CN117610735A - New energy ultra-short term generation power prediction method, device, equipment and medium - Google Patents
New energy ultra-short term generation power prediction method, device, equipment and medium Download PDFInfo
- Publication number
- CN117610735A CN117610735A CN202311649215.1A CN202311649215A CN117610735A CN 117610735 A CN117610735 A CN 117610735A CN 202311649215 A CN202311649215 A CN 202311649215A CN 117610735 A CN117610735 A CN 117610735A
- Authority
- CN
- China
- Prior art keywords
- data
- environmental
- model
- aerogel
- environment
- 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 35
- 230000007613 environmental effect Effects 0.000 claims abstract description 152
- 239000004964 aerogel Substances 0.000 claims abstract description 53
- 230000002159 abnormal effect Effects 0.000 claims abstract description 14
- 238000010248 power generation Methods 0.000 claims abstract description 14
- 238000004088 simulation Methods 0.000 claims description 57
- 239000011159 matrix material Substances 0.000 claims description 49
- 238000000605 extraction Methods 0.000 claims description 17
- 230000015654 memory Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 10
- 230000005855 radiation Effects 0.000 claims description 10
- 230000007704 transition Effects 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 9
- 239000000443 aerosol Substances 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 238000005070 sampling Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000002310 reflectometry Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000012896 Statistical algorithm Methods 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 239000005427 atmospheric aerosol Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
- 238000004800 variational method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a new energy ultra-short-term generation power prediction method, device, equipment and medium, which are implemented by acquiring environmental sensor data, satellite remote sensing data and aerogel degree data of a target area where a new energy generator set is located; correcting the environmental sensor data based on satellite remote sensing data and aerogel data by using a preset data assimilation model to obtain target environmental data; extracting features of the target environment data to obtain environment feature data of the target area; and predicting the power generation data of the new energy generator set in a short time period in the future according to the environmental characteristic data by utilizing a preset ultra-short-term power prediction model, correcting abnormal data and missing segments in the environmental meteorological data by utilizing the correlation between the satellite remote sensing data and the aerogel degree data and correcting the abnormal data and missing segments in the environmental meteorological data, so that the data quality of the environmental sensor data is ensured, and the accuracy of ultra-short-term prediction is improved.
Description
Technical Field
The application relates to the technical field of electric power prediction, in particular to a new energy ultra-short-term generation power prediction method, device, equipment and medium.
Background
Because the new energy power grid has the characteristics of intermittence and volatility, the power generation plan of the power grid dispatching department needs to be adjusted in real time, and the power supply stability is ensured, so that the ultra-short-term power generation power prediction of the new energy power grid is very necessary. At present, the new energy power grid mainly comprises a photovoltaic power grid and a wind power grid, a generator set of the new energy power grid is provided with a plurality of sensor elements such as a temperature sensor, a wind speed sensor, a wind direction sensor, a light sensor, a humidity sensor and the like, the environment where the generator set is located is complex and the weather is changeable, so that the sensor elements are easy to have the condition of missing measured data and the like in long-term use, and the new energy power generation is greatly influenced by the factors such as environmental change, weather change and the like, thereby influencing the prediction accuracy of the power generation.
Disclosure of Invention
The application provides a new energy ultra-short-term generation power prediction method, device, equipment and medium, which are used for solving the technical problem that the accuracy of generation power prediction is affected due to unstable quality of current power grid data.
In order to solve the technical problem, in a first aspect, the present application provides a method for predicting ultra-short term generated power of a new energy, including:
acquiring environmental sensor data, satellite remote sensing data and aerogel degree data of a target area where a new energy generator set is located;
correcting the environmental sensor data based on satellite remote sensing data and aerogel data by using a preset data assimilation model to obtain target environmental data;
extracting features of the target environment data to obtain environment feature data of the target area;
and predicting the power generation data of the new energy generator set in a short time period in the future according to the environmental characteristic data by using a preset ultra-short-term power prediction model.
In some implementations of the first aspect, using a preset data assimilation model, correcting the environmental sensor data based on the satellite remote sensing data and the aerogel data to obtain target environmental data includes:
simulating environmental simulation data of a target area according to satellite remote sensing data and aerogel degree data by using an environmental simulation model in a preset data assimilation model;
and correcting the environmental sensor data based on the environmental simulation data by utilizing an improved Kalman filter in the preset data assimilation model to obtain target environmental data.
