CN112215392A - Method for predicting power generation capacity of wind power medium and long term region based on equipment state and environmental factors - Google Patents

Method for predicting power generation capacity of wind power medium and long term region based on equipment state and environmental factors Download PDF

Info

Publication number
CN112215392A
CN112215392A CN202010878751.9A CN202010878751A CN112215392A CN 112215392 A CN112215392 A CN 112215392A CN 202010878751 A CN202010878751 A CN 202010878751A CN 112215392 A CN112215392 A CN 112215392A
Authority
CN
China
Prior art keywords
power generation
data
equipment
wind
wind power
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010878751.9A
Other languages
Chinese (zh)
Inventor
朱尤成
王金荣
徐坚
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.)
Guodian Power Yunnan New Energy Development Co ltd
Original Assignee
Guodian Power Yunnan New Energy Development Co ltd
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 Guodian Power Yunnan New Energy Development Co ltd filed Critical Guodian Power Yunnan New Energy Development Co ltd
Priority to CN202010878751.9A priority Critical patent/CN112215392A/en
Publication of CN112215392A publication Critical patent/CN112215392A/en
Pending legal-status Critical Current

Links

Images

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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • 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
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • 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 is applied to the field of wind power generation amount prediction, and particularly relates to a wind power generation medium-and-long-term region power generation amount prediction method based on equipment states and environmental factors, wherein the power generation amount of a fan is modeled through historical data of the environmental factors, and the wind power generation amount of a region is preliminarily predicted through environmental factor prediction data of the second year; establishing a model for normal operation of the equipment through state parameter historical data of the wind power generation equipment, and calculating the probability of normal operation of the equipment under the current state parameter through establishing communication with real-time data; and finally, correcting the preliminary prediction data of the wind power generation amount by adopting the normal operation probability of the equipment to obtain a final predicted value of the actual power generation amount of the medium-long term area. The method solves the problems of complicated calculation mode, long time consumption, complex structure and high cost of the generated energy prediction of the wind power medium-long term region in the existing method and neglects the power generation capacity of the wind power generation equipment.

