CN117332908B - Multi-objective optimization scheduling method and system for cascade reservoir of coupling set forecast - Google Patents

Multi-objective optimization scheduling method and system for cascade reservoir of coupling set forecast Download PDF

Info

Publication number
CN117332908B
CN117332908B CN202311629304.XA CN202311629304A CN117332908B CN 117332908 B CN117332908 B CN 117332908B CN 202311629304 A CN202311629304 A CN 202311629304A CN 117332908 B CN117332908 B CN 117332908B
Authority
CN
China
Prior art keywords
reservoir
scheduling
cascade
runoff
forecast
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202311629304.XA
Other languages
Chinese (zh)
Other versions
CN117332908A (en
Inventor
何绍坤
陈柯兵
李娜
曹辉
翟少军
任玉峰
朱玲玲
袁晶
董炳江
何衍杭
孙思瑞
牛庚
李圣伟
肖潇
杨成刚
李思璇
李昶
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Yangtze Power Co Ltd
Bureau of Hydrology Changjiang Water Resources Commission
Original Assignee
China Yangtze Power Co Ltd
Bureau of Hydrology Changjiang Water Resources Commission
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Yangtze Power Co Ltd, Bureau of Hydrology Changjiang Water Resources Commission filed Critical China Yangtze Power Co Ltd
Priority to CN202311629304.XA priority Critical patent/CN117332908B/en
Publication of CN117332908A publication Critical patent/CN117332908A/en
Application granted granted Critical
Publication of CN117332908B publication Critical patent/CN117332908B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06313—Resource planning in a project environment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
    • Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • General Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Operations Research (AREA)
  • General Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Development Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Primary Health Care (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Educational Administration (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to a cascade reservoir multi-objective optimization scheduling method and system for coupling set forecast, wherein the method comprises the following steps: step 1, collecting hydrologic data of a river basin; step 2, obtaining a reservoir entering runoff forecast value of each reservoir in the step reservoir under different foreseeing periods by adopting an artificial intelligence method; step 3, determining an optimization target of cascade reservoir joint operation scheduling, setting reservoir scheduling constraint conditions, and establishing a reservoir scheduling model; and 4, constructing a reservoir multi-objective scheduling rule of coupling the set runoff forecast information by adopting a Gaussian radial basis function based on the set runoff forecast information and the cascade reservoir optimal scheduling model, and optimizing and solving by adopting a multi-objective intelligent optimization method to obtain a final cascade reservoir short-term optimal scheduling scheme. The method is scientific and reasonable, is close to engineering practice, and can provide important and strong-operability reference basis for reservoir practical short-term operation scheduling.

