RFID Network Planning by ABC Algorithm Hybridized with Heuristic for Initial Number and Locations of Readers

Abstract

In the presented paper we show artificial bee colony (ABC) algorithm adjusted for the radio frequency identification (RFID) network planning problem and hybridized with heuristic for estimating the initial number and locations of RFID readers. The RFID network planning problem (RNP) belongs to the group of multi-objective NP-hard optimization problems hence it is an excellent candidate for swarm intelligence application. In many RNP implementations the number of readers represents the variable of an algorithm which often leads to uncontrolled oscillations and difficult convergence. In our approach, we employed heuristic with the goal of finding initial number and locations of readers for covering RFID network and then, when the number and approximate locations of the readers are estimated, we perform multi-objective RFID optimization with the ABC algorithm. We conducted empirical tests on six standard RFID sets of benchmark data which consist of clustered and random tag topologies. To test our approach, we performed a comparative analysis with other state-of-the-art algorithms whose performance was measured using the same test data. Our implementation obtained better results, especially considering the number of deployed readers.