Description

Method for predicting power generation capacity of wind power medium and long term region based on equipment state and environmental factors
Technical Field
The invention belongs to the technical field of wind power generation capacity prediction, and particularly relates to a method for predicting the power generation capacity of a wind power medium-long term region based on equipment states and environmental factors.
Background
In recent years, the development speed of wind power generation in China is very rapid, the wind power accumulation installed capacity is increased from 589 ten thousand kilowatts in 2007 to 16400 thousand kilowatts in 2017, the annual average growth rate reaches 39.47%, the wind power integration installed capacity in China can further increase along with the increasing shortage of coal resources, and with the continuous utilization of domestic wind resources, the problem of how to realize the prediction of regional wind power generation amount becomes important attention of various colleges and universities and scientific research institutions is solved, and the site selection influence factors of the wind power plant not only include local climate influence but also include the occupation ratio of other energy sources in the whole region. Meanwhile, the classification standard types of wind power prediction also have various modes, which not only comprise a method starting from a mechanism angle such as a modeling object and a model principle, but also comprise a mode starting from a time scale and a space range from a time-space angle, wherein the time scale is limited by the prediction capability and the technical level, the division standards of each country are different, but can be divided into ultra-short term prediction, short term prediction and medium-long term prediction, at present, on the short term prediction, experts and scholars at home and abroad already carry out a great deal of algorithm research, and the method has good effects in practical application, such as neuron network, nonparametric regression, radial basis function neural network, generalized autoregressive neural network, ELMAN neural network and other methods, and can solve the problem of short-term prediction to a certain extent. However, the influence of large-scale wind power integration on the safe and stable operation of a power system is increasing day by day.
Balance points in the wind power system have to be found to ensure the development of the wind power and the safe operation of the power system at the same time, which causes a serious wind abandon phenomenon in the region and further causes huge energy waste. Therefore, the key point of the healthy development of the wind power in China is how to solve the problem of large-scale wind power consumption. The problem of large-scale wind power consumption is a worldwide problem all the time, the countries in Europe and America generally adopt a distributed power supply network access method to enhance the peak load regulation capacity of a power grid system, but the distribution condition of resources in China is concentrated and the scale is large, so local consumption is difficult, so that China generally adopts the method of sending redundant wind power to a load center and carries out concentrated consumption by matching with the advantage of resource complementation among regions, but the electric quantity transmitted by the wind power across the regions is very large, short-time electric power transaction can generate very large influence on a scheduling system of the power grid, so a long-term electric power transaction plan needs to be made, and therefore the medium-term and long-term electric power generation quantity of the regions is predicted to be an important key point for solving the problem.
Considering the time factor of the medium-long term, the state of the equipment is necessarily considered, but the current wind volume prediction method does not take the state of the equipment as an influence factor of wind power generation amount prediction, which brings a great prediction deviation to the actual power generation amount prediction. Therefore, the method for predicting the power generation capacity of the wind power in the medium-long term region based on the equipment state and the environmental factors is very valuable.
Disclosure of Invention
The method aims to solve the problems of complexity, long time consumption, complex structure and high cost of a wind power prediction calculation method in the existing method, and the actual power generation capacity is predicted according to the equipment state of a wind driven generator so as to finally obtain the medium-term and long-term actual power generation capacity in the wind power area range.
In order to achieve the purpose, the invention adopts the technical scheme that:
a method for predicting the power generation capacity of a wind power medium-long term region based on equipment state and environmental factors is characterized by comprising the following steps:
(1) establishing a power generation amount prediction model of a single wind driven generator according to historical meteorological data in a region range;
(2) establishing a normal operation state model of the single wind driven generator through equipment historical data of the single wind driven generator;
(3) the real-time equipment data of a single wind driven generator is accessed into the model to obtain the probability that a single fan can normally operate, and the probability is recorded as Y1，Y2……YN；
(4) And predicting the power generation capacity of each generator according to weather forecast data of the second year, and recording the power generation capacity as P1，P2…PN；
(5) And (3) enabling the generated energy prediction value of the single wind driven generator obtained in the step (4) and the normal operation probability of the single fan in the step (3) to be according to the following formula:
Figure BDA0002653440210000021
and calculating to obtain the final predicted power generation amount of the long-term wind power plant in the actual area.
Further, the step (1) completes data acquisition through a programmable controller, and completes a power generation amount prediction model of a single wind driven generator through a big data algorithm, and the specific steps are as follows:
the historical data which needs to be collected by the programmable controller comprises: wind direction, wind speed, temperature, humidity, barometric pressure, and altitude;
secondly, the stabilization processing of parameters such as wind direction, wind speed, temperature, humidity, atmospheric pressure, altitude and the like is completed through empirical mode decomposition, and then normalization processing is completed;
and thirdly, establishing a model for predicting the generating capacity of the single wind driven generator through a long-time memory algorithm.
Further, the step (2) is to establish a normal operation state model of a single wind driven generator through a big data algorithm, and the specific steps are as follows:
the historical data of the equipment which needs to be collected by the programmable controller comprises: current, voltage, generator non-drive end bearing temperature, generator speed, generator coil temperature, vibration, cable twisting angle (yaw angle), nacelle and yaw angle deviation, nacelle control cabinet temperature, wind direction angle, 30 second average wind speed, main bearing temperature, active power, frequency converter power, and frequency converter reactive power;
secondly, cleaning historical data of the equipment, eliminating data dead spots and abnormal data interval points, cleaning other parameters in the same time interval after cleaning the data of a certain parameter, and recording the cleaned data as D0；
Using maximum likelihood estimation method to D0And training to obtain a Gaussian normal distribution function of the single device, namely a model for normal operation of the single device.
Further, the step (3) is used for carrying out model deviation analysis with the normal operation state model established in the step (2) by accessing real-time operation parameters of a single wind driven generator, and the specific steps are as follows:
accessing real-time data with the same roll name as that in the step (2) through communication modes such as OPC, Modbus and 485 and defining a data sample X acquired at the current moment;
secondly, calculating high-dimensional normal distribution parameters mu and sigma according to the normal running state model of the single device established in the step (2) by utilizing maximum likelihood estimation, wherein mu is the mean value of the acquisition parameters of the sensor, and sigma is the covariance of the acquisition parameters of the sensor;
thirdly, the abnormal probability of the current sample X is calculated by using the parameters mu and sigma, and the current normal working probability of the single equipment is further obtained and recorded as Y1，Y2……YN。
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a method for predicting the power generation capacity of a wind power medium-long term region based on equipment states and environmental factors, aiming at predicting the power generation capacity of the wind power medium-long term region, which comprises the following steps:
1. and data are acquired from a monitoring system of the wind power plant without increasing measuring points.
2. The long-time memory neural network algorithm is optimized by adopting empirical mode decomposition, and the accuracy of the prediction algorithm is improved.
3. The clustering algorithm is adopted to predict the equipment state, and the probability of normal operation of the equipment based on the current equipment parameters is obtained.
4. And correcting the original wind power prediction generating capacity through the normal operation probability of the equipment to obtain the actual regional wind power generating capacity.
5. And the forecasting is carried out through all meteorological elements in the area range, so that the forecasting accuracy is improved.
6. The adopted clustering algorithm can obtain the overall operation state of the equipment, and does not evaluate a certain parameter.
7. Parameters needing to be extracted in equipment modeling are pointed clearly through expert experience, and the accuracy of prediction can be improved.
Drawings
FIG. 1 is a flow chart of steps of a method for predicting power generation in a medium-and-long-term wind power region based on equipment states and environmental factors;
FIG. 2 is environmental factor training data of a wind power medium and long term region power generation capacity prediction method based on equipment states and environmental factors.
FIG. 3 is equipment state parameter training data of a wind power medium and long term region power generation capacity prediction method based on equipment states and environmental factors.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The method comprises the following steps of predicting equipment state and predicting the power generation capacity of the wind power medium and long term region of environmental factors:
the research data adopts 7 meteorological stations in a certain region and meteorological elements of a wind farm in the region, wherein the meteorological elements comprise: wind speed, air temperature, atmospheric pressure and humidity; and (4) performing load prediction on wind power generation amount by totaling the 32-dimensional regional gas image characteristic data.
The number of wind driven generators in the wind farm in the region is 30 in total.
The prediction of the power generation amount is completed by the following steps:
(1) power generation amount prediction model of single wind driven generator established through historical meteorological data in inner covering certain area
The historical data which needs to be collected by the programmable controller comprises: wind direction, wind speed, temperature, humidity, barometric pressure, altitude, etc
Secondly, the stabilization processing of parameters such as wind direction, wind speed, temperature, humidity, atmospheric pressure, altitude and the like is completed through empirical mode decomposition, and then the normalization processing is completed.
Thirdly, establishing a model for predicting the generating capacity of a single wind driven generator through a long-time memory algorithm to obtain a model M1,M2,…,MN。
(2) And establishing a normal operation state model of the single wind driven generator through the equipment historical data of the single wind driven generator.
The programmable controller respectively collects 30 pieces of historical data of the fan equipment, and the method comprises the following steps: current, voltage, generator non-drive end bearing temperature, generator speed, generator coil temperature, vibration, cable twisting angle (yaw angle), nacelle and yaw angle deviation, nacelle control cabinet temperature, wind direction angle, 30 second average wind speed, main bearing temperature, active power, converter reactive power, and the like.
Secondly, cleaning historical data of the equipment, eliminating data dead spots and abnormal data interval points, cleaning other parameters in the same time interval after cleaning the data of a certain parameter, and recording the cleaned data as D1，D2……DN。
Using maximum likelihood estimation method to D1，D2……DNTraining to obtain the Gaussian normal distribution function of the single equipment, namely the model T for normal operation of the single equipment1,T2…TN。
(3) The real-time equipment data of a single wind driven generator is accessed into a model to obtain the correction of the single fanProbability of constant operation, denoted as Y1＝95％，Y2＝98％……Y30＝96％。
(4) Predicting the power generation capacity of each generator through the weather forecast data of the second year to obtain a prediction result P1＝3000MWH，P2＝3320MWH…P30＝3150MWH。
(5) The generating capacity prediction value of the single wind driven generator obtained in the step (4) and the normal operation probability of the single fan in the step (3) are carried out according to
Figure BDA0002653440210000061
And calculating to obtain the final predicted power generation amount of the long-term wind power plant in the actual region as P (0.95 × 3000+0.98 × 3320+ … +0.96 × 3150) (-94717.9 MWH).
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims (4)