Description

Multi-objective optimization scheduling method and system for cascade reservoir of coupling set forecast
Technical Field
The application relates to the field of reservoir optimal scheduling methods, in particular to a cascade reservoir multi-objective optimal scheduling method and system for coupling set forecasting.
Background
The comprehensive development and utilization of water resources are always an important strategic direction of the international academic front edge and the sustainable development of water resources in the field of water resource management research, and enter the new century, and along with the continuous and rapid large-scale development of hydropower resources, china forms a large-scale cascade reservoir group in the river basin, and plays an increasingly important role in the efficient utilization of water resources. At present, the development and utilization of the Chinese hydropower energy have entered a key transformation period from planning construction to management operation, and the development of the reservoir optimization scheduling theory and method related research can obviously improve the reservoir profit without expanding the scale of hydraulic engineering. However, with the increasing of optimal dispatching targets, the number of reservoir operations is increasing, which also provides higher requirements and challenges for water resource comprehensive management departments facing new opportunities.
By considering comprehensive hydrologic information such as rainfall runoff in the river basin in the future and performing reliable and fine reservoir water storage and drainage operation according to the comprehensive hydrologic information, the water resource utilization efficiency can be effectively improved. However, the optimal cascade reservoir dispatching is often performed under the condition that future reservoir runoff is difficult to accurately predict, the runoff change is complex, and the runoff process of the reservoir is difficult to accurately describe. The traditional cascade reservoir optimal scheduling simplifies the reservoir-entering runoff forecasting model structure on one hand, ignores the uncertainty of hydrologic forecasting, and is limited to the traditional monotone target optimal solution on the other hand, and the method is often not in line with engineering practice and is difficult to be adopted by reservoir scheduling units. The Chinese patent publication No. CN 104268653A proposes a single-objective cascade reservoir optimal scheduling method considering probability runoff forecast information, which considers uncertainty of forecast runoff, but only takes the maximum expected value of the generated energy of a reservoir as a target, adopts a dynamic programming method to solve, has weak adaptability and does not accord with scientific practice of multi-objective reservoir optimal scheduling. How to organically combine the hydrologic set forecasting product with the multi-objective optimal scheduling decision, which is convenient for reservoir managers to directly and efficiently decide and balance the water supply demands in multiple aspects, and the related research method is still lacking at present to carry out scientific research and exploration on the hydrologic set forecasting product.
Disclosure of Invention
The embodiment of the application aims to provide a cascade reservoir multi-objective optimization scheduling method, system and storage medium for coupling set forecast information, which are scientific and reasonable, are close to engineering practice, and can provide important and high-operability reference for reservoir practical short-term operation scheduling.
In order to achieve the above purpose, the present application provides the following technical solutions:
in a first aspect, an embodiment of the present application provides a cascade reservoir multi-objective optimization scheduling method for coupling set forecast information, including the following steps:
step 1, collecting hydrologic data of a river basin;
step 2, obtaining a reservoir entering runoff forecast value of each reservoir in the step reservoir under different foreseeing periods by adopting an artificial intelligence method;
step 3, determining an optimization target of cascade reservoir joint operation scheduling, setting reservoir scheduling constraint conditions, and establishing a reservoir scheduling model;
and 4, constructing a reservoir multi-objective scheduling rule of coupling the set runoff forecast information by adopting a Gaussian radial basis function based on the set runoff forecast information and the cascade reservoir optimal scheduling model, and optimizing and solving by adopting a multi-objective intelligent optimization method to obtain a final cascade reservoir short-term optimal scheduling scheme.
The implementation of said step 2 is as follows,
dividing the cascade reservoir into a plurality of sub-watersheds according to the geographical distribution position of the reservoir, respectively establishing three layers of long-short-period memory neural network LSTM models for each sub-watershed, taking historical observed precipitation, air temperature, wind speed meteorological data and historical related runoff data as inputs, taking current time observed runoff as outputs, dividing hydrologic data into regular rate, verification period and test period, and training and optimizing to obtain a black box model capable of reflecting the hydrologic runoff rule of the current sub-watershed.
The step 3 comprises the following steps:
taking the minimum of flood control risk FCR and power generation vulnerability PGR of the cascade reservoir as an objective function, the mathematical expression is as follows:
，
，
wherein,and->The first part of the step reservoir>Flood control risk and power generation fragility at any moment;
is->Reservoir->Reservoir capacity at any moment;
and->Respectively +.>The reservoir has normal water storage level reservoir capacity and flood control water limit reservoir capacity;
is->Reservoir->Output of time unit，/>，/>Is->Output coefficient of reservoir->Is->Reservoir->Power flow at time, < > on>Is->Reservoir->An average power generation water head at the moment;
