Title :
Preventing malicious nodes in ad hoc networks using reinforcement learning
Author :
Maneenil, Karnkamon ; Usaha, Wipawee
Author_Institution :
Sch. of Telecommun., Suranaree Univ. of Technol.
Abstract :
This paper proposes an enhancement to an existing reputation method for indicating and avoiding malicious hosts in wireless ad hoc networks. The proposed method combines a simple reputation scheme with a reinforcement learning technique called the on-policy Monte Carlo method where each mobile host distributedly learns a good policy for selecting neighboring nodes in a path search. Simulation results show that the reputation scheme combined with the reinforcement learning can achieve up to 89% and 29% increase in throughput over the reputation only scheme for the static and dynamic topology case, respectively
Keywords :
Monte Carlo methods; ad hoc networks; learning (artificial intelligence); mobile radio; telecommunication computing; telecommunication security; dynamic topology; malicious hosts avoidance; malicious nodes prevention; mobile host; neighboring nodes selection; on-policy Monte Carlo method; path search; reinforcement learning; reputation method; static topology; wireless ad hoc networks; Ad hoc networks; Adaptive systems; Learning; Mobile ad hoc networks; Network topology; Peer to peer computing; Relays; Telecommunication network topology; Telecommunication traffic; Throughput; Reputation; malicious nodes; mobile ad hoc networks; network security; reinforcement learning;
Conference_Titel :
Wireless Communication Systems, 2005. 2nd International Symposium on
Conference_Location :
Siena
Print_ISBN :
0-7803-9206-X
DOI :
10.1109/ISWCS.2005.1547706