CN115965134A - Regional power grid wind power generation power prediction optimization method - Google Patents
Regional power grid wind power generation power prediction optimization method Download PDFInfo
- Publication number
- CN115965134A CN115965134A CN202211623885.1A CN202211623885A CN115965134A CN 115965134 A CN115965134 A CN 115965134A CN 202211623885 A CN202211623885 A CN 202211623885A CN 115965134 A CN115965134 A CN 115965134A
- Authority
- CN
- China
- Prior art keywords
- power
- data
- wind
- pairs
- data sub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000010248 power generation Methods 0.000 title claims abstract description 32
- 238000005457 optimization Methods 0.000 title claims description 7
- 210000002569 neuron Anatomy 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 238000009826 distribution Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 12
- 239000006185 dispersion Substances 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 claims 1
- 238000012937 correction Methods 0.000 abstract description 7
- 238000013528 artificial neural network Methods 0.000 description 13
- 238000011161 development Methods 0.000 description 13
- 230000018109 developmental process Effects 0.000 description 13
- 230000015654 memory Effects 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 230000002068 genetic effect Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 241000282414 Homo sapiens Species 0.000 description 3
- 210000000349 chromosome Anatomy 0.000 description 3
- 239000003245 coal Substances 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000003345 natural gas Substances 0.000 description 2
- 238000000053 physical method Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 239000002028 Biomass Substances 0.000 description 1
- 241000579895 Chlorostilbon Species 0.000 description 1
- 238000003916 acid precipitation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000010976 emerald Substances 0.000 description 1
- 229910052876 emerald Inorganic materials 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000010977 jade Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- ZLIBICFPKPWGIZ-UHFFFAOYSA-N pyrimethanil Chemical compound CC1=CC(C)=NC(NC=2C=CC=CC=2)=N1 ZLIBICFPKPWGIZ-UHFFFAOYSA-N 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Wind Motors (AREA)
Abstract
The application relates to the technical field of wind power generation, in particular to a method for predicting and optimizing wind power generation power of a regional power grid; the method comprises the steps of carrying out error correction on a plurality of historical power data and a plurality of historical wind speed data, constructing a wind speed-power model based on the data subjected to error correction, predicting power based on the wind speed-power model and a power prediction model, and modifying loss of the predicted power by constructing a power loss parameter to obtain the corrected real power, so that the accuracy of the whole power prediction is improved.
Description
Technical Field
The application relates to the technical field of wind power generation, in particular to a method for predicting and optimizing wind power generation power of a regional power grid.
Background
Energy is an important material basis for social development, and different energy strategies are established in all countries in the world nowadays. Energy has become one of the core competitions among the world's major countries. Energy safety is an indispensable part of national safety. The energy structure of China mainly uses fossil fuel, such as coal, petroleum, natural gas, nuclear energy and other various energy sources. The reserves of these energy sources, especially the most coal and oil consumed, are very limited. According to the authoritative data, oil can be developed for 52.9 years, coal for 109 years, and natural gas for 55.7 years in the world. It is anticipated that in the near future, mankind will certainly face the energy crisis. The annual increase of the consumption of fossil energy brings very serious damage to the ecological environment, and acid rain, haze and severe change of global climate are all related to the large-scale development and consumption of fossil energy by human beings. The environment is the root for human survival, and economic development cannot be achieved at the expense of the environment.
With the development of science and technology, the global energy consumption increases year by year, and the energy consumption of people is continuously increased in both developing countries and developed countries. The traditional energy industry cannot meet the economic development, and the development of the new energy industry is imperative. With the increase of energy consumption, the practical pressure of human developing renewable energy sources is increasing, and renewable energy sources such as solar energy, hydroenergy and biomass energy are rapidly developed.
Wind power is considered one of the most promising renewable energy sources. From 2005, the global wind power growth is rapid, the newly added installed capacity reaches 63,013MW in 2015, the accumulated installed capacity reaches 432,419MW, and the annual growth rate of 22% is realized. Wind energy is divided into onshore wind energy and offshore wind energy, the wind energy theory of China has very large exploitability, and 6 to 10 hundred million KW onshore and 20 hundred million KW offshore. Under the complex international energy bureau and severe ecological environmental pressure, the large-scale development and utilization of wind energy is a very scientific choice. Nowadays, the total wind power installation amount in China is in the first place in the world.