and->Respectively +.>The upper limit and the lower limit of the output of the reservoir unit;
y is the number of years in the scheduling period;
t is the number of study periods per year;
m is the number of step reservoirs.
The step 4 comprises the following steps:
the Gaussian radial basis function of the coupling set runoff forecast information is selected to construct a reservoir multi-objective scheduling rule, and the mathematical expression is as follows:
，
in the method, in the process of the invention,and->Representing the first day, the second day and the +.>Weather forecast traffic information; />And->The number of radial basis functions respectively representing different forecasting periods, < >>Andthe +.f corresponding to the first day forecast information respectively>Radial basis functions and weights thereof; />Andand->And the same is done; />For the traditional Gaussian radial basis function scheduling rule without considering the set forecast information, the current reservoir capacity state, the real-time reservoir flow and the corresponding time period of the reservoir are generally taken as inputs/>U is the number of radial basis functions, and each radial basis function expression is:
，
wherein E is an input vectorThe number of tuples; />And->Corresponding->A radial basis function center and a radius moment.
In a second aspect, embodiments of the present application provide a cascade reservoir multi-objective optimization scheduling system coupled with aggregated forecast information, comprising a data integration module, a runoff forecast model training module, a reservoir scheduling model building module, and a model solving module,
the data integration module is used for collecting watershed hydrological data;
the runoff forecasting model training module obtains the warehouse-in runoff forecasting values of each reservoir in the cascade reservoirs under different forecasting periods by adopting an artificial intelligence method;
the reservoir dispatching model building module determines an optimization target of cascade reservoir joint operation dispatching, sets reservoir dispatching constraint conditions and builds a reservoir dispatching model;
the model solving module is used for constructing a reservoir multi-objective dispatching rule coupling the set runoff forecast information by adopting a Gaussian radial basis function based on the set runoff forecast information and the cascade reservoir optimal dispatching model, and optimizing and solving by adopting a multi-objective intelligent optimizing method to obtain a final cascade reservoir short-term optimal dispatching scheme.
In a third aspect, embodiments of the present application provide a computer readable storage medium storing program code which, when executed by a processor, implements the steps of a step reservoir multi-objective optimized scheduling method for coupling aggregated forecast information as described above.
Compared with the prior art, the invention has the beneficial effects that:
1. scientific and reasonable, and is close to engineering practice:
the invention adopts an advanced artificial intelligence technology, can timely capture the influence of complex human activities such as upstream water reservoir scheduling, and accurately delineates the uncertainty of the warehouse-in forecast runoff of the downstream cascade reservoir by utilizing the aggregate rainfall forecast product issued by the meteorological mechanism, thereby providing a certain possibility for serving the scientific forecast scheduling of the cascade reservoir.
2. Can provide important and strong reference basis for reservoir dispatching:
the cascade reservoir multi-objective scheduling rule of coupling the integrated runoff forecast information is skillfully constructed by fully utilizing the cascade reservoir integrated runoff forecast (ESP) information, an intelligent optimization algorithm is utilized to search an optimal solution which simultaneously meets the minimum flood control risk rate and the minimum power generation fragility, the power generation benefit of the reservoirs can be improved to the greatest extent on the premise of not increasing the flood control risk of the cascade reservoirs, and the cascade reservoir multi-objective scheduling method is suitable for further popularization and application in cascade reservoir or reservoir group flood recycling scheduling.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of correction of forecast precipitation frequency distribution;
FIG. 3 is a schematic illustration of a step reservoir;
FIG. 4 is a schematic diagram of a three-layer long and short term memory neural network;
FIG. 5 is a graph showing the average value of aggregate runoff forecast flows and the aggregate forecast intervals of 90% for various forecast periods for a river basin in accordance with an exemplary embodiment;
FIG. 6 is a diagram of a multi-objective optimized scheduling result according to various embodiments.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The terms "first," "second," and the like, are used merely to distinguish one entity or action from another entity or action, and are not to be construed as indicating or implying any actual such relationship or order between such entities or actions.
The specific implementation flow of the invention is shown in fig. 1, and the steps are as follows:
and step 1, collecting hydrologic data of the river basin.
Collecting hydrologic data, including historical meteorological data (such as rainfall, evaporation and the like), historical runoff data, meteorological conditions of a forecast period, initial states of the river basin and the like, wherein the initial states of the river basin mainly comprise soil water content and can be obtained through calculation of a hydrologic model of the river basin, and the obtaining of the initial states of the river basin belongs to a conventional technology in the technical field; the weather conditions in the forecast period mainly comprise precipitation forecast products, which are usually required to be corrected and then are suitable for precipitation forecast, and the specific embodiment adopts a frequency distribution correction method, and the schematic diagram is shown in fig. 2, namely, the frequency distribution curves of the observed precipitation sequence and the forecast precipitation sequence are matched.
