Abstract: A method for a self-adaptive service function chain mapping based on a deep reinforcement learning, comprising: establishing an SFC mapping model, dividing an SFC mapping process into a three-layer structure, and representing the structure with abstract parameters; building an SFCR mapping learning neural network, and mapping the abstract parameters to a state, an action and a reward value in the SFCR mapping learning neural network; establishing an empirical playback pool and updating network parameters; summarizing request rates and utilization rates of different VNFs, a number of currently deployed VNFs and a number of unactivated VNFs based on data in the empirical playback pool; and designing a VNF redeployment strategy, and redeploying the VNFs according to the summarized data. The method has good self-adaptability, and can improve the effective service cost rate and the request mapping rate for processing service requests from users in different time periods.

Abstract: A method for intelligent traffic scheduling based on deep reinforcement learning, comprising: collecting flows in a data center network topology in real time, and dividing the flows into elephant flow or mice flow according to different types of flow features; establishing traffic scheduling models with energy saving and performance of the elephant flow and the mice flow as targets for joint optimization; establishing a DDPG intelligent routing traffic scheduling framework based on CNN improvement, and performing environment interaction; jointly inputting the three state messages as a state set into the CNN for training; setting an action as a comprehensive weight of energy saving and performance of each path under the condition of uniform transmission of flows in time and space, and selecting transmission paths for the elephant flow or the mice flow according to the weight; and designing reward value functions for the elephant flow and the mice flow.