CN109558982A - A kind of thermal power plant's water withdrawal prediction technique and device - Google Patents

A kind of thermal power plant's water withdrawal prediction technique and device Download PDF

Info

Publication number
CN109558982A
CN109558982A CN201811464749.6A CN201811464749A CN109558982A CN 109558982 A CN109558982 A CN 109558982A CN 201811464749 A CN201811464749 A CN 201811464749A CN 109558982 A CN109558982 A CN 109558982A
Authority
CN
China
Prior art keywords
target
power plant
thermal power
genset
water
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
CN201811464749.6A
Other languages
Chinese (zh)
Other versions
CN109558982B (en
Inventor
徐志侠
徐怡博
王海军
邱晓华
徐志明
褚敏
张金凤
梁珂
马思超
杨文杰
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 Institute of Water Resources and Hydropower Research
Original Assignee
China Institute of Water Resources and Hydropower Research
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 Institute of Water Resources and Hydropower Research filed Critical China Institute of Water Resources and Hydropower Research
Priority to CN201811464749.6A priority Critical patent/CN109558982B/en
Publication of CN109558982A publication Critical patent/CN109558982A/en
Application granted granted Critical
Publication of CN109558982B publication Critical patent/CN109558982B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06Energy or water supply
    • YGENERAL 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
    • Y04INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04SSYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

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

Abstract

This application provides a kind of thermal power plant's water withdrawal prediction technique and devices, this method comprises: obtaining more target gensets in target thermal power plant in the operation information at target prediction moment;For target genset described in every, operation information according to the target genset at the target prediction moment is constituted for characterizing the target genset in the target feature vector of target prediction moment operating status;By the target feature vector of the target genset, it is input in pre-generated water intaking prediction model corresponding with the target genset, obtains the target genset in the water withdrawal of at least one future time instance;According to each target genset in the water withdrawal of at least one future time instance, determine the target thermal power plant in the water intaking total amount of at least one future time instance.The embodiment of the present application can according to the target thermal power plant in the water intaking total amount of at least one future time instance come the construction for instructing thermal power plant and operation.

