Intelligent power generation control method based on multi-agent reinforcement learning having time tunnel thought
A multi-agent, reinforcement learning technology, applied in circuit devices, AC network circuits, electrical digital data processing, etc., can solve problems such as inability to win or lose standard accurate calculation
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- Publication Date
- 2017-06-27
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to an intelligent power generation control technology of a power system, in particular to an intelligent power generation control method based on multi-agent reinforcement learning with the idea of a time tunnel. Background technique
[0002] The automatic generation control (AGC) of the interconnected grid is an important technical means to adjust the frequency and active power of the grid and ensure the safe operation of the grid. At present, the design of AGC control strategy is mostly classical PI control structure. However, because the operating point of the power system changes with the day, month, season, and year, it is difficult for the fixed-gain controller based on the traditional control method to meet the control performance requirements of the increasingly complex power system. Intelligent methods such as neural network method, fuzzy control and genetic method are successively applied to the design of AGC controll...
Examples
Embodiment
[0060] In this embodiment, under the overall framework of the Central China Power Grid, each control area realizes interconnection by using a high-voltage direct current transmission system and a high-voltage alternating current transmission system. Taking Hubei Power Grid as the main research object, the simulation model is a detailed full-process dynamic simulation model built by the actual engineering project of the Hubei Provincial Power Dispatching Center. The simulation model is divided into six parts: Henan, Hubei, Jiangxi, Hunan, Chongqing and Sichuan. Regional power grid, Henan power grid is an AC / DC (AC / DC) hybrid transmission system that meets the CPS standard, and the control period of SGC is 4s. The L10 values of Henan Power Grid, Hubei Power Grid, Jiangxi Power Grid, Hunan Power Grid, Chongqing Power Grid and Sichuan Power Grid are: 214MW, 118MW, 79MW, 80MW, 125MW and 190MW respectively. Pulse load disturbance (amplitude: 1000; period: 1200s; pulse width: 50% o...