The method is specifically described by taking a step reservoir of a river at the downstream of Jinshajiang, namely a step reservoir towards a home dam as an example. The upstream hydrologic observation points of the Xiluo reservoir are three piles of control stations. The station is positioned at about 3.6km downstream of the confluence point of two rivers of Jinsha river and ya-huli river, and the control area is 38.86 km 2 . Three piles of Xiluo ferry the area of the section between the stream and the dam is about 6.58 km respectively 2 And 0.44 km 2 . Table 1 lists the deviation conditions before and after correction of three piles-Hua-Marble and Hua-xi Luo two intervals 1-3 d accumulated precipitation forecast. As can be seen from table 1, the frequency distribution correction model has a good correction effect. As the prediction period increases, the deviation correcting effect becomes more remarkable. Therefore, the frequency distribution correction method is considered to have better applicability to quantitative precipitation prediction correction in the area.
TABLE 1 error contrast (unit: mm) of cumulative forecast water quantity 1 to 3 days before and after precipitation forecast correction
Step 2, obtaining a reservoir entering runoff forecast value of each reservoir in the step reservoir under different foreseeing periods by adopting an artificial intelligence method;
this step is a conventional technique in the art, and will be described in detail for ease of understanding.
In the specific embodiment, the step reservoir is divided into a plurality of sub-watershed according to the geographical distribution position of the reservoir, a three-layer long-short-period memory neural network (LSTM) model is respectively built for each sub-watershed, historical observed rainfall, weather temperature, wind speed and other meteorological data and historical related runoff data are used as inputs, current time observed runoff is used as output, hydrologic data are divided into regular rate, verification period and test period, and training and optimization are carried out to obtain a black box model capable of reflecting the hydrologic runoff law of the current sub-watershed.
Assuming that the step reservoir studied comprises N reservoirs, as shown in fig. 3, then the following N runoff forecasting models will be obtained:
reservoir 1 represents a tap reservoir whose hydrologic process may be approximated as a natural runoff process unaffected by human activity. Because the rest reservoirs in the cascade reservoirs have a certain hydraulic connection, the lower discharge flow of the upper reservoir influences the storage flow of the lower reservoir, and therefore, for the downstream reservoirs 2, 3, … and N of the tap reservoirs, the current reservoir runoff forecast value is also related to the upstream adjacent reservoir discharge flow.
For reservoir 2, the runoff hydrologic model obtained by optimizing is denoted as LSTM2;
for the reservoir n, the runoff hydrologic model obtained by optimizing the reservoir n is marked as LSTMn;
for reservoir N, the runoff hydrologic model obtained by optimizing is denoted as LSTMN.
The present embodiment will further describe a reservoir-in flow runoff forecasting process by using a three-layer long-short-term memory neural network (LSTM), wherein the Seq2One structure is shown in fig. 4, each memory unit comprises an input gate, a forgetting gate and an output gate control, and the mathematical expression is as follows:
，
in the formulae (1) to (5),，/>，/>and->Respectively->Inputting variables at any time, forgetting the gate, inputting the gate and outputting the gate state; />And->Current +.>Time cell state and hidden layer state; />And->Then represent one +.>A time status value; w, U and b represent input weights, implicit layer weights and bias terms; />Activating a function for Sigmoid;is a hyperbolic tangent activation function; />Is a matrix element product.
Then, carrying out deterministic and uncertainty evaluation on forecast runoffs in different foreseeing periods of reservoir storage:
，
in the formulae (6) to (11),and->Respectively->Observing the flow at moment and forecasting the average flow in a set; />And->Respectively the average value of two different sequences; />And->Respectively set forecast->Forecasting the maximum value and the minimum value of the flow at the moment; t is the time series length. NSE, RMSE and +.>The typical deterministic evaluation indexes of the hydrologic flow simulation are Nash efficiency coefficient, root mean square error and correlation coefficient respectively; CR, B and D represent aggregate forecast flow uncertainty evaluation indexes, which are coverage, bandwidth and offset respectively.
Taking the flow process of the river in the flood season of 2013 as an example, fig. 5 shows the average value of the aggregate forecast flow in different forestation periods and the aggregate forecast flow interval of 90%, and comparing the aggregate forecast flow interval with the actual measurement flow process line, it can be seen that the fitting effect of the aggregate forecast flow interval and the actual measurement flow series is good.
And step 3, determining an optimization target of the cascade reservoir joint operation scheduling, setting reservoir scheduling constraint conditions, and establishing a reservoir scheduling model.
Taking the minimum of the flood prevention risk (FCR) and the power generation vulnerability (PGR) of the cascade reservoir as an objective function, the mathematical expression is as follows:
，
wherein, the method comprises the steps of,and->The first part of the step reservoir>Flood control risk and power generation fragility at any moment;
is->Reservoir->Reservoir capacity at any moment;
and->Respectively +.>The reservoir has normal water storage level reservoir capacity and flood control water limit reservoir capacity;
is->Reservoir->Output of time unit>，/>Is->Output coefficient of reservoir->Is->Reservoir->Power flow at time, < > on>Is->Reservoir->An average power generation water head at the moment;
and->Respectively +.>The upper limit and the lower limit of the output of the reservoir unit;
