CN117117819A - Photovoltaic power generation short-term power prediction method, system, equipment and medium - Google Patents
Photovoltaic power generation short-term power prediction method, system, equipment and medium Download PDFInfo
- Publication number
- CN117117819A CN117117819A CN202210523546.XA CN202210523546A CN117117819A CN 117117819 A CN117117819 A CN 117117819A CN 202210523546 A CN202210523546 A CN 202210523546A CN 117117819 A CN117117819 A CN 117117819A
- Authority
- CN
- China
- Prior art keywords
- value
- power generation
- time
- photovoltaic power
- meteorological
- 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 166
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000004364 calculation method Methods 0.000 claims abstract description 43
- 230000008859 change Effects 0.000 claims description 29
- 238000003062 neural network model Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000004088 simulation Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000053 physical method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Power Engineering (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Photovoltaic Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a photovoltaic power generation short-term power prediction method, a system, equipment and a medium, comprising the following steps: calculating Euclidean distance of the meteorological elements based on absolute errors of the meteorological elements at each forecasting time and each corresponding historical time in the forecasting period, the pre-calculated standard deviation of the meteorological elements and the pre-calculated weight value of the meteorological elements; selecting a preset number of historical moments with minimum Euclidean distance for each forecast moment, obtaining the actual power value of the photovoltaic power generation corresponding to the historical moments, and calculating the weight value corresponding to the actual power value of the photovoltaic power generation; carrying out weighted summation on the photovoltaic power generation actual power value and a weight value corresponding to the photovoltaic power generation actual power value to obtain photovoltaic power generation predicted power values at all forecast moments; summarizing the photovoltaic power generation predicted power values at each prediction time to generate photovoltaic power generation short-term power prediction; the invention has small dependence on the actually measured meteorological data, strong adaptability, simplicity, practicality, reliable calculation and easy realization and engineering field deployment.
Description
Technical Field
The invention belongs to the technical field of new energy power generation, and particularly relates to a photovoltaic power generation short-term power prediction method, a system, equipment and a medium.
Background
The photovoltaic short-term power prediction refers to the prediction of the active power of 72 hours in the future when the photovoltaic power station is in the next day, and the time resolution is 15min. The photovoltaic output has volatility and randomness, the large-scale photovoltaic power generation grid connection can cause larger influence on the safe and stable operation of the power system, the accurate photovoltaic power generation short-term power prediction is beneficial to the power dispatching department to timely adjust a dispatching plan according to the photovoltaic output change, photovoltaic resources are fully utilized, the competitiveness of the photovoltaic power generation in the power market is enhanced, and therefore larger economic benefits and social benefits are obtained.
In the prior art, a photovoltaic power generation short-term power prediction model can be established through a neural network, and a photovoltaic power generation short-term power prediction value is obtained by inputting variable parameters into the model, but the technical scheme has the following defects: (1) The training speed is low, the input variables are more, and the calculation is more complex; (2) is prone to falling into local extrema; (3) The data dependence degree is high, and a large number of historical samples are needed; the photovoltaic power station error correction type photovoltaic power generation system also can be used for forecasting meteorological elements through collecting geographic information of the photovoltaic power station, meteorological resource monitoring data and performance parameters of photovoltaic modules and through a mesoscale numerical weather forecasting mode, and establishing a photovoltaic power station forecasting element error correction type and photoelectric conversion model, and outputting a photovoltaic power generation short-term power forecasting value through the photoelectric conversion model, and the technical scheme has the following defects: (1) The error links are more, and errors can be generated in the links of weather forecast, mode correction, photoelectric conversion and the like; (2) The adaptability is not strong, the requirement on the quality of the actually measured meteorological data is high, and the modeling condition is difficult to meet in part of sites.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a photovoltaic power generation short-term power prediction method, which comprises the following steps:
calculating Euclidean distance of the meteorological elements based on absolute errors of the meteorological elements at each forecasting time and each corresponding historical time in the forecasting period, a pre-calculated standard deviation of the meteorological elements and a pre-calculated weight value of the meteorological elements;
selecting a preset number of historical moments with minimum Euclidean distance for each forecast moment, obtaining the actual power value of the photovoltaic power generation corresponding to the historical moments, and calculating the weight value corresponding to the actual power value of the photovoltaic power generation;
carrying out weighted summation on the actual power value of the photovoltaic power generation and the weight value corresponding to the actual power value of the photovoltaic power generation to obtain the predicted power value of the photovoltaic power generation at each forecasting time;
summarizing the photovoltaic power generation predicted power values at each prediction time to generate photovoltaic power generation short-term power prediction;
the Euclidean distance is calculated by combining meteorological elements with the aim of obtaining the moment similar to the characteristic of the current NWP predicted sequence.
Preferably, the calculating the euclidean distance of the meteorological element based on the absolute error of the meteorological element between each forecasting time and each corresponding historical time in the forecasting period, the pre-calculated standard deviation of the meteorological element and the pre-calculated weight value of the meteorological element includes:
setting each forecast time window and extracting each corresponding historical time window in each historical day;
acquiring meteorological element values of each forecast time and each corresponding historical time window;
and calculating absolute errors of the meteorological elements in the time windows of each forecast time and each corresponding historical time, and determining Euclidean distances between each forecast time and the meteorological elements of each corresponding historical time in the forecast period by combining the pre-calculated meteorological element weight values and the standard deviations of the meteorological elements.
