CN109389254A - Energy consumption deviation method for calculating probability, device and computer storage medium - Google Patents
Energy consumption deviation method for calculating probability, device and computer storage medium Download PDFInfo
- Publication number
- CN109389254A CN109389254A CN201811654727.6A CN201811654727A CN109389254A CN 109389254 A CN109389254 A CN 109389254A CN 201811654727 A CN201811654727 A CN 201811654727A CN 109389254 A CN109389254 A CN 109389254A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- power generating
- generating unit
- state information
- fired power
- 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.)
- Pending
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 219
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 23
- 238000013507 mapping Methods 0.000 claims abstract description 18
- 238000004364 calculation method Methods 0.000 claims description 13
- 239000003245 coal Substances 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 241001269238 Data Species 0.000 claims description 4
- 230000005619 thermoelectricity Effects 0.000 claims description 2
- 239000004744 fabric Substances 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 16
- 230000000694 effects Effects 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000013506 data mapping Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000021715 photosynthesis, light harvesting Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
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)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of energy consumption deviation method for calculating probability, device and computer storage medium, is related to thermal power generating technology field.The energy consumption deviation method for calculating probability includes: the work state information for obtaining fired power generating unit in preset time period;The work state information of fired power generating unit and the mapping relations of energy consumption data are obtained using default computation model according to the work state information of fired power generating unit in preset time period;According to the mapping relations of the work state information and energy consumption data of fired power generating unit work state information within a preset period of time and fired power generating unit, the prediction of energy consumption data of fired power generating unit within a preset period of time are calculated;According to the actual consumption data and prediction of energy consumption data of fired power generating unit within a preset period of time, calculates and obtain energy consumption deviation probability set.The present invention realizes the method by model training, on the basis of getting energy consumption deviation probability set, calculates the realization probability obtained under power dissipation obj ectives, substantially increases the calculating accuracy that probability is realized under power dissipation obj ectives.
Description
Technical field
The present invention relates to field of thermal power, and in particular to a kind of energy consumption deviation method for calculating probability, device and computer
Storage medium.
Background technique
Energy consumption level is one of the key index of thermal power generation priority control, and the year of unit is often worked out in thermal power plant
Degree, monthly energy consumption control target.Design feature, service condition and the previous energy of unit had both been considered in the formulation of the target
Water consumption is flat, it is also considered that factors such as the technological transformations of the target, device systems that are promoted to managing power consumption.
Calculating to probability is realized under power dissipation obj ectives in the prior art is by adding up energy to the history in stipulated time section
The flat and following available energy dissipation data of water consumption are analyzed to obtain.
However, the accuracy of calculated result is held very much since the above method is usually to be analyzed and determined according to artificial experience
Easily it is influenced by the subjective consciousness, it is lower so as to cause calculated result accuracy rate.
Summary of the invention
It is an object of the present invention in view of the deficiency of the prior art, provide a kind of energy consumption deviation probability calculation side
Method, device and computer storage medium, to solve in the prior art to calculate realization probability under power dissipation obj ectives, calculated result
The problem of inaccuracy.
To achieve the above object, technical solution used in the embodiment of the present invention is as follows:
In a first aspect, the embodiment of the invention provides a kind of energy consumption deviation method for calculating probability, comprising:
Obtain the work state information of fired power generating unit in preset time period;
Fired power generating unit is obtained using default computation model according to the work state information of fired power generating unit in preset time period
Work state information and energy consumption data mapping relations, preset computation model be according to fired power generating unit in history preset time period
What interior multiple groups work state information and energy consumption data training obtained;
According to fired power generating unit work state information within a preset period of time and the work state information and energy of fired power generating unit
The mapping relations of data are consumed, the prediction of energy consumption data of fired power generating unit within a preset period of time are calculated;
According to the actual consumption data and prediction of energy consumption data of fired power generating unit within a preset period of time, it is inclined to calculate acquisition energy consumption
Poor probability set, energy consumption deviation probability set are used to indicate the probability distribution of energy consumption deviation.
Optionally, according to the work state information and energy consumption data of fired power generating unit in preset time period, using default calculating
Model, before obtaining the work state information of fired power generating unit and the mapping relations of energy consumption data, further includes:
Obtain multiple groups work state information and energy consumption data of the fired power generating unit in history preset time period;
According to preset rules, multiple groups work state information is divided into different classes of, every kind of classification corresponds to different energy consumptions
Data;
According to the corresponding relationship of every kind of classification work state information and energy consumption data, training obtains default computation model.
