Distributed energy system autonomous control method and system based on deep reinforcement learning

Abstract

The invention provides a distributed energy system autonomous control method and system based on deep reinforcement learning, and the method comprises the steps: obtaining real-time environment data and change data, and inputting the obtained data into a trained agent neural network for deep reinforcement learning; and performing decision calculation to obtain a decision characteristic value, outputting the decision characteristic value to the decision space, obtaining a specific execution decision to perform simulation, adjusting controllable equipment and load in the simulation model, performing load flow calculation, and adjusting the controllable equipment and load in the real distributed energy system according to the execution decision to complete autonomous control. Deep learning isperformed on power grid data and gas network data in a distributed energy system by constructing an agent neural network, and a generated execution strategy is simulated by a simulation system to realize simulation calculation of a power distribution network. The method and the system can reflect the physical characteristics of an original component in essence, can process a complex power distribution network, can achieve the quick calculation, optimize the energy configuration, and reduce the operation cost.

Description

technical field [0001] The invention belongs to the field of power distribution and utilization, and in particular relates to a distributed energy system autonomous control method and system based on deep reinforcement learning. Background technique [0002] With the large-scale development and utilization of renewable energy, the rapid development of interactive energy facilities such as distributed energy, energy storage, and electric vehicles, and the emergence of various new forms of energy consumption, my country's energy has undergone structural changes, and the energy system has been promoted to the energy Internet. Upgrade across. The Energy Internet includes a variety of energy production, transmission, storage and consumption networks, and its topology changes dynamically. It has evolved into a giant-dimensional system with complex structures, numerous devices, and complex technologies. It has typical nonlinear random characteristics and multi-scale dynamic characte...

AI Technical Summary

Problems solved by technology

Domestic energy scientific research institutions and comprehensive energy service companies have also done related research on multi-energy scheduling and control, and applied for invention patents in user-side distributed energy system hierarchical regulation and wind-solar-hydrogen distributed energy systems, such as: CN106849835A- An online energy regulation method of a wind-solar-hydrogen distributed energy system, CN110707711A-a hierarchical regulation method and system of a user-side distributed energy system, all of which are regulated in a traditional way, and have not yet involved the use of artificial intelligence technologies such as deep reinforcement learning, and how to implement Approaches to Distributed Autonomy and Coordination Aspects of Distributed Energy Systems

Images