CN103345555A - Thermal power unit coal consumption characteristic curve modeling method based on genetic programming - Google Patents
Thermal power unit coal consumption characteristic curve modeling method based on genetic programming Download PDFInfo
- Publication number
- CN103345555A CN103345555A CN2013102813929A CN201310281392A CN103345555A CN 103345555 A CN103345555 A CN 103345555A CN 2013102813929 A CN2013102813929 A CN 2013102813929A CN 201310281392 A CN201310281392 A CN 201310281392A CN 103345555 A CN103345555 A CN 103345555A
- Authority
- CN
- China
- Prior art keywords
- genetic programming
- coal consumption
- data
- collection
- method based
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention discloses a thermal power unit coal consumption characteristic curve modeling method based on genetic programming. The method includes the following steps that at first, an original population, namely a stop character set and a function character set used for modeling, of the genetic programming is determined; on the basis of the original population, standard fitness adopted to express the overall error between an evolution individual and an objective is determined; then on the basis of the determined the standard fitness, a multi-objective genetic programming algorithm measuring adaptability of the individual is determined; coal consumption is calculated through processing of data collected by DCS equipment coming from a field; genetic programming operation is carried out on the processed data according to the determined stop character set, the function character set, the standard fitness and the multi-objective genetic programming algorithm to set up a thermal power unit coal consumption characteristic curve model. The method has the advantages of truly determining a coal consumption characteristic curve in real time, and therefore reasonably optimizing loads.
Description
Technical field
The present invention relates to the thermoelectricity power field, particularly, relate to a kind of fired power generating unit coal consumption family curve modeling method based on genetic programming.
Background technology
Along with China's electric system constantly develops, thermal power plant's installed capacity constantly increases, and considers many-sided factors such as cost of electricity-generating, overall efficiency and environmental protection, makes the set optimization operation, and energy-saving and cost-reducing is very necessary.The coal consumption family curve can reflect the funtcional relationship between monoblock coal consumption and the load, and the economical operation of research unit is played key effect with loading to optimize to distribute.Whether the coal consumption characteristic accurately directly has influence on the reliability of unit cost analysis, the rationality of load distribution.
The coal consumption characteristic has typically characteristics such as non-linear, time variation, makes the difficult more accurate model that obtains.Existing modeling method comprises modelling by mechanism and test modeling, for the coal consumption family curve, is to carry out thermal test by manufacturer to obtain, and these curves generally remain unchanged for a long period of time.But the actual motion coal consumption characteristic of unit is closely bound up with the real time status of unit, many-sided factor such as chooses as the method for operation, equipment operation condition, personnel operation technology, coal and determines all to have certain influence to coal consumption is characteristic.Existing modeling method can not be true, real-time the characteristic that reflects coal consumption, can not load more and carry out reasonably optimizing.
Summary of the invention
The objective of the invention is to, at the problems referred to above, propose a kind of fired power generating unit coal consumption family curve modeling method based on genetic programming, realizing the family curve of true, real-time definite coal consumption, thus the reasonable advantage of preferred load.
For achieving the above object, the technical solution used in the present invention is:
A kind of fired power generating unit coal consumption family curve modeling method based on genetic programming may further comprise the steps:
At first determine the initial population of genetic programming, i.e. the full stop collection that modeling is used and functor collection;
Determine to determine the expression evolution individuality of employing and the standard adaptation degree of the total error between the target on the basis of above-mentioned initial population;
On the basis of the above-mentioned fitness that settles the standard, determine to weigh the multiple goal genetic programming algorithm of individual adaptability then;
And by the data from the DCS equipment collection at scene are handled the calculating coal consumption amount;
Carry out the operation of genetic programming according to the data of above-mentioned definite full stop collection, functor collection, standard adaptation degree and multiple goal genetic programming algorithm after to above-mentioned processing, set up fired power generating unit coal consumption family curve model.
According to a preferred embodiment of the invention, described full stop collection comprises variable and constant, and described functor collection comprises sign of operation and mathematical function.
According to a preferred embodiment of the invention, described standard adaptation degree equation is:
Wherein,
f i (x)Function expression for the system of individual representative in the evolution population;
f o (x)For the function of goal systems is expressed.