Preferably, the calculating process of the weather element weight value includes:
inputting meteorological element values at corresponding historical moments into the BP neural network model to generate simulated power values;
adding a preset percentage to the meteorological element values at each corresponding historical moment, and taking the meteorological element values into a BP neural network model to generate simulated value-added power;
subtracting a preset percentage from the meteorological element value at each corresponding historical moment, and introducing the meteorological element value into the BP neural network model to generate simulated subtracted value power;
based on the analog increment power and the analog decrement power, and combining an MIV variable screening algorithm, generating an influence change value of an analog power value;
calculating an average influence change value according to influence change values of a plurality of preset forecast moments, and determining a weather element weight value based on the average influence change value;
the BP neural network model is obtained by training with a meteorological element numerical mode as input and historical photovoltaic power generation actual power as output.
Preferably, the euclidean distance between each forecasting time and each weather element at each corresponding historical time in the forecasting period is calculated according to the following formula:
wherein,for the Euclidean distance between the ith forecast time and the weather element of the corresponding historical time in the forecast period, t' i For the ith forecast moment, t i For the i-th corresponding history time, +.>Weather element value for the i < th > forecast moment, <>For the weather element value, ω, at the i-th corresponding historical time m The weight value delta of the meteorological element m m For modeling the standard deviation of the meteorological element m in the sample dataset, m is the meteorological element value.
Preferably, the meteorological element comprises at least one or more of the following: total irradiance, direct irradiance, scattered irradiance, component temperature, average wind speed, average wind direction, ambient temperature, and relative humidity.
Preferably, the weight value corresponding to the actual power value of the photovoltaic power generation is calculated according to the following formula:
wherein eta s The weight value corresponding to the s-th photovoltaic power generation actual power value, t s For the corresponding historical time of s, the value range of s is [1,2, 3. ], j]J is the total number of the preset number,the Euclidean distance between the s-th forecasting time and the weather element of the corresponding historical time in the forecasting period.
Preferably, the photovoltaic power generation predicted power value at each predicted time is calculated according to the following formula:
wherein,predicted power value, t 'for photovoltaic power generation at the i-th predicted time in the prediction period' i For the i-th forecast moment, η s And (3) for the weight value corresponding to the s-th photovoltaic power generation actual power value, the value range of s is [1,2,3 ]. The value of j]J is the total number of the preset number, +.>The actual power value of the photovoltaic power generation at the s-th historical moment.
Based on the same inventive concept, the invention also provides a photovoltaic power generation short-term power prediction system, which comprises:
the system comprises a Euclidean distance calculation module, a photovoltaic power generation predicted power weight calculation module, a photovoltaic power generation predicted power calculation module and a power generation short-term power prediction module;
the Euclidean distance calculation module is used for calculating the Euclidean distance of the meteorological elements based on the absolute error of the meteorological elements between each forecasting time and each corresponding historical time in the forecasting period, the pre-calculated standard deviation of the meteorological elements and the pre-calculated weight value of the meteorological elements;
the photovoltaic power generation prediction power weight calculation module is used for selecting a preset number of historical moments with minimum Euclidean distance for each prediction moment, obtaining a photovoltaic power generation actual power value corresponding to the historical moments, and calculating a weight value corresponding to the photovoltaic power generation actual power value;
the photovoltaic power generation prediction power calculation module is used for carrying out weighted summation on the photovoltaic power generation actual power value and a weight value corresponding to the photovoltaic power generation actual power value to obtain photovoltaic power generation prediction power values at all prediction moments;
and the power generation short-term power prediction module is used for summarizing the photovoltaic power generation predicted power values at each predicted time and generating photovoltaic power generation short-term power prediction.
Preferably, the euclidean distance calculating module is specifically configured to:
setting each forecast time window and extracting each corresponding historical time window in each historical day;
acquiring meteorological element values of each forecast time and each corresponding historical time window;
and calculating absolute errors of the meteorological elements in the time windows of each forecast time and each corresponding historical time, and determining Euclidean distances between each forecast time and the meteorological elements of each corresponding historical time in the forecast period by combining the pre-calculated meteorological element weight values and the standard deviations of the meteorological elements.
Preferably, the calculating process of the weather element weight value in the euclidean distance calculating module includes:
inputting meteorological element values at corresponding historical moments into the BP neural network model to generate simulated power values;
adding a preset percentage to the meteorological element values at each corresponding historical moment, and taking the meteorological element values into a BP neural network model to generate simulated value-added power;
subtracting a preset percentage from the meteorological element value at each corresponding historical moment, and introducing the meteorological element value into the BP neural network model to generate simulated subtracted value power;
based on the analog increment power and the analog decrement power, and combining an MIV variable screening algorithm, generating an influence change value of an analog power value;
calculating an average influence change value according to influence change values of a plurality of preset forecast moments, and determining a weather element weight value based on the average influence change value;
the BP neural network model is obtained by training with a meteorological element numerical mode as input and historical photovoltaic power generation actual power as output.
Preferably, the euclidean distance calculating module calculates the euclidean distance between each forecasting time and each meteorological element corresponding to the historical time in the forecasting period according to the following formula:
wherein the method comprises the steps of，For the Euclidean distance between the ith forecast time and the weather element of the corresponding historical time in the forecast period, t' i For the ith forecast moment, t i For the i-th corresponding history time, +.>Weather element value for the i < th > forecast moment, <>For the weather element value, ω, at the i-th corresponding historical time m The weight value delta of the meteorological element m m For modeling the standard deviation of the meteorological element m in the sample dataset, m is the meteorological element value.
