Premium
ICN routing strategy based on reinforcement learning and neural network
Author(s) -
Li Huizhu
Publication year - 2020
Publication title -
internet technology letters
Language(s) - English
Resource type - Journals
ISSN - 2476-1508
DOI - 10.1002/itl2.266
Subject(s) - routing (electronic design automation) , computer science , reinforcement learning , computer network , artificial neural network , stability (learning theory) , policy based routing , static routing , distributed computing , routing protocol , artificial intelligence , machine learning
Information‐Centric Networking (ICN) provides network infrastructure services to distribute and retrieve the content in more efficient way, in which the content is the only abstract entity with the arbitrary form. In particular, ICN routing plays an important role to support interest request and content distribution. Different from the previous routing proposals, this paper presents a Reinforcement Learning (RL) and Neural Network (NN) based ICN routing strategy to improve the distribution efficiency and the stability. Meanwhile, RL is used to obtain the stable routing, while NN is used to predict network delay and enhance the routing efficiency. The simulation experiments are driven based on NDNSIM, and the results show that the proposed ICN routing strategy is feasible and efficient.