CN109636054A - Solar energy power generating amount prediction technique based on classification and error combination prediction - Google Patents
Solar energy power generating amount prediction technique based on classification and error combination prediction Download PDFInfo
- Publication number
- CN109636054A CN109636054A CN201811570233.XA CN201811570233A CN109636054A CN 109636054 A CN109636054 A CN 109636054A CN 201811570233 A CN201811570233 A CN 201811570233A CN 109636054 A CN109636054 A CN 109636054A
- Authority
- CN
- China
- Prior art keywords
- prediction
- power generation
- error
- data
- neural network
- 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 41
- 239000011159 matrix material Substances 0.000 claims abstract description 81
- 238000013528 artificial neural network Methods 0.000 claims abstract description 76
- 238000010248 power generation Methods 0.000 claims description 84
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000009825 accumulation Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 abstract description 3
- 238000007619 statistical method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 239000002803 fossil fuel Substances 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Public Health (AREA)
- Evolutionary Biology (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the solar energy power generating amount prediction technique of a kind of classification and error combination prediction, including S1, prediction data determined it according to the time, its weather pattern is determined using KNN algorithm according to the meteorological data of forecast date and history meteorological data；Corresponding combination forecasting is used after S2, classification, is predicted to obtain respective prediction output respectively using MPSO-BP neural network and gray model GM (1,1)；S3, the error matrix obtained using sample training data, acquire the weight matrix of respective combined prediction；S4, two parts prediction output valve is combined according to weight matrix, finally obtains solar energy power generating amount.The weight of each output point is obtained further according to error after this method classification, the prediction result obtained from is relatively reliable, realizes the reliable prediction to solar energy power generating amount.
Description
Technical Field
The invention belongs to the technical field of solar energy utilization, and particularly relates to a solar photovoltaic power generation amount prediction method based on classification and error combination prediction.
Background
Nowadays, the traditional fossil fuel energy is increasingly exhausted, and meanwhile, the environment is also greatly damaged in the using process. Renewable energy is inexhaustible energy, and for sustainable development of human society, countries in the world have been focusing on renewable energy, and solar power generation is a main utilization mode of renewable energy and is a main component of a smart grid. A key goal of smart grid efforts is to greatly improve the utilization rate of environment-friendly renewable energy, while a micro-grid technology is a key technology for achieving the goal, but the uncontrollable characteristic of renewable energy power generation brings great difficulty to energy management of the micro-grid, and serious influence and threat are caused to economic, safe and stable operation of the micro-grid, so that it is very important to find a proper method for improving the reliability and effectiveness of the micro-grid.
The current progress in microgrid energy management has been significant, but to achieve efficient energy management, accurate prediction of grid load and renewable energy generation is required. The existing prediction method of solar energy power generation is mainly a statistical method and an artificial neural network method, wherein the statistical method is to use a probability theory to find out an internal rule and use the internal rule for prediction by carrying out statistical analysis on historical data; the single artificial neural network method takes sample data as input, establishes a prediction model and predicts the future power generation amount; the two methods can achieve higher prediction precision for data information with strong regularity and periodicity, but solar energy has the characteristics of randomness, volatility and the like, and by using the two methods, the prediction effect is not ideal, the requirements of the existing energy management cannot be met, and the efficiency and the reliability of the energy management of the microgrid are greatly limited.
Therefore, it is important to find a method capable of reliably predicting the solar photovoltaic power generation.
Disclosure of Invention
Aiming at the defects in the prior art, the solar photovoltaic power generation amount prediction method based on classification and error combination prediction solves the problems that the prediction effect is not ideal, the existing energy management cannot be met, and the efficiency and reliability of micro-grid energy management are limited in the existing photovoltaic power generation amount prediction method.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that: the solar photovoltaic power generation capacity prediction method based on classification and error combination prediction comprises the following steps:
s1, acquiring meteorological data of a solar photovoltaic power generation amount prediction day from a meteorological station;
s2, determining the weather type in the season to which the weather data belongs, inputting the weather data of the predicted day into the trained MPSO-BP neural network corresponding to the weather type, and obtaining the first solar power generation output time sequence
Simultaneously inputting weather data of the predicted day into a trained gray model GM (1,1) corresponding to the weather type to obtain a second solar power generation output time sequence
S3, outputting the first solar energy power generation amount to a time sequenceWith a corresponding combined prediction matrix W in the trained MPSO-BP neural networkBPMultiplying to obtain a first solar power generation prediction quantity YBP；
Simultaneously outputting the second solar power generation output time seriesWith the combined prediction matrix W in the corresponding trained gray model GM (1,1)GMMultiplying to obtain a second solar power generation prediction quantity YGM；
S4, measuring the first solar power generation prediction quantity YBPAnd a second solar power generation prediction amount YGMAdding to obtain the solar photovoltaic power generation amountPredicted power generation amount Y of measured dayP。
Further, the meteorological data in the step S1 includes a maximum air temperature value, a minimum air temperature value, a temperature value every three hours, a difference between the maximum temperature and the previous day maximum temperature, a difference between the minimum temperature and the previous day minimum temperature, a relative humidity, and a digitized ultraviolet intensity.