Preferably, the meteorological element of the euclidean distance calculating module at least comprises one or more of the following: total irradiance, direct irradiance, scattered irradiance, component temperature, average wind speed, average wind direction, ambient temperature, and relative humidity.
Preferably, the photovoltaic power generation prediction power weight calculation module calculates a weight value corresponding to the actual power value of photovoltaic power generation according to the following formula:
wherein eta s The weight value corresponding to the s-th photovoltaic power generation actual power value, t s For the corresponding historical time of s, the value range of s is [1,2, 3. ], j]J is the total number of the preset number,the Euclidean distance between the s-th forecasting time and the weather element of the corresponding historical time in the forecasting period.
Preferably, the photovoltaic power generation predicted power calculation module calculates the photovoltaic power generation predicted power value at each predicted time according to the following formula:
wherein,predicted power value, t 'for photovoltaic power generation at the i-th predicted time in the prediction period' i For the i-th forecast moment, η s And (3) for the weight value corresponding to the s-th photovoltaic power generation actual power value, the value range of s is [1,2,3 ]. The value of j]J is the total number of the preset number, +.>The actual power value of the photovoltaic power generation at the s-th historical moment.
Based on the same inventive concept, the present invention also provides a computer device, comprising: one or more processors;
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, a photovoltaic power generation short-term power prediction method as described above is implemented.
Based on the same inventive concept, the invention also provides a computer readable storage medium, on which a computer program is stored, which when executed, implements a photovoltaic power generation short-term power prediction method as described above.
Compared with the closest prior art, the invention has the following beneficial effects:
1. the invention provides a photovoltaic power generation short-term power prediction method, a system, equipment and a medium, comprising the following steps: calculating Euclidean distance of the meteorological elements based on absolute errors of the meteorological elements at each forecasting time and each corresponding historical time in the forecasting period, a pre-calculated standard deviation of the meteorological elements and a pre-calculated weight value of the meteorological elements; selecting a preset number of historical moments with minimum Euclidean distance for each forecast moment, obtaining the actual power value of the photovoltaic power generation corresponding to the historical moments, and calculating the weight value corresponding to the actual power value of the photovoltaic power generation; carrying out weighted summation on the actual power value of the photovoltaic power generation and the weight value corresponding to the actual power value of the photovoltaic power generation to obtain the predicted power value of the photovoltaic power generation at each forecasting time; summarizing the photovoltaic power generation predicted power values at each prediction time to generate photovoltaic power generation short-term power prediction; the Euclidean distance is calculated by taking the moment similar to the characteristic of the current NWP prediction sequence as a target and combining with meteorological elements, error risks of single-point prediction can be shared by online calculation in a weighted mode, large deviation is eliminated, short-term power prediction accuracy of photovoltaic power generation is improved, dependence on actual measurement meteorological data is small, adaptability is high, requirements on data quantity of historical data are low, universality is good, the method is particularly suitable for photovoltaic power stations with incomplete meteorological monitoring data conditions, and the method is simple and practical, reliable in calculation, easy to realize and deploy on engineering sites, and has very strong operability and popularization and application values.
2. According to the invention, correction is not required by actually measuring the numerical mode of the meteorological element, and the flow possibly generating forecast errors is optimized, so that the accuracy of the short-term power forecast of the photovoltaic power generation is improved.
Drawings
FIG. 1 is a flow chart of a photovoltaic power generation short-term power prediction method provided by the invention;
fig. 2 is a flowchart of a specific example of a photovoltaic power generation short-term power prediction method provided by the invention;
FIG. 3 is a schematic diagram of a physical method for photovoltaic power generation short-term power prediction;
fig. 4 is a schematic diagram of photovoltaic power generation short-term power prediction provided by the invention;
fig. 5 is a schematic diagram of a photovoltaic power generation short-term power prediction system provided by the invention.
Detailed Description
The following detailed description of specific embodiments of the invention is provided in connection with the accompanying drawings and examples.
The invention provides a photovoltaic power generation short-term power prediction method, a flow diagram of which is shown in figure 1, comprising the following steps:
step 1: calculating Euclidean distance of the meteorological elements based on absolute errors of the meteorological elements at each forecasting time and each corresponding historical time in the forecasting period, a pre-calculated standard deviation of the meteorological elements and a pre-calculated weight value of the meteorological elements;
step 2: selecting a preset number of historical moments with minimum Euclidean distance for each forecast moment, obtaining the actual power value of the photovoltaic power generation corresponding to the historical moments, and calculating the weight value corresponding to the actual power value of the photovoltaic power generation;
step 3, carrying out weighted summation on the actual power value of the photovoltaic power generation and the weight value corresponding to the actual power value of the photovoltaic power generation to obtain the predicted power value of the photovoltaic power generation at each forecasting time;
step 4: and summarizing the photovoltaic power generation predicted power values at each forecasting time to generate photovoltaic power generation short-term power prediction.
