CN107657349B - Method for extracting scheduling rules of staged power generation of reservoir - Google Patents

Method for extracting scheduling rules of staged power generation of reservoir Download PDF

Info

Publication number
CN107657349B
CN107657349B CN201710974332.3A CN201710974332A CN107657349B CN 107657349 B CN107657349 B CN 107657349B CN 201710974332 A CN201710974332 A CN 201710974332A CN 107657349 B CN107657349 B CN 107657349B
Authority
CN
China
Prior art keywords
reservoir
model
power generation
scheduling
simulation
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
CN201710974332.3A
Other languages
Chinese (zh)
Other versions
CN107657349A (en
Inventor
郭玉雪
方国华
万峰
黄显峰
贾永乐
罗乾
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.)
Hohai University HHU
Original Assignee
Hohai University HHU
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 Hohai University HHU filed Critical Hohai University HHU
Priority to CN201710974332.3A priority Critical patent/CN107657349B/en
Publication of CN107657349A publication Critical patent/CN107657349A/en
Application granted granted Critical
Publication of CN107657349B publication Critical patent/CN107657349B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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"
    • E—FIXED CONSTRUCTIONS
    • E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
    • E02B—HYDRAULIC ENGINEERING
    • E02B9/00—Water-power plants; Layout, construction or equipment, methods of, or apparatus for, making same
    • 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
    • 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
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/20—Hydro energy

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Civil Engineering (AREA)
  • Structural Engineering (AREA)
  • Educational Administration (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Mechanical Engineering (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a method for extracting a reservoir stage power generation dispatching rule, which comprises the steps of analyzing and screening stage influence factors based on grey correlation, respectively adopting a multivariate nonlinear regression model, a support vector machine model and a BP artificial neural network model to fit to obtain a stage reservoir power generation dispatching function, and carrying out multi-model weighted average by using a Bayesian model averaging method to obtain a final stage reservoir power generation dispatching function. According to the reservoir scheduling rule simulation method, GRA is introduced into reservoir scheduling rule simulation for screening influence factors, redundant attributes are removed, model complexity is reduced, and model simulation efficiency is improved; the GRA and the BMA are combined to realize the staged extraction of the reservoir power generation rule, the problem that the relevance of decision variables and influence factors to the reservoir power generation rule in different periods in reservoir scheduling is inconsistent can be balanced, the uncertainty of a single model caused by a model structure is balanced, and the model simulation precision is improved; the requirement of extracting the power generation dispatching rule of the reservoir is met, and the benefit of determinacy optimization dispatching in the aspect of the power generation process can be well inherited.

