RFID Network Planning Based On Improved Brainstorming Algorithm

Radio Frequency Identification(RFID)is a key technology for realizing the Internet of Things,and RFID technology is widely used in fields such as vehicle management,production management,personnel management,and food safety.RFID network planning(RNP)is one of the most challenging problems in the field of RFID research.RNP is a typical multi-objective optimization problem.In order to find the optimum location for effective tag coverage,the total number of readers within the defined area and their optimal locations should be explored.In order to solve the problem of RFID network planning problem,this paper applies the improved swarm intelligence optimization algorithm to RFID network planning.The goal is to adjust the number and location of deployed readers,so as to realize the objective that the coverage of readers is larger while the interference between readers is smaller,the load balance is more reasonable while the economic cost is lower,and what’s more the power loss is smaller.The main research results and innovations of this paper are as follows:1.In this paper,an improved brainstorming optimization algorithm(GABSO)is proposed,and based on this method,a static optimization model is established to optimize the reader position.The solution generation operation of the improved algorithm is ameliorated.The learning operator and the golden sine operator are introduced into the original BSO algorithm.Compared with the original algorithm,the improved algorithm achieves a balance between exploration and development,which can effectively avoid the algorithm from falling into local areas.optimal.In the same simulation experimental environment,the GABSO algorithm is compared with other swarm intelligence optimization algorithms.First,the superior performance of the improved brainstorming optimization algorithm is verified on the benchmark function.Secondly,the algorithm is applied in two RNP instance scenarios,considering four indicators of tag coverage,reader interference,economic benefit and load balancing.The experimental results show that the tag coverage of GABSO is 4.53% higher than that of the multi-group particle swarm optimization algorithm(MCPSO),9.62% higher than that of the cuckoo algorithm(CS),and 7.70% higher than that of the brainstorming algorithm(BSO).This experimental result verifies the effectiveness of GABSO algorithm in dealing with RFID network planning problem.2.The static RFID model has the disadvantage that the radiated power of the reader is not variable,and the weighted sum method is difficult to determine the weight coefficient.In this paper,a multi-objective dynamic optimization model is designed for this problem,and an improved multi-objective brainstorming optimization based on decomposition is proposed(IMOBSO): An adaptive selection probability is adopted to avoid the preset selection probability,and the update method of the solution is redesigned,and the multi-objective problem of RNP is transformed into multiple sub-problems by means of decomposition,which improves the search efficiency.In the same simulation experiment scenario,the effectiveness of the IMOBSO algorithm in dealing with complex multiobjective optimization problems is verified by the test function.The algorithm is applied to six RNP instance scenarios,considering four indicators: tag coverage,reader interference,number of deployed readers,and power consumption.The experimental results show that the tag coverage of the IMOBSO algorithm is 8.10%higher than that of the multi-objective particle swarm optimization algorithm(MOPSO),5.21% higher than that of the multi-objective firefly algorithm(MOFA),and 6.32% higher than that of the multi-objective brainstorming algorithm(MOBSO).The experimental results show that the IMOBSO algorithm can be successfully applied in RFID dynamic network planning,which can better optimize the main goal of RFID network.