Specifically, step 1 includes:
for a certain forecast time t in a forecast period i ' set time window (t) i ' -μ ,t i ' +μ ) Extracting a time window (t) corresponding to each day of the history i-μ ,t i+μ ) Calculating Euclidean distance sequence of the meteorological elements at the forecasting time:
at a forecast time t i ∈(t i-μ ,t i+μ ) For example, calculating euclidean distance between weather elements at a forecast time and a corresponding historical time requires calculating absolute errors of the weather elements in a time window of the forecast time and the corresponding historical time, and determining euclidean distance between the weather elements at the forecast time and the corresponding historical time by combining a pre-calculated weather element weight value and a weather element standard deviation, wherein the euclidean distance formula of the weather elements is as follows:
in the method, in the process of the invention,for the Euclidean distance between the ith forecast time and the weather element of the corresponding historical time in the forecast period, t' i For the ith forecast moment, t i For the i-th corresponding history time, +.>Weather element value for the i < th > forecast moment, <>For the weather element value, ω, at the i-th corresponding historical time m The weight value delta of the meteorological element m m For modeling a standard deviation of a meteorological element m in a sample dataset, m is a meteorological element value, and the meteorological element m at least comprises one or more of the following: { RG, RD, RF, TM, WS, WD, T, RH, &....degree}, the RG is the total irradiance and is the total irradiance, RD is the direct irradiance, RF is the scattered irradiance, TM is the component temperature, WS is the average wind speed, WD is the average wind direction, T is the ambient temperature, and RH is the relative humidity.
Training a BP neural network model by establishing a model training data set, removing actual power of the photovoltaic power station in abnormal time periods such as electricity limit and the like, combining with a meteorological element numerical mode to form a multi-element data sequence, wherein the establishment of the data set is according to the format of a data vector:
(P t ,{RG t ,RD t ,RF t ,TM t ,WS t ,WD t ,T t ,RH t ,......},t)
wherein P is t The actual power of the photovoltaic power generation at the moment t; { } is a meteorological element numerical pattern at time t, and meteorological element m includes: RG (radio frequency identification) t For the total irradiance at time t, RD t For the irradiance of direct radiation at time t, RF t Irradiance (TM) of scattered radiation at time t t Component temperature, WS at time t t Average wind speed, WD, at time t t Is the average wind direction at time T t Ambient temperature, RH at time t t At time tRelative humidity, etc.; t is the corresponding historical time, the resolution is usually 15 minutes, the neural network method is utilized, the model training data set is based on the model, the input is set to be a meteorological element numerical mode, and the output is set to be the actual power P of photovoltaic power generation t . And training a large number of nonlinear mapping relations f () between input and output through the self-adaptive learning capability of the neural network, and constructing a BP neural network model.
When calculating the meteorological element weight value, firstly inputting the meteorological element into a BP neural network model to generate a simulation power value, wherein the BP neural network model formula is as follows:
P t '＝f({RG t ,RD t ,RF t ,TM t ,WS t ,WD t ,T t ,RH t ,......},t)
p in BP neural network model formula t ' is the simulation power value at the time t, f () is the nonlinear mapping relation between the meteorological element numerical mode and the historical photovoltaic power generation actual power, { is the meteorological element numerical mode at the time t, and a preset percentage is added to each meteorological element and is brought into the BP neural network model to generate simulation increment power; subtracting a preset percentage from each meteorological element, and introducing the meteorological elements into a BP neural network model to generate simulated reduced power; with total irradiance RG t The following are examples: for total irradiance RG t Adding a preset percentage and subtracting the preset percentage, and generating a new meteorological element numerical mode as follows:
{RG t + ,RD t ,RF t ,TM t ,WS t ,WD t ,T t ,RH t ,......}
{RG t - ,RD t ,RF t ,TM t ,WS t ,WD t ,T t ,RH t ,......}
wherein RG is t + ＝RG t *(1+λ)，RG t - ＝RG t * (1- λ), typically λ=10%, by simulation with a BP neural network model, two simulation results are obtained:
P t,RG ' + ＝f({RG t + ,RD t ,RF t ,TM t ,WS t ,WD t ,T t ,RH t ,......},t)
P t,RG ' - ＝f({RG t - ,RD t ,RF t ,TM t ,WS t ,WD t ,T t ,RH t ,......},t)
wherein P is t,RG ' + Analog boost power, P, for total irradiance at time t t,RG ' - The difference value |P of two simulation results is the simulated subtracted power of the total irradiance at the time t t,RG ' + -P t,RG ' - I, i.e. the total irradiance RG t Variation pair P t ' influence change value of generated analog power value, RG t The calculation formula of the influence change value of the analog power value:
MIV t,RG ＝|P t,RG ' + -P t,RG ' - |
wherein the MIV t,RG For the total irradiance RG at time t t The change value of the influence of the analog power value of (a) is calculated by the total irradiance RG at n forecast times t The influence change values of the analog power values are averaged to obtain an average influence change value, and the average influence change value calculation formula is as follows:
wherein the MIV RG The average influence change value of the analog power value of the total irradiance RG at n forecast time can be obtained by the same method t Irradiance of scattered radiation RF t Temperature of component TM t Average wind speed WS t Average wind direction WD t Ambient temperature T t Relative humidity RH t Average impact change value corresponding to the meteorological elements:
{MIV RD ,MIV RF ,MIV TM ,MIV WS ,MIV WD ,MIV T ,MIV RH ,......}
then, the weight of each meteorological element affecting the photovoltaic power generation output is obtained:
{ω RG ,ω RD ,ω RF ,ω TM ,ω WS ,ω WD ,ω T ,ω RH ,......}
taking the total irradiance weight as an example, the calculation formula of the total irradiance weight is as follows:
by calculating Euclidean distances between each forecasting time and the corresponding historical time meteorological element in the forecasting period, similar characteristics can be found according to multiple meteorological elements, the time similar to the current NWP forecasting sequence characteristic can be found in the historical time corresponding to the forecasting time, the method is simple and practical, the calculation is reliable, the flow is more simplified, the mode forecasting result is not required to be corrected by actually measured weather, the photoelectric conversion process is omitted, the flow which possibly generates forecasting errors is optimized, the power forecasting precision is improved, the online calculation in a weighted error mode is facilitated, the error risk of single-point forecasting can be shared, the large deviation is eliminated, and the photovoltaic power generation short-term power forecasting precision is improved;
specifically, step 2 includes:
for each history time and forecast time t' i The euclidean distance sequence of the meteorological elements is ordered:
obtaining the first j values with the minimum Euclidean distance, and extracting the corresponding actual power values:
calculating the weight coefficient eta of each actual power value, and calculating a weight coefficient eta calculation formula of each actual power value:
wherein eta s The weight value corresponding to the s-th photovoltaic power generation actual power value, t s For the corresponding historical time of s, the value range of s is [1,2, 3. ], j]J is the total number of the preset number,the Euclidean distance between the s-th forecasting time and the weather element of the corresponding historical time in the forecasting period. The method has little dependence on actual measurement meteorological data and strong adaptability, only needs to acquire the actual power of photovoltaic power generation at the historical moment, has low requirement on the data quantity of the historical data, has good universality, and is particularly suitable for photovoltaic power stations with incomplete meteorological monitoring data conditions.
