Security-aware Cooperative Caching via Deep Reinforcement Learning in Fog Radio Access Networks
Qi Chang, Baotian Fan, Yanxiang Jiang, Fu‐Chun Zheng, Mehdi Bennis, Xiaohu You · 2022 IEEE Globecom Workshops (GC Wkshps) · 2022
In this paper, the cooperative caching problem with security guarantees in fog radio access networks (F-RANs) is investigated. To avoid file retransmission, we propose a security prediction model by training a long short-term memory (LSTM) network, which leverages the file integrity and malicious requests to determine which access points can be trusted. To minimize the file transmission delay, we formulate a cooperative caching optimization problem under the consideration of security risk. In view of the complexity of the formulated problem, we employ a soft-actor-critic (SAC) based deep reinforcement learning (DRL) algorithm. Simulation results show that our proposed scheme achieves significant performance improvement over the baseline.