摘要

One fundamental issue in wireless sensor network is the coverage problem, which reflects how well a sensor network is monitored or tracked by sensors. In this paper, a new copula-based estimation of distribution algorithms (EDAs), Scopula-EDAs, is introduced to solve this problem. Although applying copula theory to EDAs is a rising and promising research issue, how to choose the right copula becomes a hurdle to the research of copula-based EDAs. In order to solve the copula selection problem, an innovative and general method, called switched copula method is introduced, which can ignore how to determine a fixed copula beforehand, and evolve the copula selection process dynamically by organizing different kinds of copulas through a copula selection pool. The proposed algorithm is easy to implement and provides a balance between accuracy and efficiency of the copula selection, in the meantime it can be applied to the coverage problem conveniently. The experiment results validate the feasibility and efficiency of our algorithm.

全文