Further, the seasons to which the meteorological data in the step S2 belongs include spring, summer, fall and winter; each season comprises three weather types of sunny days, cloudy days and rainy days;
and a corresponding trained MPSO-BP neural network and a trained gray model GM (1,1) are arranged under each weather type in each season.
Further, the gray model GM (1,1) is:
in the formula, y(1)(ki+1j) The accumulated sequence value of the (i + 1) th output point of the j sample obtained by prediction is represented;
y(1)(kij) An accumulated sequence value representing the ith output point of the jth sample;
m is the number of output points in the sample;
u, a model to be subjected to parameter calculation;
u and a are determined from the data input to the gray model.
Further, the method for training the gray model GM (1,1) corresponding to one weather type in step S2 specifically includes:
a1, acquiring historical meteorological data of three weather types in different seasons from a meteorological station;
a2, classifying historical meteorological data under the same weather type in the same season;
a3, acquiring actual solar photovoltaic power generation amount historical data in a corresponding date according to date data in similar historical meteorological data, and inputting the actual solar photovoltaic power generation amount historical data serving as a training sample into a gray model GM (1, 1);
a4, calculating the accumulation sequence y of the gray model according to the data of the first j multiplied by m + i points of the training sample(1)And establishing a corresponding calculation matrix;
a5, calculating u and a in the gray model by the least square method according to the calculation matrix and substituting the calculated u and a into the accumulation sequence y(1)In (b) to obtain y(1)(ki+1j) And finishing the training of the gray model GM (1, 1).
Further, in the step S2, the method for training the MPSO-BP neural network corresponding to one weather type specifically includes:
b1, acquiring historical meteorological data of three weather types in different seasons from a meteorological station;
b2, classifying the historical meteorological data under the same weather type in the same season;
b3, acquiring historical data of actual solar photovoltaic power generation amount in corresponding date according to date data in similar historical meteorological data;
b4, inputting historical meteorological data as sample input training data, and outputting solar photovoltaic power generation amount as sample output training data every half an hour in actual solar photovoltaic power generation amount historical data;
b5, setting the maximum training times of the MPSO-BP neural network as EPmaxAnd expected prediction convergence error εE；
B6, inputting the sample input training data into the MPSO-BP neural network, training by taking the output sample output training data as a target until the training times reach the set maximum training times EPmaxOr at the time of trainingIs predicted by the error value epsilonpLess than a set desired prediction error value epsilonEAnd finishing the training of the MPSO-BP neural network.
Further, the determination in the step S3 is a combined prediction matrix W in the trained MPSO-BP neural networkBPAnd determining a combined prediction matrix W in the trained gray model GM (1,1)GMThe method comprises the following steps:
c1, when the training of the MPSO-BP neural network is completed, determining the error of the ith output point of the jth sample input training data as:
in the formula,inputting the predicted solar photovoltaic power generation output by the ith output point of training data for the jth sample in the MPSO-BP neural network;
kijinputting historical meteorological data corresponding to an ith output point of training data for a jth sample input into the MPSO-BP neural network;
yreal(kij) Inputting actual solar photovoltaic power generation amount historical data corresponding to the ith output point of training data for the jth sample;
meanwhile, when the training of the gray model GM (1,1) is completed, the error of the ith output point of the jth sample input training data is determined as:
in the formula,is the j-th in the gray model GM (1,1)Inputting the predicted solar photovoltaic power generation output by the ith output point of the training data by each sample;
kijinputting historical meteorological data corresponding to the ith output point of the training data for the jth sample input into the gray model GM (1, 1);
c2, according to the error of the output point corresponding to each sample input training data, obtaining an error matrix in the MPSO-BP neural network as follows:
in the formula, Et BPIs an error matrix in the neural network;
m is the number of output points;
meanwhile, according to the error of the output point corresponding to each sample input training data, the error matrix in the gray model GM (1,1) is obtained as follows:
c3, summing the error of each output point in the error matrix to obtain a prediction error matrix in the MPSO-BP neural network, wherein the prediction error matrix is as follows:
in the formula, a is an a-th training error sample;
meanwhile, summing the error of each output point corresponding to the output of the neural network in the error matrix to obtain a prediction error matrix in a gray model GM (1,1) as follows:
c4, respectively determining the weight W of the prediction error matrix of the MPSO-BP neural network according to the prediction error matrix in the MPSO-BP neural network and the prediction error matrix in the gray model GM (1,1)BP kAnd the weight W of the prediction error matrix of the gray model GM (1,1)GM k：
Wherein, the weight of the prediction error matrix of the MPSO-BP neural network is as follows:
the weight of the prediction error matrix of the gray model GM (1,1) is:
c5, respectively determining a combined prediction matrix W in the trained MPSO-BP neural network according to the weight of the prediction error matrix of the MPSO-BP neural network and the weight of the prediction error matrix of the gray model GM (1,1)BPAnd a combined prediction matrix W in a trained gray model GM (1,1)GM；
Wherein the combined prediction matrix W in the trained MPSO-BP neural networkBPComprises the following steps:
combined prediction matrix W in trained gray model GM (1,1)GMComprises the following steps:
the invention has the beneficial effects that:
1. the data are classified by KNN, so that higher accuracy is ensured in different weather data, and higher accuracy is also ensured even in the case of few samples.
