RFID network topology design based on Genetic Algorithms

Abstract

Abstract-Radio Frequency Identification (RFID) is a well known technology that has entered successfully in the realm of innumerable applications and is considered as one of the principal building blocks for the realization of the Internet of Things concept. However, the majority of RFID applications require the utilization of multiple RFID readers and therefore effective and efficient planning of their networks is a major concern. Network planning is a complex process that involves different steps, one of which is its topology design. In this paper, we focus on the topology design process of a RFID network following an optimization-based approach. More precisely, we propose a multi-objective cost function that is used to evaluate candidate solutions for the position and power levels of the set of RFID readers to be deployed. In order to obtain optimal solutions we applied Genetic Algorithms, a well known heuristic technique. Finally, a developed software tool to assist in the topology design is also presented and processing delay measurements are performed.

IGAA: An Efficient Optimization Technique for RFID Network Topology Design in Internet of Things

“…A new optimization-based approach is recently proposed in [18] to give a favorable RFID topology design. Constructed on the genetic algorithms (GA), the approach evaluates each possible solution by a defined linear weighted multi-objective fitness function which covers six objectives: overlapping of the reading area, the number of useless readers, the number of redundant readers, the number of tags located in the overlapped reading areas, the number of tags covered, and the number of readers located out of the deployment area.…”

“…To prevent our fitness function from encountering the same problem, we believe it is better to replace 1 in the denominator by 100. Based on the observation and other references [18][19][20], we redefine each objective in the fitness function to become…”

“…Illustrated in the following are the five objectives in [18]. Note that the last objectivethe number of readers located out of the deployment area -is not counted in here because we consider it unreasonable in practice to deploy readers out of the should -be-known deployment area and therefore decide to exclude the objective from our multi-objective fitness function.…”

“…Extensive simulation runs are conducted to evaluate and compare the performancein terms of solution quality and solution search time -of three related optimization approaches: GA [18][19][20][21][22], GAA [16] and IGAA, all using the proposed multi-objective fitness function. Solution quality refers to the optimality of solutions -to be indicated by the fitness values, and solution search time refers to the speed of finding desirable solutions -indicated by the needed complexity.…”

Introducing a Novel Hybrid Artificial Intelligence Algorithm to Optimize Network of Industrial Applications in Modern Manufacturing

“…Nowadays, with the developments in computer technology, and software engineering, the conventional trial and error approach has been replaced with modern computational techniques that provide important criteria such as the coverage of objects, collision of antennas, and number of antennas [15]. Computational evolutionary techniques such as Artificial Neural Networks [16], Fuzzy Logic [17], Genetic Algorithms (GA) [10,11,18], particle swarm optimization (PSO) [13,19,20], differential evolution (DE) [9], and hierarchical artificial bee colony algorithm [8] are points of interest for many scientists working with the RNP problem. In this respect, Han and Jie [21] proposed a novel optimization algorithm, namely, the multicommunity GA-PSO, for solving the problem of complicated RNP.…”