In some implementations of the first aspect, using an environmental simulation model in the preset data assimilation model, simulating environmental simulation data for the target area based on the satellite remote sensing data and the aerogel data, includes:
performing feature extraction on the satellite remote sensing data and the aerogel degree data to obtain simulated feature data;
and simulating the environment simulation data of the target area according to the simulation characteristic data by using an environment simulation model, wherein the environment simulation model is an environment weather inversion model.
In some implementations of the first aspect, feature extraction is performed on satellite remote sensing data and aerogel data to obtain simulated feature data, including:
based on a preset feature extraction model, extracting remote sensing feature data of satellite remote sensing data and aerogel feature data of aerogel degree data;
extracting first correlation characteristic data between satellite remote sensing data and environmental weather of a target area based on a preset radiation transmission model;
based on a preset aerosol model, extracting second correlation characteristic data between aerogel degree data and environmental weather of a target area, wherein the simulation characteristic data comprise remote sensing characteristic data, aerogel characteristic data, first correlation characteristic data and second correlation characteristic data.
In some implementations of the first aspect, modifying the environmental sensor data based on the environmental simulation data using an improved kalman filter in a preset data assimilation model to obtain target environmental data includes:
performing data cleaning on the environment sensor data, removing abnormal data in the environment sensor data, and determining missing segments in the environment sensor data after the abnormal data are removed;
and correcting the missing segment in the environmental sensor data by utilizing the improved Kalman filter to obtain target environmental data.
In some implementations of the first aspect, correcting the missing segments in the environmental sensor data using an improved kalman filter to obtain the target environmental data includes:
based on the environmental simulation data, the environmental sensor data, the covariance matrix and the state transition equation at the current moment, predicting environmental prediction data at the next moment;
updating a covariance matrix of the next moment based on the environment prediction data;
calculating a Kalman gain matrix based on the covariance matrix of the next moment;
based on the Kalman gain matrix, the environmental sensor data at the next moment is updated to correct the environmental sensor data, and target environmental data is obtained.
In some implementations of the first aspect, predicting environmental prediction data for a next time based on the environmental simulation data, the environmental sensor data, and the covariance matrix for the current time includes:
calculating average value data between the environment simulation data and the environment sensor data at the current moment;
based on the covariance matrix, carrying out unscented transformation on the mean value data to obtain a sigma point set;
and inputting the sigma point set into a state transition equation to obtain environmental prediction data of the next moment.
In a second aspect, the present application further provides a new energy ultra-short term generated power prediction apparatus, including:
the acquisition module is used for acquiring environmental sensor data, satellite remote sensing data and aerogel degree data of a target area where the new energy generator set is located;
the correction module is used for correcting the environmental sensor data based on satellite remote sensing data and aerogel degree data by using a preset data assimilation model to obtain target environmental data;
the extraction module is used for extracting the characteristics of the target environment data to obtain the environment characteristic data of the target area;
and the prediction module is used for predicting the power generation data of the new energy generator set in a short time period in the future according to the environmental characteristic data by using a preset ultra-short-term power prediction model.
In a third aspect, the present application further provides a computer device, including a processor and a memory, where the memory is configured to store a computer program, and the computer program when executed by the processor implements the new energy ultra-short term generated power prediction method according to the first aspect.
In a fourth aspect, the present application also provides a computer readable storage medium storing a computer program, which when executed by a processor implements the new energy ultra-short term generated power prediction method as in the first aspect.
The application has the following beneficial effects:
acquiring environmental sensor data, satellite remote sensing data and aerogel degree data of a target area where a new energy generator set is located; correcting the environmental sensor data based on satellite remote sensing data and aerogel data by using a preset data assimilation model to obtain target environmental data; extracting features of the target environment data to obtain environment feature data of the target area; and predicting the power generation data of the new energy generator set in a short time period in the future according to the environmental characteristic data by utilizing a preset ultra-short-term power prediction model, correcting abnormal data and missing segments in the environmental meteorological data by utilizing the correlation between the satellite remote sensing data and the aerogel degree data and correcting the abnormal data and missing segments in the environmental meteorological data, so that the data quality of the environmental sensor data is ensured, and the accuracy of ultra-short-term prediction is improved.