2. The method adopts the error value based on each output point as the calculation parameter of the combined prediction weight of the corresponding point, has higher precision compared with the traditional method for unifying the combined weights of all the output points, and is more suitable for the actual situation.
3. The invention adopts the highest air temperature, the lowest air temperature, the temperature data every three hours, the difference value with the highest temperature of the previous day, the difference value with the low temperature of the previous day and the numerical ultraviolet intensity as the predicted input parameters, thereby improving the accuracy of the predicted power generation amount.
Drawings
FIG. 1 is a flow chart of a solar photovoltaic power generation amount prediction method based on classification and error combination prediction in the invention.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
As shown in fig. 1, the method for predicting solar photovoltaic power generation amount based on classification and error combination prediction comprises the following steps:
s1, acquiring meteorological data of a solar photovoltaic power generation amount prediction day from a meteorological station;
wherein the meteorological data comprises a maximum air temperature value, a minimum air temperature value, a temperature value every three hours, a difference value between the maximum temperature and the maximum temperature of the previous day, a difference value between the minimum temperature and the minimum temperature of the previous day, relative humidity and digitized ultraviolet intensity.
S2, determining the weather type in the season to which the weather data belongs, inputting the weather data of the predicted day into the trained MPSO-BP neural network corresponding to the weather type, and obtaining the first solar power generation output time sequence
Simultaneously inputting weather data of the predicted day into a trained gray model GM (1,1) corresponding to the weather type to obtain a second solar power generation output time sequence
The seasons to which the meteorological data in the above step S2 belong include spring, summer, fall and winter; each season comprises three weather types of sunny days, cloudy days and rainy days, the three weather types are taken as three typical weather types, and for weather data of atypical weather (such as weather types of cloudy days, rain shower and the like) in different seasons, the distance between the weather data and the typical weather type can be calculated by adopting a K-proximity algorithm (KNN), the weather data is classified into the typical weather type with the nearest distance, and the atypical weather is classified into the typical weather. The KNN algorithm can be used for realizing more accurate classification even under fewer samples.
And a corresponding trained MPSO-BP neural network and a trained gray model GM (1,1) are arranged under each weather type in each season.
S3, outputting the first solar energy power generation amount to a time sequenceWith a corresponding combined prediction matrix W in the trained MPSO-BP neural networkBPMultiplying to obtain a first solar power generation prediction quantity YBP；
Simultaneously outputting the second solar power generation output time seriesWith the combined prediction matrix W in the corresponding trained gray model GM (1,1)GMMultiplying to obtain a second solar power generation prediction quantity YGM；
Wherein the solar power generation prediction quantity Y corresponding to the MPSO-BP neural networkBPComprises the following steps:
solar power generation prediction amount Y corresponding to gray model GM (1,1)GMComprises the following steps:
s4, measuring the first solar power generation prediction quantity YBPAnd a second solar power generation prediction amount YGMAdding to obtain the predicted power generation amount Y of the predicted day of the solar photovoltaic power generation amountP。
Wherein, the predicted power generation amount Y of the solar photovoltaic power generation amount predicted dayPComprises the following steps:
the gray model GM (1,1) in step S2 is:
in the formula, y(1)(ki+1j) The accumulated sequence value of the (i + 1) th output point of the j sample obtained by prediction is represented;
y(1)(kij) An accumulated sequence value representing the ith output point of the jth sample;
m is the number of output points in the sample;
u and a are parameters to be solved by the model;
u and a are undetermined parameters determined from the data input into the grey model;
the method for training the gray model GM (1,1) corresponding to one weather type in one season in step S2 specifically includes:
a1, acquiring historical meteorological data of three weather types in different seasons from a meteorological station;
a2, classifying historical meteorological data under the same weather type in the same season;
a3, acquiring actual solar photovoltaic power generation amount historical data in a corresponding date according to date data in similar historical meteorological data, and inputting the actual solar photovoltaic power generation amount historical data serving as a training sample into a gray model GM (1, 1);
a4, calculating the accumulation sequence y of the gray model according to the data of the first j multiplied by m + i points of the training sample(1)And establishing a corresponding calculation matrix;
a5, calculating u and a in the gray model by the least square method according to the calculation matrix and substituting the calculated u and a into the accumulation sequence y(1)In (b) to obtain y(1)(ki+1j) And finishing the training of the gray model GM (1, 1).
