellah Boulouz , Craig Thomson

Wireless sensor networks (WSNs) present dynamic challenges in various environments, often requiring careful balance between conflicting Quality of Service (QoS) metrics to optimize stack parameters and enhance network performance. This paper introduces a novel approach that incorporates proposed trade-off parameters at the application layer to model the interplay between multiple QoS metrics, including Packet Delivery Ratio (PDR), signal-to-noise ratio (SNR), Maximum Goodput (MGP), and Energy Consumption (EC). Our approach utilizes a multi-layer perceptron (MLP) model optimized using a custom Bayesian algorithm. The model employs a dynamic loss function called Weighted Error Squared (WES). It adapts dynamically to QoS statistical distributions through a scaling hyperparameter, enabling it to uncover intricate patterns specific to IEEE 802.15.4 networks. Empirical results from testing our model against a public dataset are compelling; we significantly improved prediction accuracy compared to baseline models, with R-squared values of 97%, 99%, 98%, and 93% for SNR, PDR, MGP, and EC, respectively. These results demonstrate the effectiveness of our model in predicting network behavior. Additionally, this paper presents a conceptual operational design for implementing the model in diverse real-world scenarios, suggesting avenues for future practical applications. To the best of our knowledge, this is the first design of such an integrated approach in WSNs, making our model an adaptable solution for network designers aiming to achieve optimal configurations.

{"title":"Predicting diverse QoS metrics in IoT: An adaptive deep learning cross-layer approach for performance balancing","authors":"Yassin Eljakani , Abdellah Boulouz , Craig Thomson","doi":"10.1016/j.adhoc.2025.103769","DOIUrl":"10.1016/j.adhoc.2025.103769","url":null,"abstract":"<div><div>Wireless sensor networks (WSNs) present dynamic challenges in various environments, often requiring careful balance between conflicting Quality of Service (QoS) metrics to optimize stack parameters and enhance network performance. This paper introduces a novel approach that incorporates proposed trade-off parameters at the application layer to model the interplay between multiple QoS metrics, including Packet Delivery Ratio (PDR), signal-to-noise ratio (SNR), Maximum Goodput (MGP), and Energy Consumption (EC). Our approach utilizes a multi-layer perceptron (MLP) model optimized using a custom Bayesian algorithm. The model employs a dynamic loss function called Weighted Error Squared (WES). It adapts dynamically to QoS statistical distributions through a scaling hyperparameter, enabling it to uncover intricate patterns specific to IEEE 802.15.4 networks. Empirical results from testing our model against a public dataset are compelling; we significantly improved prediction accuracy compared to baseline models, with R-squared values of 97%, 99%, 98%, and 93% for SNR, PDR, MGP, and EC, respectively. These results demonstrate the effectiveness of our model in predicting network behavior. Additionally, this paper presents a conceptual operational design for implementing the model in diverse real-world scenarios, suggesting avenues for future practical applications. To the best of our knowledge, this is the first design of such an integrated approach in WSNs, making our model an adaptable solution for network designers aiming to achieve optimal configurations.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"170 ","pages":"Article 103769"},"PeriodicalIF":4.4,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Regularized constrained total least squares localization for underwater acoustic sensor networks using angle-delay-doppler measurements

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2025-01-20 DOI: 10.1016/j.adhoc.2025.103768

Feng Qiu, Dongsheng Guo

This paper addresses the challenge of underwater acoustic localization using measurements of angle, time delay and Doppler shift. Poor sensor placement can cause numerical instability in the coefficient matrix, which diminishes localization accuracy. To tackle this, we propose a two-stage localization approach based on the regularized constrained total least squares (RCTLS) method. First, we linearize the time delay and Doppler shift equations using azimuth and elevation angles, and apply a weighted least squares (WLS) method for an initial position estimation. Second, to mitigate the impact of ill-conditioned equations and measurement errors, we employ the RCTLS method for a more robust estimation, thus reducing localization error. Due to the unique characteristics of the underwater communications, the presence of errors in the sound speed and sensor position and velocity, as well as the sensor motion effect during the observation period are considered. We also derive the hybrid Cramer Rao lower bound (CRLB) as a benchmark to evaluate estimation performance. Simulations demonstrate that our method significantly improves localization accuracy compared to conventional approaches.

