Multi objective clustering for wireless sensor networks

Hacıoğlu, Gökçe; Kand, Vahid Faryad Aghjeh; Sesli, Erhan

doi:10.1016/j.eswa.2016.04.016

Cited by 45 publications

(18 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental results showed the proposed approach achieved competitive performance compared to the standard discrete multi‐objective particle swarm optimization. Hacioglu, Kand, and Sesli () employed NSGA‐II with seven objective functions for clustering routes in wireless sensor networks. Heloulou, Radjef, and Kechadi () proposed a game‐theoretic model for multi‐objective clustering.…”

Section: Meta‐heuristic Multi‐ and Many‐objective Algorithms Applied mentioning

confidence: 99%

Meta‐heuristic multi‐ and many‐objective optimization techniques for solution of machine learning problems

2017

View full text Add to dashboard Cite

Recently, multi‐ and many‐objective meta‐heuristic algorithms have received considerable attention due to their capability to solve optimization problems that require more than one fitness function. This paper presents a comprehensive study of these techniques applied in the context of machine learning problems. Three different topics are reviewed in this work: (a) feature extraction and selection, (b) hyper‐parameter optimization and model selection in the context of supervised learning, and (c) clustering or unsupervised learning. The survey also highlights future research towards related areas.

show abstract

Section: Meta‐heuristic Multi‐ and Many‐objective Algorithms Applied mentioning

confidence: 99%

Meta‐heuristic multi‐ and many‐objective optimization techniques for solution of machine learning problems

2017

View full text Add to dashboard Cite

show abstract

“…Wireless sensor nodes are generally operated on internal power source like batteries often in isolated environments where batteries cannot be recharged, and battery outage can cause sensor node's disconnection from the network. Sensor nodes consume most of their energy in communicating with other nodes [2] [7]. It is pertinent to optimize the data communications among sensor nodes for effective and efficient use of resources, which are albeit limited, to enhance network lifetime [7].…”

Section: Introductionmentioning

confidence: 99%

ENHANCED CLUSTER HEAD MANAGEMENT IN LARGE SCALE WIRELESS SENSOR NETWORK USING PARTICLE SWARM OPTIMIZATION (PSO) ON THE BASIS OF DISTANCE, DENSITY & ENERGY

Rastogi¹,

Rastogi²,

Darbari³

2019

IJCET

View full text Add to dashboard Cite

Wireless Sensor Networks (WSNs) are utilized for a plethora of applications such as weather forecasting, monitoring systems, surveillance, and so on. The critical issues of the WSN are energy constraints, limited memory, and computation time. This spectrum of criticality takes a deep dive with large-scale WSNs. In such scenario, the network lifetime has to be efficiently utilized with the available resources by organizing into clusters. Even though the technique of clustering has proven to be highly effective in minimizing the energy, the tradition cluster based WSNs, the protocol overhead is high for Cluster Heads (CHs) as it receives and aggregates the data from its cluster members. Therefore, efficient management of CH along with routing behavior is vital in prolonging the network lifetime. In this paper, an enhanced CH-Management technique is proposed which efficiently elects its CH using Particle Swarm Optimization (PSO), hereafter referred to as PSO_DDE. The PSO_DDE approach considers various parameters such as within-cluster distance between nodes (intra-cluster distance), neighbor density, and residual energy of nodes for the best candidate selection of CH. Also, the cluster formation is defined by the k-means based on the Euclidian distance. The PSO_DDE approach is integrated with the Dynamic Source Routing (DSR) for efficiently traversing the data packet to the sink node. The performance metrics are compared with the existing approaches using NS-2 simulator, and the proposed approach shows superiority of results.

show abstract

“…Chu et al [17] proposed a distributed cooperative topology control and adaptation algorithm to achieve the extend of network lifetime. Hacioglu et al [18] presented a clustering-based routing methodology, which minimized the communication costs among clusters and maximized the node quantity in each cluster, and NSGA-II [19] was combined to select excellent solutions. However, all these studies only explored the case of 2D plane.…”

Section: Introductionmentioning

confidence: 99%

Differential Evolution-Based 3-D Directional Wireless Sensor Network Deployment Optimization

Cao

Kang

Zhao

et al. 2018

IEEE Internet Things J.

View full text Add to dashboard Cite

Wireless sensor networks (WSNs) are applied more and more widely in real life. In actual scenarios, 3D directional wireless sensors (DWSs) are constantly employed, thus, research on the real-time deployment optimization problem of 3D directional wireless sensor networks (DWSNs) based on terrain big data has more practical significance. Based on this, we study the deployment optimization problem of DWSNs in the 3D terrain through comprehensive consideration of coverage, lifetime, connectivity of sensor nodes, connectivity of cluster headers and reliability of DWSNs. We propose a modified differential evolution (DE) algorithm by adopting CR-sort and polynomial-based mutation on the basis of the cooperative coevolutionary (CC) framework, and apply it to address deployment problem of 3D DWSNs. In addition, to reduce computation time, we realize implementation of message passing interface (MPI) parallelism. As is revealed by the experimentation results, the modified algorithm proposed in this paper achieves satisfying performance with respect to either optimization results or operation time.

show abstract

Multi objective clustering for wireless sensor networks

Cited by 45 publications

References 14 publications

Meta‐heuristic multi‐ and many‐objective optimization techniques for solution of machine learning problems

Meta‐heuristic multi‐ and many‐objective optimization techniques for solution of machine learning problems

ENHANCED CLUSTER HEAD MANAGEMENT IN LARGE SCALE WIRELESS SENSOR NETWORK USING PARTICLE SWARM OPTIMIZATION (PSO) ON THE BASIS OF DISTANCE, DENSITY & ENERGY

Differential Evolution-Based 3-D Directional Wireless Sensor Network Deployment Optimization

Contact Info

Product

Resources

About