Fuzzy Rule Generation using Modified PSO for Clustering in Wireless Sensor Networks
ABSTARCT :
Clustering is one of the popular methods for improving energy efficiency in wireless sensor networks. In most of the existing fuzzy approaches, the CHs are selected first, and then clusters are generated, but this may lead to uneven distribution of the sensor nodes in the clusters. In this article, the clusters are generated using the famous Fuzzy C-means (FCM) algorithm and the Cluster Head (CH) from each cluster is selected using the Sugeno fuzzy system. FCM generates load-balanced clusters and the proposed approach named SF-MPSO selects the suitable CH from each cluster. The local information of the sensor node such as residual energy, its distance from cluster centroid and the distance from the BS is provided to SF-MPSO. In the existing algorithms, the fuzzy rules are manually designed, whereas, in this article, the modified Particle Swarm Optimization (PSO) algorithm is applied to generate optimum Sugeno fuzzy rules. A novel fitness function is designed to identify the effectiveness of the generated solution. The simulations are performed under three scenarios where SF-MPSO outperforms existing EAUCF, DUCF, FGWO and ARSH-FATI-CHS when evaluated under the parameters such as energy consumption and network lifetime.
EXISTING SYSTEM :
? The existing sensor node clustering methods based on computational intelligence have proved the effectiveness of computational intelligence technologies in providing effective solutions for WSNs.
? Most existing sensor node clustering methods do not balance the number of sensor nodes between clusters, which causes unbalanced energy consumption.
? Generally, some existing studies define the network lifetime as a period from network initialization until the energy of at least one sensor node is depleted, that is, one sensor node fails.
? In this section, existing methods for clustering sensor nodes are reviewed from two aspects, namely, non-computational intelligence and computational intelligence.
DISADVANTAGE :
? Computational intelligence has the ability to deal with imprecise information and find approximate yet good-enough solutions to these problems.
? As one of the technologies in computational intelligence, evolutionary computation imitates the process of natural evolution to provide a near-optimal solution for an optimization problem.
? Among many evolutionary algorithms, the particle swarm optimization algorithm (PSO) can find the optimal solution to a problem at a higher velocity by considering previous global and local best experiences of the entire population.
? EBCRP only shows a period of a sharp rise in the number of dead sensor nodes, whereas there is no problem of sensor nodes consuming energy prematurely.
PROPOSED SYSTEM :
• Many clustering methods have been proposed to prolong the network lifetime. One of the methods divides the sensing region equally into many grids (subregions), with sensor nodes in each grid being regarded as a cluster.
• The proposed schemes for balanced clustering scheme and rotation CH selection based on the highest residual energy are helpful in balancing the energy consumption of sensor nodes and thus prolonging the network lifetime.
• An energy-balanced cluster-routing protocol for WSNs is proposed to balance the energy consumption of sensor nodes and prolong the network lifetime.
ADVANTAGE :
? In the consequent iterations, based on previous value of particles (especially their position and speed), PSO formulations, cost function, proposed fuzzy controller, and fuzzy clustering algorithm, particles are updated in each iteration to yield better performance.
? Advantages of the proposed algorithm in reducing energy consumption and increasing the network’s lifetime are verified by several graphs.
? Most of the energy consumption is in data transfer with other nodes and the base station where several commutation and network routing algorithms are used.
? It should be noted that, besides clustering methods, optimal data transmission path management algorithms such as that in are also used in WSNs to decrease energy consumption.
|