Advertisement

Novel Combination Policy for Diffusion Adaptive Networks

  • Qiang Fan
  • Wang LuoEmail author
  • Wenzhen Li
  • Gaofeng Zhao
  • Qiwei Peng
  • Xiaolong Hao
  • Peng Wang
  • Zhiguo Li
  • Qilei Zhong
  • Min Feng
  • Lei Yu
  • Tingliang Yan
  • Shaowei Liu
  • Yuan Xia
  • Bin Han
  • Qibin Dai
  • Jie WangEmail author
  • Guan Gui
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 516)

Abstract

Diffusion adaptive networks are received attractive applications in various fields such as wireless communications. Selections of combination policies greatly influence the performance of diffusion adaptive networks. Many diffusion combination policies have been developed for the diffusion adaptive networks. However, these methods are focused either on steady-state mean square performance or on convergence speed. This paper proposes an effective combination policy, which is named as relative-deviation combination policy and uses the Euclidean norm of instantaneous deviation between the intermediate estimation vector of alone agent and the fused estimation weight to determine the combination weights of each neighbor. Computer simulations verify that the proposed combination policy outperforms the existing combination rules either in steady-state error or in convergence rate under various signal-to-noise ratio (SNR) environments.

Keywords

Combination policy Diffusion adaptive networks ATC CTA Relative-deviation combination policy 

Notes

Acknowledgements

This research was funded by State Grid Corporation Science and Technology Project (named “research on intelligent preprocessing and visual perception for transmission and transformation equipment”).

References

  1. 1.
    Tu SY, Sayed AH. Mobile adaptive networks. IEEE J Sel Top Signal Process. 2011;5(4):649–64.CrossRefGoogle Scholar
  2. 2.
    Cattivelli FS, Sayed AH. Modeling bird flight formations using diffusion adaptation. IEEE Trans Signal Process. 2011;59(5):2038–51.MathSciNetCrossRefGoogle Scholar
  3. 3.
    Chen L, IEEE MS, Ho Y, Lee H, Wu H, Liu H. An open framework for participatory PM2. 5 monitoring in smart cities. IEEE Access. 2017;5:14441–54.CrossRefGoogle Scholar
  4. 4.
    Nedic A, Ozdaglar A. Distributed subgradient methods for multi-agent optimization. IEEE Trans Automat Contr. 2009;54(1):48–61.MathSciNetCrossRefGoogle Scholar
  5. 5.
    Kar S, Moura JMF. Distributed consensus algorithms in sensor networks with imperfect communication: link failures and channel noise. IEEE Trans Signal Process. 2009;57(1):355–69.MathSciNetCrossRefGoogle Scholar
  6. 6.
    Srivastava K, Nedic A. Distributed asynchronous constrained stochastic optimization. IEEE J Sel Top Signal Process. 2011;5(4):772–90.CrossRefGoogle Scholar
  7. 7.
    Rabbat MG, Nowak RD. Quantized incremental algorithms for distributed optimization. IEEE J Sel Areas Commun. 2005;23(4):798–808.CrossRefGoogle Scholar
  8. 8.
    Lopes CG, Sayed AH. Incremental adaptive strategies over distributed networks. IEEE Trans Signal Process. 2007;55(8):4064–77.MathSciNetCrossRefGoogle Scholar
  9. 9.
    Chen J, Richard C, Hero AO, Sayed AH. Diffusion LMS for multitask problems with overlapping hypothesis subspaces. In: IEEE international workshop on machine learning for signal processing; 2014. p. 1–6.Google Scholar
  10. 10.
    Sayed AH. Adaptive networks. Proc IEEE. 2014;102(4):460–97.CrossRefGoogle Scholar
  11. 11.
    Sayed AH, Tu SY, Chen J, Zhao X, Towfic Z. Diffusion strategies for adaptation and learning over networks: an examination of distributed strategies and network behavior. IEEE Signal Process Mag. 2013;30:155–71.CrossRefGoogle Scholar
  12. 12.
    Sayed AH. Diffusion adaptation over networks. E-Ref Sig Process. 2013;61:1419–33.zbMATHGoogle Scholar
  13. 13.
    Chen J, Sayed AH. Diffusion adaptation strategies for distributed optimization and learning over networks. IEEE Trans Signal Process. 2012;60(8):4289–305.MathSciNetCrossRefGoogle Scholar
  14. 14.
    Sayed AH. Adaptation, learning, and optimization over networks. Found Trends Mach Learn. 2014;7(4–5):1–501.zbMATHGoogle Scholar
  15. 15.
    Tu S, Member S, Sayed AH. Diffusion strategies outperform consensus strategies for distributed estimation over adaptive networks. IEEE Trans Signal Process. 2012;60(12):6217–34.MathSciNetCrossRefGoogle Scholar
  16. 16.
    Blondel VD, Hendrickx JM, Olshevsky A, Tsitsiklis JN. Convergence in multiagent coordination, consensus, and flocking. In: Proceedings of the 44th IEEE conference on decision and control, and the European control conference; 2005. p. 2996–3000.Google Scholar
  17. 17.
    Xiao L, Boyd S. Fast linear iterations for distributed averaging. In: Pmedingr of the 42nd LEEK conference on UecMon and Conlrd; 2003. p. 65–78.Google Scholar
  18. 18.
    Scherber DS, Papadopoulos HC. Locally constructed algorithms for distributed computations in Ad-Hoc networks. In: Information processing in sensor networks (IPSN); 2004. p. 11–9.Google Scholar
  19. 19.
    Xiao L, Boyd S, Lall S. A scheme for robust distributed sensor fusion based on average consensus. In: Information processing in sensor networks; 2005. p. 63–70.Google Scholar
  20. 20.
    Cattivelli FS, Lopes CG, Sayed AH. Diffusion recursive least-squares for distributed estimation over adaptive networks. IEEE Trans Signal Process. 2008;56(5):1865–77.MathSciNetCrossRefGoogle Scholar
  21. 21.
    Tu S, A. Sayed AH. Optimal combination rules for adaptation and learning over networks. In: IEEE international workshop on computational advances in multi-sensor adaptive processing (CAMSAP); 2011. p. 317–20.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Qiang Fan
    • 1
  • Wang Luo
    • 1
    Email author
  • Wenzhen Li
    • 2
  • Gaofeng Zhao
    • 1
  • Qiwei Peng
    • 1
  • Xiaolong Hao
    • 1
  • Peng Wang
    • 1
  • Zhiguo Li
    • 1
  • Qilei Zhong
    • 1
  • Min Feng
    • 1
  • Lei Yu
    • 1
  • Tingliang Yan
    • 1
  • Shaowei Liu
    • 1
  • Yuan Xia
    • 1
  • Bin Han
    • 1
  • Qibin Dai
    • 1
  • Jie Wang
    • 3
    Email author
  • Guan Gui
    • 3
  1. 1.NARI Group Corporation/State Grid Electric Power Research InstituteNanjingChina
  2. 2.East Inner Mongolia Electric Power Company LimitedHohhotChina
  3. 3.Nanjing University of Posts and TelecommunicationsNanjingChina

Personalised recommendations