In the above step A5, y is obtained(1)(ki+1j) Then, the gray model is:
let y(1)(k11)＝y(k11) And obtaining the predicted value of each historical data point of the training sample.
In the step S2, the method for training the MPSO-BP neural network corresponding to one weather type in one season specifically includes:
b1, acquiring historical meteorological data of three weather types in different seasons from a meteorological station;
b2, classifying the historical meteorological data under the same weather type in the same season;
b3, acquiring historical data of actual solar photovoltaic power generation amount in corresponding date according to date data in similar historical meteorological data;
b4, inputting historical meteorological data as sample input training data, and outputting solar photovoltaic power generation amount as sample output training data every half an hour in actual solar photovoltaic power generation amount historical data;
b5, setting the maximum training times of the MPSO-BP neural network as EPmaxAnd expected prediction convergence error εE；
B6, inputting the sample input training data into the MPSO-BP neural network, training by taking the output sample output training data as a target until the training times reach the set maximum training times EPmaxOr prediction error value epsilon during trainingpLess than a set desired prediction error value epsilonEWhen the MPSO-BP neural network is trained, the training of the MPSO-BP neural network is completed;
in the above step B6, the convergence error of the MPSO-BP neural network is set to be epsilonBP＝0.5×εE，
When a group of samples are input into training data and MPSO-BP neural network outputs corresponding data, a prediction convergence error value epsilon is providedpAnd is andwherein,the predicted power generation amount is predicted according to the combination of the gray model GM (1,1) and the MPSO-BP neural network, YrealInputting actual solar photovoltaic power generation amount historical data corresponding to training data for a sample when epsilonp≤εEWhen the MPSO-BP neural network prediction model is converged, even if the MPSO-BP neural network does not meet the convergence error at the moment, the MPSO-BP neural network does not continue to learn; otherwise, the neural network continues to input the sample input training data until the training times reach the set maximum training times EPmaxOr prediction error value epsilon during trainingPLess than a set desired prediction error value epsilonEAnd finishing the training of the MPSO-BP neural network.
The combined prediction matrix W in the trained MPSO-BP neural network is determined in the step S3BPAnd determining a combined prediction matrix W in the trained gray model GM (1,1)GMThe method comprises the following steps:
c1, when the training of the MPSO-BP neural network is completed, determining the error of the ith output point of the jth sample input training data as:
in the formula,inputting the predicted solar photovoltaic power generation output by the ith output point of training data for the jth sample in the MPSO-BP neural network;
kijinputting historical meteorological data corresponding to an ith output point of training data for a jth sample input into the MPSO-BP neural network;
yreal(kij) Inputting actual solar photovoltaic power generation amount historical data corresponding to the ith output point of training data for the jth sample;
meanwhile, when the training of the gray model GM (1,1) is completed, the error of the ith output point of the jth sample input training data is determined as:
in the formula,inputting the predicted solar photovoltaic power generation output by the ith output point of training data for the jth sample in the gray model GM (1, 1);
kijinputting historical meteorological data corresponding to the ith output point of the training data for the jth sample input into the gray model GM (1, 1);
c2, according to the error of the output point corresponding to each sample input training data, obtaining an error matrix in the MPSO-BP neural network as follows:
in the formula, Et BPIs an error matrix in the neural network;
m is the number of output points;
meanwhile, according to the error of the output point corresponding to each sample input training data, the error matrix in the gray model GM (1,1) is obtained as follows:
c3, summing the error of each output point in the error matrix to obtain a prediction error matrix in the MPSO-BP neural network, wherein the prediction error matrix is as follows:
in the formula, a is an a-th training error sample;
meanwhile, summing the error of each output point corresponding to the output of the neural network in the error matrix to obtain a prediction error matrix in a gray model GM (1,1) as follows:
c4, respectively determining the weight W of the prediction error matrix of the MPSO-BP neural network according to the prediction error matrix in the MPSO-BP neural network and the prediction error matrix in the gray model GM (1,1)BP kAnd the weight W of the prediction error matrix of the gray model GM (1,1)GM k：
Wherein, the weight of the prediction error matrix of the MPSO-BP neural network is as follows:
the weight of the prediction error matrix of the gray model GM (1,1) is:
c5, respectively determining a combined prediction matrix W in the trained MPSO-BP neural network according to the weight of the prediction error matrix of the MPSO-BP neural network and the weight of the prediction error matrix of the gray model GM (1,1)BPAnd a combined prediction matrix W in a trained gray model GM (1,1)GM；
Wherein the combined prediction matrix W in the trained MPSO-BP neural networkBPComprises the following steps:
combined prediction matrix W in trained gray model GM (1,1)GMComprises the following steps:
the invention has the beneficial effects that:
1. the data are classified by KNN, so that higher accuracy is ensured in different weather data, and higher accuracy is also ensured even in the case of few samples.