Optionally, obtain multiple groups work state information and energy consumption data of the fired power generating unit in history preset time period it
Afterwards, further includes:
According to preset condition, judge whether the multiple groups work state information of fired power generating unit meets the requirements;
If not satisfied, then the work state information for the condition that is unsatisfactory for is deleted.
Optionally, it is obtained according to fired power generating unit actual consumption data within a preset period of time and prediction of energy consumption data, calculating
Take energy consumption deviation probability set, comprising:
According to the actual consumption data and prediction of energy consumption data of fired power generating unit within a preset period of time, calculates and obtain multiple energy
Consume deviation;
According to preset rules, multiple energy consumption deviations are divided into multiple sections;
According to the ratio of the quantity of energy consumption deviation in each section and energy consumption deviation sum, the corresponding energy in each section is calculated
Deviation probability is consumed, energy consumption deviation probability set is obtained.
Optionally, work state information includes following one or more: the load of fired power generating unit, confession heat flow, environment temperature
Degree and coal quality.
Second aspect, the embodiment of the invention also provides a kind of energy consumption deviation probability calculation device, which includes: to obtain
Module, processing module, the first computing module and the second computing module;
Module is obtained, for obtaining the work state information of fired power generating unit in preset time period;
Processing module, for the work state information according to fired power generating unit in preset time period, using default computation model,
The work state information of fired power generating unit and the mapping relations of energy consumption data are obtained, default computation model is to go through according to fired power generating unit
What multiple groups work state information and energy consumption data training in history preset time period obtained;
First computing module, for according to fired power generating unit work state information within a preset period of time and fired power generating unit
Work state information and energy consumption data mapping relations, calculate fired power generating unit prediction of energy consumption data within a preset period of time;
Second computing module, for according to fired power generating unit actual consumption data within a preset period of time and prediction of energy consumption number
According to calculating obtains energy consumption deviation probability set, and energy consumption deviation probability set is used to indicate the probability distribution of energy consumption deviation.
Optionally, device further include: categorization module, training module;
Above-mentioned acquisition module, be also used to obtain multiple groups work state information of the fired power generating unit in history preset time period and
Energy consumption data;Categorization module, for according to preset rules, multiple groups work state information to be divided into different classes of, every kind of classification
Corresponding different energy consumption data;Training module, for the corresponding relationship according to every kind of classification work state information and energy consumption data,
Training obtains default computation model.
Optionally, device further include: judgment module;
Judgment module, for judging whether the multiple groups work state information of fired power generating unit meets the requirements according to preset condition;
If not satisfied, then the work state information for the condition that is unsatisfactory for is deleted.
Optionally, above-mentioned second computing module, specifically for the actual consumption according to fired power generating unit within a preset period of time
Data and prediction of energy consumption data calculate and obtain multiple energy consumption deviations;According to preset rules, multiple energy consumption deviations are divided into multiple
Section;According to the ratio of the quantity of energy consumption deviation in each section and energy consumption deviation sum, the corresponding energy consumption in each section is calculated
Deviation probability obtains energy consumption deviation probability set.
The third aspect is deposited in the computer storage medium the embodiment of the invention also provides a kind of computer storage medium
Program is contained, when described program is executed by processor, realizes method described in first aspect as above.
The beneficial effects of the present invention are: by using the history work state information and energy consumption data of fired power generating unit, training
Energy consumption presets computation model, using trained default computation model, calculates and obtains fired power generating unit in the prediction of preset time period
Energy consumption data, and then fired power generating unit is obtained in the actual consumption data of preset time period and the deviation of prediction of energy consumption data, thus
Obtain energy consumption deviation probability set.It realizes and goes to calculate the reality under power dissipation obj ectives on the basis of getting energy consumption deviation probability set
Existing probability substantially increases the calculating accuracy that probability is realized under power dissipation obj ectives.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, 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 is the energy consumption deviation method for calculating probability flow diagram that one embodiment of the application provides;
Fig. 2 is the energy consumption deviation method for calculating probability flow diagram that another embodiment of the application provides;
Fig. 3 is the energy consumption deviation method for calculating probability flow diagram that the another embodiment of the application provides;
Fig. 4 is the energy consumption deviation method for calculating probability flow diagram that another embodiment of the application provides;
Fig. 5 is the energy consumption deviation probability calculation device structural schematic diagram that one embodiment of the application provides;
Fig. 6 is the energy consumption deviation probability calculation device structural schematic diagram that another embodiment of the application provides;
Fig. 7 is the energy consumption deviation probability calculation device structural schematic diagram that the another embodiment of the application provides;
Fig. 8 is the energy consumption deviation probability calculation device structural schematic diagram that one embodiment of the application provides.
