We design and evaluate DeepAutonet, a self-driving reconfigurable network exploiting deep reinforcement learning. Simulation results show that DeepAutonet can adapt its topology automatically to different traffic conditions with up to 1.9x latency reduction.

© 2019 The Author(s)

PDF Article


You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
Login to access OSA Member Subscription