Description

A kind of thermal power plant's water withdrawal prediction technique and device
Technical field
This application involves thermal power plant's administrative skill field, in particular to a kind of thermal power plant's water withdrawal prediction technique with And device
Background technique
Thermal power plant is using combustible (such as coal) as the factory of fuel production electric energy.Its basic process of production is: Fuel heating water in burning generates steam, and the chemical energy of fuel is transformed into thermal energy, the rotation of steam pressure pushing turbine, heat It can be converted into mechanical energy, then steam turbine drives generator rotation, and mechanical energy is transformed into electric energy.Wherein, prime mover is usually Steam engine or gas turbine, in some lesser power stations, it is also possible to will use internal combustion engine.They be all by using high temperature, High steam or combustion gas by turbine become the pressure drop of low-pressure air or condensed water during this to generate electricity.
Water is as essential resource in thermal power plant's power generation process, and thermal power plant is when construction, in order to meet thermoelectricity Demand of the factory to water consumption, water intake system are built according to thermal power plant's maximum water consumption.But thermal power plant is actually building If in the process, being all divided into more phase engineerings, and generating set made of built by separate periods is also to come into operation in batches.And generating set In the different moments to put into effect, water consumption also can different from.
So if the maximum water withdrawal according to thermal power plant builds water intake system, it is likely to result in and fetches water for a long period of time The problem of water intaking ability waste of system.
Summary of the invention
In view of this, the embodiment of the present application is designed to provide a kind of thermal power plant's water withdrawal prediction technique and device, Can determine generating set in the prediction of the water withdrawal of at least one future time instance, so as to according to each generating set extremely Construction and the operation of the water withdrawal of a few future time instance predicted to instruct thermal power plant.
In a first aspect, the embodiment of the present application provides a kind of thermal power plant's water withdrawal prediction technique, comprising:
More target gensets in target thermal power plant are obtained in the operation information at target prediction moment;
For target genset described in every, operation information according to the target genset at the target prediction moment, It constitutes for characterizing the target genset in the target feature vector of target prediction moment operating status;
By the target feature vector of the target genset, it is input to corresponding with the target genset pre-generated It fetches water in prediction model, obtains the target genset in the water withdrawal of at least one future time instance;
According to each target genset in the water withdrawal of at least one future time instance, determine that the target thermal power plant exists The water intaking total amount of at least one future time instance.
With reference to first aspect, the embodiment of the present application provides the first possible embodiment of first aspect, in which:
The target feature vector by the target genset is input to pre- Mr. corresponding with the target genset At water intaking prediction model in front of, further includes:
According to the model of the target genset, the water withdrawal prediction of target genset corresponding with this kind of model is determined Model.
With reference to first aspect, the embodiment of the present application provides second of possible embodiment of first aspect, in which:
Water intaking prediction model is generated using following manner:
Obtain operation information and each sample power generation of the more sample generating sets at multiple history samples moment Practical water withdrawal of the unit at multiple history samples moment;The model of more sample generating sets is identical;
For every sample generating set, operation information according to the sample generating set at multiple history samples moment, The sample generating set is generated in corresponding feature vector of each history samples moment;
With more described generating sets in corresponding feature vector of each history samples moment to input, Yi Getai Practical water withdrawal of the sample generating set at multiple history samples moment is output, is generated and each sample generating set The corresponding water intaking prediction model of model.
With reference to first aspect, the embodiment of the present application provides the third possible embodiment of first aspect, in which:
The determining target thermal power plant is after the water intaking total amount of at least one future time instance, further includes:
According to the specified water withdrawal of the target thermal power plant and the water intaking total amount of each following historical juncture, determining should Target thermal power plant is in the corresponding remaining water withdrawal of multiple future time instances;
According to the target thermal power plant in the corresponding remaining water withdrawal of multiple future time instances, it is determined as at least one A target user send time and the pushing quantity of water.
With reference to first aspect, the embodiment of the present application provides the 4th kind of possible embodiment of first aspect, in which:
The determining target thermal power plant is after the water intaking total amount of at least one future time instance, further includes:
According to the target thermal power plant in the water intaking total amount of at least one future time instance, the target thermal power plant is calculated at least The water intaking expenditure of one future time instance.
Second aspect, the embodiment of the present application provide a kind of thermal power plant's water withdrawal prediction meanss, comprising:
Module is obtained, is believed for obtaining operation of the more target gensets in target thermal power plant at the target prediction moment Breath;
Feature vector generation module, for being directed to every target genset, according to the target genset in mesh The operation information of prediction time is marked, is constituted special in the target of target prediction moment operating status for characterizing the target genset Levy vector;
Prediction module, for being input to the target feature vector of the target genset and the target genset pair In the pre-generated water intaking prediction model answered, the target genset is obtained in the water withdrawal of at least one future time instance;
Computing module, for, in the water withdrawal of at least one future time instance, being determined according to each target genset Water intaking total amount of the target thermal power plant at least one future time instance.
In conjunction with second aspect, the embodiment of the present application provides the first possible embodiment of second aspect, described pre- Survey module, be also used to by the target feature vector of the target genset, be input to it is corresponding with the target genset pre- Before in the water intaking prediction model first generated,
According to the model of the target genset, the water withdrawal prediction of target genset corresponding with this kind of model is determined Model.
In conjunction with second aspect, the embodiment of the present application provides second of possible embodiment of second aspect, further includes: Model generation module, for being generated using following manner to water intaking prediction model:
Obtain operation information and each sample power generation of the more sample generating sets at multiple history samples moment Practical water withdrawal of the unit at multiple history samples moment;The model of more sample generating sets is identical;
For every sample generating set, operation information according to the sample generating set at multiple history samples moment, The sample generating set is generated in corresponding feature vector of each history samples moment;
With more described generating sets in corresponding feature vector of each history samples moment to input, Yi Getai Practical water withdrawal of the sample generating set at multiple history samples moment is output, is generated and more sample generating sets The corresponding water intaking prediction model of model.