Specific embodiment
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, 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.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.Meanwhile in the disclosure
In description, term " first ", " second " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Fig. 1 is the energy consumption deviation method for calculating probability flow diagram that provides of one embodiment of the application, and this method can be by
The equipment such as computer or server execute, but not concrete restriction.As shown in Figure 1, the energy consumption deviation method for calculating probability includes:
S101, the work state information for obtaining fired power generating unit in preset time period.
It should be noted that the fired power generating unit of the application includes generating set and thermal power plant unit, generating set is for fire coal
It heats up water and generates vapor, the steam turbine that vapor enters steamer workshop makes rotor quick rotation generate electricity, and thermal power plant unit is for fire coal
It heats up water and generates vapor, vapor enters heat supply pipeline and carries out heat supply.
Optionally, when fired power generating unit is in running order, there can be a variety of different work state informations, for different
The working performance of work state information, fired power generating unit can be different.The working condition letter of available following N days fired power generating units
Breath, in order to assess the working performance of fired power generating unit according to the N days work state informations, to preferably go excellent
Change the performance of fired power generating unit, promotes heating effect etc..
Optionally, the work state information of fired power generating unit can indicate the ambient condition number of fired power generating unit during the work time
According to, Heating State data etc..Its usual work state information can be specifically related to practical heat demand comprising a variety of.
S102, thermoelectricity is obtained using default computation model according to the work state information of fired power generating unit in preset time period
The work state information of unit and the mapping relations of energy consumption data.
Wherein, preset computation model be according to multiple groups work state information of the fired power generating unit in history preset time period and
Energy consumption data training obtains.
It should be noted that the work state information that fired power generating unit is different, it is also different for corresponding to the energy consumption data generated
, preset computation model can be used, the mapping relations between the work state information of fired power generating unit and energy consumption data are obtained.
Optionally, preset computation model can be according to preset training rules, to the multiple groups history got
Work state information and energy consumption data in preset time period are trained acquisition.Default computation model can be (anti-using BP
To propagate multilayer feedforward neural network), LM-BP (based on Levenberg-Marquardt method backpropagation multilayer feedover), RBF (diameter
To basis function neural network), SVM (support vector machines), a variety of training patterns such as CNN (convolutional neural networks), do not limit specifically
System.
S103, believed according to the working condition of fired power generating unit work state information within a preset period of time and fired power generating unit
The mapping relations of breath and energy consumption data calculate the prediction of energy consumption data of fired power generating unit within a preset period of time.
After the mapping relations of the above-mentioned work state information for getting fired power generating unit and energy consumption data, when to following N days
Energy consumption data when being predicted, can using the work state information in following N days as the input parameter of default computation model,
According to mapping relations, following N days default energy consumption parameters can be calculated.
It is alternatively possible to which then the following N days available N group work state informations, can count accordingly as unit of one day
Calculation gets N number of energy consumption data, can also be as unit of more days, such as obtains two days work state informations, calculates this two days
The corresponding energy consumption data of work state information.Multiple groups were equally divided by following N days, every group is calculated a corresponding energy
Consume data.Specifically how time division is carried out, herein with no restrictions, as long as the number of days such as satisfaction divide.
S104, actual consumption data and prediction of energy consumption data according to fired power generating unit within a preset period of time are calculated and are obtained
Energy consumption deviation probability set, energy consumption deviation probability set are used to indicate the probability distribution of energy consumption deviation.
The prediction of energy consumption data of fired power generating unit within a preset period of time have been got above by calculating, and according to actual
Work state information can accordingly get the actual consumption data of fired power generating unit within a preset period of time.
In general, there are deviation between actual consumption data and prediction of energy consumption data, the energy consumption deviation and its corresponding is sought
Deviation probability distribution can further go the realization calculated under acquisition power dissipation obj ectives general on the basis of the deviation probability distribution
Rate, so that the calculated result more accurate and effective of the realization probability under power dissipation obj ectives.
It should be noted that since what is be calculated is prediction of energy consumption data in a period of time, i.e. prediction of energy consumption data
There are multiple, correspondingly, actual consumption data are there is also multiple, in this way, calculating the energy consumption deviation that obtains there is also multiple, lead to
It crosses preset rules to convert multiple energy consumption deviation, seeks the corresponding energy consumption deviation probability set of multiple energy consumption deviations
It closes, to get the probability distribution of energy consumption deviation.
Energy consumption deviation method for calculating probability provided by the embodiments of the present application, by using the history working condition of fired power generating unit
Information and energy consumption data, training energy consumption preset computation model, using trained default computation model, calculate and obtain fired power generating unit
In the prediction of energy consumption data of preset time period, and then fired power generating unit is obtained in the actual consumption data of preset time period and prediction energy
The deviation for consuming data, to obtain energy consumption deviation probability set.On the basis of getting energy consumption deviation probability set, go to calculate energy consumption
Realization probability under target substantially increases the calculating accuracy that probability is realized under power dissipation obj ectives.