According to a preferred embodiment of the invention, described multiple goal genetic programming algorithm is:
In the formula,
R (k, t)Expression the
tGeneration the
kThe original fitness of individuality,
NThe expression number of nodes,
MaxThe maximum deviation of function representation calculated value and actual value,
aWith
bBe weight coefficient.
According to a preferred embodiment of the invention, it is described by the data from the DCS equipment collection at scene are handled the calculating coal consumption amount, be mainly the interference of data in the data of handling the coal consumption amount that DCS equipment gathers, this interference comprises two kinds, first kind is because the random disturbance that produces during data acquisition is removed by the mode of filtering; Second kind is the bigger trip point of fluctuation ratio.
According to a preferred embodiment of the invention, above-mentioned second kind is disturbed the method for employing residual analysis to carry out Data Detection; The method of described residual analysis is: the data of establishing collection are x, data after the processing are y, Δ is the limit value of data variation, under the prerequisite in identical sampling time, absolute value with front and back double sampling data difference is weighed pace of change, for k sampled value x (k), calculates | x (k)-x (k-1) |, if | x (k)-x (k-1) |<Δ, there is not abnormity point, y (k)=x (k) then, if | x (k)-x (k-1) | 〉=Δ, then may there be abnormity point, then get 1 x (k+1) this moment again, if | x (k+1)-x (k) |≤Δ, and if variation tendency identical, then think and have disturbance, make y (k)=ax (k-1)+bx (k), a wherein, b is weight coefficient, and a, b ∈ (0.1); If variation tendency on the contrary then can think that x (k) is trip point, makes y (k)=ax (k-1)+bx (k+1), if | x (k+1)-x (k) | 〉=Δ, can think so to have abnormity point, should remove.
Technical scheme of the present invention has following beneficial effect:
Technical scheme of the present invention, with coal consumption amount and the inputoutput data of load as genetic programming, determine coal consumption family curve accurately, and adopt the genetic programming method to set up coal consumption family curve model, the funtcional relationship between reflection monoblock coal consumption amount and the load.Reached the family curve of true, real-time definite coal consumption, thus the reasonable purpose of preferred load.
Below by drawings and Examples, technical scheme of the present invention is described in further detail.
Description of drawings
Fig. 1 is the process flow diagram of the described fired power generating unit coal consumption family curve modeling method based on genetic programming of the embodiment of the invention;
Fig. 2 is the process flow diagram of the described genetic programming algorithm of the embodiment of the invention.
Embodiment
Below in conjunction with accompanying drawing the preferred embodiments of the present invention are described, should be appreciated that preferred embodiment described herein only is used for description and interpretation the present invention, and be not used in restriction the present invention.
As shown in Figure 1, a kind of fired power generating unit coal consumption family curve modeling method based on genetic programming may further comprise the steps:
At first determine the initial population of genetic programming, i.e. the full stop collection that modeling is used and functor collection;
Determine to determine the expression evolution individuality of employing and the standard adaptation degree of the total error between the target on the basis of above-mentioned initial population;
On the basis of the above-mentioned fitness that settles the standard, determine to weigh the multiple goal genetic programming algorithm of individual adaptability then;
And by the data from the DCS equipment collection at scene are handled the calculating coal consumption amount;
Carry out the operation of genetic programming according to the data of above-mentioned definite full stop collection, functor collection, standard adaptation degree and multiple goal genetic programming algorithm after to above-mentioned processing, set up fired power generating unit coal consumption family curve model.
Wherein, above-mentioned full stop collection comprises variable and constant etc., and the functor collection comprises sign of operation and mathematical function etc.Standard adaptation degree equation is:
Wherein,
f i (x)Function expression for the system of individual representative in the evolution population;
f o (x)For the function of goal systems is expressed.
The multiple goal genetic programming algorithm is:
In the formula,
R (k, t)Expression the
tGeneration the
kThe original fitness of individuality,
NThe expression number of nodes,
MaxThe maximum deviation of function representation calculated value and actual value,
aWith
bBe weight coefficient.
