Pub Date : 2026-03-20DOI: 10.1016/j.jnca.2026.104480
Jie Zhang, Fen Hou, Degan Zhang, Ting Zhang, Hui Zhao, Chuanpeng Bao, Huijing Jia, Xingrui Jiang
{"title":"New Multi-user Computation Unloading Method of Edge Computing Based on Improved Pelican Optimization Control Strategy for Smart City","authors":"Jie Zhang, Fen Hou, Degan Zhang, Ting Zhang, Hui Zhao, Chuanpeng Bao, Huijing Jia, Xingrui Jiang","doi":"10.1016/j.jnca.2026.104480","DOIUrl":"https://doi.org/10.1016/j.jnca.2026.104480","url":null,"abstract":"","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"17 1","pages":""},"PeriodicalIF":8.7,"publicationDate":"2026-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147495828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-19DOI: 10.1016/j.jnca.2026.104478
Phat T. Tran-Truong, Trung D. Mai, Ha X. Son, Phien Nguyen-Ngoc, Bang K. Le, Khanh H. Vo, Ngan N.T. Kim, Triet M. Nguyen, Anh T. Nguyen
{"title":"POP2TIC: Performance optimization for privacy-preserving fog computing using TEE and intelligent caching","authors":"Phat T. Tran-Truong, Trung D. Mai, Ha X. Son, Phien Nguyen-Ngoc, Bang K. Le, Khanh H. Vo, Ngan N.T. Kim, Triet M. Nguyen, Anh T. Nguyen","doi":"10.1016/j.jnca.2026.104478","DOIUrl":"https://doi.org/10.1016/j.jnca.2026.104478","url":null,"abstract":"","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"52 1","pages":""},"PeriodicalIF":8.7,"publicationDate":"2026-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147495835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"MLRan: A behavioural dataset for ransomware analysis and detection","authors":"Faithful Chiagoziem Onwuegbuche, Sunday Olaoluwa Adelodun, Anca Delia Jurcut, Liliana Pasquale","doi":"10.1016/j.jnca.2026.104475","DOIUrl":"https://doi.org/10.1016/j.jnca.2026.104475","url":null,"abstract":"","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"54 1","pages":""},"PeriodicalIF":8.7,"publicationDate":"2026-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147447800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-14DOI: 10.1016/j.jnca.2026.104477
Jian Wang, Yan Shen, Guosheng Zhao
{"title":"Adaptive Malicious User Detection and Interpretability Analysis for Mobile Crowdsensing Systems","authors":"Jian Wang, Yan Shen, Guosheng Zhao","doi":"10.1016/j.jnca.2026.104477","DOIUrl":"https://doi.org/10.1016/j.jnca.2026.104477","url":null,"abstract":"","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"1 1","pages":""},"PeriodicalIF":8.7,"publicationDate":"2026-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147447798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-06DOI: 10.1016/j.jnca.2026.104464
Fakhrosadat Fanian, Marjan Kuchaki Rafsanjani, Arsham Borumand Saeid
With the increasing use of Wireless Rechargeable Sensor Networks (WRSNs), optimizing energy management and charging scheduling has become a multifaceted challenge. This paper introduces the Metaheuristic-Fuzzy-Guided Machine Learning (MFGML) protocol as an innovative, integrated framework that combines the Artificial Hummingbird metaheuristic Algorithm (AHA), fuzzy logic, and Machine Learning (ML) methods to optimize clustering, information forwarding, and charging scheduling operations simultaneously and without delay. The protocol employs a multi-objective function comprising ten sub-objectives, leveraging network-wide data. This approach enables high adaptability and generalizability under variable environmental conditions and network topologies. The MFGML protocol comprises two main phases: pre-execution and operational execution. In the pre-execution phase, a fuzzy-metaheuristic approach is first applied. This approach utilizes the AHA algorithm and fuzzy logic to perform the optimization steps for clustering, forwarding, and charging scheduling. Subsequently, the data generated from this process serves to train three distinct machine learning models. The output of this training—the optimized parameters—is stored as a set of generalizable patterns. In the operational execution phase, the ML models are evaluated using valid data, and the regression-based support vector machine model is selected as the optimal choice for real-time decision-making in the protocol’s core steps. This approach reduces computational overhead and enables automated execution by eliminating reliance on complex metaheuristic-based algorithms and fuzzy logic in real time. Simulation results demonstrate that MFGML outperforms established methods, TSFM, CFMCRS, LFLCSD, LESS, and LNJNP in critical metrics: charging response time, node survival rate, charging request management, minimum system stability, and number of packets sent. These improvements stem from the intelligent integration of metaheuristic, fuzzy, and machine learning techniques, which address WRSNs’ multifaceted challenges while ensuring generalization across diverse scenarios. This underscores the MFGML protocol’s potential as a generalizable model for designing future intelligent systems.