Fig. 2 is the energy consumption deviation method for calculating probability flow diagram that another embodiment of the application provides, and optionally, is such as schemed
Shown in 2, obtained according to the work state information and energy consumption data of fired power generating unit in preset time period using default computation model
Before the work state information of fired power generating unit and the mapping relations of energy consumption data, further includes:
S201, multiple groups work state information and energy consumption data of the fired power generating unit in history preset time period are obtained.
Optionally, the work state information in multiple groups history preset time period and energy consumption data can be from server background
It is obtained in a large amount of historical datas of storage, is also possible to reading etc. directly from data record instrument, for the side of data acquisition
Formula is not particularly limited.
S202, according to preset rules, multiple groups work state information is divided into different classes of, every kind of classification corresponds to different
Energy consumption data.
It is alternatively possible to which multiple groups work state information is divided into according to the operation characteristic and moving law of fired power generating unit
It is different classes of, such as: work state information may include: tetra- kinds of status informations of A, B, C, D, when certain the group status information got
In include A and B, and the value of A and B is simultaneously when meeting its corresponding pre-set interval, then using this group of work state information as first
Class corresponds to an energy consumption data value, then, when including A, B, C in certain the group status information got, as long as the value of A and B is same
When meet its corresponding pre-set interval, this group of job information state is divided into the first kind, with the corresponding energy consumption number of the first kind
According to value.Again for example: organizing when certain got includes B and C in status information, and the value of B and C meets its corresponding preset areas simultaneously
Between when, then using this group of work state information as the second class, correspond to an energy consumption data value, then, when certain the group shape got
When including A, B, C in state information, the value of A and B do not meet its corresponding pre-set interval simultaneously, but to meet its simultaneously right for the value of B and C
The pre-set interval answered, then this group of job information state is divided into the second class, has the corresponding energy consumption data value of the second class.
By the above method, multiple groups work state information can be divided into different classes of, and the corresponding energy of every kind of classification
Consumption data are all different, and thus can obtain its corresponding energy consumption data according to different work state informations.
S203, according to the corresponding relationship of every kind of classification work state information and energy consumption data, training, which obtains, default calculates mould
Type.
By above-mentioned preset classifying rules, pair of available different classes of work state information and energy consumption data
It should be related to, according to the corresponding relationship, the multiple groups work state information for the history preset time period that will acquire calculates mould as default
The input of type is trained model using multiple energy consumption datas as the output of default computation model, to obtain the default calculating
Model.
Optionally, the preset rules in the present embodiment are not limited to above-mentioned classification method, can be according to the reality of fired power generating unit
Border working performance and rule are taken other different classification methods, are not particularly limited herein.
Fig. 3 is the energy consumption deviation method for calculating probability flow diagram that the another embodiment of the application provides, and optionally, is such as schemed
Shown in 3, fired power generating unit is obtained after the multiple groups work state information and energy consumption data in history preset time period, further includes:
S301, according to preset condition, judge whether the multiple groups work state information of fired power generating unit meets the requirements.
S302, if not satisfied, then the work state information of the condition that is unsatisfactory for is deleted.
In general, can have some invalid data in the historical data got, in order to meet the integrality of data and have
Effect property, need to according to demand delete undesirable data.
It optionally, can be right according to preset condition after getting the multiple groups work state information of history preset time period
The multiple groups work state information is screened.Such as: work state information may include various states information, every kind of status information
It is provided with preset threshold, multiple status informations that status information is less than or equal to preset threshold are deleted, to guarantee the complete of data
Whole property and validity.
Fig. 4 is the energy consumption deviation method for calculating probability flow diagram that another embodiment of the application provides, and optionally, is such as schemed
Shown in 4, according to the actual consumption data and prediction of energy consumption data of fired power generating unit within a preset period of time, calculates and obtain energy consumption deviation
Probability set, comprising:
S401, actual consumption data and prediction of energy consumption data according to fired power generating unit within a preset period of time are calculated and are obtained
Multiple energy consumption deviations.
The multiple prediction of energy consumption data of fired power generating unit within a preset period of time are got above by calculating, meanwhile, according to
Actual conditions also calculate and have got corresponding multiple actual consumption data, therefore, it can calculate and obtain multiple energy consumption deviations.
S402, according to preset rules, multiple energy consumption deviations are divided into multiple sections.