{"title":"Regularized constrained total least squares localization for underwater acoustic sensor networks using angle-delay-doppler measurements","authors":"Feng Qiu, Dongsheng Guo","doi":"10.1016/j.adhoc.2025.103768","DOIUrl":"10.1016/j.adhoc.2025.103768","url":null,"abstract":"<div><div>This paper addresses the challenge of underwater acoustic localization using measurements of angle, time delay and Doppler shift. Poor sensor placement can cause numerical instability in the coefficient matrix, which diminishes localization accuracy. To tackle this, we propose a two-stage localization approach based on the regularized constrained total least squares (RCTLS) method. First, we linearize the time delay and Doppler shift equations using azimuth and elevation angles, and apply a weighted least squares (WLS) method for an initial position estimation. Second, to mitigate the impact of ill-conditioned equations and measurement errors, we employ the RCTLS method for a more robust estimation, thus reducing localization error. Due to the unique characteristics of the underwater communications, the presence of errors in the sound speed and sensor position and velocity, as well as the sensor motion effect during the observation period are considered. We also derive the hybrid Cramer Rao lower bound (CRLB) as a benchmark to evaluate estimation performance. Simulations demonstrate that our method significantly improves localization accuracy compared to conventional approaches.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"170 ","pages":"Article 103768"},"PeriodicalIF":4.4,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Detection and Mitigation of Clock Deviation in the Verification & Validation of Drone-aided Lifting Operations

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2025-01-18 DOI: 10.1016/j.adhoc.2024.103745

Abdelhakim Baouya , Brahim Hamid , Otmane Ait Mohamed , Saddek Bensalem

Modern Cyber–Physical systems rely on diverse computation logic, communication protocols, and technologies and are susceptible to environmental phenomena and production errors that can significantly impact system behavior. The resilience of these systems necessitates considering factors during the high-level design stages to enable accurate functional forecasting and correctness. This paper presents an approach that models clock deviation’s effects within physical and environmental conditions to perform verification & validation in the context of Unmanned Aerial Vehicle domain (UAV). We employ the OMNeT++ simulation framework to define the system’s behavior in a components–port–connectors fashion. The approach leverages Probabilistic Decision Tree rules derived from the OMNeT++ simulation chart. The resulting rule-based model is then interpreted in the PRISM language for automated model verification. To validate our approach, we investigate how clock deviations influence the correctness of drone-aided lifting operations which is our primary focus, serving as a representative application scenario. The research examines clock deviations from multiple sources, including conformance to standard specifications, product manufacturing variations, operational failures, humidity, and operating temperature changes. Our examination explores the potential of validation through simulation and model checking while also studying the approach’s effectiveness through a sensitive analysis. Furthermore, the approach is demonstrated in the context of robot orchestration and water dam infrastructure for generalization purposes in Cyber–Physical Systems modeling. The research highlights the approach’s effectiveness by demonstrating its applicability, including those that incorporate degradation factors.

{"title":"Detection and Mitigation of Clock Deviation in the Verification & Validation of Drone-aided Lifting Operations","authors":"Abdelhakim Baouya , Brahim Hamid , Otmane Ait Mohamed , Saddek Bensalem","doi":"10.1016/j.adhoc.2024.103745","DOIUrl":"10.1016/j.adhoc.2024.103745","url":null,"abstract":"<div><div>Modern Cyber–Physical systems rely on diverse computation logic, communication protocols, and technologies and are susceptible to environmental phenomena and production errors that can significantly impact system behavior. The resilience of these systems necessitates considering factors during the high-level design stages to enable accurate functional forecasting and correctness. This paper presents an approach that models clock deviation’s effects within physical and environmental conditions to perform verification & validation in the context of Unmanned Aerial Vehicle domain (UAV). We employ the OMNeT++ simulation framework to define the system’s behavior in a components–port–connectors fashion. The approach leverages Probabilistic Decision Tree rules derived from the OMNeT++ simulation chart. The resulting rule-based model is then interpreted in the PRISM language for automated model verification. To validate our approach, we investigate how clock deviations influence the correctness of drone-aided lifting operations which is our primary focus, serving as a representative application scenario. The research examines clock deviations from multiple sources, including conformance to standard specifications, product manufacturing variations, operational failures, humidity, and operating temperature changes. Our examination explores the potential of validation through simulation and model checking while also studying the approach’s effectiveness through a sensitive analysis. Furthermore, the approach is demonstrated in the context of robot orchestration and water dam infrastructure for generalization purposes in Cyber–Physical Systems modeling. The research highlights the approach’s effectiveness by demonstrating its applicability, including those that incorporate degradation factors.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"170 ","pages":"Article 103745"},"PeriodicalIF":4.4,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Computational Offloading and Resource Allocation for IoT applications using Decision Tree based Reinforcement Learning