Description

Method for extracting scheduling rules of staged power generation of reservoir
Technical Field
The invention relates to the field of water conservancy and hydropower, in particular to a method for extracting a scheduling rule of staged power generation of a reservoir.
Background
Reservoir optimization scheduling research began in 1955, and a series of great theoretical achievements on optimization scheduling models have been achieved so far due to the fact that more hydropower operation benefits can be obtained. However, the deterministic optimization scheduling model is often operated on the premise that runoff is known, and the reservoir actual operation scheduling cannot be guided. Therefore, how to summarize the reservoir optimal operation rule in the optimal process obtained by the reservoir optimal scheduling model to form the scheduling rule has important practical significance for guiding the actual operation of the reservoir and improving the hydropower benefit of the reservoir.
At present, the most common expression form of reservoir dispatching rules is a dispatching graph and a dispatching function. Compared with a dispatching graph, the reservoir optimization result extraction of the dispatching function based on the deterministic optimization model can better inherit the benefits of deterministic optimization dispatching in the aspects of generating capacity, ensuring output and the like. The scheduling function extraction method mainly comprises two categories of statistical regression method and intelligent algorithm, however, most of the scheduling function researches do not carry out influence factor screening operation at present, and the research on the selection method of the influence factors is started. The preliminarily selected influence factors are more, the difficulty of the model is increased if the influence factors are considered completely, the accuracy of model simulation is also reduced, and how to find out the key factors from the factors has important practical significance for effectively carrying out scheduling rule simulation on the influence factors with higher application relevance.
At present, reservoir dispatching rule research is mainly realized by a single model. Practice shows that no model can be determined to be superior to other models under any condition, and the simulation result obtained by applying a single model cannot avoid uncertainty caused by the model structure. Therefore, providing a multi-model synthetic simulation result with a high-precision mean value is an important research direction.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a method for extracting a reservoir stage power generation dispatching rule aiming at the difference of the prior art, solves the problems that most dispatching rule researches are not carried out with influence factor screening operation and the relevance of decision variables and influence factors is inconsistent in different time periods, and provides a multi-model synthesis dispatching rule with higher precision mean value meaning based on BMA, thereby providing theoretical basis and scientific support for actual optimized operation of hydropower stations.
The technical scheme is as follows: the invention provides a method for extracting a reservoir staged power generation dispatching rule, which comprises the following steps of:
(1) establishing a deterministic reservoir optimization scheduling model taking a maximum power generation target, a water balance constraint, a water level constraint, an output constraint, a let-down flow constraint and a unit flow capacity as constraints, and solving by using dynamic programming;
(2) determining a decision variable and an influence factor attribute set based on a deterministic reservoir optimization model result;
(3) screening staging influence factors based on grey correlation analysis (GRA);
(4) fitting by adopting a multivariate nonlinear regression Model (MNLRA), a support vector machine model (SVM) and a BP artificial neural network model (BP) respectively to obtain a staged reservoir power generation scheduling function;
(5) and carrying out multi-model weighted average by applying a Bayesian model average method (BMA) to obtain a final staged reservoir power generation scheduling function.
Further, the decision variable in the step (2) is the reservoir time interval output NtThe attribute set of the influence factors comprises the initial water level of the reservoir time interval
Figure BDA0001436885130000028
Natural tap water QtAnd the superposed water level
Figure BDA0001436885130000024
Water energy in storage
Figure BDA0001436885130000025
Reservoir energy storage
Figure BDA0001436885130000026
Interaction item of reservoir energy input and energy storage
Figure BDA0001436885130000027
Further, the step (3) comprises the following steps:
(31) and respectively constructing a reference number sequence consisting of decision variables and a comparison number sequence consisting of influence factors under each month, and carrying out non-dimensionalization:
reference series: x(0)＝{N1，N2，…，Nt…，NT} (1)
Comparing the number series:
Figure BDA0001436885130000021
where T denotes time T, T denotes a calculation period, T is 1,2, …, T;