Such as: it is above-mentioned that multiple energy consumption deviations are calculated are as follows: 0.2,0.7,0.5,0.3,1.2,0.8,0.9,1.5 etc., root
According to preset interval division rule, multiple energy consumption deviation is divided into multiple sections, such as: it can choose deviation 0~1
Between be first interval, deviation between 1~2 be second interval, and so on, in this way, above-mentioned first interval include energy consumption it is inclined
Difference are as follows: 0.2,0.7,0.5,0.3,0.8,0.9, second interval includes energy consumption deviation are as follows: 1.2,1.5.
Optionally, interval division is carried out to energy consumption data and is not limited to the above method, it can be according to the practical work of fired power generating unit
Make performance effectively to be divided.
S403, according to the ratio of the quantity of energy consumption deviation in each section and energy consumption deviation sum, calculate each section pair
The energy consumption deviation probability answered obtains energy consumption deviation probability set.
As it is above-mentioned to obtained multiple energy consumption data demarcation intervals after, comprising energy consumption deviation quantity be 6, the in first interval
It comprising energy consumption deviation quantity is 2 in two sections, then, calculating and obtaining the corresponding energy consumption deviation probability of first interval is 0.75, second
The corresponding energy consumption deviation probability in section is 0.25.Certainly, different according to the length of the preset time period of selection, calculate the energy of acquisition
The quantity for consuming deviation is also different, and the energy consumption deviation probability got accordingly is not also identical, with specific reference to actual conditions, into
Row is corresponding to be calculated.
By calculating the multiple energy consumption deviation probability got, energy consumption deviation probability set can be obtained, is obtained newly when calculating
Energy consumption deviation after, which it is inclined can be obtained according to the corresponding energy consumption deviation probability in its corresponding section and the section
The corresponding energy consumption deviation probability of difference.
Optionally, it according to the energy consumption deviation probability set got, can further calculate to obtain under each power dissipation obj ectives
Probability is realized, to effectively raise the accuracy in computation for realizing probability under power dissipation obj ectives.
Optionally, work state information includes following one or more: the load of fired power generating unit, confession heat flow, environment temperature
Degree and coal quality.
The above-mentioned every group of work state information got can only include the load of fired power generating unit, confession heat flow, environment temperature
Degree is one or more with coal quality, specifically related to the operating status of fired power generating unit.
It should be noted that coal data is obtained according to the coal quality quantity being previously stored in coal yard, optionally, on
Stating energy consumption data may include: boiler efficiency, thermal loss of steam turbine rate, coal consumption for power generation, station service power consumption rate, net coal consumption rate etc..
Energy consumption deviation method for calculating probability provided by the embodiments of the present application, by using the history working condition of fired power generating unit
Information and energy consumption data, training energy consumption preset computation model, using trained default computation model, calculate and obtain fired power generating unit
In the prediction of energy consumption data of preset time period, and then fired power generating unit is obtained in the actual consumption of preset time period.
The deviation of data and prediction of energy consumption data, to obtain energy consumption deviation probability set.Getting energy consumption deviation probability
It on the basis of collection, goes to calculate the realization probability under power dissipation obj ectives, substantially increases and realize that the calculating of probability is accurate under power dissipation obj ectives
Property.
Fig. 5 is the energy consumption deviation probability calculation device structural schematic diagram that one embodiment of the application provides, as shown in figure 5, should
Device includes: to obtain module 501, processing module 502, the first computing module 503 and the second computing module 504.
Module 501 is obtained, for obtaining the work state information of fired power generating unit in preset time period.
Processing module 502, for the work state information according to fired power generating unit in preset time period, using default calculating mould
Type obtains the work state information of fired power generating unit and the mapping relations of energy consumption data, and presetting computation model is according to fired power generating unit
What multiple groups work state information and energy consumption data training in history preset time period obtained.
First computing module 503, for the work state information and thermal motor according to fired power generating unit within a preset period of time
The work state information of group and the mapping relations of energy consumption data calculate the prediction of energy consumption number of fired power generating unit within a preset period of time
According to.
Second computing module 504, for according to fired power generating unit actual consumption data within a preset period of time and prediction energy
Data are consumed, calculates and obtains energy consumption deviation probability set, energy consumption deviation probability set is used to indicate the probability distribution of energy consumption deviation.
Fig. 6 is the energy consumption deviation probability calculation device structural schematic diagram that another embodiment of the application provides, as shown in fig. 6,
Optionally, device further include: categorization module 505, training module 506.