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2025-01-18 DOI: 10.1016/j.adhoc.2024.103751

Guneet Kaur Walia, Mohit Kumar

The pervasive penetration of IoT devices in various domains such as autonomous vehicles, supply chain management, video surveillance, healthcare, industrial automation etc. necessitates for advanced computing paradigms to achieve real time response delivery. Edge computing offers prompt service response via its competent decentralized platform for catering disseminate workload, hence serving as front-runner for competently handling a wide spectrum of IoT applications. However, optimal distribution of workload in the form of incoming tasks to appropriate destinations remains a challenging issue due to multiple factors such as dynamic offloading decision, optimal resource allocation, heterogeneity of devices, unbalanced workload etc in collaborative Cloud-Edge layered architecture. Employing advanced Artificial Intelligence (AI)-based techniques, provides promising solutions to address the complex task assignment problem. However, existing solutions encounter significant challenges, including prolonged convergence time, extended learning periods for agents and inability to adapt to a stochastic environment. Hence, our work aims to design a unified framework for performing computational offloading and resource allocation in diverse IoT applications using Decision Tree Empowered Reinforcement Learning (DTRL) technique. The proposed work formulates the optimization problem for offloading decisions at runtime and allocates the optimal resources for incoming tasks to improve the Quality-of-Service parameters (QoS). The computational results conducted over a simulation environment proved that the proposed approach has the high convergence ability, exploration and exploitation capability and outperforms the existing state-of-the-art approaches in terms of delay, energy consumption, waiting time, task acceptance ratio and service cost.

{"title":"Computational Offloading and Resource Allocation for IoT applications using Decision Tree based Reinforcement Learning","authors":"Guneet Kaur Walia, Mohit Kumar","doi":"10.1016/j.adhoc.2024.103751","DOIUrl":"10.1016/j.adhoc.2024.103751","url":null,"abstract":"<div><div>The pervasive penetration of IoT devices in various domains such as autonomous vehicles, supply chain management, video surveillance, healthcare, industrial automation etc. necessitates for advanced computing paradigms to achieve real time response delivery. Edge computing offers prompt service response via its competent decentralized platform for catering disseminate workload, hence serving as front-runner for competently handling a wide spectrum of IoT applications. However, optimal distribution of workload in the form of incoming tasks to appropriate destinations remains a challenging issue due to multiple factors such as dynamic offloading decision, optimal resource allocation, heterogeneity of devices, unbalanced workload etc in collaborative Cloud-Edge layered architecture. Employing advanced Artificial Intelligence (AI)-based techniques, provides promising solutions to address the complex task assignment problem. However, existing solutions encounter significant challenges, including prolonged convergence time, extended learning periods for agents and inability to adapt to a stochastic environment. Hence, our work aims to design a unified framework for performing computational offloading and resource allocation in diverse IoT applications using Decision Tree Empowered Reinforcement Learning (DTRL) technique. The proposed work formulates the optimization problem for offloading decisions at runtime and allocates the optimal resources for incoming tasks to improve the Quality-of-Service parameters (QoS). The computational results conducted over a simulation environment proved that the proposed approach has the high convergence ability, exploration and exploitation capability and outperforms the existing state-of-the-art approaches in terms of delay, energy consumption, waiting time, task acceptance ratio and service cost.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"170 ","pages":"Article 103751"},"PeriodicalIF":4.4,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Anchor nodes selection and placement strategy for node positioning in wireless sensor networks