The wind itself is uncertain and uncontrollable. Although site selection and plant construction of wind power enterprises are in areas where wind energy can be gathered, the wind power is constantly changing along with time. The continuous variation of the wind speed with time causes the output power of the wind power generator to also vary with time. The early wind power output power of the development of the wind power industry accounts for a very small proportion, the disturbance to a power grid is also very small, and a power system can completely automatically adjust to offset the influence of wind power fluctuation by performing feedback adjustment on parameters such as primary adjustment, secondary adjustment, voltage, frequency and the like in a scientific range. With the continuous development of the wind power industry, the total amount of wind power on the internet is continuously increased, and more serious threats are caused to the safety of a power grid. Electric energy is regarded as the energy that can long-range transmission and self convenience, and the flexibility is paid attention to in the energy market. However, during the long-distance transmission of electric power, the supply and demand must be balanced, which is an important issue for the research of electric power systems. But as the scale of wind power increases, this problem becomes more difficult to solve. The fluctuation of wind power itself has become a great obstacle for restricting the development of the wind power industry. Wind power enterprises must provide relatively reliable energy to the grid, and therefore, the wind power must be predicted.
Disclosure of Invention
In order to solve the technical problems, the application provides a method for predicting and optimizing the wind power generation power of the regional power grid, and the prediction of the result of the real-time power generation power in the regional power grid is realized through a plurality of models.
In order to achieve the above purpose, the embodiments of the present application adopt the following technical solutions:
the method comprises the steps that on the first aspect, a regional power grid is provided, wherein the regional power grid comprises a plurality of wind power generation sub-lines and a convergence bus, and the plurality of wind power generation sub-lines are connected with wind power generators; the method comprises the following steps: acquiring input power of a plurality of generator line input ends, namely output power corresponding to the wind driven generator, and input power of a generator line output end, namely the input power of the convergence bus input end at the same time, acquiring output power and input power of a plurality of time periods, and acquiring power loss parameters; predicting the real-time output power of the plurality of wind motors one by one based on a power prediction model to obtain first predicted power; obtaining a target predicted power based on the power loss parameter and the first predicted power; and obtaining the regional power grid wind power generation power based on a plurality of target predicted powers.
In a first implementation manner of the first aspect, the method further includes performing data preprocessing before obtaining the power loss parameter, where the data preprocessing includes: obtaining wind speed data corresponding to the power data of the plurality of wind power motors, and arranging the wind speed data from small to large to obtain a first data pair; segmenting the first data pair based on a first rule to obtain a plurality of first data sub-pairs; removing the transverse dispersion abnormal data in the first data sub-pairs according to a second rule to obtain a plurality of second data sub-pairs; arranging the plurality of second data sub-pairs from small to large according to power to obtain third data pairs, and dividing the third data according to a third rule to obtain a plurality of third data sub-pairs; and eliminating the longitudinal dispersion abnormal data in the third data sub-pairs according to a fourth rule for the third data sub-pairs to obtain a plurality of fourth data sub-pairs.
With reference to the first implementable manner of the first aspect, in a second implementable manner of the first aspect, the fitting of a plurality of pairs of the fourth data to obtain a wind speed-power model is further included.
With reference to the first implementable manner of the first aspect, in a third implementable manner of the first aspect, the first rule is to divide a power distribution range in the first data pair based on a reference number of power division to obtain a plurality of first data sub-pairs corresponding to a plurality of power distribution ranges.
With reference to the first implementable manner of the first aspect, in a fourth implementable manner of the first aspect, the second rule is: and arranging the plurality of first data sub-pairs according to the wind speed to obtain a distribution sequence, obtaining a first quartile, a second quartile and a third quartile of the distribution sequence, determining an inner limit interval, removing the dispersion abnormal data in each first data sub-pair, and repeating the operation according to the number of the first data sub-pairs.
With reference to the first implementable manner of the first aspect, in a fifth implementable manner of the first aspect, the third rule is: and dividing the plurality of second data sub-pairs into a plurality of parts at equal intervals according to the fixed wind speed and the preset wind speed interval to obtain a plurality of third data sub-pairs.
With reference to the first implementable manner of the first aspect, in a sixth implementable manner of the first aspect, the plurality of third data sub-pairs are sorted according to power to obtain corresponding sequences, a first quartile, a second quartile and a third quartile in the sequences are obtained, an inner limit interval is determined, dispersivity abnormal data in each third data sub-pair are removed, and repeated operation is performed according to the number of the third data sub-pairs.
In a seventh implementation manner of the first aspect, the power prediction model includes an input layer, a hidden layer, and an output layer, the number of neuron nodes of the input layer is 23, the number of neuron nodes of the output layer is 1, the number of neuron nodes of the hidden layer is 10, and activation functions of the hidden layer and the output layer are a tansig function and a purelin function, respectively.
With reference to the seventh implementable manner of the first aspect, in an eighth implementable manner of the first aspect, the method for constructing the power prediction model includes: acquiring historical actual data and meteorological forecast data of the wind motor; the historical actual data comprises actual operation data of the whole-field fan; the weather forecast data comprises wind speed, temperature, humidity, wind direction cosine value and air pressure data; and training the weather forecast data as the input of the power prediction model, and finishing training convergence when the training result meets the preset learning rate and the preset error to obtain the power prediction model.
