Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A three-state energy control method based on automatic extended depth learning

A technology of deep learning and energy control, which is applied in the field of power generation scheduling and control in place of traditional multi-time scale scheduling and control, and can solve problems such as non-optimal scheduling, unit output with only one time scale, and reverse regulation. To achieve the effect of satisfying the constraints of the unit

Inactive Publication Date: 2019-01-11
GUANGXI UNIV
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the final unit output has only one time scale
Aiming at the deficiencies of traditional power generation control strategies (there are synergy problems among multi-time-scale optimal scheduling algorithms, inverse regulation problems, and non-optimal scheduling problems), the present invention designs a three-state energy control based on automatic extended deep learning method

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A three-state energy control method based on automatic extended depth learning
  • A three-state energy control method based on automatic extended depth learning
  • A three-state energy control method based on automatic extended depth learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] A three-state energy control method based on automatic extended deep learning proposed by the present invention is described in detail in conjunction with the accompanying drawings as follows:

[0031] figure 1 is a schematic diagram of the scalable neural network of the method of the present invention. The number of neurons in the input layer, the 4 hidden layers, and the output layer are respectively {n i ,n 1 no i ,n 2 no i ,n 3 no 0 ,n 4 no 0 ,n 0}, where n i , n 0 Respectively, the number of neurons in the input layer and output layer; n 1 , n 2 , n 3 , n 4 are the scaling coefficients of each hidden layer, respectively. When the input layer expands to (n′ i +n i ), the output layer is extended to (n 0 '+n 0 ), the number of neurons in each layer becomes {n i '+n i ,n 1 (n i '+n i ),n 2 (n i '+n i ), n 3 (n 0 '+n 0 ),n 4 (n 0 '+n 0 ),n 0 '+n 0}.

[0032] The designed deep learning network is used to predict the frequency deviati...

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

No PUM Login to View More

Abstract

The invention provides a three-state energy control method based on automatic extended depth learning, which can solve the problem that it is difficult to coordinate the dispatching and control methodin the form of unit combination + economic dispatching + automatic generation control + unit power distribution in the electric power system at present. The invention provides a real-time economic generation dispatching control framework which is integrated with dispatching and control, learns the system by using an automatic extended depth learning algorithm, and processes the output result by using a relaxation operation to meet the constraints of each unit in generation dispatching. The invention also discloses a real-time economic generation dispatching control framework which is integrated with dispatching and control. The three-state energy control method based on automatic extended depth learning provided by the invention can automatically expand the number of input and output variables according to the needs of the three-state energy system, and can replace the traditional multi-time scale form of scheduling and control algorithm.

Description

technical field [0001] The invention belongs to the field of power system power generation scheduling and control, relates to a traditional multi-time scale scheduling and control method, and is suitable for power system power generation scheduling and control. Background technique [0002] As renewable energy and distributed power generation are applied to smart grids, according to the "EU-funded Smart Grid Comprehensive Research Program", the power system is decomposed into several cellular systems (subsystems) in the cellular network system of the future smart grid . Traditional economic dispatch and automatic generation control algorithms are difficult to adapt to future smart grids with changing topologies. [0003] In addition, many cells in the cellular network system can be regarded as prosumers. Each prosumer has three states: Generator, Electrical Load, or Off Generator. A traditional economic scheduler acting on generators forecasts system load every fifteen mi...

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
no application Login to View More
IPC IPC(8): H02J3/00G06Q10/06G06Q50/06
CPCG06Q10/06312G06Q50/06H02J3/00H02J2203/20Y04S10/50
Inventor 殷林飞李晟源赵陆林张斌王涛高奇
Owner GUANGXI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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