Genetic Algorithm and Pure Random Search for Exosensor Distribution Optimisation

Abstract

The positioning, amount(s) and field of view(s) of exosensors are a fundamental characteristic of a smart home environment. Contemporary smart home sensor distribution is aligned to either: a) a total coverage approach; b) a human assessment approach. These methods for sensor arrangement are not data driven strategies, are unempirical, and frequently irrational. Little research has been conducted in relation to optimal resource allocation in smart homes environments. This study aimed to generate globally optimal sensor distributions for a smart home replica-kitchen using two distinct methodologies, namely a genetic algorithm (GA) and a pure random search algorithm (PRS), to ascertain which method is appropriate for this task. GA outperformed PRS consistently, with a coverage percentage that encapsulated an average of 43.6% more inhabitant spatial frequency data. The results of this study indicate that GA provides more optimal solutions than PRS for exosensor distributions in a smart home environment.