2. The method adopts the error value based on each output point as the calculation parameter of the combined prediction weight of the corresponding point, has higher precision compared with the traditional method for unifying the combined weights of all the output points, and is more suitable for the actual situation.
3. The invention adopts the highest air temperature, the lowest air temperature, the temperature data every three hours, the difference value with the highest temperature of the previous day, the difference value with the low temperature of the previous day and the numerical ultraviolet intensity as the predicted input parameters, thereby improving the accuracy of the predicted power generation amount.
Claims (7)
1. The solar photovoltaic power generation capacity prediction method based on classification and error combination prediction is characterized by comprising the following steps of:
s1, acquiring meteorological data of a solar photovoltaic power generation amount prediction day from a meteorological station;
s2, determining the weather type in the season to which the weather data belongs, inputting the weather data of the predicted day into the trained MPSO-BP neural network corresponding to the weather type, and obtaining the first solar power generation output time sequence
Simultaneously inputting weather data of the predicted day into a trained gray model GM (1,1) corresponding to the weather type to obtain a second solar power generation output time sequence
S3, outputting the first solar energy power generation amount to a time sequenceWith a corresponding combined prediction matrix W in the trained MPSO-BP neural networkBPMultiplying to obtain a first solar power generation prediction quantity YBP；
Simultaneously outputting the second solar power generation output time seriesWith the combined prediction matrix W in the corresponding trained gray model GM (1,1)GMMultiplying to obtain a second solar power generation prediction quantity YGM；
S4, measuring the first solar power generation prediction quantity YBPAnd a second solar power generation prediction amount YGMAdding to obtain the predicted power generation amount Y of the predicted day of the solar photovoltaic power generation amountP。
2. The method for solar photovoltaic power generation amount prediction based on classification and error combined prediction as claimed in claim 1, wherein the meteorological data in the step S1 includes a maximum air temperature value, a minimum air temperature value, a temperature value every three hours, a difference between the maximum temperature and the previous day maximum temperature, a difference between the minimum temperature and the previous day minimum temperature, a relative humidity and a digitized ultraviolet intensity.
3. The solar photovoltaic power generation amount prediction method based on classification and error combined prediction as claimed in claim 1, wherein the seasons to which the meteorological data in step S2 belongs include spring, summer, fall and winter; each season comprises three weather types of sunny days, cloudy days and rainy days;
and a corresponding trained MPSO-BP neural network and a trained gray model GM (1,1) are arranged under each weather type in each season.
4. The method for solar photovoltaic power generation amount prediction based on classification and error combined prediction according to claim 3, characterized in that the gray model GM (1,1) is:
in the formula, y(1)(ki+1 j) The accumulated sequence value of the (i + 1) th output point of the j sample obtained by prediction is represented;
y(1)(kij) An accumulated sequence value representing the ith output point of the jth sample;
m is the number of output points in the sample;
u, a model to be subjected to parameter calculation;
u and a are determined from the data input to the gray model.
5. The method for predicting solar photovoltaic power generation amount based on classification and error combined prediction as claimed in claim 4, wherein the method for training the corresponding gray model GM (1,1) in the step S2 is specifically as follows:
a1, acquiring historical meteorological data of three weather types in different seasons from a meteorological station;
a2, classifying historical meteorological data under the same weather type in the same season;
a3, acquiring actual solar photovoltaic power generation amount historical data in a corresponding date according to date data in similar historical meteorological data, and inputting the actual solar photovoltaic power generation amount historical data serving as a training sample into a gray model GM (1, 1);
a4, top j from training sampleData of x m + i points, calculating the accumulation sequence y of the gray model(1)And establishing a corresponding calculation matrix;
a5, calculating u and a in the gray model by the least square method according to the calculation matrix and substituting the calculated u and a into the accumulation sequence y(1)In (b) to obtain y(1)(ki+1 j) And finishing the training of the gray model GM (1, 1).
