CN116307049A - Photovoltaic power generation power prediction method, system, terminal and medium - Google Patents
Photovoltaic power generation power prediction method, system, terminal and medium Download PDFInfo
- Publication number
- CN116307049A CN116307049A CN202211658643.6A CN202211658643A CN116307049A CN 116307049 A CN116307049 A CN 116307049A CN 202211658643 A CN202211658643 A CN 202211658643A CN 116307049 A CN116307049 A CN 116307049A
- Authority
- CN
- China
- Prior art keywords
- time sequence
- data
- prediction
- long
- short
- 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
- 238000010248 power generation Methods 0.000 title claims abstract description 128
- 238000000034 method Methods 0.000 title claims abstract description 64
- 230000007774 longterm Effects 0.000 claims description 72
- 238000004458 analytical method Methods 0.000 claims description 50
- 230000000737 periodic effect Effects 0.000 claims description 34
- 230000015654 memory Effects 0.000 claims description 25
- 238000012937 correction Methods 0.000 claims description 24
- 238000010219 correlation analysis Methods 0.000 claims description 22
- 230000000875 corresponding effect Effects 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 13
- 230000002596 correlated effect Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 13
- 230000008034 disappearance Effects 0.000 abstract description 4
- 230000005855 radiation Effects 0.000 description 15
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 3
- 230000000306 recurrent effect Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 235000019800 disodium phosphate Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 239000000443 aerosol Substances 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004549 pulsed laser deposition Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a photovoltaic power generation power prediction method, a system, a terminal and a medium, which solve the problems that the correlation of short-term time sequence can be captured by the traditional photovoltaic power generation power prediction algorithm, but GRU and LSTM cannot capture longer-term time sequence characteristics in practice due to the disappearance of gradient. Experimental results show that MAE, RMSE, R of LSTC is 0.8610%,05288% and 0.7601% respectively, which are superior to other algorithms, in 24h prediction scenes aiming at photovoltaic power generation prediction. The invention provides an effective solution for photovoltaic power generation power prediction, which has important significance in the field of photovoltaic power generation power prediction.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation power prediction, in particular to a photovoltaic power generation power prediction method, a photovoltaic power generation power prediction system, a terminal and a medium.
Background
With the pushing construction of a novel power system mainly comprising new energy, photovoltaic power generation by utilizing solar energy becomes an important branch in the new energy. In recent years, the photovoltaic industry has rapidly developed, and according to the data of the International Energy Agency (IEA), the growth speed of the global photovoltaic installed amount is up to 49%, and the global photovoltaic power generation is expected to reach 16% of the total power generation amount in 2050. After the photovoltaic power station is integrated into the energy internet on a large scale, how to accurately predict the photovoltaic power generation power and reasonably schedule the power grid becomes a problem to be optimized urgently, so that the improvement of the prediction accuracy of the photovoltaic power generation power is significant for improving the operation efficiency of the power station and maintaining the stability of the power grid.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, an object of the present invention is to provide a photovoltaic power generation power prediction method, system, terminal and medium for solving the technical problem that the photovoltaic power generation power prediction accuracy is not high enough.
To achieve the above and other related objects, a first aspect of the present invention provides a photovoltaic power generation power prediction method, including: acquiring photovoltaic power generation power data in a historical period, performing periodic analysis and correlation analysis on the photovoltaic power generation power data, and obtaining short-term time sequence related data, long-term time sequence related data and non-time sequence related data according to a periodic analysis result and a correlation analysis result; performing long-short time prediction analysis on the short-term time sequence related data and the long-term time sequence related data to respectively extract short-term time sequence characteristic prediction data and long-term time sequence characteristic prediction data of the next moment; and inputting the short-term time sequence characteristic prediction data, the long-term time sequence characteristic prediction data and the non-time sequence related data into a prediction result correction module for correction so as to extract the influence of the long-term time sequence characteristic, the short-term time sequence characteristic and the non-time sequence characteristic on the photovoltaic power generation power.
In some embodiments of the first aspect of the present invention, the process of acquiring and periodically analyzing photovoltaic power generation power data over a historical period of time includes: and decomposing the curves of the photovoltaic power generation power data and the influence factor data thereof in the historical period by utilizing Fourier transformation so as to perform periodic analysis, thereby obtaining the fluctuation periods of different periodic curves.
In some embodiments of the first aspect of the invention, the fourier transform comprises:
wherein X (k) represents a Fourier series; x (n) represents a fourier series;
representing a complex function; k represents an x coordinate on the frequency domain; n represents a period.
In some embodiments of the first aspect of the present invention, the process of acquiring and correlating photovoltaic power data over a historical period of time includes: and analyzing the correlation between the photovoltaic power generation power and a plurality of weather factors by using the Pearson correlation coefficient.
In some embodiments of the first aspect of the present invention, the obtaining short-term time-series related data, long-term time-series related data, and non-time-series related data according to the periodic analysis result and the correlation analysis result includes: selecting a first group of weather influence factors positively correlated with the correlation of the photovoltaic power generation power, and selecting a second group of weather influence factors periodically correlated with the periodic analysis result of the photovoltaic power generation power; extracting intersections of the first group of weather influence factors and the second group of weather influence factors, reading historical data of each weather influence factor in the intersections, and processing the historical data into corresponding short-term time sequence related data and long-term time sequence related data; other weather-influencing factors outside the intersection are regarded as non-time-series related data.
