CN113626767A - Fan power limit identification method, system, equipment and storage medium - Google Patents

Fan power limit identification method, system, equipment and storage medium Download PDF

Info

Publication number
CN113626767A
CN113626767A CN202110881128.3A CN202110881128A CN113626767A CN 113626767 A CN113626767 A CN 113626767A CN 202110881128 A CN202110881128 A CN 202110881128A CN 113626767 A CN113626767 A CN 113626767A
Authority
CN
China
Prior art keywords
power
fan
limiting
wind
field
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110881128.3A
Other languages
Chinese (zh)
Other versions
CN113626767B (en
Inventor
杨宇凡
岳文彦
徐鹤
王俊峰
杨尚丹
潘文彪
刘璐
胡楠楠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Cecep Wind Power Corp
Original Assignee
Cecep Wind Power Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Cecep Wind Power Corp filed Critical Cecep Wind Power Corp
Priority to CN202110881128.3A priority Critical patent/CN113626767B/en
Publication of CN113626767A publication Critical patent/CN113626767A/en
Application granted granted Critical
Publication of CN113626767B publication Critical patent/CN113626767B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • 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
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Data Mining & Analysis (AREA)
  • Tourism & Hospitality (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Operations Research (AREA)
  • Health & Medical Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Mathematical Physics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Mathematical Analysis (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Algebra (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Wind Motors (AREA)
  • Control Of Eletrric Generators (AREA)

Abstract

The invention relates to a method, a system, equipment and a storage medium for identifying the electricity limit of a fan, which comprises the following steps: the method comprises the steps that the obtained wind power plant operation data and power grid side control data in a certain time period are sorted, cleaned and preliminarily screened to obtain wind power plant operation data and power grid side control data under normal working conditions; performing power fitting on the obtained wind power plant operation data under the normal working condition to obtain a fan average power curve of the wind power plant in the time period; judging whether each timestamp is power-limited or not according to the average power curve of the fan and the power grid side control data in the time period to obtain all power-limiting moments; and identifying each electricity-limiting fan based on the obtained average power curve of the fan and all electricity-limiting moments to obtain all fan numbers which are judged to be in a limited state and correspond to each electricity-limiting moment. The method can be widely applied to the field of wind power plant operation control.