6. The method for predicting solar photovoltaic power generation amount based on classification and error combined prediction as claimed in claim 3, wherein in the step S2, the method for training the MPSO-BP neural network corresponding to a weather type is specifically as follows:
b1, acquiring historical meteorological data of three weather types in different seasons from a meteorological station;
b2, classifying the historical meteorological data under the same weather type in the same season;
b3, acquiring historical data of actual solar photovoltaic power generation amount in corresponding date according to date data in similar historical meteorological data;
b4, inputting historical meteorological data as sample input training data, and outputting solar photovoltaic power generation amount as sample output training data every half an hour in actual solar photovoltaic power generation amount historical data;
b5, setting the maximum training times of the MPSO-BP neural network as EPmaxAnd expected prediction convergence error εE；
B6, inputting the sample input training data into the MPSO-BP neural network, training by taking the output sample output training data as a target until the training times reach the set maximum training times EPmaxOr prediction error value epsilon during trainingpLess than a set desired prediction error value epsilonEAnd finishing the training of the MPSO-BP neural network.
7. The method for solar photovoltaic power generation prediction based on classification and error combined prediction as claimed in claim 6, wherein the determination of the trained MPSO-BP neural network in the step S3Combined prediction matrix W in a networkBPAnd determining a combined prediction matrix W in the trained gray model GM (1,1)CMThe method comprises the following steps:
c1, when the training of the MPSO-BP neural network is completed, determining the error of the ith output point of the jth sample input training data as:
in the formula,inputting the predicted solar photovoltaic power generation output by the ith output point of training data for the jth sample in the MPSO-BP neural network;
kijinputting historical meteorological data corresponding to an ith output point of training data for a jth sample input into the MPSO-BP neural network;
yreal(kij) Inputting actual solar photovoltaic power generation amount historical data corresponding to the ith output point of training data for the jth sample;
meanwhile, when the training of the gray model GM (1,1) is completed, the error of the ith output point of the jth sample input training data is determined as:
in the formula,inputting the predicted solar photovoltaic power generation output by the ith output point of training data for the jth sample in the gray model GM (1, 1);
kijinputting historical meteorological data corresponding to the ith output point of the training data for the jth sample input into the gray model GM (1, 1);
c2, according to the error of the output point corresponding to each sample input training data, obtaining an error matrix in the MPSO-BP neural network as follows:
in the formula, Et BPIs an error matrix in the neural network;
m is the number of output points;
meanwhile, according to the error of the output point corresponding to each sample input training data, the error matrix in the gray model GM (1,1) is obtained as follows:
c3, summing the error of each output point in the error matrix to obtain a prediction error matrix in the MPSO-BP neural network, wherein the prediction error matrix is as follows:
in the formula, a is an a-th training error sample;
meanwhile, summing the error of each output point corresponding to the output of the neural network in the error matrix to obtain a prediction error matrix in a gray model GM (1,1) as follows:
c4, respectively determining the weight W of the prediction error matrix of the MPSO-BP neural network according to the prediction error matrix in the MPSO-BP neural network and the prediction error matrix in the gray model GM (1,1)BP kAnd the weight W of the prediction error matrix of the gray model GM (1,1)GM k：
Wherein, the weight of the prediction error matrix of the MPSO-BP neural network is as follows:
the weight of the prediction error matrix of the gray model GM (1,1) is:
c5, respectively determining a combined prediction matrix W in the trained MPSO-BP neural network according to the weight of the prediction error matrix of the MPSO-BP neural network and the weight of the prediction error matrix of the gray model GM (1,1)BPAnd a combined prediction matrix W in a trained gray model GM (1,1)GM；
Wherein the combined prediction matrix W in the trained MPSO-BP neural networkBPComprises the following steps:
combined prediction matrix W in trained gray model GM (1,1)GMComprises the following steps:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811570233.XA CN109636054A (en) | 2018-12-21 | 2018-12-21 | Solar energy power generating amount prediction technique based on classification and error combination prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811570233.XA CN109636054A (en) | 2018-12-21 | 2018-12-21 | Solar energy power generating amount prediction technique based on classification and error combination prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109636054A true CN109636054A (en) | 2019-04-16 |
Family
ID=66076313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811570233.XA Pending CN109636054A (en) | 2018-12-21 | 2018-12-21 | Solar energy power generating amount prediction technique based on classification and error combination prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109636054A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598896A (en) * | 2019-07-26 | 2019-12-20 | 陕西省水利电力勘测设计研究院 | Photovoltaic power prediction method based on prediction error correction |
| CN111178450A (en) * | 2019-12-31 | 2020-05-19 | 上海三一重机股份有限公司 | Method and device for evaluating state of welding seam |
| CN111798055A (en) * | 2020-07-06 | 2020-10-20 | 国网山东省电力公司电力科学研究院 | Variable weight combined photovoltaic output prediction method based on grey correlation degree |
| CN111814826A (en) * | 2020-06-08 | 2020-10-23 | 武汉理工大学 | Rapid detection and rating method for residual energy of retired power battery |
| CN111931981A (en) * | 2020-07-06 | 2020-11-13 | 安徽天尚清洁能源科技有限公司 | Photovoltaic power generation ultra-short-term prediction method based on machine learning multi-model combination |
| CN114048896A (en) * | 2021-10-27 | 2022-02-15 | 国核自仪系统工程有限公司 | Method, system, equipment and medium for predicting photovoltaic power generation data |
| JP2022550619A (en) * | 2019-11-14 | 2022-12-02 | エンヴィジョン デジタル インターナショナル ピーティーイー．エルティーディー． | Methods for Processing Solar Radiation Predictions, Methods for Training Stacked Generalized Models, and Apparatuses Therefor |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390199A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power generation capacity/power prediction device |
| CN104021427A (en) * | 2014-06-10 | 2014-09-03 | 上海电力学院 | Method for predicting daily generating capacity of grid-connected photovoltaic power station based on factor analysis |
| CN104463349A (en) * | 2014-11-11 | 2015-03-25 | 河海大学 | Photovoltaic generated power prediction method based on multi-period comprehensive similar days |
| CN104820877A (en) * | 2015-05-21 | 2015-08-05 | 河海大学 | Photovoltaic system generation power prediction method based on cloud adaptive PSO-SNN |
| CN104978611A (en) * | 2015-07-06 | 2015-10-14 | 东南大学 | Neural network photovoltaic power generation output prediction method based on grey correlation analysis |
| CN104992248A (en) * | 2015-07-07 | 2015-10-21 | 中山大学 | Microgrid photovoltaic power station generating capacity combined forecasting method |
| CN105160423A (en) * | 2015-09-14 | 2015-12-16 | 河海大学常州校区 | Photovoltaic power generation prediction method based on Markov residual error correction |
| CN107358318A (en) * | 2017-06-29 | 2017-11-17 | 上海电力学院 | Based on GM（1,1）The urban power consumption Forecasting Methodology of model and Grey Markov chain predicting model |
| CN107563573A (en) * | 2017-09-29 | 2018-01-09 | 南京航空航天大学 | A kind of Forecasting Methodology of the solar power generation amount based on adaptive learning mixed model |
-
2018
- 2018-12-21 CN CN201811570233.XA patent/CN109636054A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390199A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power generation capacity/power prediction device |
| CN104021427A (en) * | 2014-06-10 | 2014-09-03 | 上海电力学院 | Method for predicting daily generating capacity of grid-connected photovoltaic power station based on factor analysis |
| CN104463349A (en) * | 2014-11-11 | 2015-03-25 | 河海大学 | Photovoltaic generated power prediction method based on multi-period comprehensive similar days |
| CN104820877A (en) * | 2015-05-21 | 2015-08-05 | 河海大学 | Photovoltaic system generation power prediction method based on cloud adaptive PSO-SNN |
| CN104978611A (en) * | 2015-07-06 | 2015-10-14 | 东南大学 | Neural network photovoltaic power generation output prediction method based on grey correlation analysis |
| CN104992248A (en) * | 2015-07-07 | 2015-10-21 | 中山大学 | Microgrid photovoltaic power station generating capacity combined forecasting method |
| CN105160423A (en) * | 2015-09-14 | 2015-12-16 | 河海大学常州校区 | Photovoltaic power generation prediction method based on Markov residual error correction |
| CN107358318A (en) * | 2017-06-29 | 2017-11-17 | 上海电力学院 | Based on GM（1,1）The urban power consumption Forecasting Methodology of model and Grey Markov chain predicting model |