y is the number of years in the scheduling period;
t is the number of study periods per year;
m is the number of step reservoirs.
The following constraints are considered in this implementation:
(a) Reservoir water balance equation:
，
in the formula (14), the amino acid sequence of the compound,are respectively->Reservoir at->The water storage capacity is started and stopped in each scheduling period,and->Are respectively->Reservoir->The warehouse-in flow, the warehouse-out flow, the infiltration flow, the evaporation flow and the like in the period,to calculate the step size.
(b) Reservoir downflow constraints:
（15）
in the formula (15), the amino acid sequence of the compound,is->Reservoir->The minimum drainage flow of the time period is generally commonly given by downstream irrigation, ecological, shipping or water supply requirements; />Is->Reservoir->The time period allows maximum downflow, affected by reservoir capacity and reservoir downstream flood control requirements.
(c) Reservoir capacity constraint:
（16）
in the formula (16), the amino acid sequence of the compound,and->Respectively +.>Reservoir->The time period reservoir allows for minimum and maximum water storage.
(d) And (3) unit output limit:
（17）
in the formula (17), the amino acid sequence of the compound,and->Respectively +.>The reservoir allows for minimum and maximum forces.
(e) Water flow connection between step reservoirs:
（18）
in the formula (18), the training LSTM model is utilized to describe the evolution process of the upstream and downstream two reservoir river channels with hydraulic connection.
And 4, constructing a reservoir multi-objective scheduling rule of coupling the set runoff forecast information by adopting a Gaussian radial basis function based on the set runoff forecast information and the cascade reservoir optimal scheduling model, and optimizing and solving by adopting a multi-objective intelligent optimization method to obtain a final cascade reservoir short-term optimal scheduling scheme.
In the specific embodiment, a Gaussian radial basis function for coupling set runoff forecast information is selected to construct a reservoir multi-target scheduling rule, and the mathematical expression is as follows:
，
in the formula (19), the amino acid sequence of the compound,and->Representing the first day, the second day and the +.>Weather forecast traffic information; />And->The number of radial basis functions respectively representing different forecasting periods,and->The +.f corresponding to the first day forecast information respectively>Radial basis functions and weights thereof;and->And->And the same is done; />For the traditional Gaussian radial basis function scheduling rule without considering the set forecast information, the current reservoir capacity state, the real-time reservoir flow and the corresponding time period of the reservoir are generally taken as inputs +.>U is the number of radial basis functions, and each radial basis function expression is:
（20）
in the formula (20), E is an input vectorThe number of tuples; />And->Corresponding->A radial basis function center and a radius moment.
The embodiment adopts a second generation non-dominant sequencing genetic algorithm (NSGA-II) which is mature in the reservoir dispatching multi-objective optimization problem to optimize and obtain the cascade reservoir short-term joint operation optimization dispatching scheme.
In the embodiment, the NSGA-II intelligent algorithm is adopted to optimize the cascade reservoir dispatching rules by taking flood control risk rate and power generation fragility as optimization targets. Wherein, the NSGA-II algorithm sets the population number as 64, the algebra as 500, and the crossover and mutation probabilities are respectively 0.9 and 0.1. The multi-objective scheduling result considering the aggregate runoff forecast information is shown in fig. 6, and is compared with the optimization result which does not consider the aggregate runoff forecast and the original design scheduling scheme. Taking the optimal solution of the power generation vulnerability as an example, as shown in table 2, compared with the original design scheme, the water head of the reservoir is properly raised in a forecasting mode, and the water resource utilization rate can be remarkably improved and annual average power generation capacity is improved by 10.36 hundred million kW.h under the condition of controllable flood control risk in the aggregate forecasting scheme II; compared with the scheme I without considering the set forecast, the method can increase the generated energy by 3.67 hundred million kW.h under the condition that the risk is almost unchanged, and has remarkable economic and environmental benefits.
Table 2 comparison of evaluation index of different optimized scheduling schemes
In summary, the uncertainty of short-term prediction of reservoir runoff in storage is considered, the artificial precipitation products corrected by different weather prediction centers are utilized, and the reservoir runoff prediction models in different prediction periods are established based on three layers of long-short-term memory models (LSTM); then, a Gaussian radial basis function cascade reservoir dispatching rule for coupling set runoff forecast information is provided, a multi-objective intelligent search algorithm is adopted, and a cascade reservoir optimal dispatching scheme with minimum flood control risk rate and power generation fragility under the condition that reservoir dispatching constraint conditions are met is solved, so that important and high-operability reference basis can be provided for short-term actual operation dispatching of the cascade reservoir.
Embodiments of the present application provide a computer readable storage medium storing program code which, when executed by a processor, implements the steps of a method for rapidly calculating a reservoir tributary backward flow water amount as described above.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
The foregoing is merely exemplary embodiments of the present application and is not intended to limit the scope of the present application, and various modifications and variations may be suggested to one skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims (4)

