NFV service function chain dynamic arrangement method based on federal attention reinforcement learning

The invention discloses an NFV service function chain dynamic arrangement method based on federal attention reinforcement learning. The method comprises the following steps: 1) reading a current physical network topology and a service function chain request; 2) generating a placement scheme of the virtual network function set on the physical network based on federal attention reinforcement learning (FARL); 3) judging whether each virtual network function in the virtual network function set has a server for placing the virtual network function, if so, entering step 4), and otherwise, entering step 6); 4) judging whether a link meeting the placement scheme requirement exists in a physical network or not, if so, forming a link mapping scheme of a service function chain request, and entering step 5), otherwise, entering step 6); 5) receiving a service function chain request, deploying the service function chain request according to the placement scheme and the link mapping scheme, updating the physical network to