Proposal and real-world evaluation of a VANET protocol utilizing fuzzy logic and reinforcement learning

2015 Fiscal Year Final Research Report

• Project/Area Number: 25730053
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Information network
• Research Institution: The University of Electro-Communications
• Principal Investigator: Wu Celimuge 電気通信大学, 大学院情報システム学研究科, 准教授 (90596230)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Keywords: 車両アドホックネットワーク / VANET / マルチホッププロトコル

Outline of Final Research Achievements

Vehicular ad hoc networks (VANETs) have been attracting great interest due to their potential usage in interesting applications including collision avoidance systems and driving assistance systems. A multi-hop routing protocol for VANETs was proposed in this research. The proposed protocol takes into account the inter-vehicle distance, vehicle movement, wireless bandwidth, and signal quality for the link status evaluation by using a fuzzy logic-based approach. The protocol also employs a reinforcement learning-based approach to select the best route considering multi-hop efficiency. The proposed protocol was evaluated by using a real vehicular ad hoc network.

Free Research Field

情報ネットワーク