Specifically, step 3 includes:
and carrying out weighted summation on the photovoltaic power generation actual power value and the weight value corresponding to the photovoltaic power generation actual power value to obtain photovoltaic power generation predicted power values at all the forecast time, wherein the calculation formula of the photovoltaic power generation predicted power values at all the forecast time is as follows:
wherein,predicted power value, t 'for photovoltaic power generation at the i-th predicted time in the prediction period' i For the i-th forecast moment, η s And (3) for the weight value corresponding to the s-th photovoltaic power generation actual power value, the value range of s is [1,2,3 ]. The value of j]J is the total number of the preset number, +.>The actual power value of the photovoltaic power generation at the s-th historical moment. The power prediction of the predicted time is obtained by extracting the time history actual power corresponding to the predicted time and weighting according to Euclidean distanceThe method has less calculation process, can reduce errors and improve the prediction accuracy.
Specifically, step 4 includes:
and simultaneously calculating the photovoltaic power generation predicted power values at each forecasting time of the forecasting period, simultaneously outputting the photovoltaic power generation predicted power values at each forecasting time, and summarizing to generate the photovoltaic power generation short-term power prediction. The method is easy to realize, and has strong operability and popularization and application values.
Taking a photovoltaic power plant with an installed capacity of 80MW as an example, the prediction effect of the present invention is verified by a flowchart of a specific example of a photovoltaic power generation short-term power prediction method as shown in FIG. 2. Short-term predicted power and actual power generation data of 30 days in total are selected from 11 months 1 to 11 months 30 days in 2021 for verification, the predicted effect is shown in figures 3 and 4 and table 1, and the calculation result shows that each error index of the short-term predicted power is superior to that of an LSTM neural network and a physical method.
TABLE 1 prediction error indicator
Example 2:
based on the same inventive concept, the invention also provides a photovoltaic power generation short-term power prediction system, a schematic diagram of which is shown in fig. 5, comprising:
the system comprises a Euclidean distance calculation module, a photovoltaic power generation predicted power weight calculation module, a photovoltaic power generation predicted power calculation module and a power generation short-term power prediction module;
the Euclidean distance calculation module is used for calculating the Euclidean distance of the meteorological elements based on the absolute error of the meteorological elements between each forecasting time and each corresponding historical time in the forecasting period, the pre-calculated standard deviation of the meteorological elements and the pre-calculated weight value of the meteorological elements;
the photovoltaic power generation prediction power weight calculation module is used for selecting a preset number of historical moments with minimum Euclidean distance for each prediction moment, obtaining a photovoltaic power generation actual power value corresponding to the historical moments, and calculating a weight value corresponding to the photovoltaic power generation actual power value;
the photovoltaic power generation prediction power calculation module is used for carrying out weighted summation on the photovoltaic power generation actual power value and a weight value corresponding to the photovoltaic power generation actual power value to obtain photovoltaic power generation prediction power values at all prediction moments;
and the power generation short-term power prediction module is used for summarizing the photovoltaic power generation predicted power values at each predicted time and generating photovoltaic power generation short-term power prediction.
The Euclidean distance calculating module is specifically configured to:
setting each forecast time window and extracting each corresponding historical time window in each historical day;
acquiring meteorological element values of each forecast time and each corresponding historical time window;
and calculating absolute errors of the meteorological elements in the time windows of each forecast time and each corresponding historical time, and determining Euclidean distances between each forecast time and the meteorological elements of each corresponding historical time in the forecast period by combining the pre-calculated meteorological element weight values and the standard deviations of the meteorological elements.
The calculation process of the meteorological element weight value in the Euclidean distance calculation module comprises the following steps:
inputting meteorological element values at corresponding historical moments into the BP neural network model to generate simulated power values;
adding a preset percentage to the meteorological element values at each corresponding historical moment, and taking the meteorological element values into a BP neural network model to generate simulated value-added power;
subtracting a preset percentage from the meteorological element value at each corresponding historical moment, and introducing the meteorological element value into the BP neural network model to generate simulated subtracted value power;
based on the analog increment power and the analog decrement power, and combining an MIV variable screening algorithm, generating an influence change value of an analog power value;
calculating an average influence change value according to influence change values of a plurality of preset forecast moments, and determining a weather element weight value based on the average influence change value;
the BP neural network model is obtained by training with a meteorological element numerical mode as input and historical photovoltaic power generation actual power as output.
The Euclidean distance calculating module calculates Euclidean distances between each forecasting time and each meteorological element corresponding to the historical time in the forecasting time period according to the following formula:
wherein,for the Euclidean distance between the ith forecast time and the weather element of the corresponding historical time in the forecast period, t' i For the ith forecast moment, t i For the i-th corresponding history time, +.>Weather element value for the i < th > forecast moment, <>For the weather element value, ω, at the i-th corresponding historical time m The weight value delta of the meteorological element m m For modeling the standard deviation of the meteorological element m in the sample dataset, m is the meteorological element value.
The meteorological element of the Euclidean distance calculation module at least comprises one or more of the following: total irradiance, direct irradiance, scattered irradiance, component temperature, average wind speed, average wind direction, ambient temperature, and relative humidity.
The photovoltaic power generation prediction power weight calculation module calculates a weight value corresponding to an actual power value of photovoltaic power generation according to the following formula:
wherein eta s The weight value corresponding to the s-th photovoltaic power generation actual power value, t s For the corresponding historical time of s, the value range of s is [1,2, 3. ], j]J is the total number of the preset number,the Euclidean distance between the s-th forecasting time and the weather element of the corresponding historical time in the forecasting period.
The photovoltaic power generation prediction power calculation module calculates the photovoltaic power generation prediction power value at each prediction time according to the following formula:
wherein,predicted power value, t 'for photovoltaic power generation at the i-th predicted time in the prediction period' i For the i-th forecast moment, η s And (3) for the weight value corresponding to the s-th photovoltaic power generation actual power value, the value range of s is [1,2,3 ]. The value of j]J is the total number of the preset number, +.>The actual power value of the photovoltaic power generation at the s-th historical moment.
Example 3:
based on the same inventive concept, the invention also provides a computer device comprising a processor and a memory for storing a computer program comprising program instructions, the processor for executing the program instructions stored by the computer storage medium. The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application SpecificIntegrated Circuit, ASIC), off-the-shelf Programmable gate array (FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc., which are the computational core and control core of the terminal adapted to implement one or more instructions, in particular to load and execute one or more instructions in a computer storage medium to implement the corresponding method flow or corresponding functions, to implement the steps of a photovoltaic power generation short-term power prediction method in the above embodiments.
Example 4:
based on the same inventive concept, the present invention also provides a storage medium, in particular, a computer readable storage medium (Memory), which is a Memory device in a computer device, for storing programs and data. It is understood that the computer readable storage medium herein may include both built-in storage media in a computer device and extended storage media supported by the computer device. The computer-readable storage medium provides a storage space storing an operating system of the terminal. Also stored in the memory space are one or more instructions, which may be one or more computer programs (including program code), adapted to be loaded and executed by the processor. The computer readable storage medium herein may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. One or more instructions stored in a computer-readable storage medium may be loaded and executed by a processor to implement the steps of a photovoltaic power generation short-term power prediction method in the above embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the scope of protection thereof, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that various changes, modifications or equivalents may be made to the specific embodiments of the application after reading the present invention, and these changes, modifications or equivalents are within the scope of protection of the claims appended hereto.
Claims (16)
1. A photovoltaic power generation short-term power prediction method, comprising:
calculating Euclidean distance of the meteorological elements based on absolute errors of the meteorological elements at each forecasting time and each corresponding historical time in the forecasting period, a pre-calculated standard deviation of the meteorological elements and a pre-calculated weight value of the meteorological elements;
selecting a preset number of historical moments with minimum Euclidean distance for each forecast moment, obtaining the actual power value of the photovoltaic power generation corresponding to the historical moments, and calculating the weight value corresponding to the actual power value of the photovoltaic power generation;
carrying out weighted summation on the actual power value of the photovoltaic power generation and the weight value corresponding to the actual power value of the photovoltaic power generation to obtain the predicted power value of the photovoltaic power generation at each forecasting time;
summarizing the photovoltaic power generation predicted power values at each prediction time to generate photovoltaic power generation short-term power prediction;
the Euclidean distance is calculated by combining meteorological elements with the aim of obtaining the moment similar to the characteristic of the current NWP predicted sequence.
2. The method of claim 1, wherein the calculating the euclidean distance of the weather element based on the absolute error of the weather element, the pre-calculated standard deviation of the weather element, and the pre-calculated weight value of the weather element at each of the forecasted time and each of the corresponding historical time within the forecasted period comprises:
setting each forecast time window and extracting each corresponding historical time window in each historical day;
acquiring meteorological element values of each forecast time and each corresponding historical time window;
and calculating absolute errors of the meteorological elements in the time windows of each forecast time and each corresponding historical time, and determining Euclidean distances between each forecast time and the meteorological elements of each corresponding historical time in the forecast period by combining the pre-calculated meteorological element weight values and the standard deviations of the meteorological elements.
3. The method of claim 2, wherein the calculating of the weather element weight value comprises:
inputting meteorological element values at corresponding historical moments into the BP neural network model to generate simulated power values;
adding a preset percentage to the meteorological element values at each corresponding historical moment, and taking the meteorological element values into a BP neural network model to generate simulated value-added power;
subtracting a preset percentage from the meteorological element value at each corresponding historical moment, and introducing the meteorological element value into the BP neural network model to generate simulated subtracted value power;
based on the analog increment power and the analog decrement power, and combining an MIV variable screening algorithm, generating an influence change value of an analog power value;
calculating an average influence change value according to influence change values of a plurality of preset forecast moments, and determining a weather element weight value based on the average influence change value;
the BP neural network model is obtained by training with a meteorological element numerical mode as input and historical photovoltaic power generation actual power as output.