In conjunction with second aspect, the embodiment of the present application provides the third possible embodiment of second aspect, further includes: First processing module,
The first processing module, for determine target thermal power plant after the water intaking total amount of at least one future time instance, According to the specified water withdrawal of the target thermal power plant and the water intaking total amount of each following historical juncture, the target thermoelectricity is determined Factory is in the corresponding remaining water withdrawal of multiple future time instances;
According to the target thermal power plant in the corresponding remaining water withdrawal of multiple future time instances, it is determined as at least one A target user send time and the pushing quantity of water.
In conjunction with second aspect, the embodiment of the present application provides the 4th kind of possible embodiment of second aspect, further includes: Second processing module, for determining target thermal power plant after the water intaking total amount of at least one future time instance, according to the target Thermal power plant calculates the target thermal power plant in the water intaking branch of at least one future time instance in the water intaking total amount of at least one future time instance Out.
Thermal power plant's water withdrawal prediction technique provided by the embodiments of the present application and device, using acquisition target thermal power plant first In operation information of the more target gensets at the target prediction moment, then be directed to every target genset, according to the mesh Operation information of the generating set at the target prediction moment is marked, constitutes and characterizes the target genset in target prediction moment operation shape The target feature vector of state, and according to the target feature vector of the target genset and corresponding water withdrawal prediction model, Determine that each generating set in the water withdrawal of at least one future time instance, and determines the target thermal power plant at least one future The water intaking total amount at quarter, so as to instruct thermal power plant in the water intaking total amount of at least one future time instance according to the target thermal power plant Construction and operation.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows a kind of flow chart of thermal power plant's water withdrawal prediction technique provided by the embodiment of the present application one;
Fig. 2 shows in thermal power plant's water withdrawal prediction technique provided by the embodiment of the present application, generate and each generator The flow chart of the specific method of the corresponding water intaking prediction model of group model;
Fig. 3 shows a kind of flow chart of thermal power plant's water withdrawal prediction technique provided by the embodiment of the present application two;
Fig. 4 shows a kind of flow chart of thermal power plant's water withdrawal prediction technique provided by the embodiment of the present application three;
Fig. 5 shows the schematic diagram of thermal power plant's water withdrawal prediction meanss provided by the embodiment of the present application four;
Fig. 6 shows a kind of schematic diagram of computer equipment provided by the embodiment of the present application five.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application Middle attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only It is some embodiments of the present application, instead of all the embodiments.The application being usually described and illustrated herein in the accompanying drawings is real The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, below to the application's provided in the accompanying drawings The detailed description of embodiment is not intended to limit claimed scope of the present application, but is merely representative of the selected reality of the application Apply example.Based on embodiments herein, those skilled in the art institute obtained without making creative work There are other embodiments, shall fall in the protection scope of this application.
Thermal power plant includes generating set and the related auxiliary facility around generating set.It is thermal power plant that water intake system, which is used as, Power generation provides the necessary facility of water resource, would generally be prior to other auxiliary facilities in construction.Current water intake system exists When construction, the maximum value of required water withdrawal is built after usually all putting into effect according to the more phase engineerings of thermal power plant.But It is different in the water withdrawal of different times due to generating set, and the generating set in thermal power plant is all built by separate periods and puts into fortune Battalion, the water intaking ability of water intake system for a long period of time is caused much larger than required water withdrawal, to cause water intaking system The waste of system ability.
Therefore, the embodiment of the present application provides a kind of thermal power plant's water withdrawal prediction technique and device, can be by power generation Unit in the prediction of the water withdrawal of at least one future time instance, determine thermal power plant in the water intaking total amount of at least one future time instance, To instruct the construction of generating set and water intake system in thermal power plant, the waste to water intake system water intaking ability is reduced.
It is pre- to a kind of thermal power plant water withdrawal disclosed in the embodiment of the present application first for convenient for understanding the present embodiment Survey method describes in detail.
Embodiment one
It is shown in Figure 1, for the flow chart for thermal power plant's water withdrawal prediction technique that the embodiment of the present application one provides, the side Method includes step S101~S104, in which:
S101: more target gensets in target thermal power plant are obtained in the operation information at target prediction moment.
When specific implementation, operation information of the target genset at the target prediction moment, including in following information One or more:
Generating set model, generating set put into effect the time, the actual power generation of generating set, generating set volume Determine the water saving facility data etc. of generated energy, generating set.
Target thermal power plant can be the thermal power plant that operation has been put into, and can be building and have part generating set The thermal power plant to put into effect can also be the thermal power plant not built also.The target prediction moment can be current time, be also possible to Future time instance.
For the target prediction moment be current time the case where, target genset generally had been put at current time The generating set of operation.The operation information of target genset is its real information at current time.
For object time be future time instance the case where, target genset generally refers to have been put into the future time instance The generating set of operation.It should be noted that the generating set of operation has been put into future time instance for this, it is not at current time It must be the generating set to put into effect.
In that case, the operation information of target genset can be it in the real information of the future time instance, example Such as when the model of generating set, rated generation amount determine, being in the future time instance is real information;The fortune of generating set Row information is also possible to it in future time instance and estimates information;Such as actual power is estimated in the future time instance generating set Amount etc., can be used as and estimate information.
S102: be directed to every target genset, according to the target genset the target prediction moment operation Information is constituted for characterizing the target genset in the target feature vector of target prediction moment operating status.
When specific implementation, since different generating sets are in the operation information different from target prediction moment, because This will be generated based on each generating set in the operation information of target prediction moment operating status for characterizing target power generation Unit is all in the target feature vector of target prediction moment operating status.
Specifically, target feature vector can be generated using following manner:
It is determined to the operating status feature of characterization generating set operating status.For example, generating set model, generating set Put into effect the time, the actual power generation of generating set, the rated generation amount of generating set, generating set water saving facility section Water parameter, generating set operational parameter etc..
