Energy optimization in wireless sensor networks using a hybrid K-means PSO clustering algorithm

Abstract

Abstract:Energy saving in wireless sensor networks (WSNs) is a critical problem for diversity of applications. Data aggregation between sensor nodes is huge unless a suitable sensor data flow management is adopted. Clustering the sensor nodes is considered an effective solution to this problem. Each cluster should have a controller denoted as a cluster head (CH) and a number of nodes located within its supervision area. Clustering demonstrated an effective result in forming the network into a linked hierarchy. Thus, balancing the load distribution in WSNs to make efficient use of the available energy sources and reducing the traffic transmission can be achieved. In solving this problem we need to find the optimal distribution of sensors and CHs; thus, we can increase the network lifetime while minimizing the energy consumption. In this paper, we propose our initial idea on providing a hybrid clustering algorithm based on K-means clustering and particle swarm optimization (PSO); named KPSO to achieve efficient energy management of WSNs. Our KPSO algorithm is compared with traditional clustering techniques such as the low energy adaptive clustering hierarchy (LEACH) protocol and K-means clustering separately.

A Hybrid Artificial Bee Colony and Bacterial Foraging Algorithm for Optimized Clustering in Wireless Sensor Network

“…Then, Multi-hop PSO-based clustering scheme (MPSO) scheme was proposed for the efficient selection of cluster heads during the clustering process [12]. It was adopted by devising a superior fitness function that includes average distance, the energy of the member nodes in the cluster and number of cluster heads in the current iteration of the selection process.…”

Clustering Analysis of Premier Research Fields

“…Utilizing the c-means clustering model by determining a random initial centroid [5], determine the distance between objects and normalize the data to improve the process of c-means clustering [6]. The c-means algorithm has been applied in some research, such as: (1) Hygiene : Clustering of the Parkinson'sdisease [ 7 ] [ 8 ] ,Obese management [9], Health care knowledge discovery [10]; (2) Clustering image : Satellite Image [11], Segmentation of white blood cells [12], Brain image segmentation [13], Content based image retrieval (CBIR) [14], Banana Image Segmentation [15], Hand gesture segmentation [16], Segmentation of fruits based on color features [17]; (3) Network science: Network partition [18], Wireless sensor networks [19]; (4) Academic science : Student careers [20], Predicting students Performance [21] ; (5) Customer satisfaction : Evaluate the cluster customers [22], Customer satisfaction in fast-food restaurant [23]; (6) Multimedia applications [24]; (7) Chemical oxygen demand [25]; (7) Approach to characterize road accident locations [26]; (8) Watershed classification [27]; (9) Wind speed [28]; (10) Tax based on cluster [29]; (11) Plagiarism detection System [30]; (12) Dictionary learning [31]; (13) Crime analysis [32]; (14) Connection oriented telecommunication data [33]; (15) Analyze Software Architecture [34]; (16) Prediction of atomic web services reliability [35] etc. It has shown that the cmean algorithm already implemented cases to solve the human problems…”

Hybrid Particle Swarm Optimization and k-Means Clustering for Education Quality Mapping

“…Implementation of k-Means Clustering Algorithm and PSO is able to partition a number of clusters that have been determined. The PSO algorithm is used as a search for the best initial centroid values for each cluster to be established [9]. The k-Means and PSO method approach can shorten computing time.…”