The invention discloses an expressway
traffic efficiency improving method based on reinforced learning variable speed-limit control. The method comprises the steps that variable speed-limit values are determined in real time according to a reinforced learning method, an intelligent body perceives the running states of traffic flows on an expressway according to
traffic flow data, a speed-
limit value action is selected for the current state, a return valve of state transition caused by the action is calculated, the intelligent body traverses all state-action combinations till all state-action return values are convergent, and the intelligent body acquires the optimal speed-
limit value action in the different
traffic flow states off line; the intelligent body automatically selects the optimal speed-
limit value corresponding to the current state and issues the optimal speed-limit value according to the real-time
traffic flow data, and the controlled traffic flow data and speed-limit values are transmitted to a control center, so that the intelligent body continuously learns. According to the method, the defect that in the past, the subjective arbitrariness is generated when the corresponding relation between the traffic flow state and the speed-limit values in variable speed-limit control is determined is overcome, and the anti-jamming capability of a
control system is improved; the affecting law of the speed-limit values on
traffic efficiency improving is continuously mined through the intelligent body, therefore,
feedback regulation is conducted on the variable speed-limit values according to the real-time traffic flow data, and the
road traffic efficiency of a
bottleneck road section in variable speed-limit control is effectively improved.