By the data from the DCS equipment collection at scene are handled the calculating coal consumption amount, be mainly the interference of data in the data of handling the coal consumption amount that DCS equipment gathers, this interference comprises two kinds, and first kind is because the random disturbance that produces during data acquisition is removed by the mode of filtering; Second kind is the bigger trip point of fluctuation ratio.Disturb the method for employing residual analysis to carry out Data Detection for second kind; The method of described residual analysis is: the data of establishing collection are x, data after the processing are y, Δ is the limit value of data variation, under the prerequisite in identical sampling time, absolute value with front and back double sampling data difference is weighed pace of change, for k sampled value x (k), calculates | x (k)-x (k-1) |, if | x (k)-x (k-1) |<Δ, there is not abnormity point, y (k)=x (k) then, if | x (k)-x (k-1) | 〉=Δ, then may there be abnormity point, then get 1 x (k+1) this moment again, if | x (k+1)-x (k) |≤Δ, and if variation tendency identical, then think and have disturbance, make y (k)=ax (k-1)+bx (k), a wherein, b is weight coefficient, and a, b ∈ (0.1); If variation tendency on the contrary then can think that x (k) is trip point, makes y (k)=ax (k-1)+bx (k+1), if | x (k+1)-x (k) | 〉=Δ, can think so to have abnormity point, should remove.
Its specific implementation process is, adopt genetic programming that coal consumption family curve model is carried out identification and at first will produce initial population, solve required full stop collection (comprising variable, constant etc.) and the functor collection (comprising various sign of operation, mathematical function etc.) of customer problem, by full stop collection and functor collection generation initial population at random, i.e. so-called binary tree structure group of individuals.Secondly determine fitness, it is similar to the adaptability of environment to be used for weighing the ability and the occurring in nature biology that solve a certain problem exactly.The technical program accepted standard fitness is defined as:
In the formula,
f i (x)Function expression for the system of individual representative in the evolution population;
f o (x)For the function of goal systems is expressed.The standard adaptation kilsyth basalt has shown the total error between evolution individuality and the target.In order to weigh individual adaptability, this paper adopts a kind of multiple goal genetic programming algorithm, and this algorithm fitness function expression formula is:
Wherein,
R (k, t)Expression the
tGeneration the
kThe original fitness of individuality,
NThe expression number of nodes,
MaxThe maximum deviation of function representation calculated value and actual value,
aWith
bBe weight coefficient.This method can be fast near system to be identified, and is better to practical application effect.
Simultaneously, for single binary tree program the operation that copies and make a variation is taking place, and existing interlace operation between the different binary trees.The individuality that fitness is high obtains preserving in genetic process, and the individuality that fitness is low is eliminated gradually, passes through the number evolution in generation like this, has obtained the high individuality of fitness, has also just picked out the mathematical model of target gradually.
Secondly need carry out data and handle, calculate the data of coal consumption amount all from the DCS equipment at scene, data owner will exist two classes to disturb: the one, and the random disturbance that produces during owing to data acquisition can be removed by the mode of filtering; The 2nd, the trip point that fluctuation ratio is bigger.The needed data of modeling are variation continuous in time as unit load, main steam temperature, main steam pressure etc., and these data are had the restriction of amplitude limitation and pace of change, and the bigger point of this class fluctuation is abnormity point.
This method adopts the method for residual analysis to carry out Data Detection.If the data of gathering are
x, the data after the processing are
y, Δ is the limit value of data variation, under the prerequisite in identical sampling time, the absolute value of available front and back double sampling data difference is weighed pace of change.For
kIndividual sampled value
X (k), calculate
| x (k)-x (k-1) |If,
| x (k)-x (k-1) |There is not abnormity point in<Δ, then
Y (k)=x (k)If,
| x (k)-x (k-1) |Then may there be abnormity point in 〉=Δ, and then can get a bit this moment again
X (k+1)If,
| x (k+1)-x (k) |≤ Δ, and if variation tendency identical, then think to have disturbance, the order
Y (k)=ax (k-1)+bx (k), wherein
A, bBe weight coefficient, and
A, b ∈ (0.1)If variation tendency on the contrary then can think
X (k)Be trip point, order
Y (k)=ax (k-1)+bx (k+1)If
| x (k+1)-x (k) |〉=Δ can be thought to have abnormity point so, should remove.
