Article
Green & Sustainable Science & Technology
Qiang Wang, Dong Yu, Jinyu Zhou, Chaowu Jin
Summary: This paper proposes a data storage optimization model for smart grids based on Hadoop architecture using the improved Simulated Annealing algorithm to solve the penetration problem between multi-level data centers in the smart grid information transmission network. The smart grid data are considered as a task-oriented data set, and the smart grid information platform is equivalent to multiple distributed data centers. The mathematical model establishes the optimal transmission correspondence between data sets and data centers based on the dependency between task sets and data sets.
Article
Chemistry, Multidisciplinary
Hiba Apdalani Younus, Cemal Kocak
Summary: This study aimed to improve the lifespan of a wireless sensor network (WSN) and reduce energy consumption during data transfer by using a hybrid approach. The results showed that the proposed method had effective energy consumption and better reliability compared to other methods.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Zhendong Wang, Lili Huang, Shuxin Yang, Xiao Luo, Daojing He, Sammy Chan
Summary: In this paper, an energy-efficient coverage optimization technique using the multi-Strategy grey wolf optimization (MSGWO) algorithm is proposed. The method combines higher-order multinomial sensing models and a sort-driven hybrid opposition-based learning to reduce energy consumption and improve coverage area. Node movement and boundary strategies are introduced to overcome obstacles. Experimental results show that the algorithm significantly increases network coverage, extends network lifecycle, reduces deployment cost, and ensures good connectivity and scalability.
Article
Computer Science, Artificial Intelligence
Mohsen Sheikh-Hosseini, Seyed Rouhollah Samareh Hashemi
Summary: Connectivity and different coverage types, including target, area, and barrier coverages, are critical challenges in wireless sensor networks. This paper proposes a new node deployment method in both centralized and distributed modes to cover targets, provide maximum area coverage and connectivity, and manage sensors' movement, utilizing steepest descend and Genetic algorithm. Results show superior performance in managing sensors' movement and achieving 100% coverage in targets.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Yanbi Luo, Yongmao Hu
Summary: This study introduces a Parameters-Optimized HBA (POHBA) method to enhance the optimization performance of wireless sensor networks. By optimizing the parameters, POHBA achieves better network coverage rate without increasing algorithm complexity. The experiments demonstrate that POHBA outperforms other methods in various scenarios.
Article
Computer Science, Artificial Intelligence
Vahid Reza Ekhlas, Mirsaeid Hosseini Shirvani, Arash Dana, Nima Raeisi
Summary: Unlike traditional wireless sensor networks (WSNs) that use omni-directional sensors, directional sensor networks (DSNs) utilize directional sensor nodes. The paper presents a discrete grey wolf optimization algorithm (D-GWA) to address the k-coverage challenge in DSNs, which is an NP-Hard problem. Experimental results demonstrate the effectiveness and scalability of the proposed algorithm.
APPLIED SOFT COMPUTING
(2023)
Article
Engineering, Electrical & Electronic
Yindi Yao, Ying Li, Dangyuan Xie, Shanshan Hu, Chen Wang, Yangli Li
Summary: This study proposed a coverage enhancement strategy for WSNs based on the virtual force-directed ant lion optimization algorithm, which effectively addresses the issues of uneven node deployment and coverage holes in complex environments, demonstrating superior performance in simulations.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Yan Xu, Tong Lin, Pei Du
Summary: Accurate prediction of coal consumption is crucial for the development of the coal industry and formulation of energy strategies. This study proposes a hybrid prediction model, GWO_Markov_DNGM, which combines grey wolf optimization algorithm and grey Markov model. The model improves prediction accuracy by introducing the idea of Markov interval division. The results show that the proposed model outperforms other comparison models and has high prediction accuracy. The model is employed to predict the future coal consumption and provides valuable suggestions.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Engineering, Electrical & Electronic
Ying Li, Yindi Yao, Shanshan Hu, Qin Wen, Feng Zhao
Summary: To improve the quality of service and prolong the network lifetime of wireless sensor networks (WSNs), this article proposes an improved MOALO algorithm based on fast nondominated sorting (NSIMOALO). The algorithm utilizes fast nondominated sorting and elite strategy to avoid local optimal solutions, and introduces Levy flight to enhance global optimization ability. Simulation results show that NSIMOALO algorithm achieves higher convergence and coverage compared to other algorithms. When applied to WSNs sensor node deployment, it increases the coverage rate by 12.753%, 12.413%, and 4.492% and decreases sensor nodes average moving distance by 2.551, 2.316, and 4.457 m compared to MOALO algorithm, NSGA-II algorithm, and NSMOFPA algorithm, respectively.
IEEE SENSORS JOURNAL
(2023)
Article
Computer Science, Information Systems
Kavita Jaiswal, Veena Anand
Summary: This paper proposes a Grey wolf optimization-based cluster head selection technique for WSN, which considers various factors and selects relay nodes with QoS awareness to achieve efficient and reliable inter-cluster routing. The proposed technique improves network performance significantly by enhancing QoS parameters and proves to be suitable for designing WSNs in IoT applications.
PEER-TO-PEER NETWORKING AND APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Shuxin Wang, Hairong You, Yinggao Yue, Li Cao
Summary: A new topology optimization strategy for wireless sensor networks based on the wolf pack algorithm is proposed to address key optimization issues in complex industrial environments. The strategy combines the topology structure of wireless sensor networks and the optimization idea of the wolf pack algorithm, redefining group behavior for improved efficiency and accuracy in calculations. Through simulations and analysis, the algorithm shows advantages over other algorithms in terms of residual energy, transmission delay, packet delivery rate, and network coverage.
INTERNATIONAL JOURNAL OF DISTRIBUTED SENSOR NETWORKS
(2021)
Article
Computer Science, Artificial Intelligence
Jianhua Jiang, Ziying Zhao, Yutong Liu, Weihua Li, Huan Wang
Summary: This paper proposes an improved Grey Wolf Optimizer algorithm (DSGWO) to address the issues of poor population diversity and weak global search capability in the original GWO algorithm. DSGWO significantly improves the algorithm's performance through the combination of group-stage competition mechanism and exploration-exploitation balance mechanism, and its applicability and effectiveness are demonstrated through experiments.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Multidisciplinary Sciences
Kewen Li, Shaohui Li, Zongchao Huang, Min Zhang, Zhifeng Xu
Summary: In this study, a Grey Wolf Optimization algorithm based on Cauchy-Gaussian mutation and improved search strategy (CG-GWO) was proposed to address the slow convergence speed and tendency to fall into local optimal solution issues of the traditional Grey Wolf Optimization algorithm (GWO). The experimental results showed that the CG-GWO algorithm outperforms other classic optimization algorithms and improved algorithms in terms of convergence accuracy, convergence speed, and global search ability.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Information Systems
Bilal R. Al-Kaseem, Zahraa K. Taha, Sarah W. Abdulmajeed, Hamed S. Al-Raweshidy
Summary: This paper proposes an optimized energy-efficient path planning strategy for wireless sensor networks (WSNs) to address the issue of high energy consumption and poor network lifespan when integrated into the Internet of Things (IoT). The approach includes four procedures: partitioning the sensing field, introducing a stable election algorithm, determining sojourn locations, and optimizing mobile sinks' trajectories using evolutionary algorithms. The developed work significantly improved network lifetime and outperformed existing routing protocols by up to 66%.
Article
Computer Science, Information Systems
Wendi Fu, Yan Yang, Guoqi Hong, Jing Hou
Summary: This paper proposes a WSN node deployment algorithm based on real 3D terrain, utilizing actual geographic elevation data for surface modeling and introducing a probabilistic coverage model based on DEM data. The Greedy algorithm is used for node deployment, effectively improving coverage rate, reducing deployment cost, and decreasing time and space complexity in solving the WSN node deployment problem under complex 3D land surface models.
Article
Mathematical & Computational Biology
Li Cao, Yinggao Yue, Yong Zhang
Summary: The strategy of selecting cluster heads based on the improved competitive neural network and optimized self-organizing maps can effectively reduce network energy consumption, balance energy consumption, and prolong the lifetime of the sensor network.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2021)
Article
Mathematical & Computational Biology
Yinggao Yue, Dongwan Lu, Yong Zhang, Minghai Xu, Zhongyi Hu, Bo Li, Shuxin Wang, Haihua Ding
Summary: The paper proposes a path optimization mechanism for the mobile Sink in mobile wireless sensor networks based on the improved dragonfly optimization algorithm, which effectively reduces network energy consumption, extends network lifespan, and improves network connectivity and transmission delay.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2022)
Article
Computer Science, Information Systems
Li Cao, Yinggao Yue, Yong Cai, Yong Zhang
Summary: An improved Social Spider Optimization (SSO) algorithm is proposed for optimizing the deployment of sensor nodes in heterogeneous wireless sensor networks, aiming to improve network coverage and reduce network costs. By enhancing convergence speed and search ability through improving search and matching radius, the algorithm ultimately achieves an optimized solution.
Article
Computer Science, Information Systems
Li Cao, Yinggao Yue, Yong Zhang, Yong Cai
Summary: The study introduces an improved crow search algorithm to optimize the extreme learning machine, enhancing global search capability and gradually reducing search trajectory amplitude to avoid being attracted by local extremum, ultimately optimizing hidden layer neurons and connection weights for accurate prediction results.