Dual-time-scale new energy grid voltage optimization method based on deep reinforcement learning
A grid voltage and time scale technology, applied in constraint-based CAD, design optimization/simulation, electrical digital data processing, etc., can solve problems such as dependence on model accuracy, slow convergence speed, local optimum, etc., and achieve strong reactive voltage optimization effect of ability
Active Publication Date: 2022-07-29
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, these methods often have problems such as slow convergence speed, large amount of calculation, and easy to fall into local optimum.
In addition, most existing methods are based on model solving and highly depend on model accuracy, which is impractical for power systems with a large number of new energy access
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
example
[0091] according to figure 1 The flow chart of the dual-time-scale power grid voltage optimization method based on deep reinforcement learning of the present invention is shown in Fig. figure 2The improved IEEE39 node test system shown performs voltage optimization under the condition that the output of new energy sources is uncertain and the load is uncertain. Set node 6, node 23, and node 26 as the hub nodes of the area. Nodes 33 and 37 are wind farms with a rated capacity of 500MW. The shunt capacitor bank 1 and the shunt capacitor bank 2 are installed on the No. 4 and No. 8 nodes of the original system respectively. The parameters are the same, the maximum gear is 6, each gear is 50Mvar, and the maximum number of adjustments per day is 6 times. Node 6, node 23 and node 26 are each connected to a continuous device, and the adjustable range is -120 to 120 Mvar. Considering the impact of emergencies on the grid voltage, SVG sets a reactive power reserve area for reactive ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
A dual-time-scale power grid voltage optimization method based on deep reinforcement learning, comprising: dividing long-time-scale interval and short-time-scale interval in the dual-time-scale method respectively; Time-scale shunt capacitor bank switching plan; short-time-scale reactive power and voltage optimization based on DDPG algorithm to obtain short-time-scale continuous reactive power compensation device output plan. The invention realizes the complementary advantages of various reactive power compensation devices, has stronger reactive power and voltage optimization capability, and can make overall arrangements for capacitor switching plans at each optimization time point in a day, thereby effectively realizing rapid optimization.
Description
technical field [0001] The invention relates to a dual time scale grid voltage optimization method. In particular, it relates to a dual-time-scale new energy grid voltage optimization method based on deep reinforcement learning. Background technique [0002] In order to build a new power system with new energy as the main body, the penetration rate of various types of renewable energy will be further improved, and the randomness and dynamics of load demand response will be further enhanced, which will bring huge benefits to the operation and control of modern power grids. challenge. [0003] Grid reactive power and voltage optimization can effectively and economically solve the problem of large-scale voltage fluctuations caused by power system disturbances to a certain extent. constrained and nonlinear complex optimization problems. [0004] At present, the methods to deal with dynamic reactive power and voltage optimization mainly include traditional operations research ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/27H02J3/18H02J3/24G06F111/04G06F113/04
CPCG06F30/27H02J3/24H02J3/18G06F2113/04G06F2111/04Y02E40/30
Inventor 李鹏姜磊王加浩夏辉高一航李建宜
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)