In some embodiments of the first aspect of the present invention, performing long-short-term predictive analysis on the short-term timing related data and the long-term timing related data includes performing predictive analysis on the short-term timing related data using an LSTM network to obtain corresponding short-term timing characteristic predictive data.
In some embodiments of the first aspect of the present invention, performing long-short-term predictive analysis on the short-term and long-term timing related data comprises: and carrying out predictive analysis on the long-term time sequence related data by constructing a skip-GRU network to obtain corresponding long-term time sequence characteristic predictive data.
In some embodiments of the first aspect of the present invention, the performing prediction analysis on the long-term time series related data by constructing a skip-GRU network to obtain corresponding long-term time series characteristic prediction data includes:
r t ＝σ(W r [h t-p ,x t ]+b r )；
z t ＝σ(W z [h t-p ,x t ]+b z )；
wherein x is t Input data representing time t, r t Indicating reset gate, z t Representing the update gate, p is the sampling interval, h t-p Is the hidden state p times ago,
is a candidate state at this point in time, h t Is the output of this instant. W (W) r 、W z 、/>
A weight matrix respectively representing a reset gate, an update gate and a candidate state; b r 、b z The deviations of the reset gate and the update gate are indicated, respectively.
In some embodiments of the first aspect of the present invention, the short-term timing characteristic prediction data, the long-term timing characteristic prediction data, and the non-timing related data are received using an MLP network, and the prediction data is modified.
To achieve the above and other related objects, a second aspect of the present invention provides a photovoltaic power generation power prediction system, comprising: the variable selection module is used for acquiring photovoltaic power generation power data in a historical period, carrying out periodic analysis and correlation analysis on the photovoltaic power generation power data, and obtaining short-term time sequence related data, long-term time sequence related data and non-time sequence related data according to a periodic analysis result and a correlation analysis result; the long-period and short-period time sequence prediction module is used for acquiring photovoltaic power generation power data in a history period and periodically analyzing the photovoltaic power generation power data, and comprises the following steps: decomposing curves of photovoltaic power generation power data and influence factor data thereof in a historical period by utilizing Fourier transformation so as to perform periodic analysis, so as to obtain fluctuation periods of different periodic curves; and the prediction result correction module is used for inputting the short-term time sequence characteristic prediction data, the long-term time sequence characteristic prediction data and the non-time sequence related data into the prediction result correction module for correction so as to extract the influences of the long-term time sequence characteristic, the short-term time sequence characteristic and the non-time sequence characteristic on the photovoltaic power generation power.
To achieve the above and other related objects, a third aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the photovoltaic power generation power prediction method.
To achieve the above and other related objects, a fourth aspect of the present invention provides an electronic terminal, comprising: a processor and a memory; the memory is used for storing a computer program, and the processor is used for executing the computer program stored in the memory so as to enable the terminal to execute the photovoltaic power generation power prediction method.
As described above, the photovoltaic power generation power prediction method, system, terminal and medium of the present invention have the following beneficial effects: the invention solves the problems that the correlation of short time sequence can be captured by the traditional photovoltaic power generation power prediction algorithm, but GRU and LSTM are in practice due to the disappearance of gradientThe invention provides a LSTC algorithm for photovoltaic power generation power prediction, which is used for carrying out variable selection on historical data through a variable selection module, and generating short-term time sequence related data, long-term time sequence related data and non-time sequence related data after the variable selection. Experimental results show that for photovoltaic power generation power prediction, under 24h prediction scene, LSTC MAE, RMSE, R 2 0.8610%,05288%,0.7601%, respectively, are superior to other algorithms. The invention provides an effective solution for photovoltaic power generation power prediction, which has important significance in the field of photovoltaic power generation power prediction.
Drawings
Fig. 1 is a schematic flow chart of a photovoltaic power generation power prediction method according to an embodiment of the invention.
Fig. 2 is a schematic structural diagram of a photovoltaic power prediction system according to an embodiment of the invention.
Fig. 3 is a schematic diagram of a network structure of a photovoltaic power generation power prediction system according to an embodiment of the invention.
Fig. 4 is a schematic structural diagram of an electronic terminal according to an embodiment of the invention.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.
In the following description, reference is made to the accompanying drawings, which illustrate several embodiments of the invention. It is to be understood that other embodiments may be utilized and that mechanical, structural, electrical, and operational changes may be made without departing from the spirit and scope of the present invention. The following detailed description is not to be taken in a limiting sense, and the scope of embodiments of the present invention is defined only by the claims of the issued patent. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. Spatially relative terms, such as "upper," "lower," "left," "right," "lower," "upper," and the like, may be used herein to facilitate a description of one element or feature as illustrated in the figures as being related to another element or feature.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," "held," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
Furthermore, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms "comprises," "comprising," "includes," and/or "including" specify the presence of stated features, operations, elements, components, items, categories, and/or groups, but do not preclude the presence, presence or addition of one or more other features, operations, elements, components, items, categories, and/or groups. The terms "or" and/or "as used herein are to be construed as inclusive, or meaning any one or any combination. Thus, "A, B or C" or "A, B and/or C" means "any of the following: a, A is as follows; b, a step of preparing a composite material; c, performing operation; a and B; a and C; b and C; A. b and C). An exception to this definition will occur only when a combination of elements, functions or operations are in some way inherently mutually exclusive.