4. The method of claim 2, wherein the euclidean distance of each forecasted time within the forecast period from each respective historical time meteorological element is calculated as:
wherein,for the Euclidean distance between the ith forecast time and the weather element of the corresponding historical time in the forecast period, t' i For the ith forecast moment, t i For the ith corresponding historical time，/>Weather element value for the i < th > forecast moment, <>For the weather element value, ω, at the i-th corresponding historical time m The weight value delta of the meteorological element m m For modeling the standard deviation of the meteorological element m in the sample dataset, m is the meteorological element value.
5. The method of claim 1, wherein the meteorological element comprises at least one or more of: total irradiance, direct irradiance, scattered irradiance, component temperature, average wind speed, average wind direction, ambient temperature, and relative humidity.
6. The method according to claim 1, wherein the weight value corresponding to the actual power value of the photovoltaic power generation is calculated according to the following formula:
wherein eta s The weight value corresponding to the s-th photovoltaic power generation actual power value, t s For the corresponding historical time of s, the value range of s is [1,2, 3. ], j]J is the total number of the preset number,the Euclidean distance between the s-th forecasting time and the weather element of the corresponding historical time in the forecasting period.
7. The method of claim 1, wherein the predicted power value for photovoltaic power generation at each forecasted time is calculated as:
wherein,predicted power value, t 'for photovoltaic power generation at the i-th predicted time in the prediction period' i For the i-th forecast moment, η s And (3) for the weight value corresponding to the s-th photovoltaic power generation actual power value, the value range of s is [1,2,3 ]. The value of j]J is the total number of the preset number, +.>The actual power value of the photovoltaic power generation at the s-th historical moment.
8. A photovoltaic power generation short-term power prediction system, comprising:
the system comprises a Euclidean distance calculation module, a photovoltaic power generation predicted power weight calculation module, a photovoltaic power generation predicted power calculation module and a power generation short-term power prediction module;
the Euclidean distance calculation module is used for calculating the Euclidean distance of the meteorological elements based on the absolute error of the meteorological elements between each forecasting time and each corresponding historical time in the forecasting period, the pre-calculated standard deviation of the meteorological elements and the pre-calculated weight value of the meteorological elements;
the photovoltaic power generation prediction power weight calculation module is used for selecting a preset number of historical moments with minimum Euclidean distance for each prediction moment, obtaining a photovoltaic power generation actual power value corresponding to the historical moments, and calculating a weight value corresponding to the photovoltaic power generation actual power value;
the photovoltaic power generation prediction power calculation module is used for carrying out weighted summation on the photovoltaic power generation actual power value and a weight value corresponding to the photovoltaic power generation actual power value to obtain photovoltaic power generation prediction power values at all prediction moments;
and the power generation short-term power prediction module is used for summarizing the photovoltaic power generation predicted power values at each predicted time and generating photovoltaic power generation short-term power prediction.
9. The system of claim 8, wherein the euclidean distance calculation module is configured to:
setting each forecast time window and extracting each corresponding historical time window in each historical day;
acquiring meteorological element values of each forecast time and each corresponding historical time window;
and calculating absolute errors of the meteorological elements in the time windows of each forecast time and each corresponding historical time, and determining Euclidean distances between each forecast time and the meteorological elements of each corresponding historical time in the forecast period by combining the pre-calculated meteorological element weight values and the standard deviations of the meteorological elements.
10. The system of claim 9, wherein the calculating of the meteorological element weight value in the euclidean distance calculation module comprises:
inputting meteorological element values at corresponding historical moments into the BP neural network model to generate simulated power values;
adding a preset percentage to the meteorological element values at each corresponding historical moment, and taking the meteorological element values into a BP neural network model to generate simulated value-added power;
subtracting a preset percentage from the meteorological element value at each corresponding historical moment, and introducing the meteorological element value into the BP neural network model to generate simulated subtracted value power;
based on the analog increment power and the analog decrement power, and combining an MIV variable screening algorithm, generating an influence change value of an analog power value;
calculating an average influence change value according to influence change values of a plurality of preset forecast moments, and determining a weather element weight value based on the average influence change value;
the BP neural network model is obtained by training with a meteorological element numerical mode as input and historical photovoltaic power generation actual power as output.
11. The system of claim 9, wherein the euclidean distance calculation module calculates the euclidean distance of each forecasted time within a forecast period from each corresponding historical time meteorological element by:
wherein,for the Euclidean distance between the ith forecast time and the weather element of the corresponding historical time in the forecast period, t' i For the ith forecast moment, t i For the i-th corresponding history time, +.>Weather element value for the i < th > forecast moment, <>For the weather element value, ω, at the i-th corresponding historical time m The weight value delta of the meteorological element m m For modeling the standard deviation of the meteorological element m in the sample dataset, m is the meteorological element value.
12. The system of claim 8, wherein the meteorological element of the euclidean distance computation module comprises at least one or more of: total irradiance, direct irradiance, scattered irradiance, component temperature, average wind speed, average wind direction, ambient temperature, and relative humidity.
13. The system of claim 8, wherein the photovoltaic power generation predicted power weight calculation module calculates a weight value corresponding to the actual power value of photovoltaic power generation according to the following formula:
wherein eta s The weight value corresponding to the s-th photovoltaic power generation actual power value, t s For the corresponding historical time of s, the value range of s is [1,2, 3. ], j]J is the total number of the preset number,the Euclidean distance between the s-th forecasting time and the weather element of the corresponding historical time in the forecasting period.