1. The cascade reservoir multi-objective optimization scheduling method for coupling set forecast is characterized by comprising the following steps of:
step 1, collecting hydrologic data of a river basin;
step 2, obtaining a reservoir entering runoff forecast value of each reservoir in the step reservoir under different foreseeing periods by adopting an artificial intelligence method;
step 3, determining an optimization target of cascade reservoir joint operation scheduling, setting reservoir scheduling constraint conditions, and establishing a reservoir scheduling model;
step 4, constructing reservoir multi-objective scheduling rules for coupling the set runoff forecast information by adopting a Gaussian radial basis function based on the set runoff forecast information and a cascade reservoir optimal scheduling model, and optimizing and solving by adopting a multi-objective intelligent optimization method to obtain a final cascade reservoir short-term optimal scheduling scheme;
the implementation of said step 2 is as follows,
dividing a cascade reservoir into a plurality of sub-watercourses according to geographical distribution positions of the reservoir, respectively establishing three layers of long-short-period memory neural network LSTM models for each sub-watercourse, taking historical observed precipitation, air temperature, wind speed meteorological data and historical related runoff data as inputs, taking current time observed runoffs as outputs, dividing hydrologic data into regular rates, verification periods and test periods, and training and optimizing to obtain a black box model capable of reflecting the hydrologic runoff rules of the current sub-watercourses;
the step 3 comprises the following steps: risk for flood control in step reservoirFCRDegree of weakness of power generationPGRThe minimum is an objective function, and the mathematical expression is as follows:
，
，
wherein,and->The first part of the step reservoir>Flood control risk and power generation fragility at any moment;
is->Reservoir->Reservoir capacity at any moment;
and->Respectively +.>The reservoir has normal water storage level reservoir capacity and flood control water limit reservoir capacity;
is->Reservoir->Output of time unit>，/>Is->The output coefficient of the reservoir,is->Reservoir->Power flow at time, < > on>Is->Reservoir->An average power generation water head at the moment;
and->Respectively +.>The upper limit and the lower limit of the output of the reservoir unit;
y is the number of years in the scheduling period;
t is the number of study periods per year;
m is the number of step reservoirs.
2. The coupled set forecast step reservoir multi-objective optimization scheduling method according to claim 1, wherein the step 4 comprises:
based on the aggregate runoff forecast information and the cascade reservoir optimal scheduling model, a reservoir multi-objective scheduling rule for coupling the aggregate runoff forecast information is constructed by adopting a Gaussian radial basis function, and the mathematical expression is as follows:
，
in the method, in the process of the invention,and->Representing the first day, the second day and the +.>Weather forecast traffic information; />And->The number of radial basis functions respectively representing different forecasting periods, < >>And->The +.f corresponding to the first day forecast information respectively>Radial basis functions and weights thereof; />And->Andand the same is done; />For the traditional Gaussian radial basis function scheduling rule without considering the set forecast information, the current reservoir capacity state, the real-time reservoir flow and the corresponding time period of the reservoir are generally taken as inputs +.>，
UFor its radial basis function number, each radial basis function expression is:
，
in the method, in the process of the invention,Efor inputting vectorsThe number of tuples; />And->Corresponding->A radial basis function center and a radius moment.
3. A coupled aggregate forecast cascade reservoir multi-objective optimization scheduling system for realizing the method as set forth in claim 1 or 2, comprising a data integration module, a runoff forecast model training module, a reservoir scheduling model building module and a model solving module,
the data integration module is used for collecting watershed hydrological data;
the runoff forecasting model training module obtains the warehouse-in runoff forecasting values of each reservoir in the cascade reservoirs under different forecasting periods by adopting an artificial intelligence method;
the reservoir dispatching model building module determines an optimization target of cascade reservoir joint operation dispatching, sets reservoir dispatching constraint conditions and builds a reservoir dispatching model;
the model solving module is used for constructing a reservoir multi-objective dispatching rule coupling the set runoff forecast information by adopting a Gaussian radial basis function based on the set runoff forecast information and the cascade reservoir optimal dispatching model, and optimizing and solving by adopting a multi-objective intelligent optimizing method to obtain a final cascade reservoir short-term optimal dispatching scheme.
4. A computer readable storage medium storing program code which, when executed by a processor, implements the steps of the coupled set forecast step reservoir multi-objective optimization scheduling method of any of claims 1 or 2.
CN202311629304.XA 2023-12-01 2023-12-01 Multi-objective optimization scheduling method and system for cascade reservoir of coupling set forecast Active CN117332908B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311629304.XA CN117332908B (en) 2023-12-01 2023-12-01 Multi-objective optimization scheduling method and system for cascade reservoir of coupling set forecast