In order to solve the problems in the background art, the invention provides an LSTC algorithm for photovoltaic power generation power prediction, which aims at referring to the application conditions of LSTM and MLP models in the field of photovoltaic power generation power prediction and combining the bright points of an LSTnet model in time sequence data prediction, and provides a long-short time sequence correction network (Long and Short Temporal Correction networks, LSTC), wherein based on historical data of photovoltaic power generation power, a variable selection module is utilized to screen time sequence related weather variables, respectively process the weather variables into short-time sequence related data and long-time sequence related data, respectively conduct short-time sequence prediction and long-time sequence prediction through the LSTM and skip-GRU network, and transmit the prediction results and non-time sequence data into the MLP network together, so as to conduct prediction correction by utilizing excellent nonlinear fitting capacity of the weather variables.
The algorithm provided by the invention can simultaneously extract the long-term time sequence characteristic and the short-term time sequence characteristic in the photovoltaic power generation power and the influence factor historical data thereof, and can fully utilize the result which does not contain the time sequence characteristic, thereby improving the accuracy of the algorithm on the test set. The invention provides an effective solution to the practical problem of ultra-short-term and short-term prediction of the photovoltaic power generation power, and has important significance in the field of photovoltaic power generation power prediction.
In order to make the objects, technical solutions and advantages of the present invention more apparent, further detailed description of the technical solutions in the embodiments of the present invention will be given by the following examples with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Before explaining the present invention in further detail, terms and terminology involved in the embodiments of the present invention will be explained, and the terms and terminology involved in the embodiments of the present invention are applicable to the following explanation:
(1) Pearson correlation coefficient (Pearson Correlation Coefficient): for measuring the correlation between two variables, the value of which is between-1 and 1.
(2) LSTM network (Long Short-Term Memory): a time-loop neural network is specially designed for solving the long-term dependence problem of a common RNN (loop neural network), and all RNNs have a chained form of repeated neural network modules.
Embodiments of the present invention provide a photovoltaic power generation power prediction method, a system of the photovoltaic power generation power prediction method, and a storage medium storing an executable program for implementing the photovoltaic power generation power prediction method. With respect to implementation of the photovoltaic power generation power prediction method, an exemplary implementation scenario of photovoltaic power generation power prediction will be described in the embodiments of the present invention.
Fig. 1 is a schematic flow chart of a photovoltaic power generation power prediction method according to an embodiment of the present invention. The photovoltaic power generation power prediction method in the embodiment mainly comprises the following steps:
step S11: and acquiring photovoltaic power generation power data in a historical period, performing periodic analysis and correlation analysis on the photovoltaic power generation power data, and obtaining short-term time sequence related data, long-term time sequence related data and non-time sequence related data according to the periodic analysis result and the correlation analysis result.
In this embodiment, the process of acquiring photovoltaic power data in the history period and performing periodic analysis includes: and decomposing the curves of the photovoltaic power generation power data and the influence factor data thereof in the historical period by utilizing Fourier transformation so as to perform periodic analysis, thereby obtaining the fluctuation periods of different periodic curves.
It should be noted that the photovoltaic power generation power data often shows a strong timing characteristic, and has a certain periodicity in a long time range although the volatility is strong. Therefore, the embodiment of the invention selects the curves of the Fourier transform decomposition photovoltaic power generation power data and the influence factor data thereof for periodic analysis, aims at obtaining the fluctuation periods of different periodic curves, and provides a certain degree of reference for analyzing the photovoltaic power generation power prediction.
In this embodiment, the formula of the fourier transform is as follows:
wherein X (k) represents a Fourier series; x (n) represents a fourier series;
representing a complex function; k represents an x coordinate on the frequency domain; n represents a period.
In this embodiment, the process of acquiring photovoltaic power data in the history period and performing correlation analysis on the photovoltaic power data includes: and analyzing the correlation between the photovoltaic power generation power and a plurality of weather factors by using the Pearson correlation coefficient.
It should be noted that the photovoltaic power generation power has a correlation with a large number of weather factors. More specifically, solar radiation is affected by seasons and geographic positions, the season change and the daily change period are obvious, and physical and chemical conditions of the atmosphere such as cloud cover, humidity, temperature, aerosol concentration and the like can also affect the intensity of the solar radiation, so that the output of the photovoltaic power generation system has strong season change period and daily change period. In particular, the solar radiation intensity has strong correlation with the photovoltaic power generation, so that the embodiment of the invention utilizes the pearson correlation coefficient to perform correlation analysis, the pearson correlation coefficient can calculate the correlation degree of two groups of arbitrary data x and y, and the calculation formula is as follows:
wherein,,
representing the covariance of the two variables x and y; sigma (sigma) x Represents the standard deviation of variable x; sigma (sigma) y Represents the standard deviation of the variable y. It should be understood that covariance is an indicator reflecting the degree of correlation of two variables; covariance greater than 0 indicates positive correlation between the two, and less than 0 indicates negative correlation between the two.
After the periodic analysis result and the correlation analysis result are obtained after the calculation according to the calculation formulas (1) to (4), the photovoltaic power generation power data in the history period is processed into short-term time series related data, long-term time series related data and non-time series related data.
