Abstract:
Due to deployment, coverage, and capacity issues, ground wireless communication networks cannot support AI applications like intelligent transportation systems (ITS). The industry is researching the space-air-ground integrated network (SAGIN). SAGIN is flexible, reliable, and has better coverage and seamless connection than traditional wireless communication networks. SAGIN’s heterogeneity, time-varying, and self-organizing properties make deployment and use difficult, especially the orchestration of heterogeneous resources. Based on virtual network architecture and deep reinforcement learning (DRL), we model SAGIN’s heterogeneous resource orchestration as a multi-domain virtual network embedding (VNE) problem and propose a SAGIN cross-domain VNE algorithm. SAGIN’s network segments are modeled and set to meet user needs. A five-layer policy network controls the DRL agent. We train agents in a feature matrix based on SAGIN network attributes. Training determines the probability of embedding each underlying node. Using this probability, we embed virtual nodes and links in test phase. Training and testing prove the algorithm’s efficacy.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