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2025-01-18 DOI: 10.1016/j.adhoc.2025.103766

Xiaobo Gu , Jiale Liu , Yuan Liu , Yuan Chi

The positions of anchor nodes in wireless sensor networks (WSNs) significantly impacts positioning accuracy. This paper derives the Cramér–Rao lower bound (CRLB) under rigid roto-translation transformations and demonstrates that a larger equilateral triangle formed by anchor nodes minimizes positioning errors. Based on this theoretical insight, a graph theory and geometry-based anchor node selection (ANS) method is proposed. The method is further extended to solve the anchor node placement (ANP) problem, and the particle swarm optimization (PSO) is employed to determine optimal placement positions. Simulation results confirm that the proposed ANS and ANP methods outperform existing approaches in positioning accuracy.

引用次数: 0

A hybrid and efficient Federated Learning for privacy preservation in IoT devices

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2025-01-15 DOI: 10.1016/j.adhoc.2025.103761

Shaohua Cao, Shangru Liu, Yansheng Yang, Wenjie Du, Zijun Zhan, Danxin Wang, Weishan Zhang

Federated learning (FL) allows multiple participants to collaborate to train a machine learning model while ensuring that the data remain local. This approach has seen extensive application in the Internet of Things (IoT). Compared to traditional centralized training methods, FL indeed protects the raw data, but it is difficult to defend against inference attacks and other data reconstruction methods. To address this issue, existing research has introduced a variety of cryptographic techniques, mainly encompassing secure multi-party Computation (SMC), homomorphic encryption (HE), and differential privacy (DP). However, approaches reliant on HE and SMC do not provide sufficient protection for the model data itself and often lead to significant communication and computation overhead; exclusively employing DP necessitates the incorporation of substantial noise, which harms model performance. In this paper, we propose an efficient and privacy-preserving dual-key black-box aggregation method that uses Paillier threshold homomorphic encryption (TPHE), which ensures the protection of the model parameters during the transmission and aggregation phases via a two-step decryption process. To defend various data reconstruction attacks, we also achieve a node-level DP to effectively eliminate the possibility of recovering raw data from the aggregated parameters. Through experiments on MNIST, CIFAR-10, and SVHN, we have shown that our method has up to a 11% smaller reduction in model accuracy compared to other schemes. Furthermore, compared to SMC-based FL schemes, our scheme significantly reduces communication overhead from 60% to 80%, depending on the number of participating nodes. We also conduct comparative experiments on the defense against GAN attacks and membership inference attacks, proving that our method provides effective protection for data privacy.

{"title":"A hybrid and efficient Federated Learning for privacy preservation in IoT devices","authors":"Shaohua Cao, Shangru Liu, Yansheng Yang, Wenjie Du, Zijun Zhan, Danxin Wang, Weishan Zhang","doi":"10.1016/j.adhoc.2025.103761","DOIUrl":"10.1016/j.adhoc.2025.103761","url":null,"abstract":"<div><div>Federated learning (FL) allows multiple participants to collaborate to train a machine learning model while ensuring that the data remain local. This approach has seen extensive application in the Internet of Things (IoT). Compared to traditional centralized training methods, FL indeed protects the raw data, but it is difficult to defend against inference attacks and other data reconstruction methods. To address this issue, existing research has introduced a variety of cryptographic techniques, mainly encompassing secure multi-party Computation (SMC), homomorphic encryption (HE), and differential privacy (DP). However, approaches reliant on HE and SMC do not provide sufficient protection for the model data itself and often lead to significant communication and computation overhead; exclusively employing DP necessitates the incorporation of substantial noise, which harms model performance. In this paper, we propose an efficient and privacy-preserving dual-key black-box aggregation method that uses Paillier threshold homomorphic encryption (TPHE), which ensures the protection of the model parameters during the transmission and aggregation phases via a two-step decryption process. To defend various data reconstruction attacks, we also achieve a node-level DP to effectively eliminate the possibility of recovering raw data from the aggregated parameters. Through experiments on MNIST, CIFAR-10, and SVHN, we have shown that our method has up to a 11% smaller reduction in model accuracy compared to other schemes. Furthermore, compared to SMC-based FL schemes, our scheme significantly reduces communication overhead from 60% to 80%, depending on the number of participating nodes. We also conduct comparative experiments on the defense against GAN attacks and membership inference attacks, proving that our method provides effective protection for data privacy.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"170 ","pages":"Article 103761"},"PeriodicalIF":4.4,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

BFL-SC: A blockchain-enabled federated learning framework, with smart contracts, for securing social media-integrated internet of things systems

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2025-01-14 DOI: 10.1016/j.adhoc.2025.103760

Sara Salim, Nour Moustafa, Benjamin Turnbull

The integration of Social Media (SM) and the Internet of Things (IoT) is gradually transforming the activities of SM users into valuable data streams that can be analyzed using Machine Learning (ML) algorithms. Federated Learning (FL) has been widely employed to predict user and anomaly behaviors from distributed systems. However, FL encounters substantial security challenges, particularly within the context of SM-integrated IoT systems, known as SM 3.0 systems. These challenges encompass issues of accountability and vulnerabilities that render them susceptible to various cyberattacks, including single-point-of-failure, free-riding, model inversion, and poisoning attacks. We propose a Blockchain-enabled FL with Smart Contracts (SC) (BFL-SC) framework. To coordinate the learning process, track participants’ contributions and reward the participants transparently, an SC-based FL is constructed as an incentive mechanism that combats free-riding attacks and enables automated and auditable rewarding of the participants. Also, to conceal the original data points and mitigate the impact of model inversion attacks, a Differentially Privacy-based Perturbation (DPP) mechanism is proposed. To address potential poisoning attacks, a thorough verification protocol is suggested. The experimental results obtained from two datasets, namely SM 3.0 and Human Activity Recognition (HAR), show that the BFL-SC framework can achieve high utility with a precision of 96.95% over the SM 3.0 dataset and 90.14% over the HAR dataset while adhering to privacy and efficiency standards, compared with compelling techniques.

{"title":"BFL-SC: A blockchain-enabled federated learning framework, with smart contracts, for securing social media-integrated internet of things systems","authors":"Sara Salim, Nour Moustafa, Benjamin Turnbull","doi":"10.1016/j.adhoc.2025.103760","DOIUrl":"10.1016/j.adhoc.2025.103760","url":null,"abstract":"<div><div>The integration of Social Media (SM) and the Internet of Things (IoT) is gradually transforming the activities of SM users into valuable data streams that can be analyzed using Machine Learning (ML) algorithms. Federated Learning (FL) has been widely employed to predict user and anomaly behaviors from distributed systems. However, FL encounters substantial security challenges, particularly within the context of SM-integrated IoT systems, known as SM 3.0 systems. These challenges encompass issues of accountability and vulnerabilities that render them susceptible to various cyberattacks, including single-point-of-failure, free-riding, model inversion, and poisoning attacks. We propose a Blockchain-enabled FL with Smart Contracts (SC) (BFL-SC) framework. To coordinate the learning process, track participants’ contributions and reward the participants transparently, an SC-based FL is constructed as an incentive mechanism that combats free-riding attacks and enables automated and auditable rewarding of the participants. Also, to conceal the original data points and mitigate the impact of model inversion attacks, a Differentially Privacy-based Perturbation (DPP) mechanism is proposed. To address potential poisoning attacks, a thorough verification protocol is suggested. The experimental results obtained from two datasets, namely SM 3.0 and Human Activity Recognition (HAR), show that the BFL-SC framework can achieve high utility with a precision of 96.95% over the SM 3.0 dataset and 90.14% over the HAR dataset while adhering to privacy and efficiency standards, compared with compelling techniques.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"169 ","pages":"Article 103760"},"PeriodicalIF":4.4,"publicationDate":"2025-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Multi-user motion state task offloading strategy for load balancing in mobile edge computing networks

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2025-01-11 DOI: 10.1016/j.adhoc.2025.103759

Shanchen Pang, Yuanzhao Cheng, Xiao He, Yanxiang Zhang

In mobile edge computing (MEC) networks, users can offload computational tasks from their devices to nearby mobile edge servers, reducing their computational loads and improving user experience quality. However, users exhibit various movement patterns with inherent random mobility in practice. Additionally, data that needs processing arrives randomly over continuous periods. To stabilize data and energy consumption in complex real-world environments and maximize the network system’s data processing capacity, we propose a User Trajectory Prediction-Lyapunov-guided Deep Reinforcement Learning (UTP-LyDRL) algorithm. This algorithm first predicts the movement trajectories of mobile users (MUs) using a Mobility-aware Offloading (MO) mechanism. It then formulates the problem of both MUs and fixed users (FUs) as a Mixed Integer Nonlinear Programming (MINLP) problem. Through Lyapunov optimization, the multi-stage MINLP problem is decomposed into deterministic MINLP sub-problems for each time frame, ensuring long-term constraint satisfaction. Subsequently, combining model-free training with DRL, the algorithm addresses the binary offloading of FUs across sequential time frames and overall system resource allocation. Simulation results indicate that the proposed UTP-LyDRL algorithm optimizes computational performance and ensures the stability of all data and energy queues within the system.

{"title":"Multi-user motion state task offloading strategy for load balancing in mobile edge computing networks","authors":"Shanchen Pang, Yuanzhao Cheng, Xiao He, Yanxiang Zhang","doi":"10.1016/j.adhoc.2025.103759","DOIUrl":"10.1016/j.adhoc.2025.103759","url":null,"abstract":"<div><div>In mobile edge computing (MEC) networks, users can offload computational tasks from their devices to nearby mobile edge servers, reducing their computational loads and improving user experience quality. However, users exhibit various movement patterns with inherent random mobility in practice. Additionally, data that needs processing arrives randomly over continuous periods. To stabilize data and energy consumption in complex real-world environments and maximize the network system’s data processing capacity, we propose a User Trajectory Prediction-Lyapunov-guided Deep Reinforcement Learning (UTP-LyDRL) algorithm. This algorithm first predicts the movement trajectories of mobile users (MUs) using a Mobility-aware Offloading (MO) mechanism. It then formulates the problem of both MUs and fixed users (FUs) as a Mixed Integer Nonlinear Programming (MINLP) problem. Through Lyapunov optimization, the multi-stage MINLP problem is decomposed into deterministic MINLP sub-problems for each time frame, ensuring long-term constraint satisfaction. Subsequently, combining model-free training with DRL, the algorithm addresses the binary offloading of FUs across sequential time frames and overall system resource allocation. Simulation results indicate that the proposed UTP-LyDRL algorithm optimizes computational performance and ensures the stability of all data and energy queues within the system.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"169 ","pages":"Article 103759"},"PeriodicalIF":4.4,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Energy-efficient clustering and path planning for UAV-assisted D2D cellular networks

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2025-01-11 DOI: 10.1016/j.adhoc.2025.103757

Kanhu Charan Gouda, Rahul Thakur

The integration of Device-to-Device (D2D) communication and Unmanned Aerial Vehicles (UAVs) into advanced cellular networks is essential for effectively addressing the growing data demands. However, long-range communication in cellular and D2D networks typically requires higher transmission power, leading to increased energy consumption and reduced energy efficiency. To address this, we propose an innovative technique that combines hypergraph-based clustering with UAV path planning to minimize energy consumption in UAV-assisted D2D cellular networks. Our technique utilizes hypergraph theory to group UEs into clusters based on proximity and communication needs. The Particle Swarm Optimization (PSO) algorithm is employed to select a central User Equipment (UE) in each cluster, considering factors such as distance, residual energy, and degree centrality. Once the central UEs are chosen, the UAV’s path is optimized using the Ant Colony System (ACS) algorithm, addressing the Generalized Traveling Salesman Problem (GTSP) to minimize travel distance and energy consumption. We also analyze the computational complexity of the proposed technique, demonstrating its efficiency over existing techniques. Simulation results show significant improvements in system throughput, energy consumption, energy efficiency, and UAV path length.