In some examples, the deriving short-term, long-term, and non-time-series correlated data from the periodic analysis results and the correlation analysis results includes: selecting a first group of weather influence factors positively correlated with the correlation of the photovoltaic power generation power, and selecting a second group of weather influence factors periodically correlated with the periodic analysis result of the photovoltaic power generation power; extracting intersections of the first group of weather influence factors and the second group of weather influence factors, reading historical data of each weather influence factor in the intersections, and processing the historical data into corresponding short-term time sequence related data and long-term time sequence related data; other weather-influencing factors outside the intersection are regarded as non-time-series related data.
For ease of understanding, the description will be given by taking data of a photovoltaic power plant in australia as an example: the variable selection module in the long and short time sequence correction network comprises two parts of correlation analysis and periodic analysis, and the results of the correlation analysis on the photovoltaic power generation power are shown in a table 1:
TABLE 1 correlation analysis results
As can be seen from table 1, the photovoltaic power generation power is positively correlated with the direct radiation intensity, the scattered radiation intensity, the temperature and the wind speed, is negatively correlated with the humidity, the wind direction and the rainfall, and the correlation is divided by taking 0.1 as a limit according to the numerical value, so that the direct radiation intensity has the maximum correlation with the photovoltaic power generation power, the scattered radiation intensity, the temperature, the humidity, the wind speed and other variables have certain correlation with the photovoltaic power generation power, the influence factors can have certain influence on the photovoltaic power generation power, the influence capability is gradually reduced, and the wind direction and the rainfall are negatively correlated with the photovoltaic power generation power, but the numerical value is too small, and the influence degree is limited.
The results of the photovoltaic power generation power periodicity analysis are shown in table 2:
TABLE 2 periodic analysis results
As can be seen from table 2, the periods of the photovoltaic power generation power, humidity, direct radiation intensity, scattered radiation intensity are all 24.03 hours, which is approximately one day, and the periods of wind speed, wind direction, rainfall are 0.17 hours, which can be regarded as no periodicity of these influencing factors; the period of the temperature is 8760 hours, namely the period of the temperature just accords with the change of the temperature all the year round, and the result basically accords with natural logic.
Further, five influencing factors of direct radiation intensity, scattered radiation intensity, temperature, humidity and wind speed can be screened out through correlation analysis; the three influencing factors of direct radiation intensity, scattered radiation intensity and humidity are screened out by periodical analysis, and finally, the time sequence related variables of the photovoltaic power generation power are obtained by screening by a variable selection module are as follows: direct radiation intensity, scattered radiation intensity, humidity. And meanwhile, the variable selection module processes the historical data of the three influence factors into short-term time sequence related data consisting of 288 continuous data points and long-term time sequence related data consisting of 30 data points at the same moment of the same day, transmits the short-term time sequence related data into the long-short time sequence prediction module for prediction, and the other influence factors are regarded as non-time sequence related data and transmitted into the prediction result correction module for result correction.
Step S12: and carrying out long-short time prediction analysis on the short-term time sequence related data and the long-term time sequence related data so as to respectively extract short-term time sequence characteristic prediction data and long-term time sequence characteristic prediction data of the next moment.
In this embodiment, performing long-short-term predictive analysis on the short-term time-series related data and the long-term time-series related data includes performing predictive analysis on the short-term time-series related data by using an LSTM network to obtain corresponding short-term time-series characteristic predictive data.
Specifically, the LSTM network receives and predicts short-term time sequence related data, and aims to extract short-term time sequence characteristics of the data, and a specific calculation formula is as follows:
i t ＝σ(W i ·[h t-1 ,x t ]+b i ) The method comprises the steps of carrying out a first treatment on the surface of the (equation 5)
f t ＝σ(W f ·[h t-1 ,x t ]+b f ) The method comprises the steps of carrying out a first treatment on the surface of the (equation 6)
o t ＝σ(W o ·[h t-1 ,x t ]+b o ) The method comprises the steps of carrying out a first treatment on the surface of the (equation 7)
h t ＝o t *tanh(c t ) The method comprises the steps of carrying out a first treatment on the surface of the (equation 10)
Wherein x is t Input data i representing time t t Representing the input gate, f t Indicating forgetful door o t Indicating the output gate, h t-1 Is the external state at the last moment in time,
is a candidate state, c t-1 Is the internal state of the last moment, c t Is the internal state at this point in time, h t Is the output of this instant. W (W) i 、W f 、W o 、W c The weight matrixes respectively represent an input gate, a forget gate, an output gate and candidate states; b i 、b f 、b o 、b c The deviations respectively representing the input gate, the forget gate, the output gate, and the candidate state are shown.
In this embodiment, performing long-short-term predictive analysis on the short-term timing related data and the long-term timing related data includes: and carrying out predictive analysis on the long-term time sequence related data by constructing a skip-GRU network to obtain corresponding long-term time sequence characteristic predictive data.
It should be noted that, to facilitate understanding of the skip-GRU network in the embodiments of the present invention by those skilled in the art, reference may be made to the skip-RNN network in the LSTnet model: traditional Recurrent Neural Networks (RNNs) perform well in sequence modeling tasks, but training RNNs over long sequences often suffer from problems such as slow inference speed, vanishing gradients or gradient explosions, and difficulty in capturing long-term dependencies; while Skip recurrent neural network models extend the existing RNN model by skipping state updates and shorten the effective size of the computational graph.
