Multi-park energy scheduling method and system based on deep reinforcement learning

Abstract

The invention discloses a multi-park energy scheduling method based on deep reinforcement learning. The method comprises the following steps: S1, constructing a distributed park comprehensive energy system model; s2, using a multi-agent-based deep reinforcement learning algorithm to solve the dynamic scheduling problem of the integrated energy system, and building a multi-agent deep reinforcement learning framework of the distributed park integrated energy system; s3, replacing a target function with a real-time reward function, and searching for an optimal scheduling strategy of the distributed park integrated energy system by utilizing interaction between intelligent agents in each park and the environment; s4, performing scheduling decision making on the trained intelligent agent by using the test set data, and comparing the obtained target cost with the target cost obtained by the integrated energy system model after linearization processing through a solver to prove the effectiveness of the algorithm. The invention further comprises a multi-park energy scheduling system based on deep reinforcement learning. According to the invention, photovoltaic consumption in each park is promoted, and the effectiveness of economic operation of the comprehensive energy system is improved.

Description

technical field [0001] The invention relates to a multi-energy coordination and complementary optimal scheduling method based on multi-agent deep reinforcement learning. Background technique [0002] With the increase of environmental pressure and the development of renewable energy technology, the traditional power system dominated by fossil energy is gradually being replaced by an integrated energy system (Integrated Energy System, IES) that coordinates the use of fossil energy and renewable energy. While the various types of energy in the integrated energy system improve system flexibility and energy supply diversity, it also brings difficulties for the system to improve the overall energy utilization rate and realize economic operation. Therefore, it is of great significance to study the multi-energy coordinated optimal dispatch strategy in the integrated energy system to promote the consumption of renewable energy and improve the system economy. [0003] The research o...

AI Technical Summary

Problems solved by technology

The integrated energy system of this structure requires the control center to establish an accurate network structure in advance and collect the operating conditions of each device in the integrated energy system in real time, which is difficult to achieve for an integrated energy system with a complex and changeable structure

Moreover, the unified operation of a single entity is inconsistent with the current situation that the current comprehensive energy system contains multiple sub-energy systems that operate relatively independently, especially under the current market mechanism, there is a problem of information privacy

Images