2results about How to "Dynamic" patented technology

The application discloses a kind of multi-agent learning method, device and equipment based on dynamic weighted average field, method includes: according to the action of dynamic weighted average action corresponding to agent selects action;Current position information of agent is obtained Calculation aggregation factor, the weight of agent is dynamically updated using improved PSO algorithm in combination with aggregation factor;According to the action update dynamic weighted average action with weight, execute joint action to obtain next state, according to the reward update action and state, and according to the weight and reward update individual weight optimal value and group weight optimal value;Experience replay buffer is sampled from experience data including current state, joint action, reward, next state and dynamic weighted average action and updates the Q function of agent, according to the updated Q function and specified learning rate updates the target network of agent.The application can guide multi-agent to tend to group performance optimization, and also ensure that individual agent has sufficient exploration ability.

The present application belongs to the technical field of environmental hydraulics, and relates to a reservoir operation scheduling carbon transport characteristic research method, device and computer equipment. The method comprises the following steps: constructing a three-dimensional reservoir carbon transport monitoring network to obtain basic data of the carbon transport process; based on the basic data, a water dynamics-water quality coupling model for simulating the carbon transport process is constructed, and the water dynamics-water quality coupling model is verified by using monitoring data; the operation scheduling characteristics are quantified, and scheduling characteristic parameters affecting the carbon transport are extracted; a carbon flux accounting model considering the influence of scheduling is established to quantify the influence of scheduling on carbon budget; a quantitative relationship between the carbon transport characteristic parameters and the scheduling characteristic parameters is established; based on carbon environmental constraints, scheduling optimization evaluation is carried out, the carbon target is included in the scheduling optimization system, and a low-carbon scheduling scheme is proposed. The present application has systematicness and dynamicity, realizes quantitative evaluation of carbon transport, has practicability, can be popularized to carbon cycle research of other types of water bodies, and has expansibility.