Description

Fan power limit identification method, system, equipment and storage medium
Technical Field
The invention relates to a wind turbine power limit identification method, a wind turbine power limit identification system, wind turbine power limit identification equipment and a storage medium based on operation data and control data, and belongs to the field of wind power plant operation control.
Background
In recent years, the national demand for clean energy is higher and higher, wind energy is more and more emphasized due to the advantages of wide distribution range, no pollution, low cost and the like, and the installed capacity of wind power is rapidly increased. However, the wind speed and the wind direction are influenced by various factors, and have very strong uncertainty. The sudden increase of the electric field generating capacity has certain influence on the stability of a power grid, and in order to ensure the stability of a power grid transmission line, the power grid frequently issues power limiting instructions to a wind power plant, and the power limiting instructions inevitably cause certain economic loss to the electric field. With the arrival of the era of wind power flat price internet surfing, the control of the operation cost and the profit of a wind power operator is stricter. The method has higher requirements on the recognition and positioning of the abandoned wind power limiting and the recognition accuracy of the wind power limiting fan.
At present, the data mainly used for calculating the wind abandoning and electricity limiting of the wind power plant is the operation data collected in the operation process of a fan, and the calculation method is usually a benchmarking fan method for calculating the whole field from a single machine or an external characteristic modeling method for directly calculating the whole field. The method only using the operation data is simple in data acquisition, the number of required data interfaces is small, important fan operation control data are lacked, and omission is easily caused when power limit is identified. And the benchmark fan method and the external characteristic modeling method cannot carry out very accurate estimation on the actual power generation amount of the wind field due to respective limitations.
Disclosure of Invention
In view of the above problems, an object of the present invention is to provide a method, a system, a device, and a storage medium for identifying a power limit of a wind turbine based on operation data and control data, which comprehensively utilize historical operation data and control data of the wind turbine, obtain an estimated value of a full-field actual power generation by using an average power curve of each wind turbine, and identify a power limit time by combining the operation data and the control data. And at each identified electricity limiting moment, obtaining the number of all the fans which are possibly limited according to the deviation value of the actual power and the predicted power of each fan.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a wind turbine power limiting identification method, which comprises the following steps:
the method comprises the steps that the obtained wind power plant operation data and power grid side control data in a certain time period are sorted, cleaned and preliminarily screened to obtain wind power plant operation data and power grid side control data under normal working conditions;
performing power fitting on the obtained wind power plant operation data under the normal working condition to obtain a fan average power curve of the wind power plant in the time period;
judging whether each timestamp is power-limited or not according to the average power curve of the fan and the power grid side control data in the time period to obtain all power-limiting moments;
and identifying each electricity-limiting fan based on the obtained average power curve of the fan and all electricity-limiting moments to obtain all fan numbers which are judged to be in a limited state and correspond to each electricity-limiting moment.
Preferably, the method for obtaining the average power curve of the wind turbine of the wind farm in the time period by performing power fitting on the obtained wind farm operating data under the normal working condition comprises the following steps:
according to the operation logic of the fan, dividing the operation data of the wind power plant under the normal working condition according to the wind speed to obtain a first wind speed interval to a third wind speed interval;
fitting the fan power in the second wind speed interval to obtain a fan fitting power function in the second wind speed interval;
and fusing the fan fitting power in the second wind speed interval with the fan power in the first wind speed interval and the third wind speed interval to obtain a fan average power curve in the time interval. Preferably, the first and second electrodes are formed of a metal,
the method for fitting the fan power in the second wind speed interval to obtain the fan fitting power in the second wind speed interval comprises the following steps:
segmenting the wind power plant operation data in the second wind speed interval according to a preset wind speed interval to obtain a plurality of wind speed segments;
screening the operation data of the wind power plant in each wind speed section again, and removing power limit and fault shutdown data;
calculating the average power of each wind speed section, and taking the wind speed midpoint of each wind speed section to represent the wind speed section;
and fitting the obtained average power of each wind speed section and the wind speed midpoint data to obtain the fitting power of the fan.
Preferably, the method for judging whether each timestamp time is power-limited according to the average power curve of the wind turbine and the control data of the power grid side in the time period to obtain all power-limiting times includes the following steps:
calculating to obtain a predicted value P of the power generation capacity of the whole field according to the average power curve of the fan in the time periodFull field capabilityAnd the actual value P of the power generation capacityFull-field real hair；
According to the obtained full-field generating capacity predicted value PFull field capabilityAnd the actual value P of the power generation capacityFull-field real hairAnd the power grid side control data is used for judging whether the timestamp time is power-limited or not to obtain all power-limiting times.
Preferably, the predicted value P of the full-field generating capacity is obtainedFull field capabilityAnd the actual value P of the power generation capacityFull-field real hairAnd the method for controlling data at the power grid side and judging whether the timestamp moments are power-limited or not to obtain all power-limiting moments comprises the following steps:
eliminating time periods without data;
for all timestamp moments of all time periods with data, carrying out power-limiting moment judgment based on preset power-limiting moment judgment conditions; the preset power-limiting moment judgment condition is as follows:
if:
(Pfull-field real hair＞PFull field reception)or(PFull field capability＞max(PFull-field real hair+thresOperation of，PFull field reception+thresControl of))
The time will be determined as the power-limited time;
repeating the previous step, and judging to obtain all the power-limited moments in each time period
Figure BDA0003192051190000031
And according to the planned active power PFull field planActual received active power PFull field receptionActual value P of generating capacity of whole fieldFull-field real hairPredicted value P of power generation capacity of whole fieldFull field capabilityAnd all the time when electricity is limited
Figure BDA0003192051190000032
And drawing a schematic diagram of the recognition result of the electricity limiting time by data.
