Energy-efficient vehicle and/or traffic light control

A non-transitory computer-readable medium that stores instructions that is configured to, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:

• obtain, from a datastore, traffic related information comprising information indicating a total number of vehicles detected by a sensor of a first detector located at a first intersection of a plurality of intersections, and at least one activation time of the sensor;
• synchronize the activation time of the sensor with a signal phase at a downstream second intersection of the plurality of intersections;
• change a duration of the signal phase at the downstream second intersection based on said synchronizing;
• use a bilinear control model to compute traffic light timing for a next traffic signal timing cycle of the downstream second intersection;
• determine traffic light timing for at least one additional upcoming traffic signal timing cycle that occurs after the next traffic signal timing cycle by performing a predictive bilinear control algorithm using a current traffic volume at the plurality of intersections as a first input, a signal timing at the plurality of intersections as a second input, and combination of the first and second input as a third input, wherein the predictive bilinear control algorithm is solved to obtain the traffic light timing for the at least one additional upcoming traffic light timing cycle;
• and
• control a traffic light of the downstream second intersection in accordance with the duration of the signal phase that was changed, the traffic light timing for the next traffic signal timing cycle, and the traffic light timing for the at least one additional upcoming traffic signal timing cycle to reduce a probability or likelihood that a vehicle will stop at a red light thereat;
• wherein the predictive bilinear control algorithm implements an objective function to maximize a traffic volume during a future cycle of the traffic lights, timing constraints for the traffic light timing, and sequential least square regression to solve an optimization traffic light timing problem.