Drawings
Fig. 1 is a schematic flow chart of a new energy ultra-short term generated power prediction method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a new energy ultra-short term generated power prediction device according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
Referring to fig. 1, fig. 1 is a flow chart of a new energy ultra-short term power prediction method according to an embodiment of the present application. The new energy ultra-short term generation power prediction method can be applied to computer equipment, wherein the computer equipment comprises, but is not limited to, smart phones, notebook computers, tablet computers, desktop computers, physical servers, cloud servers and the like. As shown in fig. 1, the new energy ultra-short term generated power prediction method of the present embodiment includes steps S101 to S104, which are described in detail as follows:
and step S101, acquiring environmental sensor data, satellite remote sensing data and aerogel degree data of a target area where the new energy generator set is located.
In the step, the new energy generator set can be a photovoltaic generator set or a wind generator set; environmental sensor data includes, but is not limited to, temperature, humidity, illumination intensity, illumination angle, wind speed, wind direction, and the like; satellite remote sensing data is data obtained by observing and collecting the surface of the earth through satellites, is stored in the forms of multispectral images, radar images, elevation data and the like, and contains rich earth surface information; aerogel degree (Aerosol Optical Depth, AOD) is a parameter used to describe the absorption and scattering capacity of atmospheric aerosols for solar radiation.
Step S102, correcting the environmental sensor data based on the satellite remote sensing data and the aerogel degree data by using a preset data assimilation model to obtain target environmental data.
In this step, data assimilation is performed by combining the observed data with the model simulation results to update the state of the model, typically by minimizing the differences between the observed values and the model simulation results. Because the environmental sensor has faults or other abnormal conditions due to service life, environmental factor damage and other reasons, and the environmental sensor data has data mutation, deletion and other anomalies, the embodiment adopts satellite remote sensing data and aerogel degree data which have a certain physical relationship with environmental weather to correct the environmental sensor data so as to improve the data quality of the environmental sensor.
Alternatively, the data assimilation may be accomplished by algorithms such as Kalman filtering, variational methods, particle filtering, and the like. According to the embodiment, the environment prediction data predicted by the satellite remote sensing data and the aerogel degree data are used as observation data, the environment sensor data are used as actual measurement data, the improved Kalman filtering algorithm is adopted to carry out smooth interpolation, the corrected environment sensor data are ensured to be more in line with the actual environment condition, and the prediction accuracy of the subsequent generated power is improved.
And step S103, extracting the characteristics of the target environment data to obtain the environment characteristic data of the target area.
In this step, the time sequence features of the target environmental data may be extracted based on statistical algorithms such as average, variance, maximum, minimum, median, percentile, etc., and the correlation features between the target environmental data and the power data may be extracted by using algorithms based on pearson correlation coefficient, spearman correlation coefficient, decision coefficient, point two-column correlation coefficient, mutual information, machine learning, etc.
And step S104, predicting the power generation data of the new energy generator set in a short time period in the future according to the environmental characteristic data by using a preset ultra-short-term power prediction model.
In this embodiment, the preset ultra-Short Term power prediction model may be a Long Short Term Memory network (LSTM) or a convolutional neural network (Convolutional Neural Network, CNN), etc. Optionally, the target environmental data in a historical time period before the current moment is used as a model input of an ultra-short-term power prediction model to predict the generated power of the generator set in a future time period.
In one embodiment, the step S102 includes:
simulating the environment simulation data of the target area according to the satellite remote sensing data and the aerogel degree data by using an environment simulation model in the preset data assimilation model;
and correcting the environmental sensor data based on the environmental simulation data by utilizing an improved Kalman filter in the preset data assimilation model to obtain the target environmental data.
In the embodiment, the environment simulation data of the target area are simulated through the satellite remote sensing data and the aerogel data to serve as the basis for correcting the environment sensor data, so that the corrected environment sensor data are more accurate; meanwhile, an improved Kalman filter is adopted to interpolate the environmental sensor data, so that the corrected environmental sensor data is smoother and more accords with the actual environmental condition of the target area.
Alternatively, the environmental simulation model may be an inversion model based on machine learning. For example, the historical satellite remote sensing data and the aerogel degree data are used as model input, the historical environment sensor data are used as model output, and the inversion model is trained until the inversion model reaches a preset convergence condition, so that the environment simulation model is obtained.
In one embodiment, simulating environmental simulation data of the target area includes:
performing feature extraction on the satellite remote sensing data and the aerogel degree data to obtain simulated feature data;
and simulating the environment simulation data of the target area according to the simulation characteristic data by using the environment simulation model, wherein the environment simulation model is an environment weather inversion model.
In this embodiment, the simulated feature data includes the remote sensing feature data, aerogel feature data, first correlation feature data, and second correlation feature data.
Optionally, the feature extraction includes:
based on a preset feature extraction model, extracting the remote sensing feature data and aerogel feature data of aerogel degree data of the satellite remote sensing data;
extracting first correlation characteristic data between the satellite remote sensing data and the environmental weather of the target area based on a preset radiation transmission model;
and extracting second correlation characteristic data between the aerogel degree data and the environmental weather of the target area based on a preset aerosol model.
In this alternative embodiment, the preset feature extraction model may be a time series feature extraction model based on statistics or machine learning. The preset radiation transmission model comprises an atmosphere transmission model and a ground surface reflection model; the atmospheric transmission model is used for describing the attenuation and scattering of solar radiation through an atmospheric layer, and can be a US Standard Atmosphere model, a MODTRAN model, a 6S model and the like; the earth surface reflection model is used for describing the reflection and radiation state of earth surface to solar radiation, and can be a Lambert model, an expansion ball model, a proportional curve model and the like. As an embodiment, the radiation transmission model=the first weight×the output result of the atmospheric transmission model+the second weight×the earth surface reflection model is preset.
The preset aerosol model may be expressed as:
wherein,is the reflectivity of a large gas path, and is->And->Representing total transmittance from the sun to the ground and from the ground to the sensor, s i Is the sphere albedo of atmospheric illumination, +.>Is the surface reflectivity, theta 0 Is the zenith angle of the sun, θ is the zenith angle of the satellite, < ->Representing the relative azimuth angle of the sun/satellite.
In one embodiment, the data correction includes:
performing data cleaning on the environment sensor data, removing abnormal data in the environment sensor data, and determining missing segments in the environment sensor data after the abnormal data are removed;
and correcting the missing segment in the environmental sensor data by using the improved Kalman filter to obtain the target environmental data.
In this embodiment, the abnormal data may be abrupt data, and the abrupt data and the original missing segment are corrected by improving the kalman filter, so as to improve the quality of the environmental meteorological data.
In an embodiment, the correcting the missing segment in the environmental sensor data by using the improved kalman filter to obtain the target environmental data includes:
predicting environmental prediction data at the next moment based on the environmental simulation data, the environmental sensor data, the covariance matrix and the state transition equation at the current moment;
updating a covariance matrix of the next moment based on the environment prediction data;
calculating a Kalman gain matrix based on the covariance matrix of the next moment;
and updating the environmental sensor data at the next moment based on the Kalman gain matrix so as to correct the environmental sensor data to obtain the target environmental data.
Optionally, predicting the environmental prediction data for the next time instant includes:
calculating average value data between the environment simulation data and the environment sensor data at the current moment;
based on the covariance matrix, performing unscented transformation on the mean value data to obtain a sigma point set;
and inputting the sigma point set into the state transition equation to obtain environmental prediction data of the next moment.
In this embodiment, the accuracy of the current state is improved by performing mean value operation on the environmental simulation data and the environmental sensor data, and the characteristic of changeable environmental weather of the area where the generator set is located is simulated by unscented transformation, so as to better conform to the environmental weather characteristics of the target area.
Illustratively, the environmental simulation data and environmental sensor data at the current time are weighted to obtain mean value data Z (k):
wherein X (k+1) represents the state at time k+1, X (k) represents the system state at time k, W (k) represents the process noise, f represents the state update function, V (k) represents the measurement noise, and h represents the state transfer function.
And carrying out unscented transformation on the mean value data to obtain sigma sampling points:
wherein X (i) (k/k) represents an ith sample of a sigma sampling point, and is obtained by performing unscented transformation on mean value data Z (k/k);an estimated value (a priori value) representing the mean value data, n representing the dimension of the state quantity, and P (k/k) representing the covariance matrix for representing the uncertainty of the state quantity X; λ represents a constant for controlling the range and direction of the sigma point distribution. Typically, λ has a value of 3-n, where n is the dimension of the state quantity; />For the standard deviation of the covariance matrix P (k/k), the information of the covariance matrix is converted into a measure of the standard deviation for expansion or contraction +.>Is not limited in terms of the range of (a).
2n+1 sigma point sets are calculated:
X (i) (k+1/k)＝f[k，X i (k/k)]the method comprises the steps of carrying out a first treatment on the surface of the Wherein X is (i) (k/k) represents the ith sample of the sigma sampling point, and is obtained by performing unscented transformation on the mean value data Z (k/k); f represents a state update function, k represents the current time, X (i) (k+1/k) represents the ith sample of the sigma point set, sampling the sigma point X by the state update function f (i) (k+k) results from the propagation of the state.
State quantity prediction:
wherein (1)>The predicted value of the state quantity is obtained by carrying out weighted average on a sigma point set; 2n represents the total number of sigma points, w i Representing the weight corresponding to the ith sampling point, and performing weighted average on the state quantity to obtain a predicted value of the state quantity; x is X i (k+1/k) represents the i-th sample of the sigma point set, and the estimated value of the state quantity at the next time is obtained by the state update function.
Covariance matrix:
wherein P (k+1/k) represents the covariance matrix at the next moment, ω i Represents the weight corresponding to the ith sample point,/-j->The predicted value representing the state quantity is obtained by weighted average of sigma point sets, X i (k+1/k) represents the i-th sample of the sigma point set, and the estimated value of the state quantity at the next time, X, obtained by the state update function i (k+1/k) T represents X i (k+1/k), Q represents the covariance matrix of the process noise, describing the unmodeled uncertainty in the model.
And performing unscented transformation again to obtain a new sigma point set:
wherein,representing the new sigma point set obtained again; />A predicted value representing the state quantity,the standard deviation of the covariance matrix P (k/k) at the next time k+1 is represented.
Inputting the new sigma point set into a state transition equation to obtain environment prediction data:
Z i (k+1/k)＝h[X i (k+1/k)]the method comprises the steps of carrying out a first treatment on the surface of the Wherein Z is i (k+1/k) represents a new sigma point set based on the input in the state transition equationThe obtained environment prediction data, h represents a state transfer function;
calculating new mean value data:
updating a prediction covariance matrix:
updating the measurement covariance matrix:
wherein,representing mean data derived from the new environmental prediction data; w (w) i Representing the weight; z is Z i (k+1/k) represents new environmental prediction data; pz k z k Representing the prediction covariance matrix, px k z k Representing a measurement covariance matrix, R representing the covariance of the ambient noise, X i (k+1/k) represents the ith sample of the sigma point set, +.>Representing the mean data from the new sigma point set obtained again,/for the new sigma point set>Representation->Is a transpose of (a).
Calculating a Kalman gain matrix:
wherein K (k+1) represents the Kalman gain matrix at time k+1, < >>Representing a covariance matrix describing variances and covariances between the state estimates and the sensor measurements; />An inverse matrix representing the covariance matrix is used to calculate the Kalman gain matrix.
Updating the environmental sensor data at the next time:
wherein (1)>A priori values representing the state quantity at the next instant k+1; />A predicted value of the state quantity at the next time k+1 is represented, and K (k+1) represents a Kalman gain matrix; z (k+1) represents new environmental prediction data predicted at time k+1 based on the sigma point set; />Representing mean data derived from the new environmental prediction data;
updating covariance matrix of next moment:
wherein P (k+1/k+1) represents the covariance matrix of the state estimate at time k+1, K (k+1) represents the Kalman gain matrix at time k+1,representing covariance matrix, K T (k+1) represents the transpose of the Kalman gain matrix.
In order to execute the new energy ultra-short term generated power prediction method corresponding to the method embodiment, corresponding functions and technical effects are realized. Referring to fig. 2, fig. 2 shows a block diagram of a new energy ultra-short term generated power prediction device according to an embodiment of the present application. For convenience of explanation, only the portion related to this embodiment is shown, and the new energy ultra-short term generated power prediction device provided in this embodiment of the present application includes:
the acquisition module 201 is used for acquiring environmental sensor data, satellite remote sensing data and aerogel degree data of a target area where the new energy generator set is located;
the correction module 202 is configured to correct the environmental sensor data based on the satellite remote sensing data and the aerogel data by using a preset data assimilation model, so as to obtain target environmental data;
the extracting module 203 is configured to perform feature extraction on the target environmental data to obtain environmental feature data of the target area;
and the prediction module 204 is configured to predict, according to the environmental characteristic data, power generation data of the new energy generator set in a short time period in the future by using a preset ultra-short term power prediction model.
In one embodiment, the correction module 202 includes:
the simulation sub-module is used for simulating the environment simulation data of the target area according to the satellite remote sensing data and the aerogel degree data by using an environment simulation model in the preset data assimilation model;
and the correction sub-module is used for correcting the environmental sensor data based on the environmental simulation data by utilizing an improved Kalman filter in the preset data assimilation model to obtain the target environmental data.
In one embodiment, the analog sub-module includes:
the extraction unit is used for carrying out feature extraction on the satellite remote sensing data and the aerogel degree data to obtain analog feature data;
the simulation unit is used for simulating the environment simulation data of the target area according to the simulation characteristic data by using the environment simulation model, and the environment simulation model is an environment weather inversion model.
In an embodiment, the extracting unit is specifically configured to:
based on a preset feature extraction model, extracting the remote sensing feature data and aerogel feature data of aerogel degree data of the satellite remote sensing data;
extracting first correlation characteristic data between the satellite remote sensing data and the environmental weather of the target area based on a preset radiation transmission model;
and extracting second correlation characteristic data between the aerogel degree data and the environmental weather of the target area based on a preset aerosol model, wherein the simulation characteristic data comprise the remote sensing characteristic data, aerogel characteristic data, first correlation characteristic data and second correlation characteristic data.
In one embodiment, the correction submodule includes:
the cleaning unit is used for carrying out data cleaning on the environment sensor data, removing abnormal data in the environment sensor data and determining missing segments in the environment sensor data after the abnormal data are removed;
and the correction unit is used for correcting the missing segment in the environment sensor data by utilizing the improved Kalman filter to obtain the target environment data.
In an embodiment, the correction unit includes:
a prediction subunit, configured to predict environmental prediction data at a next time based on the environmental simulation data, the environmental sensor data, the covariance matrix, and the state transition equation at the current time;
an updating subunit, configured to update a covariance matrix at a next moment based on the environmental prediction data;
a calculating subunit, configured to calculate a kalman gain matrix based on the covariance matrix at the next moment;
and the correction subunit is used for updating the environmental sensor data at the next moment based on the Kalman gain matrix so as to correct the environmental sensor data to obtain the target environmental data.
In an embodiment, the prediction subunit is specifically configured to:
calculating average value data between the environment simulation data and the environment sensor data at the current moment;
based on the covariance matrix, performing unscented transformation on the mean value data to obtain a sigma point set;
and inputting the sigma point set into the state transition equation to obtain environmental prediction data of the next moment.
The new energy ultra-short-term power generation power prediction device can implement the new energy ultra-short-term power generation power prediction method of the method embodiment. The options in the method embodiments described above are also applicable to this embodiment and will not be described in detail here. The rest of the embodiments of the present application may refer to the content of the method embodiments described above, and in this embodiment, no further description is given.
Fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application. As shown in fig. 3, the computer device 3 of this embodiment includes: at least one processor 30 (only one is shown in fig. 3), a memory 31 and a computer program 32 stored in the memory 31 and executable on the at least one processor 30, the processor 30 implementing the steps in any of the method embodiments described above when executing the computer program 32.
The computer device 3 may be a smart phone, a tablet computer, a desktop computer, a cloud server, or other computing devices. The computer device may include, but is not limited to, a processor 30, a memory 31. It will be appreciated by those skilled in the art that fig. 3 is merely an example of the computer device 3 and is not meant to be limiting as the computer device 3, and may include more or fewer components than shown, or may combine certain components, or different components, such as may also include input-output devices, network access devices, etc.
The processor 30 may be a central processing unit (Central Processing Unit, CPU), the processor 30 may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 31 may in some embodiments be an internal storage unit of the computer device 3, such as a hard disk or a memory of the computer device 3. The memory 31 may in other embodiments also be an external storage device of the computer device 3, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 3. Further, the memory 31 may also include both an internal storage unit and an external storage device of the computer device 3. The memory 31 is used for storing an operating system, application programs, boot loader (BootLoader), data, other programs etc., such as program codes of the computer program etc. The memory 31 may also be used for temporarily storing data that has been output or is to be output.
In addition, the embodiment of the present application further provides a computer readable storage medium, where a computer program is stored, where the computer program is executed by a processor to implement the steps in any of the above-mentioned method embodiments.
The present embodiments provide a computer program product which, when run on a computer device, causes the computer device to perform the steps of the method embodiments described above.
In several embodiments provided herein, it will be understood that each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device to perform all or part of the steps of the method described in the various embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing embodiments have been provided for the purpose of illustrating the objects, technical solutions and advantages of the present application in further detail, and it should be understood that the foregoing embodiments are merely examples of the present application and are not intended to limit the scope of the present application. It should be noted that any modifications, equivalent substitutions, improvements, etc. made by those skilled in the art, which are within the spirit and principles of the present application, are intended to be included within the scope of the present application.
Claims (10)
1. The method for predicting the ultra-short-term generated power of the new energy is characterized by comprising the following steps of:
acquiring environmental sensor data, satellite remote sensing data and aerogel degree data of a target area where a new energy generator set is located;
correcting the environmental sensor data based on the satellite remote sensing data and the aerogel degree data by using a preset data assimilation model to obtain target environmental data;
extracting the characteristics of the target environment data to obtain the environment characteristic data of the target area;
and predicting the power generation data of the new energy generator set in a short time period in the future according to the environmental characteristic data by using a preset ultra-short-term power prediction model.
2. The method for predicting the ultra-short term generated power of a new energy source according to claim 1, wherein the correcting the environmental sensor data based on the satellite remote sensing data and the aerogel data by using a preset data assimilation model to obtain target environmental data comprises:
simulating the environment simulation data of the target area according to the satellite remote sensing data and the aerogel degree data by using an environment simulation model in the preset data assimilation model;
and correcting the environmental sensor data based on the environmental simulation data by utilizing an improved Kalman filter in the preset data assimilation model to obtain the target environmental data.
3. The method for predicting ultra-short term generated power of new energy according to claim 2, wherein the simulating the environmental simulation data of the target area according to the satellite remote sensing data and the aerogel data by using the environmental simulation model in the preset data assimilation model comprises:
performing feature extraction on the satellite remote sensing data and the aerogel degree data to obtain simulated feature data;
and simulating the environment simulation data of the target area according to the simulation characteristic data by using the environment simulation model, wherein the environment simulation model is an environment weather inversion model.
4. The method for predicting the ultra-short term generated power of new energy according to claim 3, wherein the feature extraction of the satellite remote sensing data and the aerogel degree data to obtain simulated feature data comprises the following steps:
based on a preset feature extraction model, extracting the remote sensing feature data and aerogel feature data of aerogel degree data of the satellite remote sensing data;
extracting first correlation characteristic data between the satellite remote sensing data and the environmental weather of the target area based on a preset radiation transmission model;
and extracting second correlation characteristic data between the aerogel degree data and the environmental weather of the target area based on a preset aerosol model, wherein the simulation characteristic data comprise the remote sensing characteristic data, aerogel characteristic data, first correlation characteristic data and second correlation characteristic data.
5. The method for predicting the ultra-short term generated power of a new energy according to claim 2, wherein the modifying the environmental sensor data based on the environmental simulation data by using the improved kalman filter in the preset data assimilation model to obtain the target environmental data comprises:
performing data cleaning on the environment sensor data, removing abnormal data in the environment sensor data, and determining missing segments in the environment sensor data after the abnormal data are removed;
and correcting the missing segment in the environmental sensor data by using the improved Kalman filter to obtain the target environmental data.
6. The method for predicting the ultra-short term generated power of a new energy source according to claim 5, wherein the correcting the missing segment in the environmental sensor data by using the improved kalman filter to obtain the target environmental data comprises:
predicting environmental prediction data at the next moment based on the environmental simulation data, the environmental sensor data, the covariance matrix and the state transition equation at the current moment;
updating a covariance matrix of the next moment based on the environment prediction data;
calculating a Kalman gain matrix based on the covariance matrix of the next moment;
and updating the environmental sensor data at the next moment based on the Kalman gain matrix so as to correct the environmental sensor data to obtain the target environmental data.
7. The method for predicting the ultra-short term generated power of a new energy according to claim 6, wherein predicting the environmental prediction data at the next time based on the environmental simulation data, the environmental sensor data, and the covariance matrix at the current time comprises:
calculating average value data between the environment simulation data and the environment sensor data at the current moment;
based on the covariance matrix, performing unscented transformation on the mean value data to obtain a sigma point set;
and inputting the sigma point set into the state transition equation to obtain environmental prediction data of the next moment.
8. The utility model provides a new forms of energy ultrashort term power prediction device which characterized in that includes:
the acquisition module is used for acquiring environmental sensor data, satellite remote sensing data and aerogel degree data of a target area where the new energy generator set is located;
the correction module is used for correcting the environmental sensor data based on the satellite remote sensing data and the aerogel degree data by using a preset data assimilation model to obtain target environmental data;
the extraction module is used for extracting the characteristics of the target environment data to obtain the environment characteristic data of the target area;
and the prediction module is used for predicting the power generation data of the new energy generator set in a short time period in the future according to the environmental characteristic data by using a preset ultra-short-term power prediction model.
9. A computer device comprising a processor and a memory for storing a computer program which when executed by the processor implements the new energy ultra-short term generated power prediction method of any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by a processor, implements the new-energy ultra-short-term generated power prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311649215.1A CN117610735A (en) | 2023-12-04 | 2023-12-04 | New energy ultra-short term generation power prediction method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311649215.1A CN117610735A (en) | 2023-12-04 | 2023-12-04 | New energy ultra-short term generation power prediction method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117610735A true CN117610735A (en) | 2024-02-27 |
Family
ID=89953245
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311649215.1A Pending CN117610735A (en) | 2023-12-04 | 2023-12-04 | New energy ultra-short term generation power prediction method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117610735A (en) |
-
2023
- 2023-12-04 CN CN202311649215.1A patent/CN117610735A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111815038B (en) | Photovoltaic ultra-short term prediction method and system | |
| US11231519B2 (en) | Method and device for simulating discharge, and computer device | |
| CN103117546B (en) | A kind of Ultrashort-term slide prediction method for wind power | |
| US20180275314A1 (en) | Method and system for solar power forecasting | |
| CN111126662B (en) | Irrigation decision making method, device, server and medium based on big data | |
| CN109782374B (en) | Method and device for optimizing numerical weather forecast through assimilation and inversion of water vapor content | |
| CN109033543B (en) | Method, device and equipment for estimating vegetation coverage of heterogeneous land areas | |
| Laslett et al. | A method for generating synthetic hourly solar radiation data for any location in the south west of Western Australia, in a world wide web page | |
| Wang et al. | Customized deep learning for precipitation bias correction and downscaling | |
| CN113095547B (en) | Short-term wind power prediction method based on GRA-LSTM-ICE model | |
| CN110969296B (en) | Electric heating load prediction method and device and terminal equipment | |
| CN116186493B (en) | Meteorological forecasting method, device, equipment and medium based on numerical mode correction | |
| CN117526274A (en) | New energy power prediction method, electronic equipment and storage medium in extreme climate | |
| CN117610735A (en) | New energy ultra-short term generation power prediction method, device, equipment and medium | |
| CN116245248A (en) | Cloud optical thickness-based distributed light Fu Muxian ultra-short-term power prediction method | |
| CN114970222A (en) | HASM-based regional climate mode daily average air temperature deviation correction method and system | |
| CN113435118A (en) | Irradiance determination method, irradiance determination device, irradiance determination equipment and storage medium | |
| CN117421601B (en) | Sea surface evaporation waveguide near-future rapid forecasting method | |
| CN116706906B (en) | Photovoltaic power station output power prediction method, device, equipment and medium | |
| CN116822658B (en) | Early warning method and device for wind-solar resources, computer equipment and storage medium | |
| CN113177702B (en) | Meteorological input data matching method and system | |
| CN116776651B (en) | Method and device for measuring and calculating surface evapotranspiration, electronic equipment and storage medium | |
| CN116681143A (en) | Training method of solar irradiance prediction model and solar irradiance prediction method | |
| CN116663432B (en) | Hundred-meter height wind speed forecast correction downscaling method and device | |
| CN116260141B (en) | Reconstruction method and system for power of photovoltaic power station and reconstruction terminal |
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 |