Micro-power-grid energy storage scheduling method and device based on deep Q-value network (DQN) reinforcement learning

Abstract

The invention discloses a micro-power-grid energy storage scheduling method and device based on deep Q-value network reinforcement learning. A micro-power-grid model is established; a deep Q-value network reinforcement learning algorithm is utilized for artificial intelligence training according to the micro-power-grid model; and a battery running strategy of micro-power-grid energy storage scheduling is calculated and obtained according to input parameter feature values. According to the embodiment of the invention, deep Q-value networks are utilized for scheduling management on micro-power-grid energy, an agent decides the optimal energy storage scheduling strategy through interaction with an environment, a running mode of the battery is controlled in the constantly changing environment,features of energy storage management are dynamically determined on the basis of a micro-power-grid, and the micro-power-grid is enabled to obtain a maximum running benefit in interaction with a mainpower grid; and the networks are enabled to respectively calculate an evaluation value of the environment and an additional value, which is brought by action, through using a competitive Q-value network model, decomposition of the two parts enables a learning objective to be more stable and accurate, and estimation ability of the deep Q-value networks on environment status is enabled to be higher.

Description

technical field [0001] The invention relates to the technical field of microgrid energy storage scheduling, in particular to a microgrid energy storage scheduling method and device based on deep Q-value network reinforcement learning. Background technique [0002] At present, machine learning methods are gradually applied in all walks of life. Using Deep Q-Network (DQN) to combine convolutional neural networks with traditional Q-value learning algorithms in deep learning is also an emerging research direction. . If the experience replay technology is used, by storing the experience of the agent, a part of the samples are randomly selected for the network to learn during each training, which can break the correlation between the data and make the training of the neural network convergent and stable. [0003] When the deep Q value network is applied to the management of microgrid energy storage scheduling, the target state-action Q value function has the problem of overestima...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiencies of the prior art, the purpose of the present invention is to provide a microgrid energy storage scheduling method and device based on deep Q-value network reinforcement learning, aiming to solve the problem of applying the deep Q-value network to the management of microgrid energy storage scheduling. The target state-action Q-value function is over-estimated, the learning target is not stable and accurate, and the deep Q-value network is not strong enough to estimate the environment state.

Images