(32) and solving the grey correlation coefficient of the reference number sequence and the comparison number sequence:
Figure BDA0001436885130000022
in the formula, X(i)Rho is a resolution coefficient and is generally in the range of 0-1 in order to compare the ith row of the array X;
(33) calculating the correlation degree of the influence factors relative to the decision variables, wherein the correlation degree
Figure BDA0001436885130000023
Is a reference number sequence X(0)(t) and comparison series X(i)(t) a correlation coefficient at a t-th point;
(34) performing association sorting, and respectively determining the output N of the month-by-month and the reservoir time interval according to the association sorting result of each monthtAnd the factor with stronger relevance is used as an influence factor of the final scheduling rule simulation.
Further, the step (4) comprises the following steps:
(41) determining the reservoir period output N by taking the influence factors determined under each month as input vectors and determining variablestAs an output vector; determining training samples and testing samples, wherein the number of the samples is M, the number of the training samples is N, and the number of the testing samples is M-N;
(42) respectively adopting a multivariate nonlinear regression Model (MNLRA), a support vector machine model (SVM) and a BP artificial neural network model (BP) to simulate a training sample to obtain a reservoir power generation dispatching function;
(43) testing the simulation scheduling function by using a test sample, and evaluating the simulation precision of the model by using a Root Mean Square Error (RMSE) and a Deterministic Coefficient (DC), wherein the simulation precision values of a Support Vector Machine (SVM) and a BP artificial neural network model (BP) are judged, and if the RMSE is less than 50 and the DC is more than 0.5, the simulation scheduling function is determined; if not, adjusting parameters of a support vector machine model (SVM) and a BP artificial neural network model (BP), and carrying out function simulation again;
RMSE and DC are calculated according to equations (4) and (5), respectively:
Figure BDA0001436885130000031
Figure BDA0001436885130000032
in the formula (I), the compound is shown in the specification,
Figure BDA0001436885130000033
actual force output value at time t, MW;
Figure BDA0001436885130000034
simulating a force value MW for the time t;
Figure BDA0001436885130000035
mean actual force output value, MW.
Further, the step (5) comprises the steps of:
(51) adopting the output result N of the deterministic optimization model based on the Bayesian model average method (BMA) in each monthtEvaluating the simulation results of a multivariate nonlinear regression Model (MNLRA), a Support Vector Machine (SVM) and a BP artificial neural network model (BP), thereby obtaining the weight of each model;
(52) and obtaining a final stage scheduling function according to the weighted average of the weight of the three models, namely a multivariate nonlinear regression Model (MNLRA), a support vector machine model (SVM) and a BP artificial neural network model (BP).
Has the advantages that: according to the reservoir scheduling rule simulation method, GRA is introduced into reservoir scheduling rule simulation for screening influence factors, redundant attributes are removed, model complexity is reduced, and model simulation efficiency is improved; the GRA and the BMA are combined to realize the staged extraction of the reservoir power generation rule, the problem that the relevance of decision variables and influence factors to the reservoir power generation rule in different periods in reservoir scheduling is inconsistent can be balanced, the uncertainty of a single model caused by a model structure is balanced, and the model simulation precision is improved; the method meets the requirement of extracting the power generation dispatching rule of the reservoir, can better inherit the benefit of deterministic optimal dispatching in the aspect of power generation process, realizes the aim of guiding the actual optimal operation of the reservoir on the premise of uncertain water supply, and improves the power generation benefit of the hydropower station.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIGS. 2 (a) - (1) are graphs of correlation between monthly simulated force out values and optimized force out values for the BMA and the 3 models that make up it under optimized scheduling;
FIG. 3 is a comparison graph of long series of simulated force values versus optimized force values for the BMA and the 3 models that make up it under optimized scheduling.
Detailed Description
The technical solution of the present invention is described in detail below, but the scope of the present invention is not limited to the embodiments.
