Solving minimal exposure path mep problem for improving the coverage in wireless sensor network using swarm intelligence based optimization approaches

Abstract

Wireless Sensor Networks (WSNs) have found extensive application in different fields that range from military to civilian domains. The area enclosed by the sensing field plays an important role in several applications. In the past few decades, identifying the Minimal Exposure Path (MEP) problem is one among the primary challenges faced in WSNs. Earlier, many research works have been studied and carried out to tackle with MEP related problems. The important problem encountered in the research techniques was the discovery of an optimal path. To improve the quality of coverage, more sensor nodes are deployed and yet the discovery of an optimal path is still a challenge. The other problem with the available approaches involves adjusting the sensing parameters for boosting the sensing quality. To achieve the coverage quality to the maximum extent, the modified swarm intelligence based approaches have been implemented with the aim of resolving the MEP. The initial stage is the development of road networks by employing Steiner tree problem. After this, MEP problem is regarded to be an optimization problem with required criteria. Hybrid Genetic Particle Swarm Optimization (H-GPSO) approach has been applied to get the optimum solution which in turns achieves energy efficiency. This approach makes use of the mix of both Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) Algorithm. The GA has been used for formulating an appropriate form of representing the candidate solutions. The PSO is proposed for resolving the problem of local optima. Even though, H-GPSO approach yields much better MEP solutions in comparison with BPT approach, this one does not yield in obtaining the probability function for dynamic scenarios encountered in WSN. In order to deal with this problem, Improved Artificial Bee Colony (IABC) based optimization approach is presented in the next stage along with probability functions. In the second stage, IABC approach also resolves the problem of MEP. This technique devises the MEP Problem both in the form of probability solutions and the fitness function, which yields a superior optimum solution. IABC brings in the combination operation to widen the search range of the MEP problem, and then the scanning mechanism is designed in order to solve the worst sort of local search. But, IABC approach did not take the angular property of the sensor parameters into consideration. To overcome this problem Modified Bat Algorithm (Modified BA) based optimization approach is presented in the next stage. newline