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311629304.XA CN117332908B (en) 2023-12-01 2023-12-01 Multi-objective optimization scheduling method and system for cascade reservoir of coupling set forecast

Publications (2)

Publication Number Publication Date
CN117332908A CN117332908A (en) 2024-01-02
CN117332908B true CN117332908B (en) 2024-02-13

Family

ID=89293828

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311629304.XA Active CN117332908B (en) 2023-12-01 2023-12-01 Multi-objective optimization scheduling method and system for cascade reservoir of coupling set forecast

Country Status (1)

Country Link
CN (1) CN117332908B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117541019B (en) * 2024-01-04 2024-03-26 长江水利委员会水文局 Long-term robust optimal scheduling method, system and storage medium in cascade reservoir

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007081519A2 (en) * 2005-12-30 2007-07-19 Steven Kays Genius adaptive design
CN104268653A (en) * 2014-09-28 2015-01-07 武汉大学 Cascade reservoir optimal scheduling method based on ESP
AR109623A1 (en) * 2018-02-16 2019-01-09 Pescarmona Enrique Menotti PROCESS AND SYSTEM OF ANALYSIS AND HYDROLOGICAL MANAGEMENT FOR BASINS
WO2019237440A1 (en) * 2018-06-12 2019-12-19 清华大学 Quantile probabilistic short-term power load prediction integration method
CN111695290A (en) * 2020-05-14 2020-09-22 天津大学 Short-term runoff intelligent forecasting hybrid model method suitable for variable environment
CN112184479A (en) * 2020-09-17 2021-01-05 长江水利委员会水文局 Reservoir group dispatching rule type and parameter adaptability research method for climate change
CN112700068A (en) * 2021-01-15 2021-04-23 武汉大学 Reservoir dispatching rule optimization method based on machine learning fusion of multi-source remote sensing data
CN112711896A (en) * 2021-01-05 2021-04-27 浙江大学 Complex reservoir group optimal scheduling method considering multi-source forecast error uncertainty
WO2021130512A1 (en) * 2019-12-23 2021-07-01 Total Se Device and method for predicting values of porosity lithofacies and permeability in a studied carbonate reservoir based on seismic data
WO2021218457A1 (en) * 2020-04-28 2021-11-04 中国长江三峡集团有限公司 Method for performing runoff forecast under influence of upstream reservoir group by using forecast errors
CN113723024A (en) * 2021-08-30 2021-11-30 浙江大学 Method for simulating 'stream' -river channel '-river mouth' distributed flood process suitable for coastal areas
CN113935603A (en) * 2021-09-29 2022-01-14 中水珠江规划勘测设计有限公司 Reservoir group multi-target forecast pre-discharge scheduling rule optimization method, system and medium
CN115640881A (en) * 2022-10-09 2023-01-24 河海大学 Reservoir water level correction method of reservoir warehousing runoff forecasting model based on LSTM
CN116109458A (en) * 2022-11-22 2023-05-12 华能澜沧江水电股份有限公司 Reservoir flood discharge gate scheduling method, system, storage medium and computing equipment
EP4216117A1 (en) * 2022-01-21 2023-07-26 China Three Gorges Co., Ltd. Method and apparatus for training water-and-sediment prediction model for reservoir and method and apparatus for predicting water-and-sediment in reservoir
WO2023216780A1 (en) * 2022-05-12 2023-11-16 华能澜沧江水电股份有限公司 Peak regulation optimization scheduling method for cascaded hydro-photovoltaic complementary power generation system

