An Efficient Flooding Scheme Using Chaotic Neural Networks in Wireless Sensor Networks

摘要

Recently, Wireless Sensor Network (WSN) has been studied with a great amount of interests. In WSN, flooding is required for the dissemination of queries and event announcements. The original flooding causes the overlap problems. In the original flooding, each sensor node receiving a broadcast message forwards it to its neighbors, resulting in a lot of collisions and duplicate messages. For dense WSNs, the impact caused by the original flooding may be overwhelming. The original flooding may result in the reduced network lifetime. Therefore, the selection of forwarding nodes for the dissemination of queries and event announcements is needed to prolong the lifetime of WSNs. In this study, we use the Chaotic Neural Networks (CNN) to selection of forwarding nodes for the dissemination of queries and event announcements. We evaluate the applicability of CNNs by computer simulations and discuss its development potential.%無線センサネットワーク（WSN）では，広告や制御メッセージの送信にフラツディングを用いる．一般的なフラツディングでは，すべてのセンサノードが情報をローカルブロードキャストするため，WSN全体の電力消費が問題となる．WSNの長期運用ためには，フォワーディングを行うノード（FN）を適切に選定することが重要となる．本稿では，カオスニューラルネットワークを用いたFNの選定手法を提案する．提案手法を用いれば，FNの総数を大幅に削減することができ，ネットワークの長期運用が可能となる．数値実験を行い，提案手法の有効性を示す．