Determined fitness function and obtained to carry out the operation of genetic programming after the data to be identified.Defined function set is {+,-, * }, termination set be combined into
X, K, wherein,
XThe expression unit load;
KBe the random number between-1.00 to 1.00, for generation of, mate polynomial coefficient; Adopt foregoing fitness function.The control parameter of genetic programming comprises population scale M=2000, iterations G=100, copies probability is that 0.1 crossover probability is 0.8, and stopping the operation criterion is that iterations is greater than 100.
Generate initial population then and finish a body structure.Calculate each ideal adaptation degree value of initial population, and arrange according to the size of fitness value, carry out the operation that genetic replication intersects again.Last double counting fitness value and genetic manipulation find suitable individuality until satisfying final operation principle.DCS data at the 330MW of power plant unit are carried out foregoing processing, and in result, choose 200 groups of gross coal consumption rates under the different load and carry out identification and use basic GP algorithm to carry out identification, most of evolutionary process all can produce deflection difference and be higher than 0.8 individuality in the regulation iterations, the absolute value of the output valve of optimum individual and the difference of desired value is all less than 0.01.Optimum individual is a good identification result as can be seen, almost completely overlaps with desired value, and the characteristic identification effect of coal consumption is good.
From the above, genetic programming algorithm is very intelligent for solving the characteristic identification problem of coal consumption, and it has been considered the relation of input and output and structure and parameter has all been carried out accurate identification, can draw reliable input.Simulation result shows that the genetic programming algorithm search speed is very fast, identification is accurate, and a lot of superior parts are being arranged aspect the Power Plant modeling.
Genetic programming, or claim the gene programming is a kind ofly to generate and select computer program to finish the technology of user-defined task from the inspired robotization of biological evolution process.Theoretically, the mankind only need tell computing machine " what need be finished " with genetic programming, and need not tell how it " goes to finish ", finally may realize artificial intelligence truly: the invention machine of robotization.
It should be noted that at last: the above only is the preferred embodiments of the present invention, be not limited to the present invention, although with reference to previous embodiment the present invention is had been described in detail, for a person skilled in the art, it still can be made amendment to the technical scheme that aforementioned each embodiment puts down in writing, and perhaps part technical characterictic wherein is equal to replacement.Within the spirit and principles in the present invention all, any modification of doing, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (6)
1. the fired power generating unit coal consumption family curve modeling method based on genetic programming is characterized in that, may further comprise the steps:
At first determine the initial population of genetic programming, i.e. the full stop collection that modeling is used and functor collection;
Determine to determine the expression evolution individuality of employing and the standard adaptation degree of the total error between the target on the basis of above-mentioned initial population;
On the basis of the above-mentioned fitness that settles the standard, determine to weigh the multiple goal genetic programming algorithm of individual adaptability then;
And by the data from the DCS equipment collection at scene are handled the calculating coal consumption amount;
Carry out the operation of genetic programming according to the data of above-mentioned definite full stop collection, functor collection, standard adaptation degree and multiple goal genetic programming algorithm after to above-mentioned processing, set up fired power generating unit coal consumption family curve model.
2. the fired power generating unit coal consumption family curve modeling method based on genetic programming according to claim 1 is characterized in that described full stop collection comprises variable and constant, and described functor collection comprises sign of operation and mathematical function.
3. the fired power generating unit coal consumption family curve modeling method based on genetic programming according to claim 2 is characterized in that described standard adaptation degree equation is:
Wherein,
f i (x)Function expression for the system of individual representative in the evolution population;
f o (x)For the function of goal systems is expressed.
4. the fired power generating unit coal consumption family curve modeling method based on genetic programming according to claim 3 is characterized in that described multiple goal genetic programming algorithm is:
In the formula,
R (k, t)Expression the
tGeneration the
kThe original fitness of individuality,
NThe expression number of nodes,
MaxThe maximum deviation of function representation calculated value and actual value,
aWith
bBe weight coefficient.
5. the fired power generating unit coal consumption family curve modeling method based on genetic programming according to claim 4, it is characterized in that, it is described by the data from the DCS equipment collection at scene are handled the calculating coal consumption amount, be mainly the interference of data in the data of handling the coal consumption amount that DCS equipment gathers, this interference comprises two kinds, first kind is because the random disturbance that produces during data acquisition is removed by the mode of filtering; Second kind is the bigger trip point of fluctuation ratio.