Example (b): a method for extracting a scheduling rule of staged power generation of a reservoir, as shown in fig. 1, in this embodiment, a new ampere river hydropower station is taken as an example for explanation. The water power station of Xinan river is the first large water power station designed and self-made by China and built by self, the river length above the dam site is 323km, and the basin area is 10442km2. The reservoir of Xinanjiang takes power generation as a main part, has comprehensive functions of flood control, irrigation, fishery, shipping, travel and the like, and has the performance of adjusting for many years, and the installed capacity of a power station is 810.0 MW. In the embodiment, hydrological year runoff data from 1962 to 2008 is adopted, the average running water level of multiple years of 98.4m is used as the starting water level, a month is used as a time period, the maximum total generated energy in a dispatching period is used as a target, and a dynamic programming method (DP) is used to obtain the optimal dispatching result of the Xinanjiang hydropower station long series.
First, based on GRA, the association degree of each influence factor to the decision variable is calculated, and the final influence factor is determined as shown in table 1:
TABLE 1 monthly association calculation under optimized scheduling and final impact factor screening results
Figure BDA0001436885130000041
Figure BDA0001436885130000051
As can be seen from table 1:
3-7 months: the reservoir storage period is related to the output of time intervals, the water inflow amount of the reservoir is superior to the water level of the reservoir, and the influence is more obvious particularly in the 6 th and 7 th months of the main flood season; the water volume and the reservoir water level reach a higher state in the month 5, and the influence on the output is larger, so that the natural water Q is selected in other months except for all the initially selected influence factors selected in the month 5tAnd the water in the warehouse can be used for storing water
Figure BDA0001436885130000053
And interaction item of reservoir input energy and energy storage
Figure BDA0001436885130000054
As an influencing factor.
2. Month 8: in the transitional period of supplying and storing water of the reservoir, the influence factors of the water amount and the composition of the reservoir are basically leveled with the water level of the reservoir and the influence factors of the composition of the water level, so all the initially selected influence factors are selected.
Month 9 to 1: in the water supply period of the reservoir, the water quantity of the reservoir is less, and the power generation is mainly carried out by the water level of the reservoir and the energy storage, so that the initial water level of the reservoir time period is selected
Figure BDA0001436885130000055
Superimposed water level
Figure BDA0001436885130000057
Reservoir energy storage
Figure BDA0001436885130000056
As an influencing factor.
Then, the optimization scheduling result is simulated based on three models, namely MNLRA, SVM and BP, wherein table 2 is the BMA weight of each model, and table 3 and (a) - (l) in FIG. 2 list the precision evaluation results of the BMA and the simulated values of 3 models forming the BMA in the monthly output sequence:
TABLE 2 weight values of 3 unique models constituting BMA under optimized scheduling
Figure BDA0001436885130000052
Figure BDA0001436885130000061
TABLE 3 precision evaluation results of BMA and 3 single model simulation values in monthly output sequence under optimized scheduling
Figure BDA0001436885130000062
As can be seen from table 3, the deterministic coefficients DC and the root mean square error RMSE of the 3 models composing the BMA have differences, which cannot be referred to as optimized simulation models, and the average simulation value of the BMA can balance the differences of the models to achieve relative optimization, wherein the rate periodic DC is located in [0.801, 0.997], and the RMSE is located in [1.955, 65.276 ]; the validation period DC is at [0.633, 0.986], and the RMSE is at [6.389, 79.161 ]. Fig. 2 (a) - (l) show that the simulated monthly BMA contribution corresponds to the other three unique models, closer to the actual values.
TABLE 4 precision evaluation results of BMA and simulation values of 3 models in the entire output sequence under optimized scheduling
Figure BDA0001436885130000071
As can be seen from the above table, table 4 shows the precision evaluation results of the BMA and the simulation values of the 3 models constituting it over the entire output sequence, and the BMA mean simulation value DC reaches 0.975 at the calibration period and 0.962 at the inspection period, which are all larger than the single model with the best simulation effect; accordingly, the RMSE value for BMA is also smaller than for any single model, which further illustrates that the simulation values weighted by the BMA method are better than for a single model.
Fig. 3 shows that the BMA under optimized scheduling and the long-series simulated output values of 3 models constituting the BMA are compared with the optimized output, and the optimized output value is 224.71MW, wherein the SVM simulated value is 223.22MW, the BP simulated value is 224.49MW, the MNLRA simulated value is 225.74MW, and the BMA combined simulated value is 224.68MW, which indicates that the scheduling rules formulated by different methods have a certain difference from the deterministic optimization result, but the BMA combination is closer to the actual optimized output. Overall, the BMA mean simulation value is more accurate than the simulation value of a single model.

Claims (4)

1. A method for extracting a scheduling rule of staged power generation of a reservoir is characterized by comprising the following steps: the method comprises the following steps:
(1) establishing a deterministic reservoir optimization scheduling model taking a maximum power generation target, a water balance constraint, a water level constraint, an output constraint, a let-down flow constraint and a unit flow capacity as constraints, and solving by using dynamic programming;
(2) determining a decision variable and an influence factor attribute set based on a deterministic reservoir optimization model result;
(3) analyzing and screening stage influence factors based on the grey correlation degree;
(4) fitting by adopting a multivariate nonlinear regression model, a support vector machine model and a BP artificial neural network model respectively to obtain a staged reservoir power generation scheduling function;
(5) carrying out multi-model weighted average by applying a Bayesian model average method to obtain a final stage reservoir power generation dispatching function;
wherein, the step (3) comprises the following steps:
(31) and respectively constructing a reference number sequence consisting of decision variables and a comparison number sequence consisting of influence factors under each month, and carrying out non-dimensionalization:
reference series: x(0)＝{N1,N2,…,Nt…,NT} (1)
Comparing the number series:
Figure FDA0002891200110000011
where T denotes time T, T denotes a calculation period, T is 1,2, …, T; n is a radical oftOutput is given for the reservoir time interval; z0 tIs the initial water level of the reservoir time interval; qtIs natural tap water;
Figure FDA0002891200110000012
the water level is superposed;
Figure FDA0002891200110000013
is the water energy of the warehouse;
Figure FDA0002891200110000014
storing energy for the reservoir;
Figure FDA0002891200110000015
interaction items of reservoir energy input and energy storage are provided;
(32) and solving the grey correlation coefficient of the reference number sequence and the comparison number sequence:
Figure FDA0002891200110000016
in the formula, X(i)Rho is a resolution coefficient and is generally in the range of 0-1 in order to compare the ith row of the array X;
(33) calculating the correlation degree of the influence factors relative to the decision variables, wherein the correlation degree
Figure FDA0002891200110000017
Is a reference number sequence X(0)(t) and comparison series X(i)(t) a correlation coefficient at a t-th point;
(34) performing association sorting, and respectively determining the output N of the month-by-month and the reservoir time interval according to the association sorting result of each monthtAnd the factor with stronger relevance is used as an influence factor of the final scheduling rule simulation.
2. The method for extracting the scheduling rules of staged power generation for a reservoir according to claim 1, wherein: the decision variable in the step (2) is the output N of the reservoir in time periodtThe attribute set of the influence factors comprises the initial water level of the reservoir time interval
Figure FDA0002891200110000021
Natural tap water QtAnd the superposed water level
Figure FDA0002891200110000022
Water energy in storage
Figure FDA0002891200110000023
Reservoir energy storage
Figure FDA0002891200110000024
Interaction item of reservoir energy input and energy storage
Figure FDA0002891200110000025
3. The method for extracting the scheduling rules of staged power generation for a reservoir according to claim 1, wherein: the step (4) comprises the following steps:
(41) determining the reservoir period output N by taking the influence factors determined under each month as input vectors and determining variablestAs an output vector; determining training samples and testing samples, wherein the number of the samples is M, the number of the training samples is N, and the number of the testing samples is M-N;
(42) respectively adopting a multivariate nonlinear regression model, a support vector machine model and a BP artificial neural network model to simulate a training sample to obtain a reservoir power generation dispatching function;
(43) testing the simulation scheduling function by using a test sample, and evaluating the simulation precision of the model by using a Root Mean Square Error (RMSE) and a Deterministic Coefficient (DC), wherein the simulation precision values of the support vector machine model and the BP artificial neural network model are judged, and if the RMSE is less than 50 and the DC is more than 0.5, the simulation scheduling function is determined; if not, adjusting parameters of the support vector machine model and the BP artificial neural network model, and performing function simulation again;
RMSE and DC are calculated according to equations (4) and (5), respectively:
Figure FDA0002891200110000026
Figure FDA0002891200110000027
in the formula (I), the compound is shown in the specification,
Figure FDA0002891200110000028
the actual force output value at the moment t is obtained;
Figure FDA0002891200110000029
simulating a force value for t moment;
Figure FDA00028912001100000210
is the average actual force output value.
4. The method for extracting the scheduling rules of staged power generation for a reservoir according to claim 1, wherein: the step (5) comprises the following steps:
(51) in each month, based on the Bayesian model average method, adopting the output result N of the deterministic optimization modeltEvaluating simulation results of the multivariate nonlinear regression model, the support vector machine model and the BP artificial neural network model so as to obtain the weight of each model;
(52) and obtaining a final stage scheduling function according to the weighted average of the weight of the multivariate nonlinear regression model, the support vector machine model and the BP artificial neural network model.
CN201710974332.3A 2017-10-18 2017-10-18 Method for extracting scheduling rules of staged power generation of reservoir Active CN107657349B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710974332.3A CN107657349B (en) 2017-10-18 2017-10-18 Method for extracting scheduling rules of staged power generation of reservoir

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710974332.3A CN107657349B (en) 2017-10-18 2017-10-18 Method for extracting scheduling rules of staged power generation of reservoir

Publications (2)

Publication Number Publication Date
CN107657349A CN107657349A (en) 2018-02-02
CN107657349B true CN107657349B (en) 2021-03-19

Family

ID=61118976

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710974332.3A Active CN107657349B (en) 2017-10-18 2017-10-18 Method for extracting scheduling rules of staged power generation of reservoir

Country Status (1)