| CN107563573A (en) * | 2017-09-29 | 2018-01-09 | 南京航空航天大学 | A kind of Forecasting Methodology of the solar power generation amount based on adaptive learning mixed model |
Non-Patent Citations (3)
| Title |
|---|
| 刘静宜: "基于组合模型的光伏电站发电功率短期预测方法研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
| 孙佳等: "基于改进灰色模型与BP神经网络模型组合的风力发电量预测研究", 《水电能源科学》 * |
| 师彪等: "改进粒子群—BP神经网络模型的短期电力负荷预测", 《计算机应用》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598896A (en) * | 2019-07-26 | 2019-12-20 | 陕西省水利电力勘测设计研究院 | Photovoltaic power prediction method based on prediction error correction |
| JP2022550619A (en) * | 2019-11-14 | 2022-12-02 | エンヴィジョン デジタル インターナショナル ピーティーイー．エルティーディー． | Methods for Processing Solar Radiation Predictions, Methods for Training Stacked Generalized Models, and Apparatuses Therefor |
| JP7369868B2 (en) | 2019-11-14 | 2023-10-26 | エンヴィジョン デジタル インターナショナル ピーティーイー．エルティーディー． | Methods for processing solar radiation prediction, methods for training stacked generalized models, and apparatus thereof |
| CN111178450A (en) * | 2019-12-31 | 2020-05-19 | 上海三一重机股份有限公司 | Method and device for evaluating state of welding seam |
| CN111178450B (en) * | 2019-12-31 | 2023-07-14 | 上海三一重机股份有限公司 | Weld joint state evaluation method and device |
| CN111814826A (en) * | 2020-06-08 | 2020-10-23 | 武汉理工大学 | Rapid detection and rating method for residual energy of retired power battery |
| CN111814826B (en) * | 2020-06-08 | 2022-06-03 | 武汉理工大学 | Rapid detection and rating method for residual energy of retired power battery |
| CN111798055A (en) * | 2020-07-06 | 2020-10-20 | 国网山东省电力公司电力科学研究院 | Variable weight combined photovoltaic output prediction method based on grey correlation degree |
| CN111931981A (en) * | 2020-07-06 | 2020-11-13 | 安徽天尚清洁能源科技有限公司 | Photovoltaic power generation ultra-short-term prediction method based on machine learning multi-model combination |
| CN114048896A (en) * | 2021-10-27 | 2022-02-15 | 国核自仪系统工程有限公司 | Method, system, equipment and medium for predicting photovoltaic power generation data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Photovoltaic power forecasting with a hybrid deep learning approach | |
| CN109636054A (en) | Solar energy power generating amount prediction technique based on classification and error combination prediction | |
| Liu et al. | Forecasting power output of photovoltaic system using a BP network method | |
| CN110880789B (en) | Economic dispatching method for wind power and photovoltaic combined power generation system | |
| CN112257941B (en) | Photovoltaic power station short-term power prediction method based on improved Bi-LSTM | |
| CN110729764B (en) | Optimal scheduling method for photovoltaic power generation system | |
| CN112149879B (en) | New energy medium-and-long-term electric quantity prediction method considering macroscopic volatility classification | |
| CN109858673A (en) | A kind of photovoltaic generating system power forecasting method | |
| CN109165774A (en) | A kind of short-term photovoltaic power prediction technique | |
| Lu et al. | A hybrid approach for day-ahead forecast of PV power generation | |
| CN104573879A (en) | Photovoltaic power station output predicting method based on optimal similar day set | |
| CN106295899B (en) | Wind power probability density Forecasting Methodology based on genetic algorithm Yu supporting vector quantile estimate | |
| CN114792156B (en) | Photovoltaic output power prediction method and system based on curve characteristic index clustering | |
| CN110942205B (en) | Short-term photovoltaic power generation power prediction method based on HIMVO-SVM | |
| Yadav et al. | A novel GA-ANFIS hybrid model for short-term solar PV power forecasting in Indian electricity market | |
| CN104008432A (en) | Micro-grid short-term load forecasting method based on EMD-KELM-EKF | |
| CN108280545A (en) | A kind of photovoltaic power prediction technique based on K mean cluster neural network | |
| CN105260800A (en) | Photovoltaic module temperature prediction method and device | |
| CN105160423A (en) | Photovoltaic power generation prediction method based on Markov residual error correction | |
| CN110866633B (en) | Micro-grid ultra-short-term load prediction method based on SVR support vector regression | |
| CN110334870B (en) | Photovoltaic power station short-term power prediction method based on gated cyclic unit network | |
| Kolhe et al. | GA-ANN for short-term wind energy prediction | |
| CN112001537B (en) | Short-term wind power prediction method based on gray model and support vector machine | |
| CN111626473A (en) | Two-stage photovoltaic power prediction method considering error correction | |
| CN112052913A (en) | Distributed photovoltaic power station power data virtual acquisition method |
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 |
Application publication date: 20190416 |
|
| RJ01 | Rejection of invention patent application after publication |