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

Reservoir scheduling multi-objective optimization method based on graph convolutional neural network and NSGA-II algorithm

A convolutional neural network and multi-objective optimization technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems that are not conducive to Pareto frontier convergence speed, increase computational complexity, and complex selection operations, etc., to achieve Strong global search ability, poor improvement of local search, wide application effect

Active Publication Date: 2021-06-15
HOHAI UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the method provided by this patent makes the selection operation more complicated when the population evolves, and also increases the complexity of the calculation, which is not conducive to the improvement of the convergence speed of the Pareto front

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
  • Reservoir scheduling multi-objective optimization method based on graph convolutional neural network and NSGA-II algorithm
  • Reservoir scheduling multi-objective optimization method based on graph convolutional neural network and NSGA-II algorithm
  • Reservoir scheduling multi-objective optimization method based on graph convolutional neural network and NSGA-II algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The invention is a multi-objective optimization method for reservoir dispatching based on a graph convolutional neural network and NSGA-II algorithm, which optimizes the discharge volume of the reservoir in each time period, and obtains a non-inferior scheme set for the multi-objective optimization problem of reservoir dispatching. Collect data related to reservoir flood control scheduling and establish a multi-objective optimization model for reservoir scheduling; use the NSGA-Ⅱ algorithm to obtain the first-generation population of multi-objective optimization problems for reservoir scheduling, group the population individuals through coding operations, and mark categories, each category is used as A node of the GCN graph structure, the parent-child relationship obtained by the crossover and mutation operations is mapped to the edges between the GCN graph structure nodes, and the GCN graph structure and the preliminary Pareto front are obtained; the abscissa of the obta...

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 discloses a reservoir scheduling multi-objective optimization method based on GCN and NSGA-II, and the method comprises the steps: collecting reservoir flood control scheduling related data, and building a flood control multi-objective optimization model; using NSGA-II to obtain a primary population, grouping individuals through coding operation, taking grouped categories as nodes of the GCN, and mapping a parent-child relationship obtained by crossover and mutation operation into edges between the nodes of the GCN; using NSGA-II to obtain a preliminary pareto leading edge, performing grouping labeling on the abscissa of the preliminary pareto leading edge, and training a GCN model by using the grouping label and the graph structure obtained in the step 2; classifying the nodes of the graph structure by using the trained GCN model, and then adjsuting the uniformity of the pareto leading edge by using NSGA-II; and according to the pareto leading edge adjusted by the NSGA-II, outputting a non-inferior scheme set of the reservoir scheduling multi-objective optimization problem. The method can be widely applied to multi-target reservoir optimization scheduling, and a reservoir optimization scheduling scheme meeting all targets can be rapidly given.

Description

technical field [0001] The invention belongs to the field of multi-objective optimal reservoir dispatching in the water conservancy industry, and relates to a multi-objective optimization method for reservoir dispatching based on graph convolutional neural network and NSGA-II algorithm. Background technique [0002] During the flood season, reservoir scheduling needs to consider comprehensive factors such as the water level of the reservoir dam and downstream safety. If only the goal of reducing the water level of the reservoir is considered, it may result in low environmental benefits. Then it is necessary to consider multiple objectives, adjust the discharge flow at each stage, and obtain a solution set that can make environmental benefits and flood control benefits non-inferior. The user selects a scheduling scheme according to needs. In previous studies, traditional methods (such as particle swarm optimization and genetic algorithm dynamic programming) are usually used ...

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): G06N3/00G06N3/04G06N3/08
CPCG06N3/006G06N3/08G06N3/045Y02A10/40G06Q50/06G06N3/126G06N3/0464G06N3/086
Inventor 胡鹤轩邵良欢胡强朱跃龙胡震云张晔
Owner HOHAI 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