Country Link
CN (1) CN107657349B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109886543B (en) * 2019-01-16 2022-09-16 河南大学 Reservoir optimal scheduling method based on uniform design
CN110795688B (en) * 2019-09-25 2023-03-28 珠江水利委员会珠江水利科学研究院 Remote correlation factor considered medium-and long-term reservoir scheduling method and automatic control system
CN112113316B (en) * 2020-09-18 2022-03-11 国网辽宁省电力有限公司电力科学研究院 Method for extracting air conditioner load
CN113379147B (en) * 2021-06-24 2023-04-07 武汉大学 Synchronous optimization method for remote hydropower contract and hydropower station group scheduling rule

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102708406A (en) * 2012-05-10 2012-10-03 湖北省电力公司 Scheduling graph optimizing method based on multi-target genetic algorithm
CN104462861A (en) * 2014-12-31 2015-03-25 武汉大学 Reservoir regulation decision-making method based on reservoir regulation rule synthesis
CN105243438A (en) * 2015-09-23 2016-01-13 天津大学 Multi-year regulating storage reservoir optimal scheduling method considering runoff uncertainty
CN106910012A (en) * 2017-02-13 2017-06-30 三峡大学 A kind of medium and small reservoirs system for evaluating safety index system construction method based on significant contribution degree

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102708406A (en) * 2012-05-10 2012-10-03 湖北省电力公司 Scheduling graph optimizing method based on multi-target genetic algorithm
CN104462861A (en) * 2014-12-31 2015-03-25 武汉大学 Reservoir regulation decision-making method based on reservoir regulation rule synthesis
CN105243438A (en) * 2015-09-23 2016-01-13 天津大学 Multi-year regulating storage reservoir optimal scheduling method considering runoff uncertainty
CN106910012A (en) * 2017-02-13 2017-06-30 三峡大学 A kind of medium and small reservoirs system for evaluating safety index system construction method based on significant contribution degree

Also Published As

Publication number Publication date
CN107657349A (en) 2018-02-02

Similar Documents

Publication Publication Date Title
CN107657349B (en) Method for extracting scheduling rules of staged power generation of reservoir
Wang et al. A seasonal GM (1, 1) model for forecasting the electricity consumption of the primary economic sectors
CN104392274B (en) The short-term electro-load forecast method in city based on power load and temperature trend
CN108876021B (en) Medium-and-long-term runoff forecasting method and system
CN102495937A (en) Prediction method based on time sequence
CN112036632B (en) Optimal scheduling method based on cascade reservoir ecological power generation multi-target medium and long term random scheduling model
CN101480143A (en) Method for predicating single yield of crops in irrigated area
CN105809264B (en) Power load prediction method and device
CN105634018B (en) A kind of Load Flow Solution method of random optimum containing wind-powered electricity generation based on stochastic response surface and interior point method
CN111898253B (en) Reservoir dispatching and downstream river ecological environment protection cooperation value evaluation method
Sogabe et al. Optimization of decentralized renewable energy system by weather forecasting and deep machine learning techniques
CN112669168B (en) Short-term prediction method for wind power
CN111008790A (en) Hydropower station group power generation electric scheduling rule extraction method
Gensler et al. An analog ensemble-based similarity search technique for solar power forecasting
CN107862457B (en) Method for extracting stage scheduling rules of reservoir
CN103106331A (en) Photo-etching line width intelligence forecasting method based on dimension-reduction and quantity-increment-type extreme learning machine
CN115860797A (en) Electric quantity demand prediction method suitable for new electricity price reform situation
CN111311026A (en) Runoff nonlinear prediction method considering data characteristics, model and correction
CN114971090A (en) Electric heating load prediction method, system, equipment and medium
CN115392571A (en) Short-term load prediction method for improving whale algorithm to optimize deep extreme learning machine
CN105894138A (en) Optimum weighted composite prediction method for shipment amount of manufacturing industry
CN117744501A (en) Water network system regulation node optimal scheduling and decision-making method considering ecological flow
CN117407802A (en) Runoff prediction method based on improved depth forest model
CN111967652A (en) Double-layer cooperative real-time correction photovoltaic prediction method
CN117291069A (en) LSTM sewage water quality prediction method based on improved DE and attention mechanism

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