With reference to the eighth implementable manner of the first aspect, in a ninth implementable manner of the first aspect, the learning rate is 0.05, and the preset error is 0.001.
In a second aspect, there is provided a terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the method of any one of the preceding claims when executing the computer program.
In a third aspect, there is provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements the method of any of the preceding claims.
According to the technical scheme, error correction is carried out on a plurality of historical power data and a plurality of historical wind speed data, a wind speed-power model is built based on the data after error correction, power is predicted based on the wind speed-power model through a power prediction model, and the predicted power is subjected to loss correction through building a power loss parameter, so that the corrected real power is obtained, and the accuracy of overall power prediction is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
The methods, systems, and/or programs of the figures will be further described in accordance with the exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments in which example numbers represent similar mechanisms throughout the various views of the drawings.
Fig. 1 is a schematic structural diagram of a terminal device provided in an embodiment of the present application.
FIG. 2 is a flow chart of a method of wind power generation power prediction optimization as illustrated in some embodiments of the present application.
Detailed Description
In order to better understand the technical solutions of the present application, the following detailed descriptions are provided with accompanying drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and in a case of no conflict, the technical features in the embodiments and examples of the present application may be combined with each other.
In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant guidance. It will be apparent, however, to one skilled in the art that the present application may be practiced without these specific details. In other instances, well-known methods, procedures, systems, compositions, and/or circuits have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the present application.
The present application uses flowcharts to illustrate the implementations performed by a system according to embodiments of the present application. It should be expressly understood that the execution of the flow diagrams may be performed out of order. Rather, these implementations may be performed in the reverse order or simultaneously. In addition, at least one other implementation may be added to the flowchart. One or more implementations may be deleted from the flowchart.
Before further detailed description of the embodiments of the present invention, terms and expressions mentioned in the embodiments of the present invention are explained, and the terms and expressions mentioned in the embodiments of the present invention are applied to the following explanations.
(1) In response to the condition or state indicating that the executed operation depends on, one or more of the executed operations may be in real-time or may have a set delay when the dependent condition or state is satisfied; there is no restriction on the order of execution of the operations performed unless otherwise specified.
(2) Based on the condition or state on which the operation to be performed depends, the operation or operations to be performed may be in real time or may have a set delay when the condition or state on which the operation depends is satisfied; there is no restriction on the order of execution of the operations performed unless otherwise specified.
(3) The convolutional neural network is a feedforward neural network which comprises convolution calculation and has a deep structure. Convolutional neural networks are proposed by the mechanism of the biological Receptive Field (receptor Field). Convolutional neural networks are specialized neural networks for processing data having a grid-like structure. For example, time series data (which may be regarded as a one-dimensional grid formed by regularly sampling on a time axis) and image data (which may be regarded as a two-dimensional pixel grid), the convolutional neural network employed in the present embodiment processes for the image data.
(4) The Quartile method (Quartile) is that a certain data sequence is arranged according to the size sequence and divided into 4 equal parts, data points contained in each part account for 25% of total data, data at the demarcation points of four groups of data are called quartiles and are respectively marked as a first Quartile, a second Quartile and a third Quartile.
According to the technical scheme provided by the embodiment of the application, the main application scene is the acquisition of the prediction result of the overall generated power in the regional power grid of the wind power plant. In order to develop and utilize wind energy in a large scale, wind power must be accurately predicted. Wind power prediction can enable wind power enterprises and power dispatching departments to jointly dispatch, so that more wind power can be on line and the safe operation of a power grid is guaranteed. Nowadays, wind power prediction technology becomes one of the key technologies for the development of the wind power industry. Since 2000 years, the wind power industry in China is vigorously developed, the wind power internet surfing scale is continuously enlarged, and the influence of the volatility, randomness and intermittence of the wind power internet surfing scale is larger and larger.
In the prior art, a load prediction technology is used for reference in the early development stage of the wind power prediction technology, and the load prediction technology is a mature prediction technology at present. The wind power prediction technology in the period is developed rapidly, but the prediction technology in the period is based on a single model. Generally, wind power prediction is performed by using only one prediction model, and prediction results of multiple models are not combined. The adopted prediction method comprises various different models such as a self-regression method, a linear extrapolation method, kalman filtering and the like. The models can predict the wind power to a certain extent, but the prediction accuracy is poor, the prediction duration is short, and the prediction value is low.
The wind speed can be predicted by using a numerical weather method, the Landberg reasoning method is used for predicting the meteorological information such as the wind speed and the wind direction in the 90 s of the 20 th century, the wind speed result is corrected by using some algorithms, and finally the output power is obtained according to a wind speed-power curve. Since the 20 th century, with the widespread popularization of computer technology and the continuous development of artificial intelligence theory, wind power prediction slowly begins to be completed by means of intelligent calculation. Such as time series method, neural network prediction method, wavelet analysis prediction method, genetic algorithm prediction and other prediction algorithm models. In the prior art, the wind speed data can be predicted by using a time series method, and the obtained result wind speed is used as an input variable of a neural network, so that the prediction precision is finally improved. By establishing an error and prediction model based on the neural network, the simultaneous prediction processing of the error and the wind power is realized. Based on a quantile regression analysis theory, the wind power fluctuation interval is analyzed, a quantile regression prediction model is established, and prediction of the wind power fluctuation interval is achieved. The nonparametric confidence interval estimation method based on the statistical analysis of the prediction error distribution characteristics improves the prediction accuracy. The method of combining wavelet transformation and artificial neural network can be adopted to predict the generated energy of the fan, and the time delay problem in wind power prediction is solved. But the prediction accuracy is not sufficient. In other prior arts, the LSTM model obtains the best prediction effect in each time period by comparing the prediction performances of a Long Short-Term Memory (LSTM) model, an Artificial Neural Network (ANN) model and a Support Vector Machine (SVM) model. The difference of the wind power change rules of different wind power plants is not considered. The algorithms perform different feature extraction on data by using different structural designs, the principle difference is large, but the prediction effect cannot completely meet the actual requirements of wind power enterprises. In recent years, more researchers have combined two or more prediction methods, and such prediction methods are called combined prediction methods. The combined prediction further improves the wind power prediction quality. It is also possible to combine a prediction method based on statistical prediction and a prediction method based on a physical method. A representative method of wind power prediction based on a physical method is a prediction method based on numerical weather, and the basic idea is to directly model by using local terrain and landform, solve a high-dimensional equation set by using fluid mechanics by means of meteorological prediction information and directly obtain wind speed prediction. And finally, obtaining power prediction data by using a wind speed-power curve. The prediction quality of the model is closely related to meteorological parameter prediction, and accurate meteorological prediction information is very difficult to obtain, so that the method is suitable for large-scale wind power bases and relatively high in research and development cost; the prediction quality is generally better than the prediction based on statistical methods, especially for long-term wind power. The prediction method based on statistical learning generally has the advantage that the prediction effect is rapidly reduced when the wind power is predicted for a long time. This is mainly because the model has insufficient extraction capability for the data features.
Therefore, based on the above technical background, the present embodiment employs a combined prediction model and a model in which the relevant factors influence each other to achieve the obtaining of the prediction result of the power generation amount of the power generation field.
In the embodiment, the terminal device 100 includes a memory 110, a processor 120, and a computer program stored in the memory and executable on the processor, wherein the processor executes a prediction result of a final wind power generation power based on the acquired plurality of real-time data. In this embodiment, the terminal device communicates with the user side, issues the acquired detection information to the corresponding user side, and implements sending of the detection information on hardware. The method for sending the information is realized based on a network, and before the terminal device applies, an association relation needs to be established between the user terminal and the terminal device, and the association between the terminal device and the user terminal can be realized through a registration method. The terminal device can be aimed at a plurality of user terminals or one user terminal, and the user terminal communicates with the terminal device through passwords and other encryption modes.
In this embodiment, the terminal may be a server, and includes a memory, a processor, and a communication unit with respect to a physical structure of the server. The memory, processor and communication unit components are electrically connected to each other, directly or indirectly, to enable data transfer or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory is used for storing specific information and programs, and the communication unit is used for sending the processed information to the corresponding user side.
In the embodiment, the storage module is divided into two storage areas, wherein one storage area is a program storage unit, and the other storage area is a data storage unit. The program storage unit is equivalent to a firmware area, the read-write authority of the area is set to be a read-only mode, and data stored in the area cannot be erased and changed. The data in the data storage unit can be erased or read and written, and when the capacity of the data storage area is full, the newly written data can overwrite the earliest historical data.
The Memory may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Read Only Memory (EPROM), an electrically Erasable Read Only Memory (EEPROM), and the like.
The processor may be an integrated circuit chip having signal processing capabilities. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP)), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Referring to fig. 2, in the embodiment, for the wind farm power generation amount prediction method based on machine learning, the working logic is to obtain the predicted power generation amounts of a plurality of power generation motors in the wind farm and the predicted wind speeds in the farm, obtain the independent predicted wind speeds of the corresponding power generation motors based on the combined model of the plurality of power generation motors and obtain the overall predicted power generation amount of the final farm based on the above data. The method specifically comprises the following steps:
and S210, constructing a wind speed-power model.
In this embodiment, the wind speed-power model is constructed by obtaining the historical wind speed data and the historical power data, but noise data in the historical wind speed data and the historical power data needs to be removed due to the addition of the noise data, so that the removed historical data is obtained, and the wind speed-power model is constructed based on the historical data.
The method specifically comprises the following steps:
the method comprises the steps of obtaining whether a plurality of wind power motor power data correspond to wind speed data or not, arranging the wind speed data from small to large to obtain a first data pair, and dividing the first data pair based on a first rule to obtain a plurality of first data sub-pairs. In this embodiment, the first rule is to segment the power distribution range in the first data pair based on a power segmentation reference number to obtain a plurality of first data sub-pairs corresponding to a plurality of power distribution ranges. In the embodiment, the first rule is specifically that the power interval [0, 1600] kW is divided into 160 parts at equal intervals by taking 10kW as a size.
And removing the transverse dispersion abnormal data in the first data sub-pairs according to a second rule to obtain a plurality of second data sub-pairs. In this embodiment, the second rule is: and arranging the plurality of first data sub-pairs according to the wind speed to obtain a distribution sequence, obtaining a first quartile, a second quartile and a third quartile of the distribution sequence, determining an inner limit interval, removing the dispersion abnormal data in each first data sub-pair, and repeating the operation according to the number of the first data sub-pairs.
The calculation process for the first quartile, the second quartile, the third quartile and the inner limit interval is as follows:
for an ascending data sequence, i.e. a first data sub-pair X = { X = { (X) } 1 ,x 2 ,…,x n }, satisfy x i ≤x i+1 And x belongs to (1, n-1), wherein n is the total number of the data sequences.
Calculating a corresponding second quartile:
then, the first quartile Q is calculated 1 And a third quartile Q 3 . When n =2k, Q 2 Dividing the original data sequence into two subsequences, the first quartile Q 1 And a third quartile Q 3 Is the same as the Q2 calculation, when n =4k +1 (k =0,1,2, \ 8230;),
when n =4k +3 (k =0,1,2, \ 8230),
by the above calculations, ql and Q3 can be obtained, then the four-bit spacing is:
I QR ＝Q 3 -Q 1 。
in this embodiment, the inner limit range of the abnormal value determined by the four-quarter distance is:
[F 1 ,F 2 ]＝[Q 1 -1.5I QR ,Q 3 +1.5I QR ]。
wherein Fl is the lower limit value of the sequence x; r is the upper limit value of the sequence X; all data in sequence x that are outside the inner limit are considered outliers.
And arranging the plurality of second data sub-pairs from small power to large power to obtain a third data pair, and dividing the third data according to a third rule to obtain a plurality of third data sub-pairs. In this embodiment, the third rule is: and dividing the plurality of second data sub-pairs into a plurality of parts at equal intervals according to the fixed wind speed and the preset wind speed interval to obtain a plurality of third data sub-pairs, wherein 80 parts are divided at equal intervals according to the wind speed of 0.2m/s and the wind speed interval of [0, 16] m/s.
And removing the longitudinal dispersion abnormal data in the third data sub-pairs according to a fourth rule for the third data sub-pairs to obtain a plurality of fourth data sub-pairs. In this embodiment, a fourth rule is to sort a plurality of third data sub-pairs according to power to obtain a corresponding sequence, obtain a first quartile, a second quartile and a third quartile in the sequence, determine an inner limit interval, remove dispersivity abnormal data in each third data sub-pair, and perform a repeat operation according to the number of the third data sub-pairs. The acquisition of the first quartile, the second quartile, the third quartile and the inner limit interval is realized based on the processing procedure, and the description is not repeated in the process.
And S220, acquiring a power loss parameter based on historical data.
In this embodiment, the regional power grid includes a main grid and a sub-grid, where the sub-grid is set corresponding to a plurality of wind turbines, specifically, the regional power grid includes a plurality of wind turbine sub-lines and a convergence bus, and in a wind turbine process, a transmission line is set, so that transmission power loss is caused. In this process, the acquisition of the power loss parameter is obtained based on historical data, specifically:
and acquiring input power of a plurality of generator line input ends, namely output power corresponding to the wind driven generator at the same time, and input power of a generator line output end, namely the input power of the convergence bus input end, acquiring output power and input power of a plurality of time periods, and acquiring power loss parameters.
And S230, predicting the real-time output power of the wind power motors one by one based on a power prediction model to obtain first predicted power.
In this embodiment, the power prediction model includes an input layer, a hidden layer, and an output layer, the number of neuron nodes of the input layer is 23, the number of neuron nodes of the output layer is 1, the number of neuron nodes of the hidden layer is 10, and the activation functions of the hidden layer and the output layer are respectively a tansig function and a purelin function.
In this embodiment, the basic structure of the power prediction model is a BP neural network, and the BP neural network is optimized based on a genetic algorithm, so as to implement training of the BP neural network through optimization of the genetic algorithm.
The workflow specific to the genetic algorithm specifically comprises the following parts:
(1) The weight, the threshold, the coding length of the chromosome, the number of neurons in the hidden layer, the number of layers of the BP neural network, and the number of neurons in each layer need to be set according to the type and the number of input data. In this embodiment, the input data types include wind speed, temperature, humidity, wind direction cosine value, and air pressure data, and the number of the weight and the threshold value and the encoding length of the chromosome are calculated by the following formula:
N w ＝n input ·n hide +n hide ·n output ；
N b ＝n hide +n output ；
l＝N w +N b 。
wherein, N w As the number of weights, N b Is the number of thresholds, n input Number of neurons of the input layer, n hide To imply the number of layer neurons, n output For the number of output layer neurons, l is the coding length of the genetic algorithm chromosome.
In this embodiment, the power prediction model includes an input layer, a hidden layer, and an output layer, the number of neuron nodes of the input layer is 23, the number of neuron nodes of the output layer is 1, the number of neuron nodes of the hidden layer is 10, and the activation functions of the hidden layer and the output layer are respectively a tan sig function and a purelin function.
In addition, the method for constructing the power prediction model provided in the embodiment includes:
acquiring historical actual data and weather forecast data of a regional power grid; the historical actual data comprises actual operation data of the whole-field fan; the weather forecast data comprises wind speed, temperature, humidity, wind direction cosine value and air pressure data;
and training the weather forecast data as the input of the power prediction model, and finishing training convergence when the training result meets the preset learning rate and the preset error to obtain the power prediction model. Wherein, the weight number of the neural network is 23 +10 +1= 240, the threshold number is 10+1=11, the individual coding length of the genetic algorithm is 240+11=251, the initial population size is 50, the arithmetic cross probability is 0.6, the non-uniform variation probability is 0.1, and the maximum evolution passage number is 50.
And S240, obtaining target predicted power based on the power loss parameter and the first predicted power.
In the present embodiment, for the prediction of the generated power involved in obtaining the independent wind turbine in step S230, the target predicted power after loss calculation is obtained based on the predicted generated power in combination with the power loss parameter in step S220.
And S250, obtaining the wind power generation power of the regional power grid based on the target prediction powers.
The generated power acquired in step S240 is the corresponding individual generated power, and the generated power for the regional power grid is based on the set of target predicted powers acquired by the plurality of generator motors.
According to the technical scheme provided by the embodiment of the application, error correction is carried out on a plurality of historical power data and a plurality of historical wind speed data, a wind speed-power model is built based on the error-corrected data, power is predicted based on the wind speed-power model and through a power prediction model, and the predicted power is subjected to loss correction through building a power loss parameter, so that the corrected real power is obtained, and the accuracy of the whole power prediction is improved.
It should be understood that the technical terms which are not noun-nounced in the above-mentioned contents are not limited to the meanings which can be clearly determined by those skilled in the art from the above-mentioned disclosures.
The skilled person can determine some preset, reference, predetermined, set and preference labels of technical features/technical terms, such as threshold, threshold interval, threshold range, etc., without any doubt according to the above disclosure. For some technical characteristic terms which are not explained, the technical solution can be clearly and completely implemented by those skilled in the art by reasonably and unambiguously deriving the technical solution based on the logical relations in the previous and following paragraphs. The prefixes of unexplained technical feature terms, such as "first," "second," "example," "target," and the like, may be unambiguously derived and determined from the context. Suffixes of technical-feature terms not explained, such as "set", "list", etc., can also be derived and determined unambiguously from the preceding and following text.
The above disclosure of the embodiments of the present application will be apparent to those skilled in the art from the above disclosure. It should be understood that the process of deriving and analyzing technical terms, which are not explained, by those skilled in the art based on the above disclosure is based on the contents described in the present application, and thus the above contents are not an inventive judgment of the overall scheme.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, adaptations, and alternatives may occur to one skilled in the art, though not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.
Also, this application uses specific terminology to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various portions of this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of at least one embodiment of the present application may be combined as appropriate.
In addition, those skilled in the art will recognize that the various aspects of the application may be illustrated and described in terms of several patentable species or contexts, including any new and useful combination of procedures, machines, articles, or materials, or any new and useful modifications thereof. Accordingly, aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as a "unit", "component", or "system". Furthermore, aspects of the present application may be embodied as a computer product, located in at least one computer readable medium, which includes computer readable program code.
A computer readable signal medium may comprise a propagated data signal with computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, and the like, or any suitable combination. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code on a computer readable signal medium may be propagated over any suitable medium, including radio, electrical cable, fiber optic cable, RF, or the like, or any combination of the preceding.
Computer program code required for the execution of aspects of the present application may be written in any combination of one or more programming languages, including object oriented programming, such as Java, scala, smalltalk, eiffel, JADE, emerald, C + +, C #, VB.NET, python, and the like, or similar conventional programming languages, such as the "C" programming language, visual Basic, fortran 2003, perl, COBOL 2002, PHP, ABAP, dynamic programming languages, such as Python, ruby, and Groovy, or other programming languages. The programming code may execute entirely on the user's computer, as a stand-alone software package, partly on the user's computer, partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any form of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service using, for example, software as a service (SaaS).
Additionally, the order of the process elements and sequences described herein, the use of numerical letters, or other designations are not intended to limit the order of the processes and methods unless otherwise indicated in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it should be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware means, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
It should also be appreciated that in the foregoing description of embodiments of the present application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of at least one embodiment of the invention. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Claims (10)
1. The method for predicting and optimizing the wind power generation power of the regional power grid is characterized in that the regional power grid comprises a plurality of wind power generation sub-lines and a convergence bus, and the plurality of wind power generation sub-lines are connected with wind power generators; the method comprises the following steps:
acquiring input power of a plurality of generator line input ends, namely output power corresponding to the wind driven generator, and input power of a generator line output end, namely the input power of the convergence bus input end at the same time, acquiring output power and input power of a plurality of time periods, and acquiring power loss parameters;
predicting the real-time output power of the wind motors one by one based on a power prediction model to obtain first predicted power;
obtaining a target predicted power based on the power loss parameter and the first predicted power;
and obtaining the regional power grid wind power generation power based on a plurality of target predicted powers.
2. The method for predictive optimization of regional grid wind power generation power according to claim 1, further comprising pre-processing data prior to obtaining the power loss parameter, comprising:
obtaining wind speed data corresponding to the power data of the plurality of wind power motors, and arranging the wind speed data from small to large to obtain a first data pair;
segmenting the first data pair based on a first rule to obtain a plurality of first data sub-pairs;
removing the transverse dispersion abnormal data in the first data sub-pairs according to a second rule to obtain a plurality of second data sub-pairs;
arranging the plurality of second data sub-pairs from small to large according to power to obtain third data pairs, and dividing the third data according to a third rule to obtain a plurality of third data sub-pairs;
and removing the longitudinal dispersion abnormal data in the third data sub-pairs according to a fourth rule for the third data sub-pairs to obtain a plurality of fourth data sub-pairs.
3. The method of optimizing regional power grid wind power generation power prediction according to claim 2, further comprising fitting a plurality of pairs of the fourth data sub-pairs to obtain a wind speed-power model.
4. The method according to claim 2, wherein the first rule is to divide the power distribution range in the first data pair based on a reference number of power division to obtain a plurality of first data sub-pairs corresponding to a plurality of power distribution ranges.
5. The regional grid wind power generation power prediction optimization method according to claim 2, wherein the second rule is: and arranging the plurality of first data sub-pairs according to the wind speed to obtain a distribution sequence, acquiring a first quartile, a second quartile and a third quartile of the distribution sequence, determining an inner limit interval, eliminating the dispersion abnormal data in each first data sub-pair, and repeating the operation according to the number of the first data sub-pairs.
6. The method for predicting and optimizing the wind power generation power of the regional power grid according to claim 2, wherein the third rule is: and dividing the plurality of second data sub-pairs into a plurality of parts at equal intervals according to the fixed wind speed and the preset wind speed interval to obtain a plurality of third data sub-pairs.
7. The method for predicting and optimizing the wind power generation power of the regional power grid according to claim 2, wherein the third data sub-pairs are sorted according to power to obtain corresponding sequences, a first quartile, a second quartile and a third quartile in the sequences are obtained, an inner limit interval is determined, dispersion abnormal data in each third data sub-pair are eliminated, and repeated operation is carried out according to the number of the third data sub-pairs.
8. The method according to claim 1, wherein the power prediction model comprises an input layer, a hidden layer and an output layer, the number of neuron nodes of the input layer is 23, the number of neuron nodes of the output layer is 1, the number of neuron nodes of the hidden layer is 10, and the activation functions of the hidden layer and the output layer are respectively a tansig function and a purelin function.
9. The regional power grid wind power generation power prediction optimization method according to claim 8, wherein the power prediction model is constructed by the method comprising the following steps:
acquiring historical actual data and meteorological forecast data of the wind motor; the historical actual data comprises actual operation data of the whole-field fan; the weather forecast data comprises wind speed, temperature, humidity, wind direction cosine value and air pressure data;
and training the weather forecast data as the input of the power prediction model, and finishing training convergence when the training result meets the preset learning rate and the preset error to obtain the power prediction model.
10. The machine learning based wind farm energy production prediction method according to claim 9, wherein the learning rate is 0.05 and the preset error is 0.001.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211623885.1A CN115965134A (en) | 2022-12-14 | 2022-12-14 | Regional power grid wind power generation power prediction optimization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211623885.1A CN115965134A (en) | 2022-12-14 | 2022-12-14 | Regional power grid wind power generation power prediction optimization method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115965134A true CN115965134A (en) | 2023-04-14 |
Family
ID=87353735
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211623885.1A Pending CN115965134A (en) | 2022-12-14 | 2022-12-14 | Regional power grid wind power generation power prediction optimization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115965134A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116956594A (en) * | 2023-07-25 | 2023-10-27 | 广州锐兴科技有限公司 | Rural power grid optimization method, device and equipment based on topological structure |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245805A (en) * | 2019-06-21 | 2019-09-17 | 内蒙古电力(集团)有限责任公司培训中心 | A kind of prediction technique, device and the electronic equipment of wind power |
| CN111709569A (en) * | 2020-06-11 | 2020-09-25 | 国网冀北电力有限公司电力科学研究院 | Method and device for predicting and correcting output power of wind power plant |
| CN114154567A (en) * | 2021-11-19 | 2022-03-08 | 国网宁夏电力有限公司 | Wind power plant station operation data anomaly identification method based on machine learning |
-
2022
- 2022-12-14 CN CN202211623885.1A patent/CN115965134A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245805A (en) * | 2019-06-21 | 2019-09-17 | 内蒙古电力(集团)有限责任公司培训中心 | A kind of prediction technique, device and the electronic equipment of wind power |
| CN111709569A (en) * | 2020-06-11 | 2020-09-25 | 国网冀北电力有限公司电力科学研究院 | Method and device for predicting and correcting output power of wind power plant |
| CN114154567A (en) * | 2021-11-19 | 2022-03-08 | 国网宁夏电力有限公司 | Wind power plant station operation data anomaly identification method based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 海涛，等主编: "《现代供配电技术》", 国防工业出版社, pages: 27 - 29 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116956594A (en) * | 2023-07-25 | 2023-10-27 | 广州锐兴科技有限公司 | Rural power grid optimization method, device and equipment based on topological structure |
| CN116956594B (en) * | 2023-07-25 | 2024-02-09 | 广州锐兴科技有限公司 | Rural power grid optimization method, device and equipment based on topological structure |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Wind speed prediction of IPSO-BP neural network based on lorenz disturbance | |
| He et al. | A combined model for short-term wind power forecasting based on the analysis of numerical weather prediction data | |
| CN106295899B (en) | Wind power probability density Forecasting Methodology based on genetic algorithm Yu supporting vector quantile estimate | |
| Cai et al. | Wind speed forecasting based on extreme gradient boosting | |
| CN102880810A (en) | Wind power prediction method based on time sequence and neural network method | |
| CN111353652A (en) | Wind power output short-term interval prediction method | |
| Yuan et al. | Conditional style-based generative adversarial networks for renewable scenario generation | |
| Lv et al. | A newly combination model based on data denoising strategy and advanced optimization algorithm for short-term wind speed prediction | |
| CN104036356A (en) | Method for predicting future operating state of power grid by using fractal algorithm | |
| CN115425680A (en) | Power prediction model construction and prediction method of multi-energy combined power generation system | |
| CN114386718A (en) | Wind power plant output power short-time prediction algorithm combined with particle swarm neural network | |
| Chen et al. | Research on wind power prediction method based on convolutional neural network and genetic algorithm | |
| CN115965134A (en) | Regional power grid wind power generation power prediction optimization method | |
| Zhang et al. | Achieving wind power and photovoltaic power prediction: An intelligent prediction system based on a deep learning approach | |
| CN113505909B (en) | Error compensation method for short-term wind power trend prediction | |
| Peng et al. | A short‐term wind power prediction method based on deep learning and multistage ensemble algorithm | |
| Wang et al. | Probabilistic power curve estimation based on meteorological factors and density LSTM | |
| Zhang et al. | Hybrid model for renewable energy and load forecasting based on data mining and EWT | |
| CN113887809A (en) | Power distribution network supply and demand balance method, system, medium and computing equipment under double-carbon target | |
| Kader et al. | Active power control strategy for wind farms based on power prediction errors distribution considering regional data | |
| CN105205572A (en) | Photovoltaic power generation output forecasting method based on EMD (Empirical Mode Decomposition) and Elman algorithm | |
| Xu et al. | A novel hybrid wind speed interval prediction model based on mode decomposition and gated recursive neural network | |
| CN117132132A (en) | Photovoltaic power generation power prediction method based on meteorological data | |
| Yang et al. | Day‐ahead wind power combination forecasting based on corrected numerical weather prediction and entropy method | |
| Yuan et al. | Short-term wind speed forecasting using STLSSVM hybrid model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230414 |