Preferably, the method for identifying each power-limited fan based on the obtained average power curve of the fan and all power-limited times to obtain all fan numbers determined as the limited state corresponding to each power-limited time includes the following steps:
for each power-limiting time t obtainedLimit ofSetting a time-limited time period [ t ] centered on the time-limited time periodLimit of-δ，tLimit of+δ]Calculating the estimated value of the power generation capacity of each fan in the time-limited time period by using the average power curve of the fans and the wind speed data of the fans;
obtaining an estimated value of actual power of each fan in a time-limited period through the operation data of the wind power plant, subtracting the estimated value from the average value of the power generation capacity of the fan, and correcting the difference value to obtain a power deviation value of each fan;
summing the power deviation of each fan to obtain the total power deviation of the whole field;
and judging to obtain all the fans with limited power according to the estimated value of the generating capacity of each fan, the power deviation value and the total deviation of the full-field power.
Preferably, the method for judging and obtaining all the fans limited by electricity according to the estimated power generation capacity value, the power deviation value and the total deviation sum of the full-field power of each fan comprises the following steps:
firstly, defining ratio as a percentage value of power deviation of all fans judged to be in a power-limited state to the total of power deviation of a whole field, and setting an initial value of the ratio as 0;
calculating the power deviation value of each fan
Figure BDA0003192051190000033
And estimated value of power generation capacity
Figure BDA0003192051190000034
Ratio of
Figure BDA0003192051190000035
Thirdly, judging the power limiting state: if the ratio of the fan
Figure BDA0003192051190000036
Greater than a preset third threshold thresFan blowerAnd estimated value of power generation capacity
Figure BDA0003192051190000037
Greater than a preset fourth threshold lbFan blowerJudging the fan to be in a power limiting state and deviating the power of the fan to be in a deviation value
Figure BDA0003192051190000038
Adding the percentage value accounting for the total sum of the power deviation of the full field and the ratio defined in the step (r), and if the value of res is greater than a preset fifth threshold value thres of the cumulative influence of the full field limit electric fanAll over the fieldThat isEntering the step (c), or else entering the step (d);
fourthly, all the fans which are not judged to be in the power limiting state are subjected to power deviation value according to the power deviation value
Figure BDA0003192051190000039
Sorting from big to small;
judging the fan to be in a power limiting state according to the method in the third step, and taking the percentage value of the power deviation of the fan to the total power deviation of the whole field
Figure BDA00031920511900000310
Adding with ratio until ratio > thresAll over the field；
And sixthly, outputting all fan numbers judged to be in the power-limiting state.
In a second aspect of the present invention, a wind turbine power limiting identification system is provided, which includes:
the data preprocessing module is used for carrying out sorting, cleaning and preliminary screening on the acquired wind power plant operation data and power grid side control data in a certain time period to obtain the wind power plant operation data and the power grid side control data under the normal working condition;
the power curve fitting module is used for performing power fitting on the obtained wind power plant operation data under the normal working condition to obtain a fan average power curve of the wind power plant in the time period;
the power limiting time identification module is used for judging whether each timestamp time is power limited or not according to the average power curve of the fan and the power grid side control data in the time period to obtain all power limiting times;
and the electricity-limiting fan identification module is used for identifying the electricity-limiting fans based on the obtained average power curve of the fans and all electricity-limiting moments to obtain all fan numbers which are judged to be in a limited state and correspond to all the electricity-limiting moments.
In a third aspect of the present invention, a processing device is provided, where the processing device at least includes a processor and a memory, where the memory stores a computer program, and the processor executes the computer program to implement the steps of the wind turbine power limit identification method.
In a fourth aspect of the present invention, a computer storage medium is provided, on which computer readable instructions are stored, and the computer readable instructions are executable by a processor to implement the steps of the wind turbine power limit identification method.
Due to the adoption of the technical scheme, the invention has the following advantages:
1. the invention not only can estimate the power limiting time of the full wind field, but also can give guidance suggestion of the power-limited fan at the time aiming at each full wind field power limiting time, and can provide considerable convenience for operation and maintenance work of wind power enterprises. Effective reference indexes can be provided for an evaluation system of the operation condition of the wind power plant, and better data support is provided for cooperation between the wind power plant and a power grid;
2. the method comprehensively utilizes the operation data and the control data of the wind field, and can more accurately identify the electricity limiting time compared with the traditional electricity limiting time identification method only based on the operation data. Compared with the traditional method for judging the standard pole fan, the method can consider the specific operating condition of each fan and provide more accurate power limiting time and power limiting fan identification;
3. the invention is based on a data layer method, aiming at different wind fields, the adaptation of the algorithm to different wind fields can be completed by adjusting each threshold parameter in the process. Therefore, the fan has strong adaptability and can meet the specific requirements of different fan models.
4. The invention can reduce the prediction error to the maximum extent from the two angles of the power deviation of a single fan and the power deviation of a full wind field respectively when the logic adopted by the electricity-limiting fan is judged.
Therefore, the method can be widely applied to the field of wind power plant operation control.
Drawings
FIG. 1 is a flow chart of a method for identifying a wind turbine power limit based on operational data and control data according to the present invention;
FIG. 2 is a flow chart of a power curve fitting algorithm provided by the present invention;
FIG. 3 is a flow chart of a power-limited time identification algorithm provided by the present invention;
FIG. 4 is a flow chart of a limited power fan identification algorithm provided by the present invention;
FIG. 5 is a graph showing the results of the power curve fitting algorithm between the raw data and the least square method-Sigmoid provided by the present invention;
FIG. 6 is a diagram showing the recognition result of the power-limiting time provided by the present invention;
fig. 7 is a diagram showing the recognition result of the power-limiting fan corresponding to a part of the power-limiting time in fig. 6.
Detailed Description
The invention is described in detail below with reference to the figures and examples.
The invention comprehensively utilizes the operation data collected during the operation of the fan and the control data collected by the electric field end, and obtains the average power curve of the fan in a certain time period through the preprocessed data. And estimating the average actual active power of the fan by using the power curve so as to obtain an actual power predicted value of the whole field, and identifying the power-limiting time of the wind field by using a specific algorithm. After the electricity limiting time is identified, the electric-limited fan corresponding to each electricity limiting time is obtained through the difference value between the actual power estimation value and the actual measurement value of each fan and a specific algorithm.
