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

Construction method of reservoir ecological power generation multi-target medium-and-long-term random scheduling model andand optimal scheduling method

A technology of random scheduling and construction method, applied in computing models, machine learning, instruments, etc., can solve the problem of low accuracy of ecological power generation scheduling in reservoirs

Active Publication Date: 2020-12-04
CHINA THREE GORGES UNIV
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention proposes a method for constructing a multi-objective medium- and long-term stochastic dispatching model for ecological power generation of reservoirs and an optimal dispatching method, which are used to solve or at least partially solve the technical problem of low accuracy of dispatching of ecological power generation of reservoirs existing in the prior art

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
  • Construction method of reservoir ecological power generation multi-target medium-and-long-term random scheduling model andand optimal scheduling method
  • Construction method of reservoir ecological power generation multi-target medium-and-long-term random scheduling model andand optimal scheduling method
  • Construction method of reservoir ecological power generation multi-target medium-and-long-term random scheduling model andand optimal scheduling method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0076] An embodiment of the present invention provides a method for constructing a multi-objective medium- and long-term random dispatch model for ecological power generation in reservoirs, including:

[0077] S1: According to the water level of the reservoir and the power generation situation, construct the target function of closeness degree of power generation:

[0078] h t = Z t,sy -Z t,xy =(Z t +Z t+1 ) / 2-Z t,xy (1)

[0079]

[0080]

[0081]

[0082] Z t,sy and Z t,xy Respectively, the upstream and downstream average water levels of the reservoir during period t, Z t and Z t+1 Respectively, the initial and final water levels of the reservoir in period t, H t is the average power generating head in period t, p t,jk is the state of inflow runoff in period t is Q t,fd Corresponding conditional probability, where, j=1~N, k∈[1,N], N is the discrete state number of inflow runoff, A is the comprehensive output coefficient, Q t,fd is the power generation flo...

Embodiment 2

[0113] This embodiment provides an optimal dispatching method, which is realized based on the multi-objective medium- and long-term random dispatching model of reservoir ecological power generation constructed in Embodiment 1. The optimal dispatching method includes:

[0114] The Q-learning algorithm of reinforcement learning is used to solve the multi-objective mid- and long-term stochastic scheduling model of reservoir ecological power generation, and the objective function W of reservoir ecological power generation is obtained. Use it as an optimized scheduling result.

[0115] Specifically, the present invention carries out multi-objective mid-to-long-term optimal scheduling of power generation and ecology in consideration of ecological factors, considers the randomness of inbound runoff, and solves it through reinforcement learning algorithms. Firstly, the reservoir scheduling target and ecological scheduling target are normalized, then the medium- and long-term random s...

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 construction method of a reservoir ecological power generation multi-target medium-and-long-term random scheduling model and an optimal scheduling method. According to the method, ideal ecological flow in a Tennant method is adopted. The construction of the optimal scheduling model comprises the following steps of: firstly, establishing a reservoir power generation targetfunction and an ecological flow closeness target function; performing normalization processing on the two target functions to obtain a multi-target function of power generation and ecological comprehensive benefits, so as to maximize power generation and ecological comprehensive benefits as much as possible. and describing constraint conditions of the reservoir ecological random scheduling model,and then introducing a Markov decision process of runoff random process and a random variables into a reservoir ecological power generation medium-and-long-term random optimization scheduling problem.The Q-learning algorithm is a reinforcement learning algorithm capable of determining an optimal decision-making strategy, does not need an environment model, can fully utilize and mine reservoir inflow runoff data, and realizes the unification of reservoir economic benefits and ecological benefits.

Description

technical field [0001] The invention relates to the ecological and environmental protection field of the energy-saving and environmental protection industry, in particular to a method for constructing a multi-objective medium- and long-term random dispatch model for ecological power generation of reservoirs and an optimal dispatch method. Background technique [0002] Building dams to form reservoirs is an important means to realize the scientific allocation of water resources in time and space, improve the sustainable and optimized utilization of water resources, and promote the stable development of the national economy. The dispatching of hydropower station reservoirs generally focuses on economic benefits such as power generation, and does not fully consider the water demand of the ecological environment, which will inevitably have an impact on the ecology of the river. In order to realize the ecological goal of reservoir operation, it is necessary to carry out ecologica...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q10/06G06Q50/06G06N20/00
CPCG06Q10/04G06Q10/06312G06Q10/06315G06Q50/06G06N20/00Y04S10/50
Inventor 李文武严展鹏刘江鹏徐康马浩云
Owner CHINA THREE GORGES 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