14. The system of claim 8, wherein the photovoltaic power generation predicted power calculation module calculates the photovoltaic power generation predicted power value at each forecasted time according to the following equation:
wherein,predicted power value, t 'for photovoltaic power generation at the i-th predicted time in the prediction period' i For the i-th forecast moment, η s And (3) for the weight value corresponding to the s-th photovoltaic power generation actual power value, the value range of s is [1,2,3 ]. The value of j]J is the total number of the preset number, +.>The actual power value of the photovoltaic power generation at the s-th historical moment.
15. A computer device, comprising: one or more processors;
a memory for storing one or more programs;
the photovoltaic power generation short-term power prediction method of any of claims 1 to 7 is implemented when the one or more programs are executed by the one or more processors.
16. A computer readable storage medium, characterized in that a computer program is stored thereon, which computer program, when executed, implements the photovoltaic power generation short-term power prediction method according to any of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210523546.XA CN117117819A (en) | 2022-05-13 | 2022-05-13 | Photovoltaic power generation short-term power prediction method, system, equipment and medium |
| PCT/CN2022/137289 WO2023216576A1 (en) | 2022-05-13 | 2022-12-07 | Photovoltaic power generation short-term power prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210523546.XA CN117117819A (en) | 2022-05-13 | 2022-05-13 | Photovoltaic power generation short-term power prediction method, system, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117117819A true CN117117819A (en) | 2023-11-24 |
Family
ID=88729557
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210523546.XA Pending CN117117819A (en) | 2022-05-13 | 2022-05-13 | Photovoltaic power generation short-term power prediction method, system, equipment and medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN117117819A (en) |
| WO (1) | WO2023216576A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117996756A (en) * | 2024-04-02 | 2024-05-07 | 国网山东省电力公司青州市供电公司 | New energy power generation prediction method and system based on multidimensional influence factors |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117634701A (en) * | 2023-12-13 | 2024-03-01 | 国能日新科技股份有限公司 | Solar radiation short-term forecasting method and system based on regional photovoltaic set forecasting |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6429523B2 (en) * | 2014-07-29 | 2018-11-28 | 日立造船株式会社 | Photovoltaic power generation forecast system |
| CN105005825B (en) * | 2015-07-03 | 2018-12-07 | 深圳供电局有限公司 | A kind of method and system based on dynamic neural network prediction photovoltaic power |
| CN110619360A (en) * | 2019-09-09 | 2019-12-27 | 国家电网有限公司 | Ultra-short-term wind power prediction method considering historical sample similarity |
| CN112257941B (en) * | 2020-10-28 | 2023-04-18 | 福州大学 | Photovoltaic power station short-term power prediction method based on improved Bi-LSTM |
| CN113592141A (en) * | 2021-06-28 | 2021-11-02 | 中国电力科学研究院有限公司 | Photovoltaic power generation power prediction method and device |
-
2022
- 2022-05-13 CN CN202210523546.XA patent/CN117117819A/en active Pending
- 2022-12-07 WO PCT/CN2022/137289 patent/WO2023216576A1/en unknown
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117996756A (en) * | 2024-04-02 | 2024-05-07 | 国网山东省电力公司青州市供电公司 | New energy power generation prediction method and system based on multidimensional influence factors |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023216576A1 (en) | 2023-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ramsami et al. | A hybrid method for forecasting the energy output of photovoltaic systems | |
| CN112348292B (en) | Short-term wind power prediction method and system based on deep learning network | |
| CN102945508B (en) | Model correction based wind power forecasting method | |
| CN112285807B (en) | Meteorological information prediction method and device | |
| CN117117819A (en) | Photovoltaic power generation short-term power prediction method, system, equipment and medium | |
| CN110705771B (en) | Method and device for predicting and optimizing generation power of new energy of regional power grid | |
| CN108053048A (en) | A kind of gradual photovoltaic plant ultra-short term power forecasting method of single step and system | |
| CN110601250B (en) | Method for evaluating stability of static voltage of access point based on new energy power station | |
| CN116306798A (en) | Ultra-short time wind speed prediction method and system | |
| CN113822418A (en) | Wind power plant power prediction method, system, device and storage medium | |
| CN111832800A (en) | Photovoltaic power station power prediction method and device | |
| CN111709569A (en) | Method and device for predicting and correcting output power of wind power plant | |
| CN113361737A (en) | Abnormity early warning method and system for photovoltaic module | |
| CN111697560B (en) | Method and system for predicting load of power system based on LSTM | |
| CN116707331B (en) | Inverter output voltage high-precision adjusting method and system based on model prediction | |
| CN117200223A (en) | Day-ahead power load prediction method and device | |
| CN117526274A (en) | New energy power prediction method, electronic equipment and storage medium in extreme climate | |
| CN115526429A (en) | Decoupling analysis method for wind power prediction error, processor and storage medium | |
| CN115081742A (en) | Ultra-short-term power prediction method for distributed wind power plant and related equipment | |
| CN110705769B (en) | New energy power generation power prediction optimization method and device | |
| CN114565186A (en) | Method and system for correcting predicted wind speed based on generalized regression neural network | |
| CN111027816B (en) | Photovoltaic power generation efficiency calculation method based on data envelope analysis | |
| Liu et al. | A Self-Data-Driven Method for Lifetime Prediction of PV Arrays Considering the Uncertainty and Volatility | |
| CN115563848A (en) | Distributed photovoltaic total radiation prediction method and system based on deep learning | |
| CN112036672B (en) | New energy power generation ultra-short term power prediction method and system based on iterative correction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |