The invention relates to a depth learning-based regional traffic signal lamp control system and method. The depth learning-based regional traffic signal lamp control system comprises an information acquisition unit, a storage unit, a 5G communication unit, a cloud end data processing and database unit, a regional road network model building unit, a Synchro-based simulation calculation unit, a depth learning-based traffic forecast unit a traffic signal control unit, wherein data such as traffic flow is acquired by the acquisition unit, 5G communication is used for transmission, data informationsuch as each intersection traffic flow is integrated at a cloud server, forecast is performed according to depth learning, an optimal control scheme is obtained by simulation of the forecasted traffic flow data according to Synchro and is finally transmitted to each intersection traffic light for execution, the traffic light management and control in the region can be effectively optimized, and apractical method is provided for traffic congestion reduction.