For each target genset, according to the operation information of the target genset, the target genset is determined Characteristic value under each operating status feature.
Characteristic value based on the target genset under each operating status feature, generation can characterize target power generation Target feature vector of the unit in the operating status at target prediction moment.
Herein, numerical characteristics its corresponding numerical value that then be used directly is indicated, and category feature is then used it is hot solely (one-hot) vector of corresponding one 0,1 composition of coding mode, i.e. each category feature, classification number correspond to the dimension of vector Number, i.e., a classification corresponds to the one-dimensional of vector, when the predetermined registration operation behavioural characteristic is a certain classification, the corresponding vector of the category Position takes 1, and other parts then all set 0.
S103: the target feature vector of the target genset is input to corresponding with the target genset preparatory In the water intaking prediction model of generation, the target genset is obtained in the water withdrawal of at least one future time instance.
In specific implementation, the model of generating set is different, corresponding water intaking prediction model also different from.Therefore, In another embodiment of the application, by the target feature vector of the target genset, it is input to and the target genset pair Before in the pre-generated water intaking prediction model answered, further includes: according to the model of the target genset, determining and this kind of type The water withdrawal prediction model of number corresponding generating set.
Specifically, shown in Figure 2, it is corresponding with each generating set model that the embodiment of the present application also provides a kind of generation The specific method of water intaking prediction model, comprising:
S201: more sample generating sets are obtained in the operation information and each sample at multiple history samples moment Practical water withdrawal of this generating set at multiple history samples moment;The model of more sample generating sets is identical;
S202: be directed to every sample generating set, according to the sample generating set multiple history samples moment operation Information generates the generating set in corresponding feature vector of each history samples moment.
Specifically, the life of the feature vector of the generating mode of sample generating set feature vector and above-mentioned target genset Identical at mode, details are not described herein.
S203: with more described generating sets in corresponding feature vector of each history samples moment to input, Practical water withdrawal with each sample generating set at multiple history samples moment is output, generates and generates electricity with more samples The corresponding water intaking prediction model of the model of unit.
Illustratively, water withdrawal prediction model includes: Logic Regression Models, autoregression model, moving average model(MA model), returns certainly Return moving average model(MA model), integrate rolling average autoregression model, EC GARCH, deep learning model, Decision-tree model, gradient decline tree-model, gradient promote any one in tree-model.
For different water intaking prediction models, there is different model generating methods.But its principle is similar.
Such as Logic Regression Models, autoregression model, moving average model(MA model), ARMA model, integration For rolling average autoregression model, EC GARCH, the process of training pattern, actually using obtaining The process of unknown parameter in the characteristic value of the feature vector taken and corresponding water withdrawal solving model.
Wherein, water intaking prediction model has different model training methods.But its principle is similar.
Parameter can be with are as follows: weight coefficient corresponding with each element in feature vector and additional coefficient.Model is instructed Experienced process, the process that as weight coefficient and additional coefficient are solved, namely: by the feature of multiple sample generating sets Value of the vector as each explanatory variable, using with the practical water withdrawal at each sample history moment as the value of explained variable, Calculate the weight coefficient and additional coefficient of each explanatory variable in water intaking prediction model, the water intaking prediction model after being trained.
It specifically, can be by more sample generating sets in multiple history samples when prediction model is fetched water in training The corresponding feature vector at moment constitutes explanatory variable matrix, and the parameter of each explanatory variable is constituted parameter matrix, Corresponding practical water withdrawal of different sample history moment is constituted into explained variable matrix, wherein explanatory variable matrix column table Levy the characteristic value under each operating status feature, a history samples moment of row every generating set of characterization of explanatory variable; The corresponding parameter of the different explanatory variables of row characterization of parameter matrix.The row of explained variable matrix characterizes each every generating set Corresponding practical water withdrawal.It is then based on the explanatory variable matrix, parameter matrix and explained variable matrix of composition, to parameter Matrix is solved, to obtain water intaking prediction model.
For deep learning model, need to construct deep learning network in advance, then by sample generating set each Input and the corresponding practical water intaking of a history samples moment corresponding feature vector as deep learning network Amount is used as reference result, and the training for having supervision is carried out to deep learning network, obtains water intaking prediction model.
It is corresponding with the target genset pre-generated being input to the target feature vector of the target genset Water intaking prediction model in, obtain the target genset after the water withdrawal of at least one future time instance, the embodiment of the present application The one thermal power plant's water withdrawal prediction technique provided further include:
S104: according to each target genset in the water withdrawal of at least one future time instance, target fire is determined Water intaking total amount of the power plant at least one future time instance.
Herein, target thermal power plant is in the water intaking total amount of at least one future time instance, as each in the target thermal power plant Target genset respectively corresponds the sum of water withdrawal in the future time instance.
In thermal power plant's water withdrawal prediction provided by the embodiments of the present application, using more targets in acquisition target thermal power plant first Then operation information of the generating set at the target prediction moment is directed to every target genset, according to the target genset In the operation information at target prediction moment, constitutes and characterize the target genset in the target spy of target prediction moment operating status Vector is levied, and according to the target feature vector of the target genset and corresponding water withdrawal prediction model, determines each hair Motor group at least one future time instance water withdrawal, and determine the target thermal power plant it is total in the water intaking of at least one future time instance Amount, so as to according to the target thermal power plant the water intaking total amount of at least one future time instance come the construction of instructing thermal power plant and Operation.
Embodiment two
Fig. 3 shows a kind of schematic diagram of thermal power plant's water withdrawal prediction technique of the offer of the embodiment of the present application two.Include:
S301: more target gensets in target thermal power plant are obtained in the operation information at target prediction moment;
S302: be directed to every target genset, according to the target genset the target prediction moment operation Information is constituted for characterizing the target genset in the target feature vector of target prediction moment operating status;
S303: the target feature vector of the target genset is input to corresponding with the target genset preparatory In the water intaking prediction model of generation, the target genset is obtained in the water withdrawal of at least one future time instance;
S304: according to each target genset in the water withdrawal of at least one future time instance, target fire is determined Water intaking total amount of the power plant at least one future time instance.
Herein, the specific implementation of above-mentioned S301~S304 is similar with above-mentioned A101~S104, and details are not described herein.
S305: according to the specified water withdrawal of the target thermal power plant and the water intaking total amount of each following historical juncture, really The fixed target thermal power plant is in the corresponding remaining water withdrawal of multiple future time instances.
Herein, the specified water withdrawal of target thermal power plant, for the specified water withdrawal of the water intake system of the target thermal power plant.It needs It is noted that under normal circumstances, in order to guarantee in target thermal power plant when there is certain specific demands water intaking, the volume of water intake system Determining water withdrawal generally will be lower than its maximum water withdrawal.
S306: according to the target thermal power plant in the corresponding remaining water withdrawal of multiple future time instances, it is determined as At least one target user send time and the pushing quantity of water.
Herein, target user can be in the generating set built, such as currently have generating set investment in thermal power plant Operation.Need to increase new generating set to expand the production capacity of thermal power plant.It so can be based on to each historical juncture thermoelectricity The prediction of factory's water intaking total amount and the specified water withdrawal of current goal thermal power plant, are determined to supply water for new generating set, with Guarantee the future time instance that new generating set operates normally.
It is also possible to other corollary equipments of thermal power plant, can be with the other users of right and wrong thermal power plant, such as work as thermal power plant Remaining water withdrawal it is more in the case where, can use thermal power plant remaining water withdrawal be thermal power plant periphery user carry out water conveying Deng.
Embodiment three
Fig. 4 shows a kind of schematic diagram of thermal power plant's water withdrawal prediction technique of the offer of the embodiment of the present application three.Include:
S401: more target gensets in target thermal power plant are obtained in the operation information at target prediction moment;
S402: be directed to every target genset, according to the target genset the target prediction moment operation Information is constituted for characterizing the target genset in the target feature vector of target prediction moment operating status;
S403: the target feature vector of the target genset is input to corresponding with the target genset preparatory In the water intaking prediction model of generation, the target genset is obtained in the water withdrawal of at least one future time instance;
S404: according to each target genset in the water withdrawal of at least one future time instance, target fire is determined Water intaking total amount of the power plant at least one future time instance.
Herein, the specific implementation of above-mentioned S401~S404 is similar with above-mentioned A101~S104, and details are not described herein.
S405: according to the target thermal power plant in the water intaking total amount of at least one future time instance, the target thermal power plant is calculated It is paid in the water intaking of at least one future time instance.
In specific implementation, water intaking expenditure includes: water withdrawal expenditure, energy expenditure spent during water intaking, takes It is one or more kinds of in water system maintenance expenditure, artificial expenditure etc..
It is being determined that target thermal power plant after the water intaking total amount of at least one future time instance, can estimate out total with the water intaking Measure corresponding water intaking expenditure.
Based on the same inventive concept, fire corresponding with thermal power plant's water withdrawal prediction technique is additionally provided in the embodiment of the present application Water intake of power plant amount prediction meanss, the principle solved the problems, such as due to the device in the embodiment of the present application and the above-mentioned fire of the embodiment of the present application Water intake of power plant amount prediction technique is similar, therefore the implementation of device may refer to the implementation of method, and overlaps will not be repeated.
Example IV
Referring to Figure 5, a kind of schematic diagram of the thermal power plant's water withdrawal prediction meanss provided for the embodiment of the present application five, institute Stating device includes: to obtain module 51, feature vector generation module 52, prediction module 53 and computing module 54.
Wherein, module 51 is obtained, for obtaining more target gensets in target thermal power plant at the target prediction moment Operation information;
Feature vector generation module 52 exists for being directed to every target genset according to the target genset The operation information at target prediction moment is constituted for characterizing the target genset in the target of target prediction moment operating status Feature vector;
Prediction module 53, for being input to the target feature vector of the target genset and the target genset In corresponding pre-generated water intaking prediction model, the target genset is obtained in the water withdrawal of at least one future time instance;
Computing module 54, for, in the water withdrawal of at least one future time instance, determining should according to each generating set Water intaking total amount of the target thermal power plant at least one future time instance.
In a kind of optional embodiment, the prediction module 53 is also used to the target of the target genset is special Vector is levied, before being input in pre-generated water intaking prediction model corresponding with the target genset,
According to the model of the target genset, the water withdrawal prediction of target genset corresponding with this kind of model is determined Model.
In a kind of optional embodiment, further includes: model generation module 55, for being predicted using following manner water intaking Model is generated:
Obtain operation information and each sample power generation of the more sample generating sets at multiple history samples moment Practical water withdrawal of the unit at multiple history samples moment;The model of more sample generating sets is identical;
For every sample generating set, operation information according to the sample generating set at multiple history samples moment, The generating set is generated in corresponding feature vector of each history samples moment;
With more described generating sets in corresponding feature vector of each history samples moment to input, Yi Getai Practical water withdrawal of the sample generating set at multiple history samples moment is output, is generated and more sample generating sets The corresponding water intaking prediction model of model.
In a kind of optional embodiment, further includes: first processing module 56,
The first processing module, for determine target thermal power plant after the water intaking total amount of at least one future time instance, According to the specified water withdrawal of the target thermal power plant and the water intaking total amount of each following historical juncture, the target thermoelectricity is determined Factory is in the corresponding remaining water withdrawal of multiple future time instances;
According to the target thermal power plant in the corresponding remaining water withdrawal of multiple future time instances, it is determined as at least one A target user send time and the pushing quantity of water.
In a kind of optional embodiment, further includes: Second processing module 57, for determining target thermal power plant at least one After the water intaking total amount of a future time instance, according to the target thermal power plant in the water intaking total amount of at least one future time instance, calculate The target thermal power plant pays in the water intaking of at least one future time instance.
In thermal power plant's water withdrawal prediction provided by the embodiments of the present application, using more targets in acquisition target thermal power plant first Then operation information of the generating set at the target prediction moment is directed to every target genset, according to the target genset In the operation information at target prediction moment, constitutes and characterize the target genset in the target spy of target prediction moment operating status Vector is levied, and according to the target feature vector of the target genset and corresponding water withdrawal prediction model, determines each hair Motor group at least one future time instance water withdrawal, and determine the target thermal power plant it is total in the water intaking of at least one future time instance Amount, so as to according to the target thermal power plant the water intaking total amount of at least one future time instance come the construction of instructing thermal power plant and Operation.
Embodiment five
Corresponding to thermal power plant's water withdrawal prediction technique in Fig. 1, the embodiment of the present application also provides a kind of computer equipments 600, as shown in fig. 6, being 600 structural schematic diagram of computer equipment provided by the embodiments of the present application, comprising:
Processor 61, memory 62 and bus 63;Memory 62 is executed instruction for storing, including memory 621 and outside Memory 622;Here memory 621 is also referred to as built-in storage, for temporarily storing the operational data in processor 61, and with it is hard The data that the external memories such as disk 622 exchange, processor 61 carry out data exchange by memory 621 and external memory 622, when When the user equipment 60 is run, communicated between the processor 61 and the memory 62 by bus 63, so that the place Device 61 is managed to execute in User space to give an order:
More target gensets in target thermal power plant are obtained in the operation information at target prediction moment;
For target genset described in every, operation information according to the target genset at the target prediction moment, It constitutes for characterizing the target genset in the target feature vector of target prediction moment operating status;
By the target feature vector of the target genset, it is input to corresponding with the target genset pre-generated It fetches water in prediction model, obtains the target genset in the water withdrawal of at least one future time instance;
According to each target genset in the water withdrawal of at least one future time instance, determine that the target thermal power plant exists The water intaking total amount of at least one future time instance.
In a kind of possible embodiment, in the instruction that processor 61 executes,
The target feature vector by the target genset is input to pre- Mr. corresponding with the target genset At water intaking prediction model in front of, further includes:
According to the model of the target genset, the water withdrawal prediction of target genset corresponding with this kind of model is determined Model.
In a kind of possible embodiment, in the instruction that processor 61 executes,
Water intaking prediction model is generated using following manner:
Obtain operation information and each sample power generation of the more sample generating sets at multiple history samples moment Practical water withdrawal of the unit at multiple history samples moment;The model of more sample generating sets is identical;
For every sample generating set, operation information according to the sample generating set at multiple history samples moment, The sample generating set is generated in corresponding feature vector of each history samples moment;
With more described generating sets in corresponding feature vector of each history samples moment to input, Yi Getai Practical water withdrawal of the sample generating set at multiple history samples moment is output, is generated and each sample generating set The corresponding water intaking prediction model of model.
In a kind of possible embodiment, in the instruction that processor 61 executes,
The determining target thermal power plant is after the water intaking total amount of at least one future time instance, further includes:
According to the specified water withdrawal of the target thermal power plant and the water intaking total amount of each following historical juncture, determining should Target thermal power plant is in the corresponding remaining water withdrawal of multiple future time instances;
According to the target thermal power plant in the corresponding remaining water withdrawal of multiple future time instances, it is determined as at least one A target user send time and the pushing quantity of water.
In a kind of possible embodiment, in the instruction that processor 61 executes,
The determining target thermal power plant is after the water intaking total amount of at least one future time instance, further includes:
According to the target thermal power plant in the water intaking total amount of at least one future time instance, the target thermal power plant is calculated at least The water intaking expenditure of one future time instance.
In addition, the embodiment of the present application also provides a kind of computer readable storage medium, on the computer readable storage medium It is stored with computer program, thermal power plant described in above method embodiment is executed when which is run by processor and is taken The step of water prediction technique.
The computer program product of route planning method provided by the embodiment of the present application, including storing program code Computer readable storage medium, the instruction that said program code includes can be used for executing thermoelectricity described in above method embodiment The step of factory's water withdrawal prediction technique, for details, reference can be made to above method embodiments, and details are not described herein.
The computer program product of thermal power plant's water withdrawal prediction technique and device provided by the embodiment of the present application, including The computer readable storage medium of program code is stored, the instruction that said program code includes can be used for executing previous methods reality Method described in example is applied, specific implementation can be found in embodiment of the method, and details are not described herein.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description It with the specific work process of device, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.In the application In provided several embodiments, it should be understood that disclosed systems, devices and methods, it can be real by another way It is existing.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, only a kind of logic function It can divide, there may be another division manner in actual implementation, in another example, multiple units or components can combine or can collect At another system is arrived, or some features can be ignored or not executed.Another point, shown or discussed mutual coupling Conjunction or direct-coupling or communication connection can be the indirect coupling or communication connection by some communication interfaces, device or unit, It can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme 's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product It is stored in the executable non-volatile computer-readable storage medium of a processor.Based on this understanding, the application Technical solution substantially the part of the part that contributes to existing technology or the technical solution can be with software in other words The form of product embodies, which is stored in a storage medium, including some instructions use so that One computer equipment (can be personal computer, server or the network equipment etc.) executes each embodiment institute of the application State all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. is various to deposit Store up the medium of program code.
Finally, it should be noted that embodiment described above, the only specific embodiment of the application, to illustrate the application Technical solution, rather than its limitations, the protection scope of the application is not limited thereto, although with reference to the foregoing embodiments to this Shen It please be described in detail, those skilled in the art should understand that: anyone skilled in the art Within the technical scope of the present application, it can still modify to technical solution documented by previous embodiment or can be light It is readily conceivable that variation or equivalent replacement of some of the technical features;And these modifications, variation or replacement, do not make The essence of corresponding technical solution is detached from the spirit and scope of the embodiment of the present application technical solution, should all cover the protection in the application Within the scope of.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.

Claims (10)

1. a kind of thermal power plant's water withdrawal prediction technique characterized by comprising
More target gensets in target thermal power plant are obtained in the operation information at target prediction moment;
For target genset described in every, operation information according to the target genset at the target prediction moment is constituted For characterizing the target genset in the target feature vector of target prediction moment operating status;
By the target feature vector of the target genset, it is input to pre-generated water intaking corresponding with the target genset In prediction model, the target genset is obtained in the water withdrawal of at least one future time instance;
According to each target genset in the water withdrawal of at least one future time instance, determine the target thermal power plant at least The water intaking total amount of one future time instance.
2. the method according to claim 1, wherein the target feature vector by the target genset, Before being input in pre-generated water intaking prediction model corresponding with the target genset, further includes:
According to the model of the target genset, determine that the water withdrawal of target genset corresponding with this kind of model predicts mould Type.
3. according to the method described in claim 2, it is characterized in that, generating water intaking prediction model using following manner:
More sample generating sets are obtained in the operation information and each sample generating set at multiple history samples moment In the practical water withdrawal at multiple history samples moment;The model of more sample generating sets is identical;
For every sample generating set, operation information according to the sample generating set at multiple history samples moment is generated The sample generating set is in corresponding feature vector of each history samples moment;
With more described generating sets in corresponding feature vector of each history samples moment to input, described in each Practical water withdrawal of the sample generating set at multiple history samples moment is output, generates the model with each sample generating set Corresponding water intaking prediction model.
4. the method according to claim 1, wherein the determining target thermal power plant is at least one future time instance Water intaking total amount after, further includes:
According to the specified water withdrawal of the target thermal power plant and the water intaking total amount of each following historical juncture, the target is determined Thermal power plant is in the corresponding remaining water withdrawal of multiple future time instances;
According to the target thermal power plant in the corresponding remaining water withdrawal of multiple future time instances, it is determined as at least one mesh Mark user send time and the pushing quantity of water.
5. the method according to claim 1, wherein the determining target thermal power plant is at least one future time instance Water intaking total amount after, further includes:
According to the target thermal power plant in the water intaking total amount of at least one future time instance, the target thermal power plant is calculated at least one The water intaking of future time instance is paid.
6. a kind of thermal power plant's water withdrawal prediction meanss characterized by comprising
Module is obtained, for obtaining more target gensets in target thermal power plant in the operation information at target prediction moment;
Feature vector generation module, it is pre- in target according to the target genset for being directed to every target genset Survey the moment operation information, constitute for characterize the target genset target prediction moment operating status target signature to Amount;
Prediction module, it is corresponding with the target genset for being input to the target feature vector of the target genset In pre-generated water intaking prediction model, the target genset is obtained in the water withdrawal of at least one future time instance;
Computing module, for, in the water withdrawal of at least one future time instance, determining the mesh according to each target genset Thermal power plant is marked in the water intaking total amount of at least one future time instance.
7. device according to claim 6, which is characterized in that the prediction module is also used to by the target generator The target feature vector of group, before being input in pre-generated water intaking prediction model corresponding with the target genset,
According to the model of the target genset, determine that the water withdrawal of target genset corresponding with this kind of model predicts mould Type.
8. the method according to the description of claim 7 is characterized in that further include: model generation module, for using following manner Water intaking prediction model is generated:
More sample generating sets are obtained in the operation information and each sample generating set at multiple history samples moment In the practical water withdrawal at multiple history samples moment;The model of more sample generating sets is identical;
For every sample generating set, operation information according to the sample generating set at multiple history samples moment is generated The sample generating set is in corresponding feature vector of each history samples moment;
With more described generating sets in corresponding feature vector of each history samples moment to input, described in each Practical water withdrawal of the sample generating set at multiple history samples moment is output, generates the model with more sample generating sets Corresponding water intaking prediction model.
9. device according to claim 6, which is characterized in that further include: first processing module,
The first processing module, for determine target thermal power plant after the water intaking total amount of at least one future time instance, according to The water intaking total amount of the specified water withdrawal of the target thermal power plant and each following historical juncture, determine that the target thermal power plant exists The corresponding remaining water withdrawal of multiple future time instances;
According to the target thermal power plant in the corresponding remaining water withdrawal of multiple future time instances, it is determined as at least one mesh Mark user send time and the pushing quantity of water.
10. device according to claim 6, which is characterized in that further include: Second processing module, for determining target fire Power plant is after the water intaking total amount of at least one future time instance, according to target thermal power plant the taking at least one future time instance Water inventory, the water intaking for calculating the target thermal power plant at least one future time instance are paid.
CN201811464749.6A 2018-12-03 2018-12-03 Method and device for predicting water intake of thermal power plant Active CN109558982B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811464749.6A CN109558982B (en) 2018-12-03 2018-12-03 Method and device for predicting water intake of thermal power plant

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811464749.6A CN109558982B (en) 2018-12-03 2018-12-03 Method and device for predicting water intake of thermal power plant

Publications (2)

Publication Number Publication Date
CN109558982A true CN109558982A (en) 2019-04-02
CN109558982B CN109558982B (en) 2022-06-10

Family

ID=65868622

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811464749.6A Active CN109558982B (en) 2018-12-03 2018-12-03 Method and device for predicting water intake of thermal power plant

Country Status (1)

Country Link
CN (1) CN109558982B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110092507A (en) * 2019-05-30 2019-08-06 中国水利水电科学研究院 A kind of method and device of Industrial Wastewater Treatment

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103544533A (en) * 2012-07-12 2014-01-29 上海宝信软件股份有限公司 Diversion project water resource optimal allocation dynamic model establishing system
JP2015146065A (en) * 2014-01-31 2015-08-13 中国電力株式会社 Forecasting system and forecasting method
CN104850908A (en) * 2015-05-22 2015-08-19 上海电力学院 Chaos particle swarm based thermal power unit load optimal distribution method
CN105677791A (en) * 2015-12-31 2016-06-15 新疆金风科技股份有限公司 Method and system used for analyzing operating data of wind generating set
CN105958496A (en) * 2016-07-01 2016-09-21 华北电力大学 Continuous power flow based maximum transmission capacity calculation method for system containing power source converter (VSC)
CN106873359A (en) * 2015-12-11 2017-06-20 中国电力科学研究院 A kind of wind-powered electricity generation noise rating method based on cluster analysis and neutral net
US20170186107A1 (en) * 2006-02-24 2017-06-29 Gridpoint, Inc. Energy budget manager

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170186107A1 (en) * 2006-02-24 2017-06-29 Gridpoint, Inc. Energy budget manager
CN103544533A (en) * 2012-07-12 2014-01-29 上海宝信软件股份有限公司 Diversion project water resource optimal allocation dynamic model establishing system
JP2015146065A (en) * 2014-01-31 2015-08-13 中国電力株式会社 Forecasting system and forecasting method
CN104850908A (en) * 2015-05-22 2015-08-19 上海电力学院 Chaos particle swarm based thermal power unit load optimal distribution method
CN106873359A (en) * 2015-12-11 2017-06-20 中国电力科学研究院 A kind of wind-powered electricity generation noise rating method based on cluster analysis and neutral net
CN105677791A (en) * 2015-12-31 2016-06-15 新疆金风科技股份有限公司 Method and system used for analyzing operating data of wind generating set
CN105958496A (en) * 2016-07-01 2016-09-21 华北电力大学 Continuous power flow based maximum transmission capacity calculation method for system containing power source converter (VSC)

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
董雷 等: "基于模型预测控制的主动配电网多时间尺度动态优化调度", 《中国电机工程学报》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110092507A (en) * 2019-05-30 2019-08-06 中国水利水电科学研究院 A kind of method and device of Industrial Wastewater Treatment

Also Published As

Publication number Publication date
CN109558982B (en) 2022-06-10

Similar Documents

Publication Publication Date Title
Simopoulos et al. Unit commitment by an enhanced simulated annealing algorithm
Momoh et al. Optimal generation scheduling based on AHP/ANP
US10684598B1 (en) Building management system with efficient model generation for system identification
Azmy et al. Online optimal management of PEMFuel cells using neural networks
Ye et al. A hybrid multiagent framework with Q-learning for power grid systems restoration
CN109299834A (en) A kind of the water process amount prediction technique and device of water treatment plant
JP3980541B2 (en) Distributed energy community control system, central controller, distributed controller, and control method thereof
Gopalakrishnan et al. Operational planning of combined heat and power plants through genetic algorithms for mixed 0–1 nonlinear programming
Sardou et al. Coordinated operation of natural gas and electricity networks with microgrid aggregators
CN110178280A (en) The implicit controller of the layering of system for being shielded in power grid
JP7053299B2 (en) Operation plan generation device and operation plan generation method
CN110135064B (en) Method, system and controller for predicting temperature faults of rear bearing of generator
Pinto et al. Strategic bidding in electricity markets: An agent-based simulator with game theory for scenario analysis
JP2005143218A (en) Control unit and control method for energy system
Ma et al. Fully distributed social welfare optimization with line flow constraint consideration
CN109284939B (en) Thermoelectric combined random production simulation method, device and equipment of comprehensive energy system
US8682635B2 (en) Optimal self-maintained energy management system and use
Joshi et al. Survey on AI and machine learning techniques for microgrid energy management systems
CN106712116B (en) Fully distributed electric system unit investment configuration method and system
Sanjari et al. Analytical approach to online optimal control strategy of energy storage devices in energy system
Azizivahed et al. Multi-area dynamic economic dispatch considering water consumption minimization, wind generation, and energy storage system
CN109558982A (en) A kind of thermal power plant's water withdrawal prediction technique and device
KR20210046789A (en) Method for controlling the exchange of energy between energy sub-systems in coordinated and harmonized conditions; control center; energy system; computer program; and storage media
Antal et al. MoSiCS: Modeling, simulation and optimization of complex systems–A case study on energy efficient datacenters
Yan et al. Data-driven economic control of battery energy storage system considering battery degradation

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