Scheduling method and device for energy storage system of wind power plant integrated with prediction and decision
An energy storage system and a technology for forecasting and decision-making, applied in forecasting, neural learning methods, data processing applications, etc., can solve problems such as loss of effective decision-making basis, and achieve the effects of improving referenceability, avoiding modeling errors, and avoiding loss
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0037] The integrated wind farm energy storage system scheduling method of this embodiment includes:
[0038] Sample accumulation step: the wind farm status s t Input to the evaluation network, output the Q value of all actions in the action space A and determine the scheduling instruction a of the energy storage system by the ε-greedy strategy t , after the energy storage system executes the scheduling instruction, calculate the returned reward r t And observe the state of the wind farm in the next period s t+1 , will (s t ,a t ,r t ,s t+1 ) is stored in the buffer as a sample, and the above process is repeated until the number of samples in the buffer reaches a preset upper limit;
[0039] Among them, the evaluation network is a deep neural network, and the structure of the evaluation network in this example is as follows: image 3 shown;
[0040]Q value iterative step: Batch sampling of the stored samples, and then calculate the time difference deviation value of ea...
Embodiment 2
[0122] An integrated wind farm energy storage system dispatching device for forecasting and decision-making in this embodiment includes:
[0123] (1) Sample accumulation module, which is used for: the wind farm status s at the current moment t Input to the evaluation network, output the Q value of all actions in the action space A and determine the scheduling instruction a of the energy storage system by the ε-greedy action selection strategy t , after the energy storage system executes the scheduling instruction, calculate the returned reward r t And observe the state of the wind farm in the next period s t+1 , will (s t ,a t ,r t ,s t+1 ) is stored in the buffer as a sample, and the above process is repeated until the number of samples in the buffer reaches a preset upper limit;
[0124] (2) Q value iteration module, which is used to: batch sample the stored samples, then calculate the time difference deviation value of each sample through the evaluation network and th...
Embodiment 3
[0128] A computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps in the method for scheduling the wind farm energy storage system with integrated forecasting and decision-making as described in Embodiment 1 are implemented.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com