Systems and methods of optimizing capacity of network equipment in mobile networks. A computing device receives a user identification and a user attribute, the user identification corresponding to a characteristic of the mobile network user, the user attribute corresponding to at least one characteristic of mobile network usage by the mobile network user. The computing device generates a usage prediction based on the user identification and the user attribute, the usage prediction including information corresponding to anticipated future data usage of the mobile network user, the anticipated future mobile network usage corresponding to at least one mobile resource. The computing device transmits the usage prediction to a serving gateway (SGW) such that the SGW routes the mobile network user to one of a legacy packet data network gateway (PGW) and a network function virtualization (NFV) PGW based on the usage prediction.