Example 1
As shown in fig. 1, the method for identifying the wind turbine power limit based on the operation data and the control data provided by the invention comprises the following steps:
1) data acquisition: and acquiring wind power plant operation data and power grid side control data counted at a specific frequency within a certain time period. Wherein the wind farm operational data comprises average wind speed
Figure BDA0003192051190000051
And average active power
Figure BDA0003192051190000052
Wherein i is the serial number of the fan, i is 1, …, and N is the total number of the fans of the wind field; power grid side control data packetActive power PFull field planAnd actually receives active power PFull field reception。
2) Data preprocessing: and (4) carrying out sorting, cleaning and preliminary screening on the obtained wind power plant operation data and the power grid side control data to obtain the wind power plant operation data and the power grid side control data under the normal working condition.
When the wind power plant operation data after being cleaned up is primarily screened, the data under the normal operation state of the fan can be screened out by using a two-time interval quartile method according to the wind speed and the power.
3) And (3) power curve fitting: and performing power fitting on the obtained wind power plant operation data under the normal working condition to obtain a fan average power curve of the wind power plant in the time period.
The method comprises the following steps of carrying out power fitting on wind power plant operation data under a normal working condition by adopting a power curve fitting algorithm based on a least square method-Sigmoid, and specifically comprises the following steps:
and 3.1) dividing the operation data of the wind power plant under the normal working condition according to the operation logic of the fan and the wind speed to obtain a first-third wind speed interval.
Wherein the wind speed v in the first wind speed interval sectionWind speedLess than the cut-in wind speed V of the fanCutting intoI.e. 0. ltoreq. vWind speed＜＝VCutting intoAt this time, the corresponding fan power is 0; wind speed v in the second wind speed intervalWind speedGreater than the cut-in wind speed V of the fanCutting intoThe lowest wind speed V corresponding to the full power of the fan is less thanexpI.e. VCutting into＜vWind speed＜VexpFitting the fan power of the wind power field in the section; wind speed v in the third wind speed intervalWind speedIs greater than the lowest wind speed V corresponding to full power generation of the fanexpI.e. Vexp＜＝vWind speedAt this moment, the corresponding fan power is the power value P of the single machine full powermax。
And 3.2) fitting the fan power in the second wind speed interval by adopting a power curve fitting algorithm based on a least square method-Sigmoid to obtain the fan fitting power in the second wind speed interval.
Specifically, the method comprises the following steps:
and 3.2.1) segmenting the operating data of the wind power plant in the second wind speed interval according to a preset wind speed interval to obtain a plurality of wind speed segments. Wherein, the preset wind speed interval is preferably 0.5.
3.2.2) screening the operation data of the wind power plant in each wind speed section again, and removing obvious electricity limiting and fault shutdown data.
3.2.3) calculating the average power of each wind speed section, and taking the wind speed midpoint of each wind speed section to represent the wind speed section.
3.2.4) fitting the average power and the wind speed midpoint data of each wind speed section obtained in the step 3.2.3) by using a least square method to obtain a fan fitting power function f (v)Wind speed) The calculation formula is as follows:
Figure BDA0003192051190000061
in the formula, a, b, c and d are parameters, vWind speedIs the wind speed.
And 3.3) fusing the fitted power of the fan in the second wind speed interval with the power of the fan in the first wind speed interval and the third wind speed interval to obtain an average power curve of the fan in the time interval.
Wherein, the average power curve of the fan in this time quantum is:
Figure BDA0003192051190000062
in the formula, VCutting intoFor wind speed cut-in of the fan, VexpIs the lowest wind speed corresponding to full power generation of the fan obtained according to experience, f is a curve fitting function of wind speed-power, PmaxThe power value of the single machine full transmission.
4) Recognizing the power limiting time: and judging whether each timestamp time is power-limited in the time period by adopting a power-limiting time judgment algorithm according to the average power curve of the fan and the power grid side control data in the time period to obtain all power-limiting times.
Specifically, the method comprises the following steps:
4.1) calculating to obtain a predicted value P of the generating capacity of the whole field according to the average power curve of the fan in the time periodFull field capabilityAnd the actual value P of the power generation capacityFull-field real hair。
First, the predicted value P of the generating capacity of the whole fieldFull field capabilityThe calculation method comprises the following steps:
first, at each time-stamped instant within the time period, the average of the full-field wind speed is used
Figure BDA0003192051190000063
Substituting the average power curve obtained in the step 3) to obtain the average power predicted value of each fan at each timestamp moment
Figure BDA0003192051190000064
Wherein the average value of the wind speed of the whole field
Figure BDA0003192051190000065
The calculation formula of (2) is as follows:
Figure BDA0003192051190000066
in the formula (I), the compound is shown in the specification,
Figure BDA0003192051190000071
the wind speed value of the fan i is shown, and N is the total number of the fans of the wind power plant.
Secondly, according to the average power predicted value of each fan corresponding to each timestamp time
Figure BDA0003192051190000072
And the total number N of all fans in operation without fault shutdownOperation ofAnd calculating to obtain a predicted value P of the generating capacity of the whole fieldFull field capabilityThe calculation formula is as follows:
Figure BDA0003192051190000073
in the formula, NOperation ofAnd the total number of all the fans in the operation without the fault shutdown at the time of the timestamp.
Actual value P of generating capacity of whole fieldFull-field real hairThe calculation formula of (2) is as follows:
Figure BDA0003192051190000074
wherein i is a fan number, and i is 1, …, N;
Figure BDA0003192051190000075
the actual power value of the fan i is obtained.
4.2) according to the obtained full-field generating capacity predicted value PFull field capabilityAnd the actual value P of the power generation capacityFull-field real hairAnd power grid side control data, and judging whether the timestamp time is power-limited by adopting a power-limiting time judgment algorithm to obtain all power-limiting times.
Specifically, the electricity-limiting time judgment algorithm comprises the following steps:
4.2.1) eliminating time sections without data.
4.2.2) for each time stamp moment in all time periods with data, carrying out power-limiting moment judgment based on preset power-limiting moment judgment conditions.
Wherein, predetermine the power limit moment and judge the condition and include:
if the actual received active power P in the grid side control dataFull field receptionGreater than the planned active power PFull field planThen the moment is judged as a limited power state;