Specifically, skip RNN receives an input sequence x= (x) 1 ,…,x T ) Outputting a state sequence s=(s) from the received input sequence 1 ,…,s T ) The core difference between Skip RNN and normal RNN is a binary state update gate ut e {0,1}, where when ut=0, the state of RNN is updated, and when ut=1, the state of RNN is replicated for the previous time step, that is, no update occurs, and this process can be expressed as: s is(s) t ＝ut·S(s t-1 ,x t )+(1-ut)·s t-1 ；s t Sum s t-1 States of the recurrent neural network at time steps t and t-1, respectively, ut indicates whether the state is updated, S (S) t-1 ,x t ) Representing a status update procedure.
The skip-GRU network in the embodiment of the invention receives the long-term time sequence related data for prediction, aims at extracting the long-term time sequence characteristic prediction data of the data, and has the following specific calculation formula:
r t ＝σ(W r [h t-p ,x t ]+b r ) The method comprises the steps of carrying out a first treatment on the surface of the (equation 11)
z t ＝σ(W z [h t-p ,x t ]+b z ) The method comprises the steps of carrying out a first treatment on the surface of the (equation 12)
Wherein x is t Input data representing time t, r t Indicating reset gate, z t Representing the update gate, p is the sampling interval, h t-p Is the hidden state p times ago,
is a candidate state at this point in time, h t Is the output of this instant. W (W) r 、W z 、/>
A weight matrix respectively representing a reset gate, an update gate and a candidate state; b r 、b z The deviations of the reset gate and the update gate are indicated, respectively.
Step S13: and inputting the short-term time sequence characteristic prediction data, the long-term time sequence characteristic prediction data and the non-time sequence related data into a prediction result correction module for correction so as to extract the influence of the long-term time sequence characteristic, the short-term time sequence characteristic and the non-time sequence characteristic on the photovoltaic power generation power.
In this embodiment, the MLP network is utilized to receive the short-term timing characteristic prediction data, the long-term timing characteristic prediction data and the non-timing related data, and correct the prediction data, so that the corrected result fully extracts the long-term timing characteristic and the short-term timing characteristic, and also fully extracts the influence of the non-timing data on the photovoltaic power generation power.
The description is as follows: the long-short time sequence prediction module obtains a long time sequence prediction result and a short time sequence prediction result of the next moment respectively, and in the prediction result correction module, non-time sequence data (weather data which is not selected in the variable selection module) of the moment and the prediction result of the long-short time sequence prediction module are transmitted into a fully-connected network together for prediction, and final prediction data of the next moment is output.
It should be appreciated that MLP (Multi-Layer Perceptron), a Multi-Layer Perceptron, is an artificial neural network that tends to structure, mapping a set of input vectors to a set of output vectors. The MLP can be seen as a directed graph, consisting of multiple layers of nodes, each layer being fully connected to the next. Except for the input nodes, each node is a neuron (or processing unit) with a nonlinear activation function. A supervised learning approach based on a back propagation algorithm may be used to train the MLP network.
In summary, the photovoltaic power generation power prediction method provided by the embodiment of the invention solves the problem that the correlation of short-term time sequence can be captured by the traditional photovoltaic power generation power prediction algorithm, but the GRU and the LSTM can not capture longer-term time sequence characteristics in practice due to the disappearance of gradient. Experimental results show that for photovoltaic power generation power prediction, under 24h prediction scene, LSTC MAE, RMSE, R 2 0.8610%,05288%,0.7601%, respectively, are superior to other algorithms. The invention provides an effective solution for photovoltaic power generation power prediction, which has important significance in the field of photovoltaic power generation power prediction.
As shown in fig. 2, a schematic structural diagram of a photovoltaic power generation power prediction system according to an embodiment of the present invention is shown. The photovoltaic power generation power prediction system 200 in the present embodiment includes: a variable selection module 201, a long-short-term time sequence prediction module 202 and a prediction result correction module 203.
Specifically, the variable selection module 201 is configured to obtain photovoltaic power generation power data in a history period, perform periodic analysis and correlation analysis on the photovoltaic power generation power data, and obtain short-term time-series related data, long-term time-series related data, and non-time-series related data according to the result of the periodic analysis and the result of the correlation analysis.
In some examples, the process of the variable selection module 201 obtaining and periodically analyzing photovoltaic power generation power data over a historical period of time includes: and decomposing the curves of the photovoltaic power generation power data and the influence factor data thereof in the historical period by utilizing Fourier transformation so as to perform periodic analysis, thereby obtaining the fluctuation periods of different periodic curves.
In some examples, the process of the variable selection module 201 obtaining and correlating photovoltaic power data over a historical period of time includes: and analyzing the correlation between the photovoltaic power generation power and a plurality of weather factors by using the Pearson correlation coefficient.
The long-short time sequence prediction module 202 is configured to perform long-short time prediction analysis on the short-term time sequence related data and the long-term time sequence related data, so as to extract short-term time sequence feature prediction data and long-term time sequence feature prediction data at the next moment respectively.
