A multi-source data-driven traffic control approach is developed to alleviate traffic overload at bottleneck road segments. In the proposed approach, the high-penetration feature of mobile-phone signalling data and the real-time feature of taxi global-positioning-system data are combined to simulate traffic flows in the road network of Shenzhen, a major city of southern China. The road intersections for implementing traffic control schemes are selected by locating the major vehicle sources of the bottleneck road segments, and a genetic algorithm was used to solve the dynamic traffic control schemes. Two important bottleneck road segments in Shenzhen were used as case studies to test the effectiveness of the proposed approach. The authors also propose a method to calibrate the simulated traffic flows when traffic count data are available in the future.