CN107657349A - A kind of reservoir power generation dispatching Rules extraction method by stages - Google Patents

A kind of reservoir power generation dispatching Rules extraction method by stages Download PDF

Info

Publication number
CN107657349A
CN107657349A CN201710974332.3A CN201710974332A CN107657349A CN 107657349 A CN107657349 A CN 107657349A CN 201710974332 A CN201710974332 A CN 201710974332A CN 107657349 A CN107657349 A CN 107657349A
Authority
CN
China
Prior art keywords
mrow
model
msub
reservoir
msubsup
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.)
Granted
Application number
CN201710974332.3A
Other languages
Chinese (zh)
Other versions
CN107657349B (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

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

Abstract

The invention provides a kind of reservoir power generation dispatching Rules extraction method by stages, factor of influence by stages is screened based on grey relational grade analysis, multivariate nonlinear regression analysis model, supporting vector machine model and BP artificial nerve network models is respectively adopted and is fitted to obtain hydropower station scheduling function by stages, carrying out multi-model weighted average using Bayesian model averaging method obtains final hydropower station scheduling function by stages.GRA is introduced into regulation o f reservoir operation simulation and carries out factor of influence screening by the present invention, removes redundant attributes, reduces model complexity, improves modeling efficiency；And GRA and BMA are combined to the extraction by stages realized to hydropower station rule, being capable of balanced decision variable and the problem of not consistent correlation of the factor of influence for the different periods in reservoir operation therebetween, and the uncertainty that single model is brought by model structure is balanced, improve modeling precision；The requirement of hydropower station scheduling rule extraction is met, can preferably inherit benefit of the deterministic optimization scheduling in terms of power generation process.