6. the fired power generating unit coal consumption family curve modeling method based on genetic programming according to claim 5 is characterized in that, above-mentioned second kind is disturbed the method for employing residual analysis to carry out Data Detection; The method of described residual analysis is: the data of establishing collection are x, data after the processing are y, Δ is the limit value of data variation, under the prerequisite in identical sampling time, absolute value with front and back double sampling data difference is weighed pace of change, for k sampled value x (k), calculates | x (k)-x (k-1) |, if | x (k)-x (k-1) |<Δ, there is not abnormity point, y (k)=x (k) then, if | x (k)-x (k-1) | 〉=Δ, then may there be abnormity point, then get 1 x (k+1) this moment again, if | x (k+1)-x (k) |≤Δ, and if variation tendency identical, then think and have disturbance, make y (k)=ax (k-1)+bx (k), a wherein, b is weight coefficient, and a, b ∈ (0.1); If variation tendency on the contrary then can think that x (k) is trip point, makes y (k)=ax (k-1)+bx (k+1), if | x (k+1)-x (k) | 〉=Δ, think so to have abnormity point, should remove.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013102813929A CN103345555A (en) | 2013-07-05 | 2013-07-05 | Thermal power unit coal consumption characteristic curve modeling method based on genetic programming |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013102813929A CN103345555A (en) | 2013-07-05 | 2013-07-05 | Thermal power unit coal consumption characteristic curve modeling method based on genetic programming |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103345555A true CN103345555A (en) | 2013-10-09 |
Family
ID=49280350
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2013102813929A Pending CN103345555A (en) | 2013-07-05 | 2013-07-05 | Thermal power unit coal consumption characteristic curve modeling method based on genetic programming |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103345555A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104467028A (en) * | 2014-11-20 | 2015-03-25 | 云南电网公司电力科学研究院 | Method for automatically distributing load to units of thermal power plant |
CN104595924A (en) * | 2015-01-14 | 2015-05-06 | 河北省电力建设调整试验所 | Method and device for establishing boiler combustion process model |
CN105487496A (en) * | 2015-08-10 | 2016-04-13 | 河北省电力建设调整试验所 | Optimization method for heat-engine plant thermal on-line process identification and control algorithm based on dual-objective parallel ISLAND-HFC mixed model genetic programming algorithm |
CN109934493A (en) * | 2019-03-14 | 2019-06-25 | 国网山东省电力公司电力科学研究院 | A kind of method of quick determining thermal power generation unit coal consuming character |
CN112508365A (en) * | 2020-11-26 | 2021-03-16 | 贵州电网有限责任公司 | Online coal consumption curve rolling correction method and system |
CN112510704A (en) * | 2020-11-26 | 2021-03-16 | 贵州电网有限责任公司 | Online coal consumption curve real-time generation method and system |
CN114336778A (en) * | 2021-11-29 | 2022-04-12 | 中国华能集团清洁能源技术研究院有限公司 | Method and device for determining starting sequence of thermoelectric generator set in wind-light-fire storage system |
-
2013
- 2013-07-05 CN CN2013102813929A patent/CN103345555A/en active Pending
Non-Patent Citations (4)
Title |
---|
K. RODRÍGUEZ-VÁZQUEZ 等: "Identifying the Structure of NonLinear Dynamic Systems Using Multiobjective Genetic Programming", 《IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS》 * |
冯培燕: "基于模糊多目标优化的火电厂负荷优化分配研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
李太兴 等: "基于MATLAB工具箱的锅炉机组煤耗特性曲线研究", 《第十一届全国电工数学学术年会论文集》 * |
白焰 等: "基于遗传编程的火电厂主汽温系统建模研究", 《系统仿真学报》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104467028A (en) * | 2014-11-20 | 2015-03-25 | 云南电网公司电力科学研究院 | Method for automatically distributing load to units of thermal power plant |
CN104595924A (en) * | 2015-01-14 | 2015-05-06 | 河北省电力建设调整试验所 | Method and device for establishing boiler combustion process model |
CN105487496A (en) * | 2015-08-10 | 2016-04-13 | 河北省电力建设调整试验所 | Optimization method for heat-engine plant thermal on-line process identification and control algorithm based on dual-objective parallel ISLAND-HFC mixed model genetic programming algorithm |