In some examples, the long-short timing prediction module 202 includes an LSTM network for performing predictive analysis on the short-term timing related data to obtain corresponding short-term timing characteristic prediction data.
In some examples, the long-short-term timing prediction module 202 includes a skip-GRU network for performing predictive analysis on the long-term timing related data to obtain corresponding long-term timing characteristic prediction data.
The prediction result correction module 203 is configured to input the short-term timing characteristic prediction data, the long-term timing characteristic prediction data, and the non-timing related data into the prediction result correction module to correct, so as to extract the influences of the long-term timing characteristic, the short-term timing characteristic, and the non-timing characteristic on the photovoltaic power generation power.
In some examples, the prediction result correction module 203 includes an MLP network, that is, the MLP network is used to receive the short-term timing characteristic prediction data, the long-term timing characteristic prediction data, and the non-timing related data, and correct the prediction data, so that the corrected result fully extracts both the long-term timing characteristic and the short-term timing characteristic, and also fully extracts the influence of the non-timing data on the photovoltaic power generation power.
For a better understanding of the network structure of the photovoltaic power generation power prediction system in the embodiment of the present invention, the following description will be made with reference to fig. 3:
the data is input to a variable selection module, and the variable selection module outputs corresponding short-term time sequence related data, long-term time sequence related data and non-time sequence related dataData. Short-term timing related data such as X t-2k ,…,X t-k ,…,X t The method comprises the steps of carrying out a first treatment on the surface of the Long-term timing related data such as X t-3k+1 ,X t-3k+2 ,…,X t-2k+1 ,X t-2k+2 ,…,X t-k+1 ,X t-k+2 The method comprises the steps of carrying out a first treatment on the surface of the Non-timing related data such as W t-2k ,…,W t-k ,…,W t 。
The short-term time sequence related data is input into an LSTM network in the long-short term time sequence prediction module, and short-term time sequence characteristic prediction data is output. And inputting the long-term time sequence related data into a skip-GRU network in the long-term and short-term time sequence prediction module, and outputting long-term time sequence characteristic prediction data.
And inputting the short-term time sequence characteristic prediction data output by the LSTM network, the long-term time sequence characteristic prediction data output by the skip-GRU network and the non-time sequence related data output by the variable selection module into the prediction result correction module, so as to output a final corrected prediction result.
It should be noted that, in the photovoltaic power generation power prediction apparatus provided in the foregoing embodiment, only the division of the foregoing program modules is used as an example, and in practical application, the foregoing process allocation may be performed by different program modules according to needs, that is, the internal structure of the apparatus is divided into different program modules, so as to complete all or part of the processing described above. In addition, the photovoltaic power generation power prediction system and the photovoltaic power generation power prediction method provided in the foregoing embodiments belong to the same concept, and detailed implementation processes of the photovoltaic power generation power prediction system and the photovoltaic power generation power prediction method are detailed in the method embodiments, which are not described herein again.
It should be understood that, in terms of a hardware structure of the photovoltaic power generation power prediction terminal, please refer to fig. 4, which is an optional hardware structure schematic diagram of the photovoltaic power generation power prediction terminal 400 provided in the embodiment of the present invention, the terminal 400 may be a mobile phone, a computer device, a tablet device, a personal digital processing device, a factory background processing device, etc. The photovoltaic power generation power prediction terminal 400 includes: at least one processor 401, a memory 402, at least one network interface 404, and a user interface 406. The various components in the device are coupled together by a bus system 405. It is understood that the bus system 405 is used to enable connected communications between these components. The bus system 405 includes a power bus, a control bus, and a status signal bus in addition to a data bus. But for clarity of illustration the various buses are labeled as bus systems in fig. 4.
The user interface 406 may include, among other things, a display, keyboard, mouse, trackball, click gun, keys, buttons, touch pad, or touch screen, etc.
It is to be appreciated that memory 402 can be either volatile memory or nonvolatile memory, and can include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read Only Memory (ROM), a programmable Read Only Memory (PROM, programmable Read-Only Memory), which serves as an external cache, among others. By way of example, and not limitation, many forms of RAM are available, such as static random Access Memory (SRAM, staticRandom Access Memory), synchronous static random Access Memory (SSRAM, synchronous Static RandomAccess Memory). The memory described by embodiments of the present invention is intended to comprise, without being limited to, these and any other suitable types of memory.
The memory 402 in the embodiment of the present invention is used to store various kinds of data to support the operation of the photovoltaic power generation power prediction terminal 400. Examples of such data include: any executable programs for operating on the photovoltaic power generation power prediction terminal 400, such as an operating system 4021 and application programs 4022; the operating system 4021 contains various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application programs 4022 may include various application programs such as a media player (MediaPlayer), a Browser (Browser), and the like for implementing various application services. The photovoltaic power generation power prediction method provided by the embodiment of the invention can be contained in the application program 4022.
The method disclosed in the above embodiment of the present invention may be applied to the processor 401 or implemented by the processor 401. The processor 401 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 401 or by instructions in the form of software. The processor 401 described above may be a general purpose processor, a digital signal processor (DSP, digital Signal Processor), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. Processor 401 may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. The general purpose processor 401 may be a microprocessor or any conventional processor or the like. The steps of the accessory optimization method provided by the embodiment of the invention can be directly embodied as the execution completion of the hardware decoding processor or the execution completion of the hardware and software module combination execution in the decoding processor. The software modules may be located in a storage medium having memory and a processor reading information from the memory and performing the steps of the method in combination with hardware.
