Diversity Driven Multi Parent Evolutionary Algorithm with Adaptive Non Uniform Mutation

Abstract

Evolutionary algorithm inspired by Darwinian s theory based on evolutionary computational have been one of the powerful tools to deal with nonlinear, complex and real world optimization problems. These real world problems are having various characteristics such as non separability, multi modality, ill conditioning and non-linearity either embedded in objective function model or is constraint representing the physical limitation of the equipment involved. Evolutionary algorithms majorly used for solving one and almost all optimization problems these days. Evolutionary algorithms are able to give near optimum solutions at a faster rate depending on complexity of the algorithm and the design of the operators but sometimes with a risk of being stuck in a premature convergence for a local optimum resulting in poor accuracy of solution and hence slow speed of convergence. In this work an evolutionary algorithm is proposed to deal with the problem associated with wireless sensor network WSN, digital filter design, and fault identification. newline newlineAs is widely used in our daily life, WSN is considered as one of the most important phenomena of the new century. WSNs are widely used in many defence, industrial and civilian application areas, including industrial process monitoring and control, environmental and habitat monitoring, healthcare applications, home automation, traffic control, and many more. A wireless sensor network consists of a large number of densely deployed sensor nodes which work in collaborative manner to periodically sense the parameters under consideration of a monitored area, process the acquired data and transmit it to a sink for storage and archival purposes. The advancements in technology have made the wireless sensor networks economically affordable, small and manageable. newline newline