1. A method for predicting the power generation capacity of a wind power medium-long term region based on equipment state and environmental factors is characterized by comprising the following steps:
(1) establishing a power generation amount prediction model of a single wind driven generator according to historical meteorological data in a region range;
(2) establishing a normal operation state model of the single wind driven generator through equipment historical data of the single wind driven generator;
(3) the real-time equipment data of a single wind driven generator is accessed into the model to obtain the probability that a single fan can normally operate, and the probability is recorded as Y1，Y2……YN；
(4) Passing weather forecast of the second yearPredicting the power generation amount of each generator by using the report data, and recording as P1，P2…PN；
(5) And (3) enabling the generated energy prediction value of the single wind driven generator obtained in the step (4) and the normal operation probability of the single fan in the step (3) to be according to the following formula:
Figure FDA0002653440200000011
and calculating to obtain the final predicted power generation amount of the long-term wind power plant in the actual area.
2. The method for predicting the power generation amount of the wind power medium and long term area based on the equipment state and the environmental factors according to claim 1, wherein in the step (1), the data acquisition is completed through a programmable controller, and the power generation amount prediction model of a single wind power generator is completed through a big data algorithm, and the method comprises the following specific steps:
the historical data which needs to be collected by the programmable controller comprises: wind direction, wind speed, temperature, humidity, barometric pressure, and altitude;
secondly, the stabilization processing of parameters such as wind direction, wind speed, temperature, humidity, atmospheric pressure, altitude and the like is completed through empirical mode decomposition, and then normalization processing is completed;
and thirdly, establishing a model for predicting the generating capacity of the single wind driven generator through a long-time memory algorithm.
3. The method for predicting the power generation amount of the wind power medium and long term region based on the equipment state and the environmental factors according to claim 1, wherein in the step (2), a normal operation state model of a single wind driven generator is established through a big data algorithm, and the specific steps are as follows:
the historical data of the equipment which needs to be collected by the programmable controller comprises: current, voltage, generator non-drive end bearing temperature, generator speed, generator coil temperature, vibration, cable twisting angle (yaw angle), nacelle and yaw angle deviation, nacelle control cabinet temperature, wind direction angle, 30 second average wind speed, main bearing temperature, active power, frequency converter power, and frequency converter reactive power;
secondly, cleaning historical data of the equipment, eliminating data dead spots and abnormal data interval points, cleaning other parameters in the same time interval after cleaning the data of a certain parameter, and recording the cleaned data as D0；
Using maximum likelihood estimation method to D0And training to obtain a Gaussian normal distribution function of the single device, namely a model for normal operation of the single device.
4. The method for predicting the power generation amount of the wind power medium and long term region based on the equipment state and the environmental factors according to claim 1, wherein the step (3) is used for performing model deviation analysis on the model in the normal operation state established in the step (2) by accessing real-time operation parameters of a single wind power generator, and the specific steps are as follows:
accessing real-time data with the same roll name as that in the step (2) through communication modes such as OPC, Modbus and 485 and defining a data sample X acquired at the current moment;
secondly, calculating high-dimensional normal distribution parameters mu and sigma according to the normal running state model of the single device established in the step (2) by utilizing maximum likelihood estimation, wherein mu is the mean value of the acquisition parameters of the sensor, and sigma is the covariance of the acquisition parameters of the sensor;
thirdly, the abnormal probability of the current sample X is calculated by using the parameters mu and sigma, and the current normal working probability of the single equipment is further obtained and recorded as Y1，Y2……YN。
CN202010878751.9A 2020-08-27 2020-08-27 Method for predicting power generation capacity of wind power medium and long term region based on equipment state and environmental factors Pending CN112215392A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010878751.9A CN112215392A (en) 2020-08-27 2020-08-27 Method for predicting power generation capacity of wind power medium and long term region based on equipment state and environmental factors

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010878751.9A CN112215392A (en) 2020-08-27 2020-08-27 Method for predicting power generation capacity of wind power medium and long term region based on equipment state and environmental factors

Publications (1)

Publication Number Publication Date
CN112215392A true CN112215392A (en) 2021-01-12

Family

ID=74058846

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010878751.9A Pending CN112215392A (en) 2020-08-27 2020-08-27 Method for predicting power generation capacity of wind power medium and long term region based on equipment state and environmental factors

Country Status (1)

Country Link
CN (1) CN112215392A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114169650A (en) * 2022-01-27 2022-03-11 中国华能集团有限公司江西分公司 Thermal power generation medium-long term modeling prediction method based on deep self-learning
CN115330092A (en) * 2022-10-13 2022-11-11 山东东盛澜渔业有限公司 Artificial intelligence-based energy supply control method for renewable energy sources of marine ranching

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114169650A (en) * 2022-01-27 2022-03-11 中国华能集团有限公司江西分公司 Thermal power generation medium-long term modeling prediction method based on deep self-learning
CN115330092A (en) * 2022-10-13 2022-11-11 山东东盛澜渔业有限公司 Artificial intelligence-based energy supply control method for renewable energy sources of marine ranching

Similar Documents

Publication Publication Date Title
CN102663513B (en) Utilize the wind power combined prediction modeling method of grey relational grade analysis
CN102184453A (en) Wind power combination predicting method based on fuzzy neural network and support vector machine
CN201813161U (en) Wind power forecasting system
Mao et al. A review of wind power forecasting & prediction
CN104899665A (en) Wind power short-term prediction method
Cai et al. Wind speed forecasting based on extreme gradient boosting
CN115796393B (en) Energy management optimization method, system and storage medium based on multi-energy interaction
CN112215392A (en) Method for predicting power generation capacity of wind power medium and long term region based on equipment state and environmental factors
Mahmoud et al. Advanced method for short‐term wind power prediction with multiple observation points using extreme learning machines
CN112072643A (en) Light-storage system online scheduling method based on depth certainty gradient strategy
Xiaolan et al. One-month ahead prediction of wind speed and output power based on EMD and LSSVM
Yang et al. Short‐term photovoltaic power dynamic weighted combination forecasting based on least squares method
CN105844350A (en) Short period wind power prediction system based on covariance preferable combination model
Zhang et al. Short-term wind power prediction based on EMD-LSTM combined model
CN105207255B (en) A kind of power system peak regulation computational methods suitable for wind power output
Zhen et al. Multi-level wavelet decomposition based day-ahead solar irradiance forecasting
CN116167508A (en) Short-term photovoltaic output rapid prediction method and system based on meteorological factor decomposition
CN111898812B (en) Distributed photovoltaic data virtual acquisition method
CN114239920A (en) Short-term wind power prediction method
Zhou et al. Ultra-short term hybrid power forecasting model for photovoltaic power station with meteorological monitoring data
Xu Coastal Wind Power Forecasting Research Scheme Design
Li et al. Improvement of Renewable Power Forecasting Indicators Based on System Flexibility
Liu et al. Statistical Analysis on the Power Energy Adequacy of the PV Generation in South China
Xu et al. A novel power forecasting method for distributed PV system based on finite data
Ma et al. Short-term Power Prediction Based on Improved NWP Data Considering Wind Speed Distribution Inner Wind Farm

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