if the predicted value P of the full-field generating capacity isFull field capabilityGreater than the actual value P of the full field generating capacityFull-field real hairAdding a preset first threshold thresOperation ofAnd actually receives active power PFull field receptionAdding a preset second threshold thresControl ofThe maximum value of (i) is:
Pfull field capability＞max(PFull-field real hair+thresOperation of，PFull field reception+thresControl of)；
Then the time will be judged as the power-limited time.
The above two conditions are taken into account in combination, i.e. if:
(Pfull-field real hair＞PFull field reception)or(PFull field capability＞max(PFull-field real hair+thresOperation of，PFull field reception+thresControl of))
The time stamp time is determined as the power limit time.
Wherein, a first threshold thres is presetOperation ofAnd a preset second threshold thresControl ofThe value of (a) needs to be adjusted according to the specific operation condition of each wind power plant, and generally, the value of (a) is recommended to be less than 3 times of the rated power of a single fan.
4.2.3) repeating the step 4.2.2), and judging to obtain all the limited electricity moments in each time period
Figure BDA0003192051190000076
And according to the planned active power PFull field planActual received active power PFull field receptionActual value P of generating capacity of whole fieldFull-field real hairPredicted value P of power generation capacity of whole fieldFull field capabilityAnd all the time when electricity is limited
Figure BDA0003192051190000077
And drawing a schematic diagram of the recognition result of the electricity limiting time by data.
5) Recognizing the power-limiting fan: and identifying each power-limiting fan based on the average power curve of the fan obtained in the step 3) and all the power-limiting moments obtained in the step 4) to obtain all fan numbers which are judged to be in a limited state and correspond to each power-limiting moment.
Specifically, the method comprises the following steps:
5.1) for each of the resulting electricity-limiting instants
Figure BDA0003192051190000081
Setting a time-limited time period with the time-limited time period as the center
Figure BDA0003192051190000082
Wherein delta is a half value of the length of the time-limited time period, and the average power curve of the fan obtained in the step 3) and the wind speed data thereof are used for calculating the estimated value of the power generation capacity of each fan in the time-limited time period
Figure BDA0003192051190000083
5.2) obtaining the average value of the real power of each fan in the time-limited time period through the operation data of the wind power plant
Figure BDA0003192051190000084
And compares it with an estimated value of the power generation capacity of the corresponding fan
Figure BDA0003192051190000085
Making a difference, and correcting the difference to obtain a power deviation value of each fan
Figure BDA0003192051190000086
According to the estimated value of the power generation capacity of the fan
Figure BDA0003192051190000087
And mean value of real power
Figure BDA0003192051190000088
When the power deviation of the fan is obtained through calculation, the calculation formula is as follows:
Figure BDA0003192051190000089
wherein, i is 1, …, and n is the fan number.
Considering the characteristic of electricity limitation, the real power generation of the wind turbine is often less than the actual power generation capacity when the wind turbine is limited in electricity, so that only the set with a positive power deviation value is considered when the full-field power is limited, namely:
Figure BDA00031920511900000810
5.3) summing the power deviation values of all the fans in the wind power plant to obtain the total power deviation sum delta P of the whole wind power plantAll over the field。
Wherein the total power deviation sum of the full field Δ PAll over the fieldThe calculation formula of (2) is as follows:
Figure BDA00031920511900000811
5.4) estimating the power generation capacity of each fan
Figure BDA00031920511900000812
Power deviation value
Figure BDA00031920511900000813
And the total sum of the power deviations Δ PAll over the fieldAnd judging to obtain all fan numbers which are judged to be in the power-limited state and correspond to each power-limited moment by adopting a power-limited fan identification algorithm.
Specifically, the method comprises the following steps:
5.4.1) defining the ratio as the percentage value of the power deviation of all the fans judged to be in the electricity-limiting state to the total sum of the power deviations of the whole field, and setting the initial value of the ratio as 0;
5.4.2) calculating the power deviation value of each fan
Figure BDA00031920511900000814
And estimated value of power generation capacity
Figure BDA00031920511900000815
Ratio of
Figure BDA00031920511900000816
The calculation formula is as follows:
Figure BDA00031920511900000817
5.4.3) judging the power limiting state: if the ratio of the fan
Figure BDA00031920511900000818
Greater than a preset third threshold thresFan blowerAnd estimated value of power generation capacity
Figure BDA0003192051190000091
Greater than a preset fourth threshold lbFan blowerThen the fan is judged as the electricity limiting state and the power deviation value of the fan is judged
Figure BDA0003192051190000092
Adding the percentage value accounting for the total sum of the full-field power deviation and the ratio defined in the step 5.1), and if the value of the ratio is greater than a preset fifth threshold value thres of the cumulative influence of the full-field electric fanAll over the fieldThen step 5.4.6) is entered, otherwise step 5.4.4) is entered);
5.4.4) all fans which are not determined to be in the power limiting state according to the power deviation values of the fans
Figure BDA0003192051190000093
Sorting from big to small;
5.4.5) sequentially judging the fan as the fan in the electricity limiting state according to the method of the step 5.4.3), and taking the percentage value of the power deviation of the fan to the total sum of the power deviations of the whole field
Figure BDA0003192051190000094
Adding with ratio until ratio > thresAll over the field；
5.4.6) outputs all the fan numbers which are judged to be in the power-limiting state.
Example 2
The above embodiment 1 provides a wind turbine power limit identification method based on operation data and control data, and correspondingly, this embodiment provides a wind turbine power limit identification system based on operation data and control data. The identification system provided by this embodiment may implement the wind turbine power limiting identification method based on the operation data and the control data in embodiment 1, and the identification system may be implemented by software, hardware, or a combination of software and hardware. For example, the identification system may comprise integrated or separate functional modules or functional units to perform the corresponding steps in the methods of embodiment 1. Since the identification system of this embodiment is basically similar to the method embodiment, the description process of this embodiment is relatively simple, and reference may be made to the partial description of embodiment 1 for relevant points.
The fan power limit identification system that this embodiment provided, it includes:
the data acquisition module is used for acquiring wind power plant operation data and power grid side control data counted at a specific frequency within a certain time period;
the data preprocessing module is used for carrying out sorting, cleaning and preliminary screening on the acquired wind power plant operation data and power grid side control data to obtain the wind power plant operation data and the power grid side control data under the normal working condition;
the power curve fitting module is used for performing power fitting on the obtained wind power plant operation data under the normal working condition to obtain a fan average power curve of the wind power plant in the time period;
the power limiting time identification module is used for judging whether each timestamp time in the time period is power limited or not by adopting a power limiting time judgment algorithm according to the average power curve of the fan and the power grid side control data in the time period to obtain all power limiting times;
and the electricity-limiting fan identification module is used for identifying the electricity-limiting fans based on the obtained average power curve of the fans and all electricity-limiting moments to obtain all fan numbers which are judged to be in a limited state and correspond to all the electricity-limiting moments.
Example 3
The present embodiment provides a processing device corresponding to the fan power limit identification method provided in embodiment 1, where the processing device may be a processing device for a client, such as a mobile phone, a notebook computer, a tablet computer, a desktop computer, and the like, to execute the identification method of embodiment 1.
The processing equipment comprises a processor, a memory, a communication interface and a bus, wherein the processor, the memory and the communication interface are connected through the bus so as to complete mutual communication. The memory stores a computer program capable of running on the processor, and the processor executes the fan power limit identification method provided by embodiment 1 when running the computer program.
In some implementations, the Memory may be a high-speed Random Access Memory (RAM), and may also include a non-volatile Memory, such as at least one disk Memory.
In other implementations, the processor may be various general-purpose processors such as a Central Processing Unit (CPU), a Digital Signal Processor (DSP), and the like, and is not limited herein.
Example 4
The fan power limit identification method of this embodiment 1 may be embodied as a computer program product, and the computer program product may include a computer readable storage medium on which computer readable program instructions for executing the fan power limit identification method of this embodiment 1 are loaded.
The computer readable storage medium may be a tangible device that retains and stores instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any combination of the foregoing.
Example 5
The invention is explained in further detail below with reference to the drawings:
the data source is a wind field with 80 wind driven generators of 2.5MW, the running data sampling period is 10 minutes, the data sampling period is controlled to be 5 minutes, and the data acquisition time period is from 1 month 00:00:00 in 2020 and 9 months to 31 days 23:55:00 in 2020 and 9 months.
As shown in fig. 1, the present invention comprises the steps of:
the method comprises the following steps: and acquiring operation data of the wind power plant and control data of the power grid side.
The stations that need to be collected from the operational data include: time, wind speed of each fan and actual power of each fan; the stations that need to be collected from the control data include: time, grid planned power, grid received power.
Step two: data sorting, cleaning and preprocessing.
The data is sorted as follows: the operation data and the control data are spliced according to the month and the fan, the spliced data are aligned according to the condition that the data sampling frequency is low, in the implementation, the sampling period of the operation data is 10 minutes, the control data is 5 minutes, and the sampling period of the spliced data is 10 minutes. If the measuring point has no data at a certain moment, setting the data at the position to be null;
the data cleaning is as follows: eliminating error data, wherein in the implementation, the specific scheme is to eliminate data with the wind speed of more than 25 m/s;
the data preprocessing comprises the following steps: after the two steps of processing, recording the time point of data missing in the data table, and filling the blank value in the data table by a linear interpolation method.
Step three: and (3) power curve fitting:
fig. 2 is a flow chart showing the power curve fitting of data by using the least square method-Sigmoid algorithm. And (3) using all fan data for power curve fitting, segmenting the data according to the wind speed, screening the data in each segment, removing obvious power limiting data, calculating the average power value in each segment, and performing least square fitting based on a Sigmoid function by using the obtained data to obtain a final power curve fitting function. And calculating the estimated value of the power generation capacity and the estimated value of the normal power generation capacity of each fan by using the function and the wind speed.
Fig. 5 is a diagram showing the results of the power curve and the raw data scatter points obtained by the least square method-Sigmoid algorithm shown in fig. 2. The power curve obtained by fitting can better reflect the wind speed-power relation when the fan normally operates.
Step four: recognizing the power limiting time:
the power-limiting time identification algorithm shown in fig. 3 is adopted to identify the power-limiting time. The algorithm comprises the following steps:
1. judging whether data exist at the current moment or not, and if not, directly ending;
2. judging whether the planned power of the control data is larger than the received power or not, and if so, judging the current moment as the electricity limiting moment;
3. full field generating capacity and control data obtained by integrating the operating data, if PFull field capability＞max(PFull-field real hair+thresOperation of，PFull field reception+thresControl of) If the logic value is true, the current moment is judged as the electricity-limiting moment;
4. all the recognized power-limit timings are output as the power-limit timing recognition results on xxxx days 9 months in 2020 as shown in fig. 6.
Step five: recognizing the power-limiting fan:
and for the electricity limiting time identified in the fourth step, identifying the electricity limiting fan by adopting an electricity limiting fan identification algorithm shown in fig. 4. The algorithm comprises the following steps:
1. calculating the power deviation ratio of each fan and the ratio of the power deviation value of the whole field;
2. judging whether the single machine deviation ratio of each fan is higher than a threshold value, if so, judging the fan to be in a power limiting state, and meanwhile, accumulating the ratio of the fan to the full-field deviation;
3. sorting the remaining fans from large to small according to the occupation ratio of the full-field power deviation value, sequentially judging the fans to be in a power limiting state, and accumulating the occupation ratios of the full-field deviation until the accumulated value is larger than a threshold value;
4. the fan number determined to be in the power-limited state corresponding to this time is output as the power-limited fan number corresponding to each power-limited time on 9 month xxxx day 2020 as shown in fig. 7.
In conclusion, the invention comprehensively utilizes the operation data acquired during the operation of the fan and the control data of the power grid end, and can accurately identify the power limiting time of the air outlet electric field and the serial number of the power-limited fan at the power-limited time. Meanwhile, the invention is a method based on a data layer, aiming at different wind fields, the adaptation of the algorithm to different wind fields can be completed by adjusting each threshold parameter in the process. Therefore, the fan has strong adaptability and can meet the specific requirements of different fan models.
The above embodiments are only used for illustrating the present invention, and the structure, connection mode, manufacturing process, etc. of the components may be changed, and all equivalent changes and modifications performed on the basis of the technical solution of the present invention should not be excluded from the protection scope of the present invention.

Claims (10)

1. A wind turbine power limiting identification method is characterized by comprising the following steps:
the method comprises the steps that the obtained wind power plant operation data and power grid side control data in a certain time period are sorted, cleaned and preliminarily screened to obtain wind power plant operation data and power grid side control data under normal working conditions;
performing power fitting on the obtained wind power plant operation data under the normal working condition to obtain a fan average power curve of the wind power plant in the time period;
judging whether each timestamp is power-limited or not according to the average power curve of the fan and the power grid side control data in the time period to obtain all power-limiting moments;
and identifying each electricity-limiting fan based on the obtained average power curve of the fan and all electricity-limiting moments to obtain all fan numbers which are judged to be in a limited state and correspond to each electricity-limiting moment.
2. The wind turbine power limiting identification method of claim 1, characterized in that: the method for performing power fitting on the obtained wind power plant operation data under the normal working condition to obtain the average power curve of the fans of the wind power plant in the time period comprises the following steps:
according to the operation logic of the fan, dividing the operation data of the wind power plant under the normal working condition according to the wind speed to obtain a first wind speed interval to a third wind speed interval;
fitting the fan power in the second wind speed interval to obtain a fan fitting power function in the second wind speed interval;
and fusing the fan fitting power in the second wind speed interval with the fan power in the first wind speed interval and the third wind speed interval to obtain a fan average power curve in the time interval.
3. The wind turbine power limiting identification method of claim 2, characterized in that: the method for fitting the fan power in the second wind speed interval to obtain the fan fitting power in the second wind speed interval comprises the following steps:
segmenting the wind power plant operation data in the second wind speed interval according to a preset wind speed interval to obtain a plurality of wind speed segments;
screening the operation data of the wind power plant in each wind speed section again, and removing power limit and fault shutdown data;
calculating the average power of each wind speed section, and taking the wind speed midpoint of each wind speed section to represent the wind speed section;
and fitting the obtained average power of each wind speed section and the wind speed midpoint data to obtain the fitting power of the fan.
4. The wind turbine power limiting identification method of claim 1, characterized in that: the method for judging whether each timestamp is power-limited or not according to the average power curve of the fan and the power grid side control data in the time period to obtain all power-limiting moments comprises the following steps:
calculating to obtain a predicted value P of the power generation capacity of the whole field according to the average power curve of the fan in the time periodFull field capabilityAnd the actual value P of the power generation capacityFull-field real hair；
According to the obtained full-field generating capacity predicted value PFull field capabilityAnd the actual value P of the power generation capacityFull-field real hairAnd power grid side control data for judging whether each timestamp is power-limited or not to obtain all the timestamp timeAnd (5) power limiting time.
5. The wind turbine power limiting identification method of claim 4, wherein: the predicted value P of the full-field generating capacity is obtained according to the obtainedFull field capabilityAnd the actual value P of the power generation capacityFull-field real hairAnd the method for controlling data at the power grid side and judging whether the timestamp moments are power-limited or not to obtain all power-limiting moments comprises the following steps:
eliminating time periods without data;
for all timestamp moments of all time periods with data, carrying out power-limiting moment judgment based on preset power-limiting moment judgment conditions; the preset power-limiting moment judgment condition is as follows:
if:
(Pfull-field real hair＞PFull field reception)or(PFull field capability＞max(PFull-field real hair+thresOperation of，PFull field reception+thresControl of))
The time will be determined as the power-limited time;
repeating the previous step, and judging to obtain all the power-limited moments in each time period
Figure FDA0003192051180000021
And according to the planned active power PFull field planActual received active power PFull field receptionActual value P of generating capacity of whole fieldFull-field real hairPredicted value P of power generation capacity of whole fieldFull field capabilityAnd all the time when electricity is limited
Figure FDA0003192051180000022
And drawing a schematic diagram of the recognition result of the electricity limiting time by data.
6. The wind turbine power limiting identification method of claim 1, characterized in that: the method for identifying each electricity-limiting fan based on the obtained average power curve of the fan and all electricity-limiting moments to obtain all fan numbers which are judged to be in a limited state and correspond to each electricity-limiting moment comprises the following steps:
for each power-limiting time t obtainedLimit ofSetting a time-limited time period [ t ] centered on the time-limited time periodLimit of-δ，tLimit of+δ]Calculating the estimated value of the power generation capacity of each fan in the time-limited time period by using the average power curve of the fans and the wind speed data of the fans;
obtaining an estimated value of actual power of each fan in a time-limited period through the operation data of the wind power plant, subtracting the estimated value from the average value of the power generation capacity of the fan, and correcting the difference value to obtain a power deviation value of each fan;
summing the power deviation of each fan to obtain the total power deviation of the whole field;
and judging to obtain all the fans with limited power according to the estimated value of the generating capacity of each fan, the power deviation value and the total deviation of the full-field power.
7. The wind turbine power limiting identification method of claim 6, wherein: the method for judging and obtaining all the fans with limited power according to the estimated value of the generating capacity, the power deviation value and the total deviation sum of the full-field power of each fan comprises the following steps:
firstly, defining ratio as a percentage value of power deviation of all fans judged to be in a power-limited state to the total of power deviation of a whole field, and setting an initial value of the ratio as 0;
calculating the power deviation value of each fan
Figure FDA0003192051180000023
And estimated value of power generation capacity
Figure FDA0003192051180000024
Ratio of
Figure FDA0003192051180000025
Thirdly, judging the power limiting state: if the ratio of the fan
Figure FDA0003192051180000026
Greater than a preset third threshold thresFan blowerAnd estimated value of power generation capacity
Figure FDA0003192051180000027
Greater than a preset fourth threshold lbFan blowerJudging the fan to be in a power limiting state and deviating the power of the fan to be in a deviation value
Figure FDA0003192051180000028
Adding the percentage value accounting for the total sum of the power deviation of the full field and the ratio defined in the step (r), and if the value of res is greater than a preset fifth threshold value thres of the cumulative influence of the full field limit electric fanAll over the fieldEntering the step (sixthly), otherwise entering the step (sixthly);
fourthly, all the fans which are not judged to be in the power limiting state are subjected to power deviation value according to the power deviation value
Figure FDA0003192051180000031
Sorting from big to small;
judging the fan to be in a power limiting state according to the method in the third step, and taking the percentage value of the power deviation of the fan to the total power deviation of the whole field
Figure FDA0003192051180000032
Adding with ratio until ratio > thresAll over the field；
And sixthly, outputting all fan numbers judged to be in the power-limiting state.
8. A wind turbine power limiting identification system, comprising:
the data preprocessing module is used for carrying out sorting, cleaning and preliminary screening on the acquired wind power plant operation data and power grid side control data in a certain time period to obtain the wind power plant operation data and the power grid side control data under the normal working condition;
the power curve fitting module is used for performing power fitting on the obtained wind power plant operation data under the normal working condition to obtain a fan average power curve of the wind power plant in the time period;
the power limiting time identification module is used for judging whether each timestamp time is power limited or not according to the average power curve of the fan and the power grid side control data in the time period to obtain all power limiting times;
and the electricity-limiting fan identification module is used for identifying the electricity-limiting fans based on the obtained average power curve of the fans and all electricity-limiting moments to obtain all fan numbers which are judged to be in a limited state and correspond to all the electricity-limiting moments.
9. A processing device comprising at least a processor and a memory, the memory having stored thereon a computer program, characterized in that the steps of the method for identifying a wind turbine power limit as claimed in any one of claims 1 to 7 are performed when the computer program is executed by the processor.
10. A computer storage medium having computer readable instructions stored thereon which are executable by a processor to perform the steps of the wind turbine power limit identification method according to any one of claims 1 to 7.
CN202110881128.3A 2021-08-02 2021-08-02 Fan electricity limiting identification method, system, equipment and storage medium Active CN113626767B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110881128.3A CN113626767B (en) 2021-08-02 2021-08-02 Fan electricity limiting identification method, system, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110881128.3A CN113626767B (en) 2021-08-02 2021-08-02 Fan electricity limiting identification method, system, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113626767A true CN113626767A (en) 2021-11-09
CN113626767B CN113626767B (en) 2022-06-28

Family

ID=78382261

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110881128.3A Active CN113626767B (en) 2021-08-02 2021-08-02 Fan electricity limiting identification method, system, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113626767B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114444820A (en) * 2022-04-11 2022-05-06 南方电网数字电网研究院有限公司 New energy power prediction power limiting data identification method based on meteorological-power characteristics
CN114444291A (en) * 2022-01-20 2022-05-06 中节能风力发电股份有限公司 Method, system, equipment and medium for finely measuring and calculating power generation loss of fan
CN117235449A (en) * 2023-11-14 2023-12-15 湖北省气象服务中心（湖北省专业气象服务台） Method for processing wind power abnormal data based on sigmoid curve and double-wrapping algorithm

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102097828A (en) * 2010-12-30 2011-06-15 中国电力科学研究院 Wind power optimal scheduling method based on power forecast
CN104112241A (en) * 2014-07-28 2014-10-22 国家电网公司 Fan head wind speed method based wind power plant theoretical power calculation method
US20160061188A1 (en) * 2014-09-03 2016-03-03 General Electric Company System and method for regulating power in a wind farm
CN109086253A (en) * 2018-07-20 2018-12-25 西安西热电站信息技术有限公司 A kind of Wind turbines loss electricity calculation method based on reliability dimension
CN111146806A (en) * 2020-01-03 2020-05-12 国电联合动力技术有限公司 Active available output dynamic calculation optimization method for wind power plant and energy management platform
CN111460360A (en) * 2020-04-24 2020-07-28 国能日新科技股份有限公司 Power curve fitting data preprocessing method and device based on density distribution
CN111950131A (en) * 2020-07-20 2020-11-17 东南大学 Wind power plant output equivalent aggregation model construction method considering electricity limiting factors
CN111987741A (en) * 2020-07-24 2020-11-24 山西大学 Wind power plant energy management technology based on operation data mining and dynamic interval control
CN112131703A (en) * 2020-08-13 2020-12-25 国网新源张家口风光储示范电站有限公司 Fan running characteristic analysis system based on MATLAB functional module
CN112597620A (en) * 2020-09-24 2021-04-02 新天绿色能源股份有限公司 Wind turbine generator power curve modeling method based on k-medoids algorithm

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102097828A (en) * 2010-12-30 2011-06-15 中国电力科学研究院 Wind power optimal scheduling method based on power forecast
CN104112241A (en) * 2014-07-28 2014-10-22 国家电网公司 Fan head wind speed method based wind power plant theoretical power calculation method
US20160061188A1 (en) * 2014-09-03 2016-03-03 General Electric Company System and method for regulating power in a wind farm
CN109086253A (en) * 2018-07-20 2018-12-25 西安西热电站信息技术有限公司 A kind of Wind turbines loss electricity calculation method based on reliability dimension
CN111146806A (en) * 2020-01-03 2020-05-12 国电联合动力技术有限公司 Active available output dynamic calculation optimization method for wind power plant and energy management platform
CN111460360A (en) * 2020-04-24 2020-07-28 国能日新科技股份有限公司 Power curve fitting data preprocessing method and device based on density distribution
CN111950131A (en) * 2020-07-20 2020-11-17 东南大学 Wind power plant output equivalent aggregation model construction method considering electricity limiting factors
CN111987741A (en) * 2020-07-24 2020-11-24 山西大学 Wind power plant energy management technology based on operation data mining and dynamic interval control
CN112131703A (en) * 2020-08-13 2020-12-25 国网新源张家口风光储示范电站有限公司 Fan running characteristic analysis system based on MATLAB functional module
CN112597620A (en) * 2020-09-24 2021-04-02 新天绿色能源股份有限公司 Wind turbine generator power curve modeling method based on k-medoids algorithm

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张方红等: "基于相关向量机的风电机组功率曲线建模与监测", 《船舶工程》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114444291A (en) * 2022-01-20 2022-05-06 中节能风力发电股份有限公司 Method, system, equipment and medium for finely measuring and calculating power generation loss of fan
CN114444820A (en) * 2022-04-11 2022-05-06 南方电网数字电网研究院有限公司 New energy power prediction power limiting data identification method based on meteorological-power characteristics
CN114444820B (en) * 2022-04-11 2022-10-18 南方电网数字电网研究院有限公司 New energy power prediction electricity limiting data identification method based on meteorological-power characteristics
CN117235449A (en) * 2023-11-14 2023-12-15 湖北省气象服务中心（湖北省专业气象服务台） Method for processing wind power abnormal data based on sigmoid curve and double-wrapping algorithm

Also Published As

Publication number Publication date
CN113626767B (en) 2022-06-28

Similar Documents

Publication Publication Date Title
CN113626767B (en) Fan electricity limiting identification method, system, equipment and storage medium
Shen et al. A combined algorithm for cleaning abnormal data of wind turbine power curve based on change point grouping algorithm and quartile algorithm
Hu et al. Adaptive confidence boundary modeling of wind turbine power curve using SCADA data and its application
Kang et al. Big data analytics in China's electric power industry: modern information, communication technologies, and millions of smart meters
CN104573876A (en) Wind power plant short-period wind speed prediction method based on time sequence long memory model
CN104252649A (en) Regional wind power output prediction method based on correlation between multiple wind power plants
CN110659693A (en) K-nearest neighbor classification-based rapid topology identification method and system for power distribution network and readable storage medium
CN106570790B (en) Wind power plant output data restoration method considering wind speed data segmentation characteristics
CN103971175A (en) Short-term load prediction method of multistage substations
CN116089777B (en) Intelligent new energy settlement method and system based on intelligent information matching
CN113191575A (en) Power distribution network maintenance power failure mode optimization method and device, terminal and storage medium
CN115456304A (en) Offshore wind farm reliability index calculation method and device considering typhoon influence
CN113988398A (en) Wind turbine generator power prediction method and device, electronic equipment and storage medium
CN111639583A (en) Method and system for identifying power quality disturbance of power grid
CN108471137B (en) Wind power prediction wind speed power probabilistic mapping method
CN107808209B (en) Wind power plant abnormal data identification method based on weighted kNN distance
CN103473607B (en) By track characteristic optimization and the wind-powered electricity generation ultra-short term prediction method of coupling Extrapolating model
CN112365090A (en) Deep learning-based non-invasive electrical load identification method and device
CN115898787A (en) Method and device for dynamically identifying static yaw error of wind turbine generator
CN116307886A (en) Method and device for monitoring production state of enterprise in real time
CN116109152A (en) System and method for evaluating effectiveness of power-added and upgraded product of wind generating set
CN116470491A (en) Photovoltaic power probability prediction method and system based on copula function
CN115528684A (en) Ultra-short-term load prediction method and device and electronic equipment
CN113283035B (en) Method, system, equipment and storage medium for constructing double-parameter wind turbine engine room transfer function
Momani et al. Short-term load forecasting based on NARX and radial basis neural networks approaches for the Jordanian power grid

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant