Complexity Suppression of Neural Networks for PAPR Reduction of OFDM Signal

• OHTA Masaya

  Graduate School of Engineering, Osaka Prefecture University

• MIZUTANI Keiichi

  Graduate School of Science and Engineering, Tokyo Institute of Technology

• YAMASHITA Katsumi

  Graduate School of Engineering, Osaka Prefecture University

抄録

In this letter, a neural network (NN) for peak power reduction of an orthogonal frequency-division multiplexing (OFDM) signal is improved in order to suppress its computational complexity. Numerical experiments show that the amount of IFFTs in the proposed NN can be reduced to half, and its computational time can be reduced by 21.5% compared with a conventional NN. In comparison with the SLM, the proposed NN is effective to achieve high PAPR reduction and it has an advantage over the SLM under the equal computational condition.

収録刊行物

• IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

  IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E93-A (9), 1704-1708, 2010

  一般社団法人 電子情報通信学会

キーワード

• OFDM
• peak-to-average power ratio (PAPR)
• hopfield neural network

詳細情報

• CRID: 1390001206309781120
• NII論文ID: 10027638054
• NII書誌ID: AA10826239
• DOI: 10.1587/transfun.e93.a.1704
• ISSN: 17451337
• ISSN: 09168508
• Web Site: http://www.jstage.jst.go.jp/article/transfun/E93.A/9/E93.A_9_1704/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可