Above-mentioned acquisition module 501 is also used to obtain multiple groups working condition letter of the fired power generating unit in history preset time period
Breath and energy consumption data;Categorization module 505, it is different classes of for according to preset rules, multiple groups work state information to be divided into, often
Kind classification corresponds to different energy consumption datas;Training module 506, for according to every kind of classification work state information and energy consumption data
Corresponding relationship, training obtain default computation model.
Fig. 7 is the energy consumption deviation probability calculation device structural schematic diagram that the another embodiment of the application provides, as shown in fig. 7,
Optionally, device further include: judgment module 507.
Judgment module 507, for judging whether the multiple groups work state information of fired power generating unit meets and wanting according to preset condition
It asks;If not satisfied, then the work state information for the condition that is unsatisfactory for is deleted.
Optionally, above-mentioned second computing module 504, specifically for the practical energy according to fired power generating unit within a preset period of time
Data and prediction of energy consumption data are consumed, calculates and obtains multiple energy consumption deviations;According to preset rules, multiple energy consumption deviations are divided into more
A section;According to the ratio of the quantity of energy consumption deviation in each section and energy consumption deviation sum, the corresponding energy in each section is calculated
Deviation probability is consumed, energy consumption deviation probability set is obtained.
The method that above-mentioned apparatus is used to execute previous embodiment offer, it is similar that the realization principle and technical effect are similar, herein not
It repeats again.
The above module can be arranged to implement one or more integrated circuits of above method, such as: one
Or multiple specific integrated circuits (Application Specific Integrated Circuit, abbreviation ASIC), or, one
Or multi-microprocessor (digital singnal processor, abbreviation DSP), or, one or more field programmable gate
Array (Field Programmable Gate Array, abbreviation FPGA) etc..For another example, when some above module passes through processing elements
When the form of part scheduler program code is realized, which can be general processor, such as central processing unit (Central
Processing Unit, abbreviation CPU) or it is other can be with the processor of caller code.For another example, these modules can integrate
Together, it is realized in the form of system on chip (system-on-a-chip, abbreviation SOC).
Fig. 8 is the energy consumption deviation probability calculation device structural schematic diagram that one embodiment of the application provides, as shown in figure 8, should
Device can integrate the chip in terminal device or terminal device, which, which can be, has energy consumption deviation probability calculation function
Calculating equipment.
The device includes: memory 601, processor 602.
Memory 601 is for storing program, the program that processor 602 calls memory 601 to store, to execute the above method
Embodiment.Specific implementation is similar with technical effect, and which is not described herein again.
Optionally, the present invention also provides a kind of program product, such as computer readable storage medium, including program, the journeys
Sequence is when being executed by processor for executing above method embodiment.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or logical of device or unit
Letter connection 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, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) or processor (English: processor) execute this hair
The part steps of bright each embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory
(English: Read-Only Memory, abbreviation: ROM), random access memory (English: Random Access Memory, letter
Claim: RAM), the various media that can store program code such as magnetic or disk.
Claims (10)
1. a kind of energy consumption deviation method for calculating probability characterized by comprising
Obtain the work state information of fired power generating unit in preset time period;
The thermoelectricity is obtained using default computation model according to the work state information of fired power generating unit in the preset time period
The work state information of unit and the mapping relations of energy consumption data, the default computation model are to be gone through according to the fired power generating unit
What multiple groups work state information and energy consumption data training in history preset time period obtained;
According to fired power generating unit work state information within a preset period of time and the work state information of the fired power generating unit
With the mapping relations of energy consumption data, the prediction of energy consumption data of the fired power generating unit within a preset period of time are calculated;
According to the actual consumption data and the prediction of energy consumption data of the fired power generating unit within a preset period of time, calculates and obtain energy
Deviation probability set is consumed, the energy consumption deviation probability set is used to indicate the probability distribution of energy consumption deviation.
2. the method according to claim 1, wherein the work according to fired power generating unit in the preset time period
Make status information and energy consumption data, using default computation model, obtains the work state information and energy consumption number of the fired power generating unit
According to mapping relations before, further includes:
Obtain multiple groups work state information and energy consumption data of the fired power generating unit in history preset time period;
According to preset rules, the multiple groups work state information is divided into different classes of, every kind of classification corresponds to different energy consumptions
Data;
According to the corresponding relationship of every kind of classification work state information and the energy consumption data, training obtains the default calculating
Model.
3. according to the method described in claim 2, it is characterized in that, described obtain the fired power generating unit in history preset time period
After interior multiple groups work state information and energy consumption data, further includes:
According to preset condition, judge whether the multiple groups work state information of the fired power generating unit meets the requirements;
If not satisfied, then the work state information for the condition that is unsatisfactory for is deleted.
