Journal on Communications ›› 2020, Vol. 41 ›› Issue (12): 118-127.doi: 10.11959/j.issn.1000-436X.2020230

• Papers • Previous Articles     Next Articles

Access selection algorithm for heterogeneous wireless network based on DA optimized fuzzy neural network

Zhihong QIAN, Yinuo FENG, Jiani SUN, Xue WANG   

  1. College of Communication Engineering, Jilin University, Changchun 130012, China
  • Revised:2020-09-21 Online:2020-12-25 Published:2020-12-01
  • Supported by:
    The National Natural Science Foundation of China(61771219);Fundamental Research Funds of Jilin University(SXGJQY2017-9);Fundamental Research Funds of Jilin University(2017TD-19)

Abstract:

To solve the access selection problem of heterogeneous wireless network, an access selection algorithm based on dragonfly algorithm (DA) optimized fuzzy neural network (FNN) was proposed, considering the user’s business type and network state.In view of the low convergence speed of the fuzzy neural network, the dragonfly algorithm was used to optimize the membership function parameters of the second and fifth layers of the fuzzy neural network, so as to obtain the initial value of membership function parameters of the fuzzy neural network.The most suitable network was selected for the users according to their preference to the network and the output score of the network under different business types.The experimental results show that dragonfly algorithm optimization can improve the convergence speed of fuzzy neural network, improve system throughput, reduce blocking rate, and reduce switching times to some extent.

Key words: heterogeneous wireless network, access selection, fuzzy neural network, dragonfly algorithm

CLC Number: 

No Suggested Reading articles found!