CN105487496B (en) * | 2015-08-10 | 2018-06-26 | 河北省电力建设调整试验所 | The optimization method of Power Plant Thermal on-line process identification and control algolithm based on Bi-objective Parallel I SLAND-HFC mixed model genetic programming algorithms |
CN109934493A (en) * | 2019-03-14 | 2019-06-25 | 国网山东省电力公司电力科学研究院 | A kind of method of quick determining thermal power generation unit coal consuming character |
CN109934493B (en) * | 2019-03-14 | 2020-12-22 | 国网山东省电力公司电力科学研究院 | Method for rapidly determining coal consumption characteristic curve of thermal generator set |
CN112508365A (en) * | 2020-11-26 | 2021-03-16 | 贵州电网有限责任公司 | Online coal consumption curve rolling correction method and system |
CN112510704A (en) * | 2020-11-26 | 2021-03-16 | 贵州电网有限责任公司 | Online coal consumption curve real-time generation method and system |
CN112508365B (en) * | 2020-11-26 | 2022-07-01 | 贵州电网有限责任公司 | Online coal consumption curve rolling correction method and system |
CN112510704B (en) * | 2020-11-26 | 2022-10-11 | 贵州电网有限责任公司 | Online coal consumption curve real-time generation method and system |
CN114336778A (en) * | 2021-11-29 | 2022-04-12 | 中国华能集团清洁能源技术研究院有限公司 | Method and device for determining starting sequence of thermoelectric generator set in wind-light-fire storage system |
CN114336778B (en) * | 2021-11-29 | 2023-09-22 | 中国华能集团清洁能源技术研究院有限公司 | Method and device for determining starting sequence of thermal power generating unit in wind, light and fire storage system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103345555A (en) | Thermal power unit coal consumption characteristic curve modeling method based on genetic programming | |
CN108063456B (en) | Distributed photovoltaic power generation grid-connected planning method and terminal equipment | |
CN103942453A (en) | Intelligent electricity utilization anomaly detection method for non-technical loss | |
CN108183488B (en) | High-permeability distributed energy system intelligent pressure regulating method based on cluster division | |
CN103425743A (en) | Steam pipe network prediction system based on Bayesian neural network algorithm | |
CN113822418A (en) | Wind power plant power prediction method, system, device and storage medium | |
CN109740962A (en) | Voltage stabilization probability evaluation method of failure based on scene subregion and cumulant | |
CN109856973A (en) | A kind of Technique for Controlling Greenhouse Environment and system based on fuzzy neural network | |
Liao et al. | Short term load forecasting and early warning of charging station based on PSO-SVM | |
CN114971090A (en) | Electric heating load prediction method, system, equipment and medium | |
Yu et al. | Development of a distributed artificial fish swarm algorithm to optimize pumps working in parallel mode | |
CN114429248A (en) | Transformer apparent power prediction method | |
CN110738363A (en) | photovoltaic power generation power prediction model and construction method and application thereof | |
Wang et al. | Prediction of water quality in South to North Water Transfer Project of China based on GA-optimized general regression neural network | |
CN117113086A (en) | Energy storage unit load prediction method, system, electronic equipment and medium | |
CN116542385A (en) | Integrated learning method and system for wind and light power prediction | |
Xie et al. | Expansion modelling of discrete grey model based on multi-factor information aggregation | |
CN104346448A (en) | Incremental data mining method based on genetic programming algorithm | |
CN115130924A (en) | Microgrid power equipment asset evaluation method and system under source grid storage background | |
CN115347556A (en) | Energy storage power station capacity configuration method for promoting new energy consumption | |
CN113762646A (en) | Photovoltaic short-term power intelligent prediction method and system | |
CN105068423B (en) | Method for realizing intelligent parameter identification of steam turbine and speed regulating system thereof by one key | |
Shi et al. | Power missing data filling based on improved k-means algorithm and rbf neural network | |
CN103994858A (en) | Dynamic balance detection control method based on biogeographical intelligent optimization support vector machine algorithm | |
Ke et al. | Short-term wind power dynamic prediction based on GA-BP neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20131009 |
|
RJ01 | Rejection of invention patent application after publication |