| Title | Security Service-aware Reinforcement Learning for Efficient Network Service Provisioning |
| Publication Type | Conference Paper |
| Year of Publication | 2022 |
| Authors | Jo, Hyeonjun, Kim, Kyungbaek |
| Conference Name | 2022 23rd Asia-Pacific Network Operations and Management Symposium (APNOMS) |
| Keywords | Costs, delays, faces, Link state, Network provisioning, Network security, network security equipment, Prediction algorithms, pubcrawl, QoS, reinforcement learning, resilience, Resiliency, Routing, Scalability, SDN, SDN security, security constraints |
| Abstract | In case of deploying additional network security equipment in a new location, network service providers face difficulties such as precise management of large number of network security equipment and expensive network operation costs. Accordingly, there is a need for a method for security-aware network service provisioning using the existing network security equipment. In order to solve this problem, there is an existing reinforcement learning-based routing decision method fixed for each node. This method performs repeatedly until a routing decision satisfying end-to-end security constraints is achieved. This generates a disadvantage of longer network service provisioning time. In this paper, we propose security constraints reinforcement learning based routing (SCRR) algorithm that generates routing decisions, which satisfies end-to-end security constraints by giving conditional reward values according to the agent state-action pairs when performing reinforcement learning. |
| Notes | ISSN: 2576-8565 |
| DOI | 10.23919/APNOMS56106.2022.9919928 |
| Citation Key | jo_security_2022 |
Security Service-aware Reinforcement Learning for Efficient Network Service Provisioning