{"title":"An Expert-Aware Intelligent Multi-Phase Protocol: Metaheuristic-Fuzzy-Guided Machine Learning for Enhanced Generalizability in Smart WRSNs","authors":"Fakhrosadat Fanian, Marjan Kuchaki Rafsanjani, Arsham Borumand Saeid","doi":"10.1016/j.jnca.2026.104464","DOIUrl":"https://doi.org/10.1016/j.jnca.2026.104464","url":null,"abstract":"With the increasing use of Wireless Rechargeable Sensor Networks (WRSNs), optimizing energy management and charging scheduling has become a multifaceted challenge. This paper introduces the Metaheuristic-Fuzzy-Guided Machine Learning (MFGML) protocol as an innovative, integrated framework that combines the Artificial Hummingbird metaheuristic Algorithm (AHA), fuzzy logic, and Machine Learning (ML) methods to optimize clustering, information forwarding, and charging scheduling operations simultaneously and without delay. The protocol employs a multi-objective function comprising ten sub-objectives, leveraging network-wide data. This approach enables high adaptability and generalizability under variable environmental conditions and network topologies. The MFGML protocol comprises two main phases: pre-execution and operational execution. In the pre-execution phase, a fuzzy-metaheuristic approach is first applied. This approach utilizes the AHA algorithm and fuzzy logic to perform the optimization steps for clustering, forwarding, and charging scheduling. Subsequently, the data generated from this process serves to train three distinct machine learning models. The output of this training—the optimized parameters—is stored as a set of generalizable patterns. In the operational execution phase, the ML models are evaluated using valid data, and the regression-based support vector machine model is selected as the optimal choice for real-time decision-making in the protocol’s core steps. This approach reduces computational overhead and enables automated execution by eliminating reliance on complex metaheuristic-based algorithms and fuzzy logic in real time. Simulation results demonstrate that MFGML outperforms established methods, TSFM, CFMCRS, LFLCSD, LESS, and LNJNP in critical metrics: charging response time, node survival rate, charging request management, minimum system stability, and number of packets sent. These improvements stem from the intelligent integration of metaheuristic, fuzzy, and machine learning techniques, which address WRSNs’ multifaceted challenges while ensuring generalization across diverse scenarios. This underscores the MFGML protocol’s potential as a generalizable model for designing future intelligent systems.","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"101 1","pages":""},"PeriodicalIF":8.7,"publicationDate":"2026-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147392332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2025-12-22DOI: 10.1016/j.jnca.2025.104414
Huseyin Ozgur Kamali , Ali Berkay Gorgulu , Murat Karakus , Evrim Guler , Suleyman Uludag
The growing pressures of urbanization, vehicular proliferation, and fragmented parking infrastructure pose significant sustainability and mobility challenges in modern cities. In response, we present SPOSChain (Smart Parking Optimization with SDN and Blockchain), a novel Blockchain-enhanced and Software-Defined Networking (SDN)-based smart parking system that unifies independent parking providers under a decentralized, intelligent coordination framework. SPOSChain introduces a four-layer architecture integrating IoT, data, control, and blockchain layers, to ensure transparency, scalability, and real-time responsiveness. The core parking assignment task is formulated as a fairness-driven optimization problem, which is mathematically equivalent to a parallel job scheduling problem, known to be NP-hard, thereby necessitating the development of efficient heuristic strategies. To this end, we propose, adopt, and evaluate multiple heuristic and hybrid algorithms, including Local Search, Branch-and-Bound, and Genetic Search, culminating in a time-aware Hybrid Search model. Simulation results under diverse vehicle arrival distributions (uniform, normal, and exponential) demonstrate that our approach significantly reduces load imbalance, quantified via the Total of Differences metric, while improving responsiveness and maintaining scalability. SPOSChain not only enables equitable and efficient parking allocation but also supports sustainable urban mobility by reducing driver search time, CO emissions, and network overhead. These results underscore the transformative potential of programmable, decentralized parking systems in future smart city infrastructures.