{"title":"Energy-efficient clustering and path planning for UAV-assisted D2D cellular networks","authors":"Kanhu Charan Gouda, Rahul Thakur","doi":"10.1016/j.adhoc.2025.103757","DOIUrl":"10.1016/j.adhoc.2025.103757","url":null,"abstract":"<div><div>The integration of Device-to-Device (D2D) communication and Unmanned Aerial Vehicles (UAVs) into advanced cellular networks is essential for effectively addressing the growing data demands. However, long-range communication in cellular and D2D networks typically requires higher transmission power, leading to increased energy consumption and reduced energy efficiency. To address this, we propose an innovative technique that combines hypergraph-based clustering with UAV path planning to minimize energy consumption in UAV-assisted D2D cellular networks. Our technique utilizes hypergraph theory to group UEs into clusters based on proximity and communication needs. The Particle Swarm Optimization (PSO) algorithm is employed to select a central User Equipment (UE) in each cluster, considering factors such as distance, residual energy, and degree centrality. Once the central UEs are chosen, the UAV’s path is optimized using the Ant Colony System (ACS) algorithm, addressing the Generalized Traveling Salesman Problem (GTSP) to minimize travel distance and energy consumption. We also analyze the computational complexity of the proposed technique, demonstrating its efficiency over existing techniques. Simulation results show significant improvements in system throughput, energy consumption, energy efficiency, and UAV path length.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"170 ","pages":"Article 103757"},"PeriodicalIF":4.4,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-sensor system deployment planning method for underwater surveillance based on formation characteristics

IF 4.4 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks

Pub Date : 2025-01-11 DOI: 10.1016/j.adhoc.2025.103763

Zheping Yan , Sijia Cai , Shuping Hou , Mingyao Zhang

The deployment planning issue for a multi-sensor system comprising a limited number of sensors designed to detect underwater intrusion targets is defined as a multi-objective NP-hard problem. This problem is constituted by two competing and incommensurable optimization objectives: "larger sensor coverage" and "higher probability of detecting intrusion targets". The map of the mission area is transformed into a topological map through the application of polygon fitting and segmentation based on Delaunay triangulation. This study employs a characteristics-based non-dominated sorting genetic algorithm (CBNSGA) to address the deployment planning issue of the multi-sensor system. In this algorithm, Mean-Shift clustering is employed to yield characteristics information through the clustering of the multi-sensor system formation. Subsequently, this information is employed to enhance the crossover, mutation, and selection strategies. Adaptive parameters are designed to accelerate convergence and avoid local optima. Additionally, the Cauchy inverse cumulative distribution operator is employed to enhance the mutation step. The feasibility and effectiveness of the CBNSGA in multi-sensor system deployment planning are demonstrated through simulation and comparison with other algorithms.

{"title":"Multi-sensor system deployment planning method for underwater surveillance based on formation characteristics","authors":"Zheping Yan , Sijia Cai , Shuping Hou , Mingyao Zhang","doi":"10.1016/j.adhoc.2025.103763","DOIUrl":"10.1016/j.adhoc.2025.103763","url":null,"abstract":"<div><div>The deployment planning issue for a multi-sensor system comprising a limited number of sensors designed to detect underwater intrusion targets is defined as a multi-objective NP-hard problem. This problem is constituted by two competing and incommensurable optimization objectives: \"larger sensor coverage\" and \"higher probability of detecting intrusion targets\". The map of the mission area is transformed into a topological map through the application of polygon fitting and segmentation based on Delaunay triangulation. This study employs a characteristics-based non-dominated sorting genetic algorithm (CBNSGA) to address the deployment planning issue of the multi-sensor system. In this algorithm, Mean-Shift clustering is employed to yield characteristics information through the clustering of the multi-sensor system formation. Subsequently, this information is employed to enhance the crossover, mutation, and selection strategies. Adaptive parameters are designed to accelerate convergence and avoid local optima. Additionally, the Cauchy inverse cumulative distribution operator is employed to enhance the mutation step. The feasibility and effectiveness of the CBNSGA in multi-sensor system deployment planning are demonstrated through simulation and comparison with other algorithms.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"170 ","pages":"Article 103763"},"PeriodicalIF":4.4,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Ad Hoc Networks

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