Analysis of asynchronous distributed multi-master parallel genetic algorithm optimization on CAN bus

被引：0
作者：
Vahid Jamshidi
Vahab Nekoukar
Mohammad Hossein Refan
机构：
[1] Shahid Rejaee Teacher Training University,Electrical Engineering School
来源：
Evolving Systems | 2020年 / 11卷
关键词：
CAN bus; Multi-master architecture; Parallel genetic algorithm; Busmaster simulator;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Industrial optimization problems are usually difficult to solve due to complexity and high number of constraints. Evolutionary algorithms are a conventional method to solve these problems. However, many industrial applications are real-time or we need to find a feasible optima solution in a limited time. Parallel genetic algorithm is a method to utilize properties of the genetic algorithm and parallel processing and implementation of a fast evolutionary algorithm. Controller Area Network (CAN) protocol is widely used in various industries such as automotive, medical, aerospace. In this paper, we implement a multiple-population coarse-grained parallel genetic algorithm on CAN bus to improve speed and performance of the conventional genetic algorithm which is asynchronous distributed multi-master. Evaluation criteria such as speed up, efficiency, serial fraction and reliability are calculated for the proposed parallel processing which is used for optimization problem of five benchmark functions. And finally, this structure is compared with the master–slave model. The proposed structure is created conditions for improving network reliability with very low cost of communication.
引用
收藏
页码：673 / 682
页数：9
相关论文
共 37 条
  • [1] Alba E(2002)Parallel evolutionary algorithms can achieve super-linear performance Inf Process Lett 82 7-13
  • [2] Alba E(2001)Analyzing synchronous and asynchronous parallel distributed genetic algorithms Future Gener Comput Syst 17 451-465
  • [3] Troya JM(2002)Parallelism and evolutionary algorithms IEEE Transact Evolut Comput 6 443-462
  • [4] Alba E(2014)Modeling and optimization for microstructural properties of Al/SiC nanocomposite by artificial neural network and genetic algorithm Expert Syst Appl 41 5817-5831
  • [5] Tomassini M(2015)Distributed evolutionary algorithms and their models: a survey of the state-of-the-art Appl Soft Comput 34 286-300
  • [6] Esmaeili R(2015)An auto-tuning PID control system based on genetic algorithms to provide delay guarantees in passive optical networks Expert Syst Appl 42 9211-9220
  • [7] Dashtbayazi MR(2015)Voltage stability enhancement using VSC-OPF including wind farms based on Genetic algorithm Int J Electr Power Energy Syst 73 560-567
  • [8] Gong YJ(2015)Optimization of an absorption heat transformer with two-duplex components using inverse neural network and solved by genetic algorithm Appl Therm Eng 85 322-333
  • [9] Chen WN(2007)A survey of genetic algorithms applications for image enhancement and segmentation Inf Technol Control 36 278-284
  • [10] Zhan ZI(2013)Real-time and reliability analysis of time-triggered CAN-bus Chin J Aeronaut 26 171-178
1234