Description

A kind of reservoir power generation dispatching Rules extraction method by stages
Technical field
The present invention relates to field of water conservancy, and in particular to a kind of reservoir power generation dispatching Rules extraction method by stages.
Background technology
Optimizing scheduling of reservoir research starts from nineteen fifty-five, because it can obtain more water power on-road efficiencies, so far excellent Change and achieved a series of plentiful and substantial theoretical results on scheduling model.But deterministic optimization scheduling model often in runoff Operated on the premise of knowing, can not guide practical reservoir operation scheduling.Therefore, how to be obtained from Model on Formulate Operation of Reservoir optimal During summarize reservoir optimizing moving law, and then formed scheduling rule, to guide practical reservoir operation, improve reservoir water power Benefit has important practical significance.
At present, what regulation o f reservoir operation was the most frequently used takes the form of scheduling graph and scheduling function.Compared with scheduling graph, scheduling Reservoir optimizing result extraction of the function based on deterministic optimization model, can preferably inherit deterministic optimization scheduling and generate electricity Amount, the benefit for ensureing output etc..Scheduling function extracting method mainly includes statistical regression method and the major class of intelligent algorithm two, so And most of scheduling function research at present does not carry out factor of influence screening operation, studied for the choosing method of factor of influence Still starting to walk.Tentatively selected factor of influence is more, if all considering that the difficulty of model must be increased, can also reduce modeling Accuracy, how from these factors to find key factor, the factor of influence higher to application relativity is effectively adjusted Metric is then simulated, and has important practical significance.
At present, studied on regulation o f reservoir operation mainly by single model realization.Practice have shown that none of model It can affirm that it is better than other models in any condition, the analog result obtained using single model can not be avoided by model Structure is brought uncertain.Therefore it provides the multi-model synthesis analog result of the higher average meaning of precision, turn into one it is important Research direction.
The content of the invention
Goal of the invention：It is an object of the invention to the difference for prior art, there is provided a kind of reservoir generates electricity tune by stages Spend Rules extraction method, solve at present most of scheduling rule research do not have progress factor of influence screening operation and it is different when The problem of section making policy decision variable and not consistent factor of influence correlation, while provide precision higher average meaning based on BMA Multi-model synthesis scheduling rule, provide theoretical foundation and science for the operation of power station actual optimization and support.
Technical scheme：The invention provides a kind of reservoir power generation dispatching Rules extraction method by stages, comprise the following steps：
(1) structure constrained with the maximum target that generates electricity, with water balance, restriction of water level, units limits, letdown flow constraint with And unit conveyance capacity is the certainty Model on Formulate Operation of Reservoir constrained and solved with Dynamic Programming；
(2) certainty reservoir optimizing model result is based on, determines decision variable and factor of influence property set；
(3) factor of influence by stages is screened based on grey relational grade analysis (GRA)；
(4) it is manually refreshing that multivariate nonlinear regression analysis model (MNLRA), supporting vector machine model (SVM) and BP is respectively adopted Hydropower station scheduling function by stages is obtained through network model (BP) fitting；
(5) carry out multi-model weighted average using Bayesian model averaging method (BMA) and obtain final hydropower station by stages Scheduling function.
Further, step (2) described decision variable is reservoir period output Nt, the factor of influence property set includes reservoir Water level at the beginning of periodNatural water Qt, superposition water levelBe put in storage water energyReservoir accumulation of energyReservoir, which enters, to be interacted with accumulation of energy
Further, step (3) comprises the following steps：
(31) under each month, the reference sequence being made up of decision variable and the ratio being made up of factor of influence are built respectively Compared with ordered series of numbers, and carry out nondimensionalization processing：
Reference sequence：X(0)={ N1, N2..., Nt..., NT} (1)
Compare ordered series of numbers：
In formula, t represents t, and T represents calculation interval, t=1,2 ..., T；
(32) grey incidence coefficient of reference sequence ordered series of numbers compared with is sought：
In formula, X(i)To compare ordered series of numbers X the i-th row, ρ is resolution ratio, typically among 0~1；
(33) degree of association of the factor of influence relative to decision variable, the wherein degree of association are calculatedFor reference sequence X(0)(t) and ordered series of numbers X is compared(i)(t) in the incidence coefficient of t points；
(34) sequence is associated, according to the relational degree taxis result in each month, when determining month by month part respectively with reservoir Section output NtThe factor of influence that the stronger factor of relevance is simulated as final scheduling rule.
Further, step (4) comprises the following steps：
(41) using the factor of influence determined under each month as input vector, decision variable reservoir period output NtAs Output vector；Training sample and test sample are determined, wherein, sample number M, number of training N, test sample number are M-N；
(42) it is manually refreshing that multivariate nonlinear regression analysis model (MNLRA), supporting vector machine model (SVM) and BP is respectively adopted Simulation is carried out to training sample through network model (BP) and obtains hydropower station scheduling function；
(43) performance test sample is tested operation simulation function, using root-mean-square error RMSE and certainty system Number DC carrys out the simulation precision of Evaluation model, wherein, judge supporting vector machine model (SVM) and BP artificial nerve network models (BP) simulation precision value, if RMSE ＜ 50, DC ＞ 0.5, determines operation simulation function；If no, adjust supporting vector machine model (SVM) and BP artificial nerve network models (BP) parameter, re-start functional simulation；
RMSE, DC are calculated by formula (4), (5) respectively：
In formula,For the actual power generating value of t, MW；Power generating value, MW are simulated for t；For average actual output Value, MW.
Further, step (5) comprises the following steps：
(51) under each month, based on Bayesian model averaging method (BMA), using the output of deterministic optimization model As a result NtTo multivariate nonlinear regression analysis model (MNLRA), supporting vector machine model (SVM) and BP artificial nerve network models (BP) result of three modelings is evaluated, so as to obtain the weight of each model；
(52) according to multivariate nonlinear regression analysis model (MNLRA), supporting vector machine model (SVM) and BP ANN The Weight of network model (BP) three models averagely regulation by stage function to the end.
Beneficial effect：GRA is introduced into regulation o f reservoir operation simulation and carries out factor of influence screening by the present invention, removes redundancy category Property, model complexity is reduced, improves modeling efficiency；And GRA and BMA are combined realization hydropower station rule is divided Phase extracts, can balanced decision variable and factor of influence for the correlation therebetween of the different periods in reservoir operation not The problem of consistent, and the uncertainty that single model is brought by model structure is balanced, improve modeling precision；Meet reservoir The requirement of power generation dispatching Rule Extraction, benefit of the deterministic optimization scheduling in terms of power generation process can be preferably inherited, is realized The purpose of the guidance run under the premise of water is uncertain to reservoir actual optimization, improve the power benefit in power station.
Brief description of the drawings
Fig. 1 is flow chart of the method for the present invention；
Fig. 2 (a)-(1) is that the power generating value of simulation month by month of its 3 models of BMA and composition is contributed with optimization under Optimized Operation It is worth dependency graph；
Fig. 3 is the long series analog power generating value of its 3 models of BMA and composition and optimization power generating value contrast under Optimized Operation Figure.
Embodiment
Technical solution of the present invention is described in detail below, but protection scope of the present invention is not limited to the implementation Example.
Embodiment：A kind of reservoir power generation dispatching Rules extraction method by stages, as shown in figure 1, the present embodiment is with Xinanjiang River water Power station illustrates as example.Xin'anjiang Hydropower Station is that the First of China's designed, designed, home-built equipment and oneself construction is big Type power station, the long 323km in dam site above river, drainage area 10442km2.Xin ' anjiang Reservoir has flood control concurrently, filled based on generating electricity Irrigate, fishery, shipping, the comprehensive function such as tourism, there is many years regulation performance, installed capacity of power station 810.0MW.The present embodiment uses - 2008 years 1962 hydrological annual runoff data, using more annual operating water level 98.4m as starting-point detection, using the moon as the period, to adjust Spend gross generation in the phase and be up to target, with dynamic programming (DP) obtain Xin'anjiang Hydropower Station grow serial Optimized Operation into Fruit.
First, correlation degree of each factor of influence to decision variable is calculated based on GRA, it is determined that final factor of influence such as table 1 It is shown：
Calculation of relationship degree and final factor of influence the selection result month by month under the Optimized Operation of table 1
As can be seen from Table 1：
3~July：The reservoir filling phase, with associating for period output, reservoir carrys out water and is better than reservoir level, especially main Flood season 6, July influence to become apparent from；Carry out the state that water and reservoir level all reach higher May, output had a great influence, Therefore, in addition to May selects whole primary election factors of influence, select in other months to select natural water Qt, storage water energyWith And reservoir enters and can interact item with accumulation of energyAs factor of influence.
2nd, August part：Reservoir supplies the water storage transitional period, and reservoir carrys out the influent factor and reservoir level and its composition of water and composition Influent factor remain basically stable, therefore select primary election whole factors of influence.
9~January：Reservoir delivery period, it is less that reservoir carrys out water, relies primarily on reservoir level and accumulation of energy is generated electricity, Therefore water level at the beginning of the selection reservoir periodIt is superimposed water level, reservoir accumulation of energyAs factor of influence.
Then, Optimized Operation achievement is simulated based on tri- models of MNLRA, SVM and BP, table 2 is each model BMA weights, table 3 and Fig. 2 list BMA and form accuracy assessment knot of the analogue value in output sequence month by month of its 3 models Fruit：
Weighted value shared by BMA 3 single models is formed under the Optimized Operation of table 2
Accuracy assessment result of the analogue value of BMA and 3 single model in output sequence month by month under the Optimized Operation of table 3
From table 3 it can be seen that the deterministic coefficient DC and root-mean-square error RMSE of composition BMA 3 models respectively have difference It is different, can not be referred to as optimizing simulation model, BMA averaging analogs value can balanced each model difference, realize it is relatively optimal, its In, the regular DC of rate is located at [0.801,0.997], and RMSE is located at [1.955,65.276]；Checking phase DC positioned at [0.633, 0.986], RMSE is located at [6.389,79.161].The BMA output analogues value that Fig. 2 shows month by month correspond to other three it is single Model, closer to actual value.
Accuracy assessment result of the analogue value of BMA and 3 model in whole output sequence under the Optimized Operation of table 4
As can be seen from the above table, table 4 is BMA and forms precision of the analogue value in whole output sequence of its 3 models Evaluation result, BMA averaging analog values DC periodically reach 0.975 in rate, reach 0.962 in probative term, and these are than simulation effect most Good single model is all big；Correspondingly, BMA RMSE value is also all smaller than any single model, and this further illustrates pass through The analogue value after BMA method weighted averages is better than the simulation effect of single model.
Fig. 3 is the long series analog power generating value of its 3 models of BMA and composition and optimization output contrast under Optimized Operation, Optimize power generating value 224.71MW, wherein SVM analogues value 223.22MW, BP analogues value 224.49MW, the MNLRA analogue value 225.74MW, BMA combination die analog values 224.68MW, the scheduling rule and deterministic optimization result for illustrating distinct methods formulation have A certain distance, but BMA combinations and actual optimization output are closer.Generally, BMA averaging analogs value contrasts single model The analogue value, simulation precision are higher.

Claims (5)

  1. A kind of 1. reservoir power generation dispatching Rules extraction method by stages, it is characterised in that：Comprise the following steps：
    (1) structure constrains with the maximum target that generates electricity, with water balance, restriction of water level, units limits, letdown flow constrain and machine Group conveyance capacity is the certainty Model on Formulate Operation of Reservoir of constraint and solved with Dynamic Programming；
    (2) certainty reservoir optimizing model result is based on, determines decision variable and factor of influence property set；
    (3) factor of influence by stages is screened based on grey relational grade analysis；
    (4) multivariate nonlinear regression analysis model, supporting vector machine model and BP artificial nerve network models is respectively adopted to be fitted To hydropower station scheduling function by stages；
    (5) carry out multi-model weighted average using Bayesian model averaging method and obtain final hydropower station scheduling function by stages.
  2. 2. reservoir according to claim 1 power generation dispatching Rules extraction method by stages, it is characterised in that：Step (2) is described Decision variable is reservoir period output Nt, the factor of influence property set includes water level at the beginning of the reservoir periodNatural water Qt, it is folded Add water levelBe put in storage water energyReservoir accumulation of energyReservoir, which enters, to interact item with accumulation of energy
  3. 3. reservoir according to claim 2 power generation dispatching Rules extraction method by stages, it is characterised in that：Step (3) includes Following steps：
    (31) under each month, the reference sequence being made up of decision variable and the comparison number being made up of factor of influence are built respectively Row, and carry out nondimensionalization processing：
    Reference sequence：X(0)={ N1, N2..., Nt..., NT} (1)
    Compare ordered series of numbers：
    In formula, t represents t, and T represents calculation interval, t=1,2 ..., T；
    (32) grey incidence coefficient of reference sequence ordered series of numbers compared with is sought：
    <mrow> <msub> <mi>&amp;eta;</mi> <mi>i</mi> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <mrow> <mi>min</mi> <mi> </mi> <mi>i</mi> <mi> </mi> <mi>min</mi> <mi> </mi> <mi>t</mi> <mo>|</mo> <msub> <mi>X</mi> <mrow> <mo>(</mo> <mi>i</mi> <mo>)</mo> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>-</mo> <msub> <mi>X</mi> <mrow> <mo>(</mo> <mn>0</mn> <mo>)</mo> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>|</mo> <mo>+</mo> <mi>&amp;rho;</mi> <mi>max</mi> <mi> </mi> <mi>i</mi> <mi> </mi> <mi>max</mi> <mi> </mi> <mi>t</mi> <mo>|</mo> <msub> <mi>X</mi> <mrow> <mo>(</mo> <mi>i</mi> <mo>)</mo> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>-</mo> <msub> <mi>X</mi> <mrow> <mo>(</mo> <mn>0</mn> <mo>)</mo> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>|</mo> </mrow> <mrow> <msub> <mi>X</mi> <mrow> <mo>(</mo> <mi>i</mi> <mo>)</mo> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>-</mo> <msub> <mi>X</mi> <mrow> <mo>(</mo> <mn>0</mn> <mo>)</mo> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>+</mo> <mi>&amp;rho;</mi> <mi>max</mi> <mi> </mi> <mi>i</mi> <mi> </mi> <mi>max</mi> <mi> </mi> <mi>t</mi> <mo>|</mo> <msub> <mi>X</mi> <mrow> <mo>(</mo> <mi>i</mi> <mo>)</mo> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>-</mo> <msub> <mi>X</mi> <mrow> <mo>(</mo> <mn>0</mn> <mo>)</mo> </mrow> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>|</mo> </mrow> </mfrac> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>3</mn> <mo>)</mo> </mrow> </mrow>
    In formula, X(i)To compare ordered series of numbers X the i-th row, ρ is resolution ratio, typically among 0~1；
    (33) degree of association of the factor of influence relative to decision variable, the wherein degree of association are calculatedFor reference sequence X(0) (t) and ordered series of numbers X is compared(i)(t) in the incidence coefficient of t points；
    (34) sequence is associated, according to the relational degree taxis result in each month, determines that month by month part goes out with the reservoir period respectively Power NtThe factor of influence that the stronger factor of relevance is simulated as final scheduling rule.
  4. 4. reservoir according to claim 1 power generation dispatching Rules extraction method by stages, it is characterised in that：Step (4) includes Following steps：
    (41) using the factor of influence determined under each month as input vector, decision variable reservoir period output NtAs output Vector；Training sample and test sample are determined, wherein, sample number M, number of training N, test sample number are M-N；
    (42) multivariate nonlinear regression analysis model, supporting vector machine model and BP artificial nerve network models is respectively adopted to training Sample carries out simulation and obtains hydropower station scheduling function；
    (43) performance test sample is tested operation simulation function, using root-mean-square error RMSE and deterministic coefficient DC Carry out the simulation precision of Evaluation model, wherein, judge the simulation precision of supporting vector machine model and BP artificial nerve network models Value, if RMSE ＜ 50, DC ＞ 0.5, determines operation simulation function；If no, adjust supporting vector machine model and BP artificial neurons The parameter of network model, re-starts functional simulation；
    RMSE, DC are calculated by formula (4), (5) respectively：
    <mrow> <mi>R</mi> <mi>M</mi> <mi>S</mi> <mi>E</mi> <mo>=</mo> <msqrt> <mfrac> <mrow> <msubsup> <mi>&amp;Sigma;</mi> <mrow> <mi>t</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>T</mi> </msubsup> <msup> <mrow> <mo>(</mo> <msubsup> <mi>N</mi> <mi>o</mi> <mi>t</mi> </msubsup> <mo>-</mo> <msubsup> <mi>N</mi> <mi>s</mi> <mi>t</mi> </msubsup> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow> <mi>T</mi> </mfrac> </msqrt> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>4</mn> <mo>)</mo> </mrow> </mrow>
    <mrow> <mi>D</mi> <mi>C</mi> <mo>=</mo> <mn>1</mn> <mo>-</mo> <mfrac> <mrow> <msubsup> <mi>&amp;Sigma;</mi> <mrow> <mi>t</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>T</mi> </msubsup> <msup> <mrow> <mo>(</mo> <msubsup> <mi>N</mi> <mn>0</mn> <mi>t</mi> </msubsup> <mo>-</mo> <msubsup> <mi>N</mi> <mi>s</mi> <mi>t</mi> </msubsup> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow> <mrow> <msubsup> <mi>&amp;Sigma;</mi> <mrow> <mi>t</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>T</mi> </msubsup> <msup> <mrow> <mo>(</mo> <mover> <msub> <mi>N</mi> <mi>o</mi> </msub> <mo>&amp;OverBar;</mo> </mover> <mo>-</mo> <msubsup> <mi>N</mi> <mi>s</mi> <mi>t</mi> </msubsup> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow> </mfrac> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>5</mn> <mo>)</mo> </mrow> </mrow>
    In formula,For the actual power generating value of t, MW；Power generating value, MW are simulated for t；For average actual power generating value, MW。
  5. 5. reservoir according to claim 1 power generation dispatching Rules extraction method by stages, it is characterised in that：Step (5) includes Following steps：
    (51) under each month, based on Bayesian model averaging method, using the output result N of deterministic optimization modeltTo more First nonlinear regression model (NLRM), the result of three modelings of supporting vector machine model and BP artificial nerve network models are commented Valency, so as to obtain the weight of each model；
    (52) according to multivariate nonlinear regression analysis model, supporting vector machine model and BP artificial nerve network models three models Weight averagely regulation by stage function to the end.
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 true CN107657349A (en) 2018-02-02
CN107657349B 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)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109886543A (en) * 2019-01-16 2019-06-14 河南大学 Reservoir optimizing and dispatching method based on uniform design
CN110795688A (en) * 2019-09-25 2020-02-14 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
CN112113316A (en) * 2020-09-18 2020-12-22 国网辽宁省电力有限公司电力科学研究院 Method for extracting air conditioner load
CN113379147A (en) * 2021-06-24 2021-09-10 武汉大学 Synchronous optimization method for remote hydropower contract and hydropower station group scheduling rule
CN113962463A (en) * 2021-10-25 2022-01-21 河海大学 Reservoir optimal scheduling rule extraction method with dynamic time-varying structure

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

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109886543A (en) * 2019-01-16 2019-06-14 河南大学 Reservoir optimizing and dispatching method based on uniform design
CN109886543B (en) * 2019-01-16 2022-09-16 河南大学 Reservoir optimal scheduling method based on uniform design
CN110795688A (en) * 2019-09-25 2020-02-14 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
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
CN112113316A (en) * 2020-09-18 2020-12-22 国网辽宁省电力有限公司电力科学研究院 Method for extracting air conditioner load
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
CN113379147A (en) * 2021-06-24 2021-09-10 武汉大学 Synchronous optimization method for remote hydropower contract and hydropower station group scheduling rule
CN113962463A (en) * 2021-10-25 2022-01-21 河海大学 Reservoir optimal scheduling rule extraction method with dynamic time-varying structure

Also Published As

Publication number Publication date
CN107657349B (en) 2021-03-19

Similar Documents

Publication Publication Date Title
CN107657349A (en) A kind of reservoir power generation dispatching Rules extraction method by stages
CN104779611B (en) Micro-capacitance sensor economic load dispatching method based on centralized and distributed dual-layer optimization strategy
CN106682810B (en) Long-term operation method of cross-basin cascade hydropower station group under dynamic production of giant hydropower station
CN105811403B (en) Probabilistic loadflow algorithm based on cumulant and Series Expansion Method
CN107451680A (en) A kind of electrical interconnection system random optimum trend heuristic calculation methods
CN105243438A (en) Multi-year regulating storage reservoir optimal scheduling method considering runoff uncertainty
CN111080157B (en) Method and system for scheduling phosphorus discharge amount of cascade hydropower station
CN104638672B (en) Determining method of photovoltaic transmission power limit considering variable correlation
CN103117546A (en) Ultrashort-term slide prediction method for wind power
CN106599562B (en) River ecological water demand computational methods based on probability weight FDC methods
CN103996079B (en) Wind power weighting predication method based on conditional probability
CN108596242A (en) Power grid meteorology load forecasting method based on wavelet neural network and support vector machines
CN112036632B (en) Optimal scheduling method based on cascade reservoir ecological power generation multi-target medium and long term random scheduling model
CN110400232A (en) Consider the monthly trading program quantity division method of GROUP OF HYDROPOWER STATIONS of power grid profile constraints
CN109871622A (en) A kind of low-voltage platform area line loss calculation method and system based on deep learning
CN116757446B (en) Cascade hydropower station scheduling method and system based on improved particle swarm optimization
CN105846425A (en) Economic dispatching method based on general wind power forecasting error model
CN104636834B (en) A kind of improved joint probability plan model system optimization method
CN107069835A (en) New energy power station distribution method active in real time and distributor
CN107862457B (en) Method for extracting stage scheduling rules of reservoir
CN104915788B (en) A method of considering the Electrical Power System Dynamic economic load dispatching of windy field correlation
CN111311026A (en) Runoff nonlinear prediction method considering data characteristics, model and correction
CN105279582B (en) Super short-period wind power prediction technique based on dynamic correlation feature
CN105896547A (en) Large power network graded voltage control method under wind power access
CN108537581A (en) Based on the GMDH energy consumption Time Series Forecasting Methods selectively combined and device

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