Microgrid controller based on artificial intelligence control method

Abstract

The invention relates to a microgrid controller based on an artificial intelligence control method. According to the invention, a historical sample database is used to form an observation set of a deep deterministic policy gradient network to perform action exploration; training is performed according to continuous interactions between the microgrid controller and a microgrid system environment; mapping relationships between microgrid operation conditions and coordination control results are directly constructed; the microgrid controller directly uses a microgrid controller model which is trained offline to carry out rapid online decision making, so that the calculation and response speed is very high; and an offline training sample library is periodically updated to realize rolling optimization of the model and continuous improvement of policies. Therefore, real-time coordination control of the microgrid controller on a power supply, a grid, loads and storage in a system is realized, and the high efficiency and the robustness of the microgrid controller are effectively improved.

Description

technical field [0001] The invention relates to the technical field of micro-grid control, in particular to a micro-grid controller based on an artificial intelligence control method. Background technique [0002] A microgrid is a collection of distributed power sources, energy storage devices, and loads. As an important form of distributed energy utilization, it can fully promote the large-scale access of renewable energy and distributed energy, and realize the integration of multiple energy forms for loads. Highly reliable supply. Compared with traditional energy sources such as thermal power and hydropower, renewable energy sources such as wind power and photovoltaics in microgrids have disadvantages such as being easily affected by weather conditions and having low energy density, and their output power fluctuates; load power is affected by seasonal climate, life and production There is also some uncertainty in the impact. While the controllable power unit and energy s...

AI Technical Summary

Problems solved by technology

[0007] 1) The coordinated control of the source, network, load, and storage in the microgrid is accompanied by strong coupling characteristics, and it is difficult to accurately model and analyze its physical characteristics and operating characteristics;

[0008] 2) Relying on the internal connection and mechanism of the system unit, it needs to be modeled according to the network topology and power grid operation mode, sensitive to changes in the network topology, and not very adaptable to the connection of new power equipment;

[0009] 3) The data accumulated by the microgrid controller in the operation process contains rich correlations, which have guiding significance for future decision-making control. The traditional model-driven method lacks the mining and utilization of historical decision-making data information;

[0010] 4) The microgrid control problem is essentially a nonlinear, multi-constraint, multi-objective complex system optimization problem. There is a contradiction between accuracy and efficiency. Improving decision-making efficiency by simplifying the model often leads to a decrease in accuracy

Images