Patent Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007081519A2 (en) * 2005-12-30 2007-07-19 Steven Kays Genius adaptive design
CN104268653A (en) * 2014-09-28 2015-01-07 武汉大学 Cascade reservoir optimal scheduling method based on ESP
AR109623A1 (en) * 2018-02-16 2019-01-09 Pescarmona Enrique Menotti PROCESS AND SYSTEM OF ANALYSIS AND HYDROLOGICAL MANAGEMENT FOR BASINS
WO2019237440A1 (en) * 2018-06-12 2019-12-19 清华大学 Quantile probabilistic short-term power load prediction integration method
WO2021130512A1 (en) * 2019-12-23 2021-07-01 Total Se Device and method for predicting values of porosity lithofacies and permeability in a studied carbonate reservoir based on seismic data
WO2021218457A1 (en) * 2020-04-28 2021-11-04 中国长江三峡集团有限公司 Method for performing runoff forecast under influence of upstream reservoir group by using forecast errors
CN111695290A (en) * 2020-05-14 2020-09-22 天津大学 Short-term runoff intelligent forecasting hybrid model method suitable for variable environment
CN112184479A (en) * 2020-09-17 2021-01-05 长江水利委员会水文局 Reservoir group dispatching rule type and parameter adaptability research method for climate change
CN112711896A (en) * 2021-01-05 2021-04-27 浙江大学 Complex reservoir group optimal scheduling method considering multi-source forecast error uncertainty
CN112700068A (en) * 2021-01-15 2021-04-23 武汉大学 Reservoir dispatching rule optimization method based on machine learning fusion of multi-source remote sensing data
CN113723024A (en) * 2021-08-30 2021-11-30 浙江大学 Method for simulating 'stream' -river channel '-river mouth' distributed flood process suitable for coastal areas
CN113935603A (en) * 2021-09-29 2022-01-14 中水珠江规划勘测设计有限公司 Reservoir group multi-target forecast pre-discharge scheduling rule optimization method, system and medium
EP4216117A1 (en) * 2022-01-21 2023-07-26 China Three Gorges Co., Ltd. Method and apparatus for training water-and-sediment prediction model for reservoir and method and apparatus for predicting water-and-sediment in reservoir
WO2023216780A1 (en) * 2022-05-12 2023-11-16 华能澜沧江水电股份有限公司 Peak regulation optimization scheduling method for cascaded hydro-photovoltaic complementary power generation system
CN115640881A (en) * 2022-10-09 2023-01-24 河海大学 Reservoir water level correction method of reservoir warehousing runoff forecasting model based on LSTM
CN116109458A (en) * 2022-11-22 2023-05-12 华能澜沧江水电股份有限公司 Reservoir flood discharge gate scheduling method, system, storage medium and computing equipment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Long-Short Term Echo State Network for Time Series Prediction;zheng kaihong;IEEE Access;第91961-91974页 *
一种考虑径流预报及其不确定性的水库优化调度模型;唐国磊 等;水利学报;第42卷(第6期);第641-647页 *

Also Published As

Publication number Publication date
CN117332908A (en) 2024-01-02

Similar Documents

Publication Publication Date Title
Suwal et al. Optimisation of cascade reservoir operation considering environmental flows for different environmental management classes
Liu et al. Deriving reservoir operation rule based on Bayesian deep learning method considering multiple uncertainties
Li et al. Dynamic control of flood limited water level for reservoir operation by considering inflow uncertainty
CN108109076B (en) Method for analyzing risk of abandoned water in power generation dispatching of cascade hydropower station group by considering runoff forecasting
CN117332908B (en) Multi-objective optimization scheduling method and system for cascade reservoir of coupling set forecast
CN108764515A (en) A kind of reservoir operation Application of risk decision method of Coupled Numerical meteorological model DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM
Avesani et al. Short-term hydropower optimization driven by innovative time-adapting econometric model
Meng et al. Flood control operation coupled with risk assessment for cascade reservoirs
CN112184479B (en) Reservoir group dispatching rule type and parameter adaptability research method for climate change
Tan et al. Two-stage stochastic optimal operation model for hydropower station based on the approximate utility function of the carryover stage
Mohammad Ashrafi Two-stage metaheuristic mixed integer nonlinear programming approach to extract optimum hedging rules for multireservoir systems
CN114492233B (en) Watershed water simulation method based on webGIS platform and considering comprehensive utilization requirements
Yan et al. A novel IBAS-ELM model for prediction of water levels in front of pumping stations
Mansouri et al. An improved MOPSO algorithm for multi-objective optimization of reservoir operation under climate change
Li et al. Research on short-term joint optimization scheduling strategy for hydro-wind-solar hybrid systems considering uncertainty in renewable energy generation
Liu et al. Quantifying streamflow predictive uncertainty for the optimization of short-term cascade hydropower stations operations
CN110707682B (en) Fuzzy C-means clustering-based method for configuring water, wind and light power supply capacity in micro-grid
Verma et al. Optimizing Multi-reservoir Systems with the Aid of Genetic Algorithm: Mahanadi Reservoir Project Complex, Chhattisgarh
Deng et al. A Survey of the Researches on Grid-Connected Solar Power Generation Systems and Power Forecasting Methods Based on Ground-Based Cloud Atlas
Liu et al. Effect of the quality of streamflow forecasts on the operation of cascade hydropower stations using stochastic optimization models
CN116756498A (en) Runoff probability prediction algorithm based on LSTM and quantile regression
de Souza Zambelli et al. Advantages of deterministic optimization in long-term hydrothermal scheduling of large-scale power systems
CN114548609B (en) Water resource collaborative allocation method for ecological power generation and water supply
CN115496128A (en) Urban waterlogging risk forecasting method based on raininess-raininess characteristic parameter combined distribution
Yi et al. Optimal operation of urban tidal drainage pumping station based on genetic algorithm coupled with head-water level successive approximation

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant