CN112836900B - Wind power prediction error probability calculation method and device and readable storage medium - Google Patents

Wind power prediction error probability calculation method and device and readable storage medium Download PDF

Info

Publication number
CN112836900B
CN112836900B CN202110246791.6A CN202110246791A CN112836900B CN 112836900 B CN112836900 B CN 112836900B CN 202110246791 A CN202110246791 A CN 202110246791A CN 112836900 B CN112836900 B CN 112836900B
Authority
CN
China
Prior art keywords
wind power
prediction error
time
quality function
historical
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.)
Active
Application number
CN202110246791.6A
Other languages
Chinese (zh)
Other versions
CN112836900A (en
Inventor
邵常政
谢开贵
胡博
丁劲峰
牛涛
李春燕
潘聪聪
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.)
Chongqing University
Original Assignee
Chongqing University
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 Chongqing University filed Critical Chongqing University
Priority to CN202110246791.6A priority Critical patent/CN112836900B/en
Publication of CN112836900A publication Critical patent/CN112836900A/en
Application granted granted Critical
Publication of CN112836900B publication Critical patent/CN112836900B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] 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
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
    • 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

Abstract

The invention discloses a wind power prediction error probability calculation method, which comprises the following steps: acquiring historical wind power data and quality function parameters; generating a wind power prediction error model based on the wind power historical data and the quality function parameter fusion multisource information training; calculating wind power output based on the double-layer Monte Carlo sampling wind power prediction error model; and calculating a system reliability index by using the optimal power flow model and taking the minimum load as an objective function based on the historical wind power data and the wind power output. The invention also discloses a wind power prediction error probability calculation device and a readable storage medium. The wind power prediction method and the wind power prediction device can improve the accuracy of wind power prediction and the running reliability of the power system.

Description

Wind power prediction error probability calculation method and device and readable storage medium
Technical Field
The invention relates to the technical field of wind power, in particular to a wind power prediction error probability calculation method and device and a readable storage medium.
Background
At present, the influence of wind power generation on the environment is small, the power generation cost is negligible, and the contribution of the wind power generation to global power supply is larger and larger. Although wind power generation has many environmental benefits, the uncertainty resulting from the tremendous popularity of wind power generation also presents a significant challenge for reliable operation of the power system. In order to accurately measure uncertainty of wind power output, wind power prediction technology is rapidly developed. However, the wind power prediction has low accuracy and large uncertainty.
Disclosure of Invention
In view of the above, the invention aims to provide a wind power prediction error probability calculation method, a wind power prediction error probability calculation device and a readable storage medium, which aim to improve the accuracy of wind power prediction and the operation reliability of a power system.
In order to achieve the above object, the present invention provides a wind power prediction error probability calculation method, which includes the following steps:
acquiring historical wind power data and quality function parameters;
generating a wind power prediction error model based on the wind power historical data and the quality function parameter fusion multisource information training;
calculating wind power output based on the double-layer Monte Carlo sampling wind power prediction error model;
and calculating a system reliability index by using the optimal power flow model and taking the minimum load as an objective function based on the historical wind power data and the wind power output.
Optionally, the quality function parameter includes: the historical wind power data comprises rated power, and the step of generating a wind power prediction error model based on wind power historical data and quality function parameter fusion multi-source information training comprises the following steps:
establishing an error identification framework according to the interval parameters and the rated power;
Calculating to obtain an original quality function based on the error identification frame and the historical wind power data;
obtaining a modified quality function and a second expert quality function based on the discount factor and the original quality function;
detecting whether a predicted value of the first time in the historical wind power data is in a critical area or not;
if the predicted value of the first time in the historical wind power data is in a critical area, calculating a first expert quality function of the first time based on the historical wind power data of the first time and the error identification frame;
and generating a wind power prediction error model based on the corrected quality function, the first expert quality function at the first time and the second expert quality function in a fusion mode.
Optionally, after the step of detecting whether the predicted value of the first time in the historical wind power data is in the critical area, the method includes:
and if the predicted value of the first time in the historical wind power data is not in the critical area, generating a wind power prediction error model based on the fusion of the correction quality function and the second expert quality function.
Optionally, after the step of calculating the wind power output based on the double-layer monte carlo sampling the wind power prediction error model, the method includes:
Detecting whether the first time is less than a prediction period;
if the first time is smaller than the prediction period, detecting whether a predicted value of the second time in the historical wind power data is in a critical area, wherein the second time is equal to the sum of the first time and a time interval;
if the predicted value of the second time in the historical wind power data is in the critical area, calculating a first expert quality function of the second time based on the historical wind power data of the second time and the error identification framework;
generating a wind power prediction error model based on the modified mass function, the first expert mass function at the second time, and the second expert mass function;
if the predicted value of the second time in the historical wind power data is not in the critical area, generating the wind power prediction error model based on the correction quality function and a second expert quality function of the second time;
and the like, when the Nth time is greater than or equal to the prediction period, executing the steps of: and calculating a system reliability index by using the optimal power flow model and taking the minimum load as an objective function based on the historical wind power data and the wind power output.
Optionally, a modified quality function of a daym 1 The calculation formula of (2) is as follows:
m 1 (H 1 )＝α H 1 ＝{E p1 ，...，E q1 }；
wherein { E p1 ，...，E q1 -is the minimum extended focal element that can include all history data, α is the discount factor;
wherein a first expert quality function m of a first time of a day 2 The calculation formula is as follows:
m 2 (H 2 )＝γ+(1-γ)m 0 (H 2 ) H 2 ＝{E p2 ，...，E q2 }；
gamma is the credibility of the first expert information; { E p2 ，...，E q2 -is the smallest extended focal element that can include all history data;
wherein the second expert quality function m of a certain day 3 The calculation formula of (2) is as follows:
m 3 (H 3 )＝α/2+(1-α)m 0 (H 3 ) H 3 ＝{E p3 ，...，E q3 }；
m 3 (H 3 )＝α/2+(1-α)m 0 (H 3 ) H 3 ＝Θ；
wherein { E p3 ，...，E q3 The maximum confidence boundary [ -R ] that can include historical data 2 ，R 2 ]Is the minimum extended focal element, R 2 And historical wind power minimumAnd historical wind power maximum +.>The relation of (2) is as follows: />
Optionally, the first expert quality function based on the modified quality function and the second time
The step of generating a wind power prediction error model by fusing the second expert quality function comprises the following steps:
fusion quality function m of a certain day 4 The calculation formula of (2) is as follows:
fusion quality function m based on a certain day 4 Obtaining a wind power prediction error model: bel ({ E) of 0.ltoreq.Bel 1 ，...，E k-1 })≤P WPFE (E k )≤Pl({E 1 ，...，E k-1 })≤1；
Wherein,
wherein Bel (H) 1 ) A trust function for a day; pl (H) 1 ) Is a likelihood function of a certain day.
Optionally, the step of calculating the wind power output based on the double-layer monte carlo sampling the wind power prediction error model includes:
Sampling the wind power prediction error model based on an outer Monte Carlo to obtain an extended focal element;
and obtaining wind power output based on the inner Monte Carlo sampling the prediction error interval.
Optionally, the wind power data includes: the state data of each wind power equipment, and the system reliability index comprises: the step of calculating a system reliability index by using the optimal power flow model and taking the minimum cut load as an objective function based on the historical wind power data and the wind power output comprises the following steps:
simulating the state data of each wind power device to obtain a device state sequence;
constraining the wind power output by using an optimal power flow model and taking the minimum load shedding amount as an objective function and the equipment state sequence to obtain the load shedding amount;
and calculating the power shortage probability and the expected value of the power shortage according to the shaving load quantity.
In addition, to achieve the above object, the present invention also provides an apparatus comprising: the wind power prediction error probability calculation method comprises a memory, a processor and a wind power prediction error probability calculation program which is stored in the memory and can run on the processor, wherein the wind power prediction error probability calculation program is executed by the processor to realize the steps of the wind power prediction error probability calculation method.
In addition, in order to achieve the above object, the present invention also provides a readable storage medium having stored thereon a wind power prediction error probability calculation program which, when executed by a processor, implements the steps of the wind power prediction error probability calculation method as described above.
The invention provides a wind power prediction error probability calculation method, a wind power prediction error probability calculation device and a readable storage medium, wherein historical wind power data and quality function parameters are obtained; generating a wind power prediction error model based on the wind power historical data and the quality function parameter fusion multisource information training; calculating wind power output based on the double-layer Monte Carlo sampling wind power prediction error model; and calculating a system reliability index by using the optimal power flow model and taking the minimum load as an objective function based on the historical wind power data and the wind power output. By the mode, the wind power prediction accuracy can be improved, and the operation reliability of the power system can be improved.
Drawings
FIG. 1 is a schematic diagram of a terminal structure of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart of a first embodiment of a wind power prediction error probability calculation method according to the present invention;
FIG. 3 is a schematic diagram of a double-layer Monte Carlo sampling the wind power prediction error model to calculate wind power output;
FIG. 4 is a flowchart of a second embodiment of a wind power prediction error probability calculation method according to the present invention;
FIG. 5 is a flowchart of a third embodiment of a wind power prediction error probability calculation method according to the present invention;
fig. 6 is a flowchart of a fourth embodiment of a wind power prediction error probability calculation method according to the present invention.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The main solutions of the embodiments of the present invention are: acquiring historical wind power data and quality function parameters; generating a wind power prediction error model based on the wind power historical data and the quality function parameter fusion multisource information training; calculating wind power output based on the double-layer Monte Carlo sampling wind power prediction error model; based on the historical wind power data and the wind power output, calculating a system reliability index by using an optimal power flow model and taking the minimum load as an objective function
The influence of the existing wind power generation on the environment is small, the power generation cost is negligible, and the contribution of the wind power generation to global power supply is larger and larger. Although wind power generation has many environmental benefits, the uncertainty resulting from the tremendous popularity of wind power generation also presents a significant challenge for reliable operation of the power system. In order to accurately measure uncertainty of wind power output, wind power prediction technology is rapidly developed. However, the wind power prediction has low accuracy and large uncertainty.
The method aims to improve the accuracy of wind power prediction and the operation reliability of the power system.
As shown in fig. 1, fig. 1 is a schematic diagram of a terminal structure of a hardware running environment according to an embodiment of the present invention.
The terminal of the embodiment of the invention can be a PC, or can be mobile terminal equipment with a display function, such as a smart phone, a tablet personal computer and the like.
As shown in fig. 1, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Preferably, the terminal may further include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and the like. Among other sensors, such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display screen according to the brightness of ambient light, and a proximity sensor that may turn off the display screen and/or the backlight when the mobile terminal moves to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the acceleration in all directions (generally three axes), and can detect the gravity and the direction when the mobile terminal is stationary, and the mobile terminal can be used for recognizing the gesture of the mobile terminal (such as horizontal and vertical screen switching, related games, magnetometer gesture calibration), vibration recognition related functions (such as pedometer and knocking), and the like; of course, the mobile terminal may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, and the like, which are not described herein.
It will be appreciated by those skilled in the art that the terminal structure shown in fig. 1 is not limiting of the terminal and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a wind power prediction error probability calculation program may be included in a memory 1005 as one type of computer storage medium.
In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call a wind power prediction error probability calculation program stored in the memory 1005, and perform the following operations:
acquiring historical wind power data and quality function parameters;
generating a wind power prediction error model based on the wind power historical data and the quality function parameter fusion multisource information training;
calculating wind power output based on the double-layer Monte Carlo sampling wind power prediction error model;
and calculating a system reliability index by using the optimal power flow model and taking the minimum load as an objective function based on the historical wind power data and the wind power output.
Further, wherein the quality function parameters include: interval parameters and discount factors, the historical wind power data includes rated power, and the processor 1001 may call a wind power prediction error probability calculation program stored in the memory 1005, and further perform the following operations:
establishing an error identification framework according to the interval parameters and the rated power;
calculating to obtain an original quality function based on the error identification frame and the historical wind power data;
obtaining a modified quality function and a second expert quality function based on the discount factor and the original quality function;
detecting whether a predicted value of the first time in the historical wind power data is in a critical area or not;
if the predicted value of the first time in the historical wind power data is in a critical area, calculating a first expert quality function of the first time based on the historical wind power data of the first time and the error identification frame;
and generating a wind power prediction error model based on the corrected quality function, the first expert quality function at the first time and the second expert quality function in a fusion mode.
Further, the processor 1001 may call the wind power prediction error probability calculation program stored in the memory 1005, and further perform the following operations:
And if the predicted value of the first time in the historical wind power data is not in the critical area, generating a wind power prediction error model based on the fusion of the correction quality function and the second expert quality function.
Further, the processor 1001 may call the wind power prediction error probability calculation program stored in the memory 1005, and further perform the following operations:
detecting whether the first time is less than a prediction period;
if the first time is smaller than the prediction period, detecting whether a predicted value of the second time in the historical wind power data is in a critical area, wherein the second time is equal to the sum of the first time and a time interval;
if the predicted value of the second time in the historical wind power data is in the critical area, calculating a first expert quality function of the second time based on the historical wind power data of the second time and the error identification framework;
generating a wind power prediction error model based on the modified mass function, the first expert mass function at the second time, and the second expert mass function;
if the predicted value of the second time in the historical wind power data is not in the critical area, generating the wind power prediction error model based on the correction quality function and a second expert quality function of the second time;
And the like, when the Nth time is greater than or equal to the prediction period, executing the steps of: and calculating a system reliability index by using the optimal power flow model and taking the minimum load as an objective function based on the historical wind power data and the wind power output.
Further, the modified quality function m of a day 1 The calculation formula of (2) is as follows:
m 1 0H 1 )＝α H 1 ＝{E p1 ，..，E q1 }；；
wherein { E p1 ，...，E q1 -is the minimum extended focal element that can include all history data, α is the discount factor;
wherein a first expert quality function m of a first time of a day 2 The calculation formula is as follows:
m 2 (H 2 )＝γ+(1-γ)m 0 (H 2 ) H 2 ＝{E p2 ，...，E q2 }；
gamma is the credibility of the first expert information; { E p2 ，...，E q2 -is the smallest extended focal element that can include all history data;
wherein the second expert quality function m of a certain day 3 The calculation formula of (2) is as follows:
m 3 (H 3 )＝α/2+(1-α)m 0 (H 3 ) H 3 ＝{E p3 ，...，E q3 }；
m 3 (H 3 )＝α/2+(1-α)m 0 (H 3 ) H 3 ＝Θ；
wherein { E p3 ，...，E q3 The maximum confidence boundary [ -R ] that can include historical data 2 ，R 2 ]Is the minimum extended focal element, R 2 And historical wind power minimumAnd historical wind power maximum +.>The relation of (2) is as follows: />
Further, the fusion quality function m of a certain day 4 The calculation formula of (2) is as follows:
fusion quality function m based on a certain day 4 Obtaining a wind power prediction error model: bel ({ E) of 0.ltoreq.Bel 1 ，...，E k-1 })≤P WPFE (E k )≤Pl({E 1 ，...，E k-1 })≤1；
Wherein,
wherein Bel (H) 1 ) A trust function for a day; pl (H) 1 ) Is a likelihood function of a certain day.
Further, the processor 1001 may call the wind power prediction error probability calculation program stored in the memory 1005, and further perform the following operations:
sampling the wind power prediction error model based on an outer Monte Carlo to obtain an extended focal element;
and obtaining wind power output based on the inner Monte Carlo sampling the prediction error interval.
Further, the processor 1001 may call the wind power prediction error probability calculation program stored in the memory 1005, and further perform the following operations:
simulating the state data of each wind power device to obtain a device state sequence;
constraining the wind power output by using an optimal power flow model and taking the minimum load shedding amount as an objective function and the equipment state sequence to obtain the load shedding amount;
and calculating the power shortage probability and the expected value of the power shortage according to the shaving load quantity.
Based on the hardware structure, the embodiment of the wind power prediction error probability calculation method is provided.
The invention discloses a wind power prediction error probability calculation method.
Referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of a wind power prediction error probability calculation method according to the present invention.
In the embodiment of the invention, the wind power prediction error probability calculation method is applied to a wind power prediction error probability calculation device, and comprises the following steps:
S10, acquiring historical wind power data and quality function parameters;
in this embodiment, in order to improve accuracy of wind power prediction and improve reliability of operation of the power system, the wind power prediction error probability calculation device obtains historical wind power data and quality function parameters. Wherein, historical wind power data includes: the method comprises the steps of electrical parameters (such as upper and lower output limits of a unit, upper and lower power limits of a circuit and the like), reliability parameters (such as failure rate and repair rate of the unit and the circuit), a power grid structure (element connection mode in a network), historical data of wind power output power and rated power of the wind power unit. Wherein the quality function parameters include: interval parameters, a discount factor alpha and the credibility gamma of the first expert information.
S20, generating a wind power prediction error model based on the wind power historical data and the quality function parameter fusion multisource information training;
in this embodiment, after the wind power prediction error probability calculation device acquires the historical wind power data, the wind power prediction error probability calculation device fuses the multi-source information training according to the wind power historical data and the quality function to generate a wind power prediction error model. The wind power prediction error model is used for accurately modeling wind power prediction errors.
Step S30, calculating wind power output based on the double-layer Monte Carlo sampling wind power prediction error model;
in this embodiment, the wind power prediction error probability calculation device calculates the wind power output by using the double-layer monte carlo sampling wind power prediction error model after generating the wind power prediction error model.
Step S30 calculates wind power output based on the double-layer monte carlo sampling the wind power prediction error model, and may include:
step a1, sampling the wind power prediction error model based on an outer layer Monte Carlo to obtain an extended focal element;
in this embodiment, after the wind power prediction error probability calculation device generates the wind power prediction error model, the wind power prediction error probability calculation device obtains the prediction error interval based on the wind power prediction error model sampled by the outer layer monte carlo.
Wherein the error recognition frame Θ= { E 1 ，E 2 ，...，E N And the wind power prediction error interval is a set of wind power prediction error intervals. The error recognition frame divides the wind power interval of a wind turbine into a plurality of cells (for example, the wind power interval of a wind turbine is 0-1.5 megawatts, the wind power interval of the wind turbine is divided into 10 cells E) k I.e. 0-0.15, 0.15-0.3, 0.3-0.45 … … 1.2-1.35, 1.35-1.5 megawatts). Extended focal element H is a power set of Θ Elements of (a) and (b); the extended focal element may include multiple cells (e.g., the extended focal element includes: 0.3-0.45, 0.75-0.9).
Wherein an extended focal element Θ (an interval) corresponds to a probability. Each sample is taken of a particular wind power prediction error value. Therefore, the outer layer Monte Carlo is used to sample a prediction error interval, the extended focal element (interval) is used, and then the inner layer Monte Carlo is used to sample a specific value (namely wind power output) in the extended focal element (interval).
Wherein, the outer Monte Carlo sampling can be expressed as:
u 1 representing random numbers between 01, each random number can find the corresponding extended focal element (interval) of the random number, and the extended focal element can be a single interval or a large interval formed by combining a plurality of continuous intervals. I.e.And r is more than or equal to 1 and s is more than or equal to N.
And a step a2, sampling the extended focal element based on the inner Monte Carlo to obtain wind power output.
In this embodiment, after obtaining the extended focal element, the wind power prediction error probability calculation device samples the extended focal element based on the inner layer monte carlo to obtain the wind power output.
Wherein the inner Monte Carlo is extracted from the outer Monte Carlo Random sampling in interval, assuming that the sampling is uniformly distributed, and arbitrary taking random number u 2 ，/>See in particular figure 3.
And S40, calculating a system reliability index by using the optimal power flow model and taking the minimum cut load amount as an objective function based on the historical wind power data and the wind power output.
In this embodiment, after the wind power output is calculated, the wind power prediction error probability calculation device calculates the system reliability index by using the optimal power flow model with the minimum cut load as the objective function based on the historical wind power data and the wind power output. Wherein, the system reliability index includes: the probability of power shortage (LOLP, loss of load probability method) and the expected value of power shortage (EENS, expected energy not served). Wherein, the calculation formula of the power shortage probability is as follows:
wherein,the load shedding amount corresponding to the inode at the T hour of the H evaluation day, T is the total evaluation hour number (default 24), H is the total evaluation day, and B is the set of all the nodes of the evaluation system.
The calculation formula of the expected value of the electric quantity shortage is as follows:
according to the embodiment, through the scheme, historical wind power data and quality function parameters are obtained; generating a wind power prediction error model based on the wind power historical data and the quality function parameter fusion multisource information training; calculating wind power output based on the double-layer Monte Carlo sampling wind power prediction error model; and calculating a system reliability index by using the optimal power flow model and taking the minimum load as an objective function based on the historical wind power data and the wind power output. Therefore, the accuracy of wind power prediction is improved, and the running reliability of the power system is improved.
Further, referring to fig. 4, fig. 4 is a flowchart illustrating a second embodiment of a wind power prediction error probability calculation method according to the present invention. Based on the embodiment shown in fig. 2, the quality function parameters include: the interval parameters and the discount factors, the historical wind power data comprises rated power, and the step S20 of generating a wind power prediction error model based on wind power historical data and quality function parameter fusion multi-source information training can comprise the following steps:
s21, establishing an error identification framework according to the interval parameters and the rated power;
in this embodiment, after obtaining the interval parameter and the discount factor in the quality function parameter and the rated power in the historical wind power data, the wind power prediction error probability calculating device establishes an error identification frame according to the interval parameter and the rated power. Wherein the error recognition frame Θ= { E 1 ，E 2 ，...，E N And the wind power prediction error interval is a set of wind power prediction error intervals. The error recognition frame divides the wind power interval of a wind turbine into a plurality of cells (for example, the wind power interval of a wind turbine is 0-1.5 megawatts, the wind power interval of the wind turbine is divided into 10 cells E) k I.e. 0-0.15, 0.15-0.3, 0.3-0.45 … … 1.2-1.35, 1.35-1.5 megawatts). Extended focal element H is a power set of ΘElements of (a) and (b); the extended focal element may include a plurality of cells (e.g., the extended focal element includes: 0.3-0.45, 0.75-0.9); the quality function is also called basic probability distribution, i.e. BPA (basic probability assignment), and is used to assign probabilities to the individual extended focal elements. The mass function includes: original quality function m 0 Correction of the mass function m 1 First expert quality function m 2 And a second expert quality function m 3 The method comprises the steps of carrying out a first treatment on the surface of the Correcting the mass function m 1 First expert quality function m 2 Second expert quality function m 3 Are calculated based on the error recognition framework.
Step S22, calculating to obtain an original quality function based on the error identification frame and the historical wind power data;
in this embodiment, the wind power prediction error probability calculation device calculates an original quality function according to the error recognition frame and the historical wind power data after the error recognition frame is established. Wherein the original quality function m 0 Is calculated by adopting a frequency statistical method according to historical wind power data.
And step S23, obtaining a modified quality function and a second expert quality function based on the discount factors and the original quality function.
In the embodiment, after the wind power prediction error probability calculation device obtains the original quality function, a corrected quality function is obtained based on the discount factor and the original quality function; and obtaining a second expert quality function based on the discount factor and the original quality function.
Modified mass function m of a day 1 The calculation formula of (2) is as follows:
m 1 (H 1 )＝α H 1 ＝{E p1 ，...，E q1 }；
wherein { E p1 ，...，E q1 -is the minimum extended focal element that can include all history data, α is the discount factor; the discount factor α may be set to 0.05.
Wherein the second expert quality function m of a certain day 3 The calculation formula of (2) is as follows:
m 3 (H 3 )＝α/2+(1-α)m 0 (H 3 ) H 3 ＝{E p3 ，，E q3 }；
m 3 (H 3 )＝α/2+(1-α)m 0 (H 3 ) H 3 ＝Θ；
wherein { E p3 ，...，E q3 The maximum confidence boundary [ -R ] that can include historical data 2 ，R 2 ]Is the minimum extended focal element, R 2 And historical wind power minimumAnd historical wind power maximum +.>The relation of (2) is as follows: />
Wherein the calculation of the quality function is entirely based on the identification frame Θ, and the interval formed by the minimum value of the historical wind power and the maximum value of the historical wind power may not be the standard interval E divided in advance k A similar normalization operation is required, and a section formed by the minimum value of the historical wind power and the maximum value of the historical wind power is required to be included in one cell E k Inner or multiple inter-cell E k And (3) inner part. For example, the wind power of the wind turbine is divided into 10 sections according to the identification frame Θ, i.e. [0,0.15 ]]、[0.15，0.3]…[1.35，1.5]. However, when the minimum and maximum values of the historical wind power are 0.1 and 1.3, it corresponds to [0.1,1.3 ]]This interval, however, cannot be combined from 10 intervals that we have previously divided. Can include all historical wind power, i.e. [0.1,1.3 ]]The left boundary of the interval is less than or equal to the minimum value of the historical data, [0.1,1.3 ]]The right boundary of the interval is greater than or equal to the maximum value of the historical data, namely the minimum extended focal element is [0,1.35 ]]. Other { E p ，...，E q The minimum extended focal element represented by is determined in the manner described above.
Step S24, detecting whether a predicted value of the first time in the historical wind power data is in a critical area;
in this embodiment, after the wind power prediction error probability calculating device establishes the error recognition frame or after obtaining the modified quality function and the second expert quality function, the wind power prediction error probability calculating device determines whether the predicted value of the first time in the historical wind power data is in the critical area. The historical wind power data comprises a predicted value of a first time, a predicted value of a second time and a predicted value of an Nth time … …. The predicted value of the first time is known information, for example, the operation reliability of the next day is to be evaluated, and then the predicted value of the wind power of the next day is input into the wind power prediction error probability calculation device as known data.
Wherein R is provided with 1 The critical area width is the wind power predictionAreas having values close to their upper or lower boundaries, i.e. upper critical areasAnd lower critical area [0, R 1 ]Critical area width R 1 And critical coefficient beta and rated power of fan +.>The relation of (2) is as follows: />The critical coefficient β is a constant. If the wind power predicted value at the moment t is in the upper critical area { E } p ，...，E q [0, R ] can be included 1 ]Is a minimum extended focal element of (2); if the wind power predicted value at the moment t is in the lower critical area { E } p ，...，E q Is capable of including [ -R } 1 ，0]Is a minimum extended focal element of (2).
Step S24 of detecting whether the predicted value of the first time in the historical wind power data is in the critical area may include:
and b, if the predicted value of the first time in the historical wind power data is not in the critical area, generating a wind power prediction error model based on the fusion of the correction quality function and the second expert quality function.
In this embodiment, when the wind power prediction error probability calculating device determines that the predicted value of the first time in the historical wind power data is not in the critical area, the wind power prediction error probability calculating device generates a wind power prediction error model based on the modified quality function and the second expert quality function.
Step b, generating a wind power prediction error model based on the modified quality function and the second expert quality function fusion, may include:
step c1, fusion quality function m of a day 4 The calculation formula of (2) is as follows:
/>
step c2, fusion quality function m based on a certain day 4 Obtaining a wind power prediction error model: bel ({ E) of 0.ltoreq.Bel 1 ，...，E k-1 })≤P WPFE (E k )≤Pl({E 1 ，...，E k-1 })≤1；
Wherein,
wherein Bel (H) 1 ) A trust function for a day; pl (H) 1 ) Is a likelihood function of a certain day.
Wherein an extended focal element Θ (an interval) corresponds to a probability.
Step S25, if the predicted value of the first time in the historical wind power data is in a critical area, calculating a first expert quality function of the first time based on the historical wind power data of the first time and the error recognition frame;
in this embodiment, when the wind power prediction error probability calculating device determines that the predicted value of the first time in the historical wind power data is in the critical area, the wind power prediction error probability calculating device calculates the first expert quality function of the first time based on the historical wind power data of the first time and the error recognition frame.
Wherein the first expert quality function m of a certain day 2 The calculation formula is as follows:
m 2 (H 2 )＝γ+(1-γ)m 0 (H 2 ) H 2 ＝{E p2 ，...，E q2 }；
gamma is the credibility of the first expert information; gamma may be 0.95.{ E p2 ，...，E q2 -is the smallest extended focal element that can include all history data;
and S26, generating a wind power prediction error model based on the corrected quality function, the first expert quality function at the first time and the second expert quality function in a fusion mode.
In this embodiment, after the wind power prediction error probability calculation device calculates the correction quality function, the first expert quality function at the first time, and the second expert quality function, the wind power prediction error probability calculation device generates a wind power prediction error model based on fusion of the correction quality function, the first expert quality function at the first time, and the second expert quality function.
Step S26 generates a wind power prediction error model based on the modified quality function, the first expert quality function at the first time, and the second expert quality function fusion, and may include:
step d1, fusion quality function m of a day 4 The calculation formula of (2) is as follows:
step d2, fusion quality function m based on a certain day 4 Obtaining a wind power prediction error model: bel ({ E) of 0.ltoreq.Bel 1 ，...，E k-1 })≤P WPFE (E k )≤Pl({E 1 ，...，E k-1 })≤1；
Wherein,
wherein Bel (H) 1 ) A trust function for a day; pl (H) 1 ) Is a likelihood function of a certain day.
Wherein an extended focal element Θ (an interval) corresponds to a probability.
According to the scheme, an error identification frame is established according to the interval parameter and the rated power; calculating to obtain an original quality function based on the error identification frame and the historical wind power data; obtaining a modified quality function and a second expert quality function based on the discount factor and the original quality function; detecting whether a predicted value of the first time in the historical wind power data is in a critical area or not; if the predicted value of the first time in the historical wind power data is in a critical area, calculating a first expert quality function of the first time based on the historical wind power data of the first time and the error identification frame; and generating a wind power prediction error model based on the corrected quality function, the first expert quality function at the first time and the second expert quality function in a fusion mode. Therefore, the accuracy of wind power prediction is improved, and the running reliability of the power system is improved.
Further, referring to fig. 5, fig. 5 is a flowchart illustrating a third embodiment of a wind power prediction error probability calculation method according to the present invention. Based on the embodiment shown in fig. 4, step S30 may include, after calculating the wind power output based on the two-layer monte carlo sampling the wind power prediction error model:
Step S51, detecting whether the first time is smaller than a prediction period;
in this embodiment, the wind power prediction error probability calculation means determines whether the first time is smaller than the prediction period after calculating the wind power output. Wherein the predicted week is typically set to 24 hours. The first hour is the first hour of 1 day.
Step S52, if the first time is smaller than the prediction period, detecting whether the predicted value of the second time in the historical wind power data is in a critical area, wherein the second time is equal to the sum of the first time and a time interval;
in this embodiment, when the wind power prediction error probability calculating device determines that the first time is smaller than the prediction period, the wind power prediction error probability calculating device determines whether the predicted value of the second time in the historical wind power data is in the critical area, where the second time is equal to the sum of the first time and the time interval.
Wherein R is provided with 1 The critical area is the area of wind power predicted value near the upper or lower boundary, i.e. the upper critical areaAnd lower critical area [0, R 1 ]Critical area width R 1 And critical coefficient beta and rated power of fan +.>The relation of (2) is as follows: />The critical coefficient β is a constant. If the wind power predicted value at the moment t is in the upper critical area { E } p ，...，E q [0, R ] can be included 1 ]Is a minimum extended focal element of (2); if the wind power predicted value at the moment t is in the lower critical area { E } p ，...，E q Is capable of including [ -R } 1 ，0]Is a minimum extended focal element of (2).
Step S53, if the predicted value of the second time in the historical wind power data is in the critical area, calculating a first expert quality function of the second time based on the historical wind power data of the second time and the error recognition frame;
in this embodiment, when the wind power prediction error probability calculating device determines that the predicted value of the second time in the historical wind power data is in the critical area, the wind power prediction error probability calculating device calculates a first expert quality function of the second time based on the historical wind power data of the second time and the error recognition frame;
wherein a first expert quality function m of a second time of day 2 The calculation formula is as follows:
m 2 (H 2 )＝γ+(1-γ)m 0 (H 2 ) H 2 ＝{E p2 ，...，E q2 }；
gamma is the credibility of the first expert information; { E p2 ，...，E q2 -is the smallest extended focal element that can include all history data;
and step S54, generating a wind power prediction error model based on the modified quality function, the first expert quality function of the second time and the second expert quality function.