4. the method according to claim 1, wherein it is described according to the fired power generating unit within a preset period of time
Actual consumption data and the prediction of energy consumption data calculate and obtain energy consumption deviation probability set, comprising:
According to the actual consumption data and the prediction of energy consumption data of the fired power generating unit within a preset period of time, it is more to calculate acquisition
A energy consumption deviation;
According to preset rules, the multiple energy consumption deviation is divided into multiple sections;
According to the ratio of the quantity of energy consumption deviation in each section and energy consumption deviation sum, it is corresponding to calculate each section
Energy consumption deviation probability, obtain energy consumption deviation probability set.
5. the method according to claim 1, wherein the work state information includes following one or more:
Load, confession heat flow, environment temperature and the coal quality of fired power generating unit.
6. a kind of energy consumption deviation probability calculation device characterized by comprising obtain module, processing module, the first computing module
And second computing module;
The acquisition module, for obtaining the work state information of fired power generating unit in preset time period;
The processing module, for the work state information according to fired power generating unit in the preset time period, using default calculating
Model, obtains the work state information of the fired power generating unit and the mapping relations of energy consumption data, and the default computation model is root
It is obtained according to multiple groups work state information of the fired power generating unit in history preset time period and energy consumption data training;
First computing module, for according to fired power generating unit work state information within a preset period of time and described
The work state information of fired power generating unit and the mapping relations of energy consumption data calculate the fired power generating unit within a preset period of time pre-
Survey energy consumption data;
Second computing module, for according to fired power generating unit actual consumption data within a preset period of time and described pre-
Energy consumption data is surveyed, calculates and obtains energy consumption deviation probability set, the energy consumption deviation probability set is used to indicate the probability point of energy consumption deviation
Cloth.
7. device according to claim 6, which is characterized in that further include: categorization module, training module;
The acquisition module, be also used to obtain multiple groups work state information of the fired power generating unit in history preset time period and
Energy consumption data;
The categorization module, for according to preset rules, the multiple groups work state information to be divided into different classes of, every type
Different energy consumption datas is not corresponded to;
The training module, for the corresponding relationship according to every kind of classification work state information and the energy consumption data, instruction
Practice and obtains the default computation model.
8. device according to claim 7, which is characterized in that further include: judgment module;
The judgment module, for judging whether the multiple groups work state information of the fired power generating unit meets according to preset condition
It is required that;If not satisfied, then the work state information for the condition that is unsatisfactory for is deleted.
9. device according to claim 6, which is characterized in that second computing module is specifically used for according to the fire
The actual consumption data and the prediction of energy consumption data of motor group within a preset period of time calculate and obtain multiple energy consumption deviations;Root
According to preset rules, the multiple energy consumption deviation is divided into multiple sections;According to the quantity of energy consumption deviation in each section
And the ratio of energy consumption deviation sum calculates the corresponding energy consumption deviation probability in each section, obtains energy consumption deviation probability set.
10. a kind of computer storage medium, which is characterized in that be stored with program, described program in the computer storage medium
When being executed by processor, the method as described in any one of claims 1 to 5 is realized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811654727.6A CN109389254A (en) | 2018-12-29 | 2018-12-29 | Energy consumption deviation method for calculating probability, device and computer storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811654727.6A CN109389254A (en) | 2018-12-29 | 2018-12-29 | Energy consumption deviation method for calculating probability, device and computer storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109389254A true CN109389254A (en) | 2019-02-26 |
Family
ID=65430936
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811654727.6A Pending CN109389254A (en) | 2018-12-29 | 2018-12-29 | Energy consumption deviation method for calculating probability, device and computer storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109389254A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111332809A (en) * | 2020-03-18 | 2020-06-26 | 华润电力技术研究院有限公司 | Material piling and taking control method and system for coordinating coal inventory and bucket wheel machine |
CN111445132A (en) * | 2020-03-26 | 2020-07-24 | 华润电力技术研究院有限公司 | Data processing method, data processing system and computer storage medium |