In an exemplary embodiment, the photovoltaic power generation power prediction terminal 400 may be used by one or more application specific integrated circuits (ASIC, application Specific Integrated Circuit), DSPs, programmable logic devices (PLDs, programmable Logic Device), complex programmable logic devices (CPLDs, complex Programmable LogicDevice) for performing the aforementioned methods.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the method embodiments described above may be performed by computer program related hardware. The aforementioned computer program may be stored in a computer readable storage medium. The program, when executed, performs steps including the method embodiments described above; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
In the embodiments provided herein, the computer-readable storage medium may include read-only memory, random-access memory, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, flash memory, U-disk, removable hard disk, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer. In addition, any connection is properly termed a computer-readable medium. For example, if the instructions are transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital Subscriber Line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. It should be understood, however, that computer-readable and data storage media do not include connections, carrier waves, signals, or other transitory media, but are intended to be directed to non-transitory, tangible storage media. Disk and disc, as used herein, includes Compact Disc (CD), laser disc, optical disc, digital Versatile Disc (DVD), floppy disk and blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers.
In summary, the invention provides a method, a system, a terminal and a medium for predicting photovoltaic power generation power, and the invention provides a method for improving photovoltaic power generation power prediction efficiency, which solves the problems that the correlation of short-term time sequence can be captured by the traditional photovoltaic power generation power prediction algorithm, but the GRU and the LSTM can not capture longer-term time sequence characteristics in practice due to the disappearance of gradient. Experimental results show that for photovoltaic power generation power prediction, under 24h prediction scene, LSTC MAE, RMSE, R 2 0.8610%,05288%,0.7601%, respectively, are superior to other algorithms. The invention provides an effective solution for photovoltaic power generation power prediction, which has important significance in the field of photovoltaic power generation power prediction. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. Accordingly, it is intended that all equivalent modifications and variations of the invention be covered by the claims, which are within the ordinary skill of the art, be within the spirit and scope of the present disclosure.
Claims (12)
1. A photovoltaic power generation power prediction method, comprising:
acquiring photovoltaic power generation power data in a historical period, performing periodic analysis and correlation analysis on the photovoltaic power generation power data, and obtaining short-term time sequence related data, long-term time sequence related data and non-time sequence related data according to a periodic analysis result and a correlation analysis result;
performing long-short time prediction analysis on the short-term time sequence related data and the long-term time sequence related data to respectively extract short-term time sequence characteristic prediction data and long-term time sequence characteristic prediction data of the next moment;
and inputting the short-term time sequence characteristic prediction data, the long-term time sequence characteristic prediction data and the non-time sequence related data into a prediction result correction module for correction so as to extract the influence of the long-term time sequence characteristic, the short-term time sequence characteristic and the non-time sequence characteristic on the photovoltaic power generation power.
2. The method of claim 1, wherein the process of obtaining and periodically analyzing photovoltaic power data over a historical period of time comprises: and decomposing the curves of the photovoltaic power generation power data and the influence factor data thereof in the historical period by utilizing Fourier transformation so as to perform periodic analysis, thereby obtaining the fluctuation periods of different periodic curves.
3. The method of claim 2, wherein the fourier transform comprises:
wherein X (k) represents a Fourier series; x (n) represents a fourier series;
representing a complex function; k represents an x coordinate on the frequency domain; n represents a period.
4. The method of claim 1, wherein the process of obtaining and correlating photovoltaic power data over a historical period of time comprises: and analyzing the correlation between the photovoltaic power generation power and a plurality of weather factors by using the Pearson correlation coefficient.
5. The method according to claim 1, wherein the obtaining short-term time series related data, long-term time series related data, and non-time series related data from the periodic analysis result and the correlation analysis result includes: selecting a first group of weather influence factors positively correlated with the correlation of the photovoltaic power generation power, and selecting a second group of weather influence factors periodically correlated with the periodic analysis result of the photovoltaic power generation power; extracting intersections of the first group of weather influence factors and the second group of weather influence factors, reading historical data of each weather influence factor in the intersections, and processing the historical data into corresponding short-term time sequence related data and long-term time sequence related data; other weather-influencing factors outside the intersection are regarded as non-time-series related data.
6. The method of claim 1, wherein performing long-short-term predictive analysis on the short-term and long-term time-series related data comprises performing predictive analysis on the short-term time-series related data using an LSTM network to obtain corresponding short-term time-series characteristic predictive data.
7. The photovoltaic power generation power prediction method according to claim 1, characterized by performing long-short time prediction analysis on the short-term time series related data and long-term time series related data, comprising: and carrying out predictive analysis on the long-term time sequence related data by constructing a skip-GRU network to obtain corresponding long-term time sequence characteristic predictive data.
8. The method for predicting photovoltaic power generation according to claim 7, wherein the predicting and analyzing the long-term time series related data by constructing a skip-GRU network to obtain the corresponding long-term time series characteristic prediction data comprises:
r t ＝σ(W r [h t-p ,x t ]+b r )；
z t ＝σ(W z [h t-p ,x t ]+b z )；
wherein x is t Input data representing time t, r t Indicating reset gate, z t Representing the update gate, p is the sampling interval, h t-p Is the hidden state p times ago,
is a candidate state at this point in time, h t Is the output of this instant. W (W) r 、W z 、/>
A weight matrix respectively representing a reset gate, an update gate and a candidate state; b r 、b z The deviations of the reset gate and the update gate are indicated, respectively.
9. The method of claim 1, further comprising: and receiving the short-term time sequence characteristic prediction data, the long-term time sequence characteristic prediction data and the non-time sequence related data by using the MLP network, and correcting the prediction data.
10. A photovoltaic power generation power prediction system, comprising:
the variable selection module is used for acquiring photovoltaic power generation power data in a historical period, carrying out periodic analysis and correlation analysis on the photovoltaic power generation power data, and obtaining short-term time sequence related data, long-term time sequence related data and non-time sequence related data according to a periodic analysis result and a correlation analysis result;
the long-short time sequence prediction module is used for carrying out long-short time prediction analysis on the short-term time sequence related data and the long-term time sequence related data so as to respectively extract short-term time sequence characteristic prediction data and long-term time sequence characteristic prediction data of the next moment;
and the prediction result correction module is used for inputting the short-term time sequence characteristic prediction data, the long-term time sequence characteristic prediction data and the non-time sequence related data into the prediction result correction module for correction so as to extract the influences of the long-term time sequence characteristic, the short-term time sequence characteristic and the non-time sequence characteristic on the photovoltaic power generation power.
11. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the photovoltaic power generation power prediction method of any one of claims 1 to 9.
12. An electronic terminal, comprising: a processor and a memory;
the memory is used for storing a computer program;
the processor is configured to execute the computer program stored in the memory, to cause the terminal to execute the photovoltaic generation power prediction method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211658643.6A CN116307049A (en) | 2022-12-22 | 2022-12-22 | Photovoltaic power generation power prediction method, system, terminal and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211658643.6A CN116307049A (en) | 2022-12-22 | 2022-12-22 | Photovoltaic power generation power prediction method, system, terminal and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116307049A true CN116307049A (en) | 2023-06-23 |
Family
ID=86817434
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211658643.6A Pending CN116307049A (en) | 2022-12-22 | 2022-12-22 | Photovoltaic power generation power prediction method, system, terminal and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116307049A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117748496A (en) * | 2023-12-29 | 2024-03-22 | 武安市耀能新能源科技有限公司 | Distributed photovoltaic energy storage regulation and control system and method based on intelligent prediction |
-
2022
- 2022-12-22 CN CN202211658643.6A patent/CN116307049A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117748496A (en) * | 2023-12-29 | 2024-03-22 | 武安市耀能新能源科技有限公司 | Distributed photovoltaic energy storage regulation and control system and method based on intelligent prediction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Adaptive learning hybrid model for solar intensity forecasting | |
| CN111784041B (en) | Wind power prediction method and system based on graph convolution neural network | |
| CN112364975B (en) | Terminal running state prediction method and system based on graph neural network | |
| Huang et al. | Wind power forecasting using attention-based recurrent neural networks: a comparative study | |
| CN113988477A (en) | Photovoltaic power short-term prediction method and device based on machine learning and storage medium | |
| CN109409561B (en) | Construction method of multi-time scale time sequence collaborative prediction model | |
| CN116449462B (en) | Method, system, storage medium and equipment for predicting effective wave height space-time sequence of sea wave | |
| CN116502692A (en) | Model training method, photovoltaic power generation power prediction method and device | |
| CN114330935A (en) | New energy power prediction method and system based on multiple combined strategy integrated learning | |
| CN113111592A (en) | Short-term wind power prediction method based on EMD-LSTM | |
| Girimurugan et al. | Application of deep learning to the prediction of solar irradiance through missing data | |
| CN116307049A (en) | Photovoltaic power generation power prediction method, system, terminal and medium | |
| CN114330934A (en) | Model parameter self-adaptive GRU new energy short-term power generation power prediction method | |
| CN118095891A (en) | Active power distribution network payload prediction method and system considering source load meteorological characteristic decoupling | |
| CN116205382B (en) | Prediction method and prediction device for electricity consumption, electronic device and electronic equipment | |
| CN117076738A (en) | Medium-long term weather prediction method, system and medium based on variable grid model | |
| CN115907131A (en) | Method and system for building electric heating load prediction model in northern area | |
| CN112732777A (en) | Position prediction method, apparatus, device and medium based on time series | |
| CN113779861A (en) | Photovoltaic power prediction method and terminal equipment | |
| Yang et al. | A hybrid vmd-based ARIMA-LSTM model for day-ahead pv prediction and uncertainty analysis | |
| Alamgeer et al. | Data Mining with Comprehensive Oppositional Based Learning for Rainfall Prediction. | |
| Fang et al. | Interval prediction of PV power based on double sample entropy framework and integrated bidomain decomposition deep learning | |
| Huang et al. | Ultra-short-term prediction of microgrid source load power considering weather characteristics and multivariate correlation | |
| Shivashankaraiah et al. | Developing a Deep Learning and Reliable Optimization Techniques for Solar Photovoltaic Power Prediction | |
| CN116544931B (en) | Power load distribution prediction method based on integrated fragment transformation and time convolution network |
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 |