In this embodiment, after the wind power prediction error probability calculation device calculates the corrected quality function, the first expert quality function at the second time, and the second expert quality function, the wind power prediction error probability calculation device generates a wind power prediction error model based on fusion of the corrected quality function, the first expert quality function at the second time, and the second expert quality function.
Step S55, if the predicted value of the second time in the historical wind power data is not in the critical area, generating the wind power prediction error model based on the modified quality function and the second expert quality function of the second time;
in this embodiment, when the wind power prediction error probability calculating device determines that the predicted value of the second time in the historical wind power data is not in the critical area, the wind power prediction error probability calculating device generates a wind power prediction error model based on the modified quality function and the second expert quality function fusion.
Step S55 generates a wind power prediction error model based on the modified quality function, the first expert quality function and the second expert quality function of the second time in a fusion manner, and may include:
Step e1, fusion quality function m of a day 4 The calculation formula of (2) is as follows:
step c2, fusion quality function m based on a certain day 4 Obtaining a wind power prediction error model: bel ({ E) of 0.ltoreq.Bel 1 ，...，E k-1 })≤P WPFE (E k )≤Pl({E 1 ，...，E k-1 })≤1；
Wherein,
wherein Bel (H) 1 ) A trust function for a day; pl (H) 1 ) Is a likelihood function of a certain day.
Step S56, and so on, until the nth time is greater than or equal to the prediction period, executing the steps of: and calculating a system reliability index by using the optimal power flow model and taking the minimum load as an objective function based on the historical wind power data and the wind power output.
In the present embodiment, step S40 is performed until the nth time is greater than or equal to the prediction period. Wherein, the nth time is 24 hours of 1 day.
According to the embodiment, through the scheme, whether the first time is smaller than a prediction period is detected; if the first time is smaller than the prediction period, detecting whether a predicted value of the second time in the historical wind power data is in a critical area, wherein the second time is equal to the sum of the first time and a time interval; if the predicted value of the second time in the historical wind power data is in the critical area, calculating a first expert quality function of the second time based on the historical wind power data of the second time and the error identification framework; generating a wind power prediction error model based on the modified mass function, the first expert mass function at the second time, and the second expert mass function; if the predicted value of the second time in the historical wind power data is not in the critical area, generating the wind power prediction error model based on the correction quality function and a second expert quality function of the second time; and the like, when the Nth time is greater than or equal to the prediction period, executing the steps of: and calculating a system reliability index by using the optimal power flow model and taking the minimum load as an objective function based on the historical wind power data and the wind power output. Therefore, the accuracy of wind power prediction is improved, and the running reliability of the power system is improved.
Further, referring to fig. 6, fig. 6 is a flowchart illustrating a fourth embodiment of a wind power prediction error probability calculation method according to the present invention. Based on the embodiment shown in fig. 5, the wind power data includes: the state data of each wind power equipment, and the system reliability index comprises: step S40, based on the historical wind power data and the wind power output, calculates a system reliability index by using an optimal power flow model and using a minimum cut load as an objective function, and may include:
s41, simulating the state data of each wind power device to obtain a device state sequence;
in this embodiment, after obtaining the state data of each wind power device, the wind power prediction error probability calculating apparatus first determines the initial state of the device (i.e., the element), and generally assumes that all the elements are in an operating state at the initial time; the duration that each device (element) remains in the current state is then sampled. For the repairable two-state element, according to the failure rate lambda and repair rate mu of the element, adopting a transformation method to obtain the failure-free working time tau meeting the exponential distribution 1 And fault repair time τ 2 ：
Wherein U is 1 And U 2 Is [0,1 ]]Uniformly distributing random numbers.
Then, based on the non-faulty operation time and the fault repair time of the device (element), the element state sequence within a given prediction period T (i.e., the simulated total period) is simulated.
S42, restraining the wind power output by using an optimal power flow model and taking the minimum load shedding amount as an objective function and the equipment state sequence to obtain the load shedding amount;
in this embodiment, after obtaining the device state sequence, the wind power prediction error probability calculation device uses the optimal power flow model to constrain wind power output by using the minimum cut load as an objective function and the device state sequence to obtain the cut load.
Wherein the amount of shaving load can be obtained by constraint by the formulas (1) to (9).
/>
Wherein, formula (1) is the power balance constraint of each node, formulas (2) - (4) are the power constraint of each line, formula (5) is the power constraint of the generator, formula (6) is the load shedding amount constraint, formula (7) is the unit climbing constraint, formula (8) is the phase angle constraint, and formula (9) is the phase angle constraint of the balance node.
The output of the g-th machine set at the moment t is a variable;
the power on the line from the j node to the i node at the moment t is a variable;
The power on the line from the i node to the j node at the moment t is a variable;
the output of the w fan at the t moment is constant and is obtained by summing the sampling value and the predicted value (known) of the WPFE model, and the ∈>Wherein (1)>Is the predicted force of the w th fan at the moment t,/->The prediction error sampling result of the w th fan at the moment t is obtained by sampling a double-layer Monte Carlo through an established WPFE model;
the load shedding amount of the i node at the moment t is a variable;
the load of the i node at the moment t is constant;
B ij representing the electrical connection relation between the i node and the j node;
δ i，t is the phase angle of the i node at the moment t;
m is a sufficiently large constant;
all bands min and max superscripts represent lower and upper limits, being constant.
S43, calculating the power shortage probability and the expected value of the power shortage according to the shaving load quantity.
In the present embodiment, the wind power prediction error probability calculation means calculates the power shortage probability and the expected value of the power shortage from the cut load amount after the cut load amount is obtained.
The probability of power shortage (LOLP, loss of load probability method) and the expected value of power shortage (EENS, expected energy not served). Wherein, the calculation formula of the power shortage probability is as follows:
wherein, The load shedding amount corresponding to the inode at the T hour of the H evaluation day, T is the total evaluation hour number (default 24), H is the total evaluation day, and B is the set of all the nodes of the evaluation system. />
The calculation formula of the expected value of the electric quantity shortage is as follows:
the lower the LOLP and EENS are, the more accurate the wind power prediction is, and the better the running reliability of the power system is;
the lower the LOLP, the lower the probability of representing a power system loss of load;
the lower EENS indicates a lower expected under-charge, i.e., less load is lost.
According to the embodiment, through the scheme, the state data of each wind power device are simulated to obtain a device state sequence; constraining the wind power output by using an optimal power flow model and taking the minimum load shedding amount as an objective function and the equipment state sequence to obtain the load shedding amount; and calculating the power shortage probability and the expected value of the power shortage according to the shaving load quantity. Therefore, the accuracy of wind power prediction is improved, and the running reliability of the power system is improved.
The invention further provides a wind power prediction error probability calculation device.
The wind power prediction error probability calculation device comprises: the wind power prediction error probability calculation method comprises a memory, a processor and a wind power prediction error probability calculation program which is stored in the memory and can run on the processor, wherein the wind power prediction error probability calculation program is executed by the processor to realize the steps of the wind power prediction error probability calculation method.
The method implemented when the wind power prediction error probability calculation program running on the processor is executed may refer to each embodiment of the wind power prediction error probability calculation method of the present invention, and will not be described herein.
The invention also provides a readable storage medium.
The wind power prediction error probability calculation program is stored on a readable storage medium, and the wind power prediction error probability calculation program realizes the steps of the wind power prediction error probability calculation method when being executed by a processor.
The method implemented when the wind power prediction error probability calculation program running on the processor is executed may refer to each embodiment of the wind power prediction error probability calculation method of the present invention, and will not be described herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for description, and do not represent advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.