CN112700122A (en) * | 2020-12-29 | 2021-04-23 | 华润电力技术研究院有限公司 | Thermodynamic system performance calculation method, device and equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101266485A (en) * | 2008-04-08 | 2008-09-17 | 南京迪玛斯电气有限公司 | Thermal power unit operation energy consumption actual measurement system |
CN101363653A (en) * | 2008-08-22 | 2009-02-11 | 日滔贸易(上海)有限公司 | Energy consumption control method and device of central air-conditioning refrigeration system |
CN106056469A (en) * | 2016-06-01 | 2016-10-26 | 广东工业大学 | Data processing method and device applied to power system unit commitment technology |
CN108054750A (en) * | 2017-12-08 | 2018-05-18 | 西南大学 | The peak load regulation network control system and method for a kind of meter and summer air conditioning load difference characteristic |
CN108833491A (en) * | 2018-05-24 | 2018-11-16 | 朔联科技(上海)有限公司 | The energy consumption statistical method and server of Internet of things system |
CN108988356A (en) * | 2018-07-03 | 2018-12-11 | 上海交通大学 | Electric heating microgrid interconnection tie power fluctuation based on virtual energy storage stabilizes method |
-
2018
- 2018-12-29 CN CN201811654727.6A patent/CN109389254A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101266485A (en) * | 2008-04-08 | 2008-09-17 | 南京迪玛斯电气有限公司 | Thermal power unit operation energy consumption actual measurement system |
CN101363653A (en) * | 2008-08-22 | 2009-02-11 | 日滔贸易(上海)有限公司 | Energy consumption control method and device of central air-conditioning refrigeration system |
CN106056469A (en) * | 2016-06-01 | 2016-10-26 | 广东工业大学 | Data processing method and device applied to power system unit commitment technology |
CN108054750A (en) * | 2017-12-08 | 2018-05-18 | 西南大学 | The peak load regulation network control system and method for a kind of meter and summer air conditioning load difference characteristic |
CN108833491A (en) * | 2018-05-24 | 2018-11-16 | 朔联科技(上海)有限公司 | The energy consumption statistical method and server of Internet of things system |
CN108988356A (en) * | 2018-07-03 | 2018-12-11 | 上海交通大学 | Electric heating microgrid interconnection tie power fluctuation based on virtual energy storage stabilizes method |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111332809A (en) * | 2020-03-18 | 2020-06-26 | 华润电力技术研究院有限公司 | Material piling and taking control method and system for coordinating coal inventory and bucket wheel machine |
CN111445132A (en) * | 2020-03-26 | 2020-07-24 | 华润电力技术研究院有限公司 | Data processing method, data processing system and computer storage medium |
CN111445132B (en) * | 2020-03-26 | 2023-05-02 | 华润电力技术研究院有限公司 | Data processing method, data processing system and computer storage medium |
CN112700122A (en) * | 2020-12-29 | 2021-04-23 | 华润电力技术研究院有限公司 | Thermodynamic system performance calculation method, device and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gao et al. | An improved artificial bee colony algorithm for flexible job-shop scheduling problem with fuzzy processing time | |
Fallah-Mehdipour et al. | MOPSO algorithm and its application in multipurpose multireservoir operations | |
Chen | Two-level hierarchical approach to unit commitment using expert system and elite PSO | |
Paul et al. | Demand response in data centers through energy-efficient scheduling and simple incentivization | |
CN109389254A (en) | Energy consumption deviation method for calculating probability, device and computer storage medium | |
Chen et al. | An optimal sample allocation strategy for partition-based random search | |
Yang et al. | The cascade reservoirs multi-objective ecological operation optimization considering different ecological flow demand | |
Hardiansyah et al. | Solving economic load dispatch problem using particle swarm optimization technique | |
CN109546646A (en) | A kind of region power spot market distributing goes out clearing method, device, equipment and medium | |
Nieße et al. | Conjoint dynamic aggregation and scheduling methods for dynamic virtual power plants | |
CN112130538B (en) | Method, device, equipment and medium for control optimization and model training of coal mill | |
CN109272353A (en) | Meter and integration requirement, which respond probabilistic system dynamic probability, can flow analysis method | |
Pan et al. | A single machine-based scheduling optimisation model integrated with preventive maintenance policy for maximising the availability | |
CN103905227B (en) | A kind of server energy consumption control method and system | |
CN115829134A (en) | Power supply scheduling method and system oriented to source network load uncertainty | |
Uzunoğlu | An adaptive Bayesian approach with subjective logic reliability networks for preventive maintenance | |
CN114897447A (en) | Comprehensive energy cooperative control method and system | |
CN106162668A (en) | The method and apparatus determining network parameter | |
CN115983733B (en) | Electric power market clear data processing method and device based on water level control | |
US20140365023A1 (en) | Systems and Methods for Computer Implemented Energy Management | |
CN106598716A (en) | Task scheduling method based on multiple processors | |
CN116362504A (en) | Optimal scheduling method for electric heating combined energy system, terminal equipment and storage medium | |
Anderson et al. | Optimize Deep Decarbonization Pathways in California with Power System Planning Using Surrogate Level-based Lagrangian Relaxation | |
Pan et al. | A mixed integer linear programming method for dynamic economic dispatch with valve point effect | |
dos Santos et al. | A new approach for area interchange control modeling |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190226 |