城市化、车辆激增和零散的停车基础设施带来的日益增长的压力，对现代城市的可持续性和流动性构成了重大挑战。作为回应，我们提出了SPOSChain（基于SDN和区块链的智能停车优化），这是一种新型的基于区块链增强和软件定义网络（SDN）的智能停车系统，它将独立的停车提供商统一在一个分散的智能协调框架下。SPOSChain引入了集成物联网、数据、控制和区块链层的四层架构，以确保透明度、可扩展性和实时响应能力。核心停车分配任务是一个公平驱动的优化问题，它在数学上相当于一个并行作业调度问题，被称为NP-hard，因此需要开发有效的启发式策略。为此，我们提出、采用并评估了多种启发式和混合算法，包括局部搜索、分支定界和遗传搜索，最终形成了具有时间意识的混合搜索模型。不同车辆到达分布（均匀分布、正态分布和指数分布）下的仿真结果表明，我们的方法显著降低了负载不平衡（通过Total of Differences度量进行量化），同时提高了响应能力并保持了可扩展性。SPOSChain不仅能实现公平高效的停车分配，还能通过减少驾驶员搜索时间、二氧化碳排放和网络开销来支持可持续的城市交通。这些结果强调了可编程的、分散的停车系统在未来智慧城市基础设施中的变革潜力。
{"title":"Smart parking optimization with software defined networking and blockchain: SPOSChain","authors":"Huseyin Ozgur Kamali , Ali Berkay Gorgulu , Murat Karakus , Evrim Guler , Suleyman Uludag","doi":"10.1016/j.jnca.2025.104414","DOIUrl":"10.1016/j.jnca.2025.104414","url":null,"abstract":"<div><div>The growing pressures of urbanization, vehicular proliferation, and fragmented parking infrastructure pose significant sustainability and mobility challenges in modern cities. In response, we present <span>SPOSChain</span> (Smart Parking Optimization with SDN and Blockchain), a novel Blockchain-enhanced and Software-Defined Networking (SDN)-based smart parking system that unifies independent parking providers under a decentralized, intelligent coordination framework. <span>SPOSChain</span> introduces a four-layer architecture integrating IoT, data, control, and blockchain layers, to ensure transparency, scalability, and real-time responsiveness. The core parking assignment task is formulated as a fairness-driven optimization problem, which is mathematically equivalent to a parallel job scheduling problem, known to be NP-hard, thereby necessitating the development of efficient heuristic strategies. To this end, we propose, adopt, and evaluate multiple heuristic and hybrid algorithms, including Local Search, Branch-and-Bound, and Genetic Search, culminating in a time-aware Hybrid Search model. Simulation results under diverse vehicle arrival distributions (uniform, normal, and exponential) demonstrate that our approach significantly reduces load imbalance, quantified via the Total of Differences metric, while improving responsiveness and maintaining scalability. <span>SPOSChain</span> not only enables equitable and efficient parking allocation but also supports sustainable urban mobility by reducing driver search time, CO<span><math><msub><mrow></mrow><mrow><mn>2</mn></mrow></msub></math></span> emissions, and network overhead. These results underscore the transformative potential of programmable, decentralized parking systems in future smart city infrastructures.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"247 ","pages":"Article 104414"},"PeriodicalIF":8.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145813948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2025-12-25DOI: 10.1016/j.jnca.2025.104410
Muhammad Suhail Shaikh , Shuwei Qiu , Xiaoqing Dong , Chang Wang , Wulfran Fendzi Mbasso
Enhancing coverage and reducing energy consumption are fundamental challenges in wireless sensor networks (WSNs) for high-volume and data-intensive deployment. WSNs play an important role in emerging technologies and face practical limitations, particularly related to coverage and energy consumption. Strategical placement of these sensor nodes is important to ensure service quality; however, many existing optimization algorithms for sensor node placement struggle with low coverage rate and high energy consumption. A significant issue lies in determining the optimal sensor node locations, as these significantly influence the network's coverage and energy consumption. This work presented a Piecewise Chaotic Starfish Optimization Algorithm (CSFOA) for addressing the challenge of optimizing the sensor node placement to maximize coverage and minimize energy consumption in WSNs. The integration of the piecewise chaotic map enhances the convergence and exploration capacity of the algorithm in identifying better solutions. The effectiveness of CSFOA is confirmed by a range of diverse benchmark functions as unimodal, multimodal, fixed, and variable, proving its excellence in optimization performance. CSFOA obtained better results for sensor node deployment in real test cases. For instance, in Test System 1 with 20 nodes, the coverage rate is 97.4757 % and the energy consumption is 0.29967 nJ/bit. In Test System 2 with 30 nodes, the coverage is 99.9713 % and the energy consumption is 3.2193 nJ/bit. Test System 3 with 40 nodes has a 98.8690 % coverage rate and energy consumption of 5.1107 nJ/bit. Compared to CMFO, CSSA, CPSO, SFOA, MFO, SSA, and PSO algorithms, CSFOA realizes an average improvement of 16.41 %, 5.36 %, 3.45 %, 2.371 %, 2.80 %, and 2.18 % on various evaluation metrics. These results underscore the algorithm's capability in balancing coverage and energy efficiency enhancement, and they confirm the algorithm's value as a more effective solution to sensor node deployment issues in different applications.
{"title":"A piecewise chaotic starfish optimization algorithm for energy-efficient coverage in wireless sensor networks","authors":"Muhammad Suhail Shaikh , Shuwei Qiu , Xiaoqing Dong , Chang Wang , Wulfran Fendzi Mbasso","doi":"10.1016/j.jnca.2025.104410","DOIUrl":"10.1016/j.jnca.2025.104410","url":null,"abstract":"<div><div>Enhancing coverage and reducing energy consumption are fundamental challenges in wireless sensor networks (WSNs) for high-volume and data-intensive deployment. WSNs play an important role in emerging technologies and face practical limitations, particularly related to coverage and energy consumption. Strategical placement of these sensor nodes is important to ensure service quality; however, many existing optimization algorithms for sensor node placement struggle with low coverage rate and high energy consumption. A significant issue lies in determining the optimal sensor node locations, as these significantly influence the network's coverage and energy consumption. This work presented a Piecewise Chaotic Starfish Optimization Algorithm (CSFOA) for addressing the challenge of optimizing the sensor node placement to maximize coverage and minimize energy consumption in WSNs. The integration of the piecewise chaotic map enhances the convergence and exploration capacity of the algorithm in identifying better solutions. The effectiveness of CSFOA is confirmed by a range of diverse benchmark functions as unimodal, multimodal, fixed, and variable, proving its excellence in optimization performance. CSFOA obtained better results for sensor node deployment in real test cases. For instance, in Test System 1 with 20 nodes, the coverage rate is 97.4757 % and the energy consumption is 0.29967 nJ/bit. In Test System 2 with 30 nodes, the coverage is 99.9713 % and the energy consumption is 3.2193 nJ/bit. Test System 3 with 40 nodes has a 98.8690 % coverage rate and energy consumption of 5.1107 nJ/bit. Compared to CMFO, CSSA, CPSO, SFOA, MFO, SSA, and PSO algorithms, CSFOA realizes an average improvement of 16.41 %, 5.36 %, 3.45 %, 2.371 %, 2.80 %, and 2.18 % on various evaluation metrics. These results underscore the algorithm's capability in balancing coverage and energy efficiency enhancement, and they confirm the algorithm's value as a more effective solution to sensor node deployment issues in different applications.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"247 ","pages":"Article 104410"},"PeriodicalIF":8.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145845509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2025-12-19DOI: 10.1016/j.jnca.2025.104412
Kaifeng Hua , Shengchao Su , Nannan Zhang
With the growing demand for dynamic resources in the Internet of Vehicles, service migration has become essential for maintaining user service continuity. However, existing techniques often transfer redundant dirty page data during operation state file transfers, leading to high network traffic and significant migration delays, which are unsuitable for the low latency and low traffic requirements of intelligent transportation scenarios. To overcome this issue, this paper proposes a Intelligent Adaptive Container Migration Technique called IACMT, which is based on dynamic filtering of dirty pages with two-stage compression. IACMT features a dirty page filtering mechanism that intelligently identifies active dirty pages by monitoring the frequency of page accesses and modification patterns in real time. This mechanism facilitates the delayed transmission of less critical dirty pages, effectively reducing the data size during the iterative transmission phase. Furthermore, it incorporates a two-stage data compression algorithm that employs run-length encoding (RLE) followed by dynamic Huffman coding. In the initial stage, RLE eliminates redundant byte sequences in the state file. The subsequent output is then adaptively compressed using a dynamic Huffman tree, improving compression efficiency while managing computational overhead. Experimental results show that IACMT reduces data transmission volume by approximately 35 % for typical in-vehicle workloads, while cutting migration time and service interruption duration by around 24 % and 34 %, respectively.
{"title":"Seamless service migration for the Internet of Vehicles in edge computing: A dynamic dirty page filtering and two-stages compression technique","authors":"Kaifeng Hua , Shengchao Su , Nannan Zhang","doi":"10.1016/j.jnca.2025.104412","DOIUrl":"10.1016/j.jnca.2025.104412","url":null,"abstract":"<div><div>With the growing demand for dynamic resources in the Internet of Vehicles, service migration has become essential for maintaining user service continuity. However, existing techniques often transfer redundant dirty page data during operation state file transfers, leading to high network traffic and significant migration delays, which are unsuitable for the low latency and low traffic requirements of intelligent transportation scenarios. To overcome this issue, this paper proposes a <u>I</u>ntelligent <u>A</u>daptive <u>C</u>ontainer <u>M</u>igration <u>T</u>echnique called IACMT, which is based on dynamic filtering of dirty pages with two-stage compression. IACMT features a dirty page filtering mechanism that intelligently identifies active dirty pages by monitoring the frequency of page accesses and modification patterns in real time. This mechanism facilitates the delayed transmission of less critical dirty pages, effectively reducing the data size during the iterative transmission phase. Furthermore, it incorporates a two-stage data compression algorithm that employs run-length encoding (RLE) followed by dynamic Huffman coding. In the initial stage, RLE eliminates redundant byte sequences in the state file. The subsequent output is then adaptively compressed using a dynamic Huffman tree, improving compression efficiency while managing computational overhead. Experimental results show that IACMT reduces data transmission volume by approximately 35 % for typical in-vehicle workloads, while cutting migration time and service interruption duration by around 24 % and 34 %, respectively.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"247 ","pages":"Article 104412"},"PeriodicalIF":8.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145785053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the rapid development of science and technology, wireless sensor networks (WSN) are increasingly applied in environmental monitoring, industrial control, and smart cities. However, WSN deployment faces three core challenges that existing algorithms fail to address comprehensively. (1) Insufficient coverage precision. Traditional optimization algorithms (e.g., NSGA-II, MOPSO) often leave local coverage holes due to limited fine-grained search capability. (2) High resource redundancy. Fixed grid or weight-based methods (e.g., MOEA/D) cannot dynamically adjust node distribution according to environmental density, leading to redundant deployment. (3) Unbalanced energy consumption. Single-objective or simplified multi-objective approaches ignore the trade-off between coverage, waste rate, and energy consumption, shortening network lifetime. To tackle these issues, a multi-objective parrot optimizer (MOPO) based on improved Lévy flight and an adaptive elliptical segmentation screening mechanism is proposed for WSN deployment optimization. The randomness of original Lévy flight causes large step-length jumps, making fine-grained searches difficult. Thus, a Sigmoid perturbation mechanism is integrated into Lévy flight to enhance local search accuracy while preserving global exploration. Based on this improvement, an elite non-dominated strategy is combined with an adaptive grid (dynamic adjustment by solution density) and elliptical segmentation selection—this ensures retention of optimal individuals in high-density areas, maintains population diversity, and accelerates exploration of sparse regions. An external archive further preserves a uniform and diverse Pareto solution set. MOPO is tested in obstacle-free/obstacle WSN models with coverage, waste rate, and energy consumption rate as objectives. Comparative experiments with NSGA-II, MOPSO, and MOGWO in different monitoring areas show MOPO ranks first in all Friedman tests. A real-world test (41°10′20″N, 29°04′30″E, 1320 × 610 m2) achieves 94 % target coverage. This proves MOPO effectively solves the three core challenges of WSN deployment, providing a practical and efficient optimization method for large-scale, resource-constrained WSN scenarios.
{"title":"Multi-objective parrot optimizer with improved Lévy flight and adaptive elliptical segmentation - based screening mechanism for layout optimization of wireless sensor networks","authors":"Yun-Hao Zhang, Jie-Sheng Wang, Yu-Xuan Xing, Yu-Feng Sun, Si-Wen Zhang, Xue-Lian Bai","doi":"10.1016/j.jnca.2025.104413","DOIUrl":"10.1016/j.jnca.2025.104413","url":null,"abstract":"<div><div>With the rapid development of science and technology, wireless sensor networks (WSN) are increasingly applied in environmental monitoring, industrial control, and smart cities. However, WSN deployment faces three core challenges that existing algorithms fail to address comprehensively. (1) Insufficient coverage precision. Traditional optimization algorithms (e.g., NSGA-II, MOPSO) often leave local coverage holes due to limited fine-grained search capability. (2) High resource redundancy. Fixed grid or weight-based methods (e.g., MOEA/D) cannot dynamically adjust node distribution according to environmental density, leading to redundant deployment. (3) Unbalanced energy consumption. Single-objective or simplified multi-objective approaches ignore the trade-off between coverage, waste rate, and energy consumption, shortening network lifetime. To tackle these issues, a multi-objective parrot optimizer (MOPO) based on improved Lévy flight and an adaptive elliptical segmentation screening mechanism is proposed for WSN deployment optimization. The randomness of original Lévy flight causes large step-length jumps, making fine-grained searches difficult. Thus, a Sigmoid perturbation mechanism is integrated into Lévy flight to enhance local search accuracy while preserving global exploration. Based on this improvement, an elite non-dominated strategy is combined with an adaptive grid (dynamic adjustment by solution density) and elliptical segmentation selection—this ensures retention of optimal individuals in high-density areas, maintains population diversity, and accelerates exploration of sparse regions. An external archive further preserves a uniform and diverse Pareto solution set. MOPO is tested in obstacle-free/obstacle WSN models with coverage, waste rate, and energy consumption rate as objectives. Comparative experiments with NSGA-II, MOPSO, and MOGWO in different monitoring areas show MOPO ranks first in all Friedman tests. A real-world test (41°10′20″N, 29°04′30″E, 1320 × 610 m<sup>2</sup>) achieves 94 % target coverage. This proves MOPO effectively solves the three core challenges of WSN deployment, providing a practical and efficient optimization method for large-scale, resource-constrained WSN scenarios.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"247 ","pages":"Article 104413"},"PeriodicalIF":8.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145813864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：