Claims (5)

1. The wind power prediction error probability calculation method is characterized by comprising the following steps of:
acquiring historical wind power data and quality function parameters;
generating a wind power prediction error model based on the historical wind power data and the quality function parameter fusion multisource information training;
calculating wind power output based on the double-layer Monte Carlo sampling wind power prediction error model;
based on the historical wind power data and the wind power output, calculating a system reliability index by using an optimal power flow model and taking the minimum load as an objective function;
wherein the quality function parameters include: the historical wind power data comprises rated power, and the step of generating a wind power prediction error model based on wind power historical data and quality function parameter fusion multi-source information training comprises the following steps:
establishing an error identification framework according to the interval parameters and the rated power;
calculating to obtain an original quality function based on the error identification frame and the historical wind power data;
obtaining a modified quality function and a second expert quality function based on the discount factor and the original quality function;
Detecting whether a predicted value of the first time in the historical wind power data is in a critical area or not;
if the predicted value of the first time in the historical wind power data is in a critical area, calculating a first expert quality function of the first time based on the historical wind power data of the first time and the error identification frame;
generating a wind power prediction error model based on the corrected quality function, the first expert quality function at the first time and the second expert quality function in a fusion mode;
after the step of detecting whether the predicted value of the first time in the historical wind power data is in the critical area, the method comprises the following steps:
if the predicted value of the first time in the historical wind power data is not in the critical area, generating a wind power prediction error model based on the fusion of the correction quality function and the second expert quality function;
after the step of calculating the wind power output based on the double-layer Monte Carlo sampling the wind power prediction error model, the method comprises the following steps:
detecting whether the first time is less than a prediction period;
if the first time is smaller than the prediction period, detecting whether a predicted value of the second time in the historical wind power data is in a critical area, wherein the second time is equal to the sum of the first time and a time interval;
If the predicted value of the second time in the historical wind power data is in the critical area, calculating a first expert quality function of the second time based on the historical wind power data of the second time and the error identification framework;
generating a wind power prediction error model based on the modified mass function, the first expert mass function at the second time, and the second expert mass function;
if the predicted value of the second time in the historical wind power data is not in the critical area, generating the wind power prediction error model based on the correction quality function and a second expert quality function of the second time;
and the like, when the Nth time is greater than or equal to the prediction period, executing the steps of: based on the historical wind power data and the wind power output, calculating a system reliability index by using an optimal power flow model and taking the minimum load as an objective function;
repair of a certain dayPositive mass function m 1 The calculation formula of (2) is as follows:
m 1 (H 1 )＝αH 1 ＝{E p1 ,...,E q1 }；
wherein { E p1 ,…,E q1 -is the minimum extended focal element that can include all history data, α is the discount factor;
wherein a first expert quality function m of a first time of a day 2 The calculation formula is as follows:
m 2 (H 2 )＝γ+(1-γ)m 0 (H 2 )H 2 ＝{E p2 ,...,E q2 }；
Gamma is the credibility of the first expert information; { E p2 ,...,E q2 -is the smallest extended focal element that can include all history data;
wherein the second expert quality function m of a certain day 3 The calculation formula of (2) is as follows:
m 3 (H 3 )＝α/2+(1-α)m 0 (H 3 )H 3 ＝{E p3 ,...,E q3 }；
m 3 (H 3 )＝α/2+(1-α)m 0 (H 3 )H 3 ＝Θ；
wherein { E p3 ,...,E q3 The maximum confidence boundary [ -R ] that can include historical data 2 ,R 2 ]Is the minimum extended focal element, R 2 And historical wind power minimumAnd historical wind power maximum +.>The relation of (2) is as follows: />
The step of generating a wind power prediction error model based on the corrected mass function, the first expert mass function of the second time and the second expert mass function in a fusion way comprises the following steps:
fusion quality function m of a certain day 4 The calculation formula of (2) is as follows:
fusion quality function m based on a certain day 4 Obtaining a wind power prediction error model: bel ({ E) of 0.ltoreq.Bel 1 ,...,E k-1 })≤P WPFE (E k )≤Pl({E 1 ,...,E k-1 })≤1；
Wherein,
wherein Bel (H) 1 ) A trust function for a day; pl (H) 1 ) Is a likelihood function of a certain day.
2. The wind power prediction error probability calculation method according to claim 1, characterized in that: the step of calculating wind power output based on the double-layer Monte Carlo sampling wind power prediction error model comprises the following steps:
sampling the wind power prediction error model based on an outer Monte Carlo to obtain an extended focal element;
and obtaining wind power output based on the inner Monte Carlo sampling the prediction error interval.
3. The wind power prediction error probability calculation method according to claim 1, characterized in that: the wind power data comprises: the state data of each wind power equipment, and the system reliability index comprises: the step of calculating a system reliability index by using the optimal power flow model and taking the minimum cut load as an objective function based on the historical wind power data and the wind power output comprises the following steps:
simulating the state data of each wind power device to obtain a device state sequence;
constraining the wind power output by using an optimal power flow model and taking the minimum load shedding amount as an objective function and the equipment state sequence to obtain the load shedding amount;
and calculating the power shortage probability and the expected value of the power shortage according to the shaving load quantity.
4. The wind power prediction error probability calculating device is characterized in that: the device comprises: a memory, a processor and a wind power prediction error probability calculation program stored on the memory and running on the processor, which when executed by the processor, implements the steps of the wind power prediction error probability calculation method of any one of claims 1 to 3.
5. A readable storage medium, characterized by: the readable storage medium has stored thereon a wind power prediction error probability calculation program which, when executed by a processor, implements the steps of the wind power prediction error probability calculation method according to any one of claims 1 to 3.
CN202110246791.6A 2021-03-05 2021-03-05 Wind power prediction error probability calculation method and device and readable storage medium Active CN112836900B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110246791.6A CN112836900B (en) 2021-03-05 2021-03-05 Wind power prediction error probability calculation method and device and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110246791.6A CN112836900B (en) 2021-03-05 2021-03-05 Wind power prediction error probability calculation method and device and readable storage medium

Publications (2)

Publication Number Publication Date
CN112836900A CN112836900A (en) 2021-05-25
CN112836900B true CN112836900B (en) 2024-01-02

Family

ID=75934659

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110246791.6A Active CN112836900B (en) 2021-03-05 2021-03-05 Wind power prediction error probability calculation method and device and readable storage medium

Country Status (1)

Country Link
CN (1) CN112836900B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103136428A (en) * 2013-03-12 2013-06-05 上海交通大学 Vehicle body structure steady design method based two uncertain saloon cars
CN104659819A (en) * 2015-03-19 2015-05-27 武汉大学 Wind power adsorption estimation method involving wind power prediction error
CN107069721A (en) * 2017-06-21 2017-08-18 华北电力大学 A kind of electric power system operation risk assessment method theoretical based on random set
CN109102155A (en) * 2018-07-09 2018-12-28 中国南方电网有限责任公司 A kind of ultra-short term deploying node probability forecasting method and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103136428A (en) * 2013-03-12 2013-06-05 上海交通大学 Vehicle body structure steady design method based two uncertain saloon cars
CN104659819A (en) * 2015-03-19 2015-05-27 武汉大学 Wind power adsorption estimation method involving wind power prediction error
CN107069721A (en) * 2017-06-21 2017-08-18 华北电力大学 A kind of electric power system operation risk assessment method theoretical based on random set
CN109102155A (en) * 2018-07-09 2018-12-28 中国南方电网有限责任公司 A kind of ultra-short term deploying node probability forecasting method and system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于条件风险方法的风电黑启动价值评估及其应用;叶茂;刘艳;顾雪平;韩思聪;胡琪;;电网技术(11);373-382 *

Also Published As

Publication number Publication date
CN112836900A (en) 2021-05-25

Similar Documents

Publication Publication Date Title
JP4886322B2 (en) Wind power generation output prediction method, wind power generation output prediction apparatus, and program
JP5940922B2 (en) Renewable energy prediction device
JP5888640B2 (en) Photovoltaic power generation prediction apparatus, solar power generation prediction method, and solar power generation prediction program
CN111091196B (en) Passenger flow data determination method and device, computer equipment and storage medium
KR102468316B1 (en) Time series prediction method and apparatus based on past prediction data
CN112285807B (en) Meteorological information prediction method and device
WO2021179700A1 (en) Electricity generation prediction method, apparatus and device, and computer readable storage medium
CN114330935B (en) New energy power prediction method and system based on multiple combination strategies integrated learning
US20220215485A1 (en) Methods and systems for an enhanced energy grid system
US20190138913A1 (en) Prediction model generation device, prediction model generation method, and recording medium
CN113822460A (en) Traffic flow prediction method and device, electronic equipment and storage medium
JP2020134300A (en) Prediction method, prediction program and information processing apparatus
US10998725B2 (en) Electric power generation prediction method based on expected value calculation, electric power generation prediction system based on expected value calculation, and electric power generation prediction program product based on expected value calculation
CN112801357B (en) Solar radiation quantity prediction method, device, equipment and storage medium
CN112836900B (en) Wind power prediction error probability calculation method and device and readable storage medium
CN116565864B (en) Photovoltaic power generation power forecasting method based on PCA-RBF algorithm
JP2011165152A (en) Energy-demand predicting device and energy demand prediction method
CN112801374A (en) Model training method, power load prediction method, device and equipment
JP7212310B2 (en) Power demand forecasting device, power demand forecasting method, and program thereof
JP6552077B1 (en) Solar radiation normalization statistical analysis system, solar radiation normalization statistical analysis method and solar radiation normalization statistical analysis program
CN113011674A (en) Photovoltaic power generation prediction method and device, electronic equipment and storage medium
CN110389947A (en) A kind of blacklist generation method, device, equipment and medium
US20190006850A1 (en) Method for forecasting the power daily generable by a solar inverter
JP6552076B1 (en) Solar radiation appearance probability distribution analysis method, solar radiation appearance probability distribution analysis system, and solar radiation appearance probability distribution analysis program
CN116449456B (en) Gust forecast output method, gust forecast output device, computer equipment and storage medium

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