CN112116127B - Photovoltaic power prediction method based on association of meteorological process and power fluctuation - Google Patents
Photovoltaic power prediction method based on association of meteorological process and power fluctuation Download PDFInfo
- Publication number
- CN112116127B CN112116127B CN202010840478.0A CN202010840478A CN112116127B CN 112116127 B CN112116127 B CN 112116127B CN 202010840478 A CN202010840478 A CN 202010840478A CN 112116127 B CN112116127 B CN 112116127B
- Authority
- CN
- China
- Prior art keywords
- power
- fluctuation
- photovoltaic
- value
- sequence
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 92
- 230000005684 electric field Effects 0.000 claims abstract description 32
- 238000001556 precipitation Methods 0.000 claims description 47
- 238000005457 optimization Methods 0.000 claims description 26
- 230000035772 mutation Effects 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 7
- 238000007619 statistical method Methods 0.000 claims description 7
- 238000005096 rolling process Methods 0.000 claims description 6
- 241000143229 Idaea consanguinaria Species 0.000 claims description 3
- 230000007812 deficiency Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- 238000010248 power generation Methods 0.000 description 5
- 238000009412 basement excavation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Water Supply & Treatment (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Public Health (AREA)
- Algebra (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
Abstract
The invention relates to a photovoltaic power prediction method based on association of a meteorological process and power fluctuation, which comprises the following specific steps: the invention aims to provide a photovoltaic power prediction method based on the association of a meteorological process and power fluctuation, which can obviously reduce the error of photovoltaic electric field short-term power prediction.
Description
Technical Field
The invention relates to the field of operation and control of power systems, in particular to a photovoltaic power prediction method based on association of a meteorological process and power fluctuation.
Background
Solar energy is a clean renewable energy source, and as the global demand for clean energy increases, photovoltaic power generation plays an important role. Photovoltaic power generation has received increasing attention over the past few decades, and integration of photovoltaic power generation has brought significant economic and environmental benefits. However, the high permeability of photovoltaic power generation also presents many new challenges to the operation of existing grid systems due to its uncertainty and intermittence. These challenges include sensitivity of the photovoltaic power source to weather conditions, high installation costs, and intermittence of the power generation. Improving the accuracy of photovoltaic power predictions is an effective solution to overcome these challenges.
For photovoltaic systems, the irradiance of the solar spectrum received by the photovoltaic array is often affected by other meteorological factors, and thus the photovoltaic power fluctuation characteristics under different weather conditions are different. This means that the photovoltaic power prediction accuracy depends not only on the selected prediction mode, but also on the weather conditions. The photovoltaic power is predicted in a short period according to the concept of the correlation excavation of the weather process and the power fluctuation process, and the method has important significance for improving the accuracy of the photovoltaic power short-period prediction.
Disclosure of Invention
In order to overcome the defect of inaccurate short-term prediction in the photovoltaic power fluctuation process, the invention divides the photovoltaic electric field power prediction into an ideal day prediction type and a non-ideal day prediction type based on numerical weather forecast data; secondly, defining photovoltaic power fluctuation parameters, expressing fluctuation characteristics of a photovoltaic daily power sequence in a mathematical form, so as to provide discriminant of five fluctuation types of an ideal daily fluctuation model and a non-ideal daily fluctuation type, carrying out statistical analysis on power characteristics corresponding to models divided by meteorological factors in numerical weather forecast, eliminating data of unmatched power and numerical weather forecast, and improving sample quality; and constructing a mapping model of weather factors and photovoltaic power fluctuation parameters based on the photovoltaic power and numerical weather forecast data sets under each fluctuation model. And matching the numerical weather forecast value at each time of the day to be predicted with the corresponding time value of the historical database according to the numerical weather forecast of 15 minutes of the day to be predicted. And finally, carrying out optimization matching on the numerical weather forecast value to be predicted for 72 hours before the day by taking 15min as a unit, taking the power prediction error at the moment with the highest optimization matching degree as a prediction compensation value at the moment, and finally completing the prediction process. Through the expression, the accuracy of the photovoltaic electric field short-term power prediction meets the scheduling requirement.
The invention aims to provide a photovoltaic power prediction method based on the association of a meteorological process and power fluctuation, which can obviously reduce the error of short-term power prediction of a photovoltaic electric field.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a photovoltaic power prediction method based on association of meteorological processes and power fluctuation comprises the following steps:
A. data processing layer: collecting a photovoltaic electric field historical active output power sequence and a numerical weather forecast time sequence, preprocessing collected data, dividing daily historical numerical weather forecast data based on cloud cover, humidity, large-scale precipitation and convection precipitation, determining a weather interval threshold according to a short-term weather forecast national standard, and dividing a photovoltaic electric field power prediction model into an ideal day prediction model and a non-ideal day prediction model;
B. wave definition layer: defining a fluctuation process of a single-day historical active output power sequence, and then describing the fluctuation process by using photovoltaic power fluctuation parameters, wherein the photovoltaic power fluctuation parameters comprise: photovoltaic solar power sequence fluctuation peak value R m The fluctuation frequency f of the photovoltaic solar power sequence and the fluctuation mutation rate eta of the photovoltaic solar power sequence m And photovoltaic solar power sequence fluctuation symmetry degree D P ；
C. Wave division layer: respectively identifying power data under an ideal day prediction model and a non-ideal day prediction model according to photovoltaic power fluctuation parameters, carrying out statistical analysis on the power data and the numerical weather forecast data in the ideal day prediction model, removing data which are not matched with the power data and the numerical weather forecast data, defining the power data and the numerical weather forecast data in the ideal day prediction model as ideal day fluctuation types according to the size of the photovoltaic power fluctuation parameters, and obtaining weather parting thresholds under ideal days; carrying out mathematical statistical analysis on the power data and the numerical weather forecast data in the non-ideal daily prediction model, dividing the power data and the numerical weather forecast data in the non-ideal daily prediction model into small fluctuation types, medium fluctuation types, large fluctuation types and complex strong fluctuation types according to the size of the photovoltaic power fluctuation parameters, and obtaining parting thresholds under each type;
D. prediction layer: respectively constructing a mapping model of weather factors and photovoltaic power fluctuation parameters under an ideal day prediction model and a non-ideal day prediction model; defining a matching error value according to the extreme differences of weather factors in an ideal day prediction model and a non-ideal day prediction model, then constructing a matching error sequence according to a time sequence, setting a matching error threshold, selecting numerical weather forecast data and photovoltaic power data which are smaller than or equal to the matching error threshold in a historical database, and carrying out weighted average on the selected photovoltaic power data according to the matching error value to serve as primary forecast power of a day to be predicted;
E. optimization layer: and D, according to the numerical weather forecast data of the day to be predicted and the weather factor error matching principle in the step D, carrying out optimization matching on the numerical weather forecast data of 72 hours before the day to be predicted by taking 15min as a unit, taking the power forecast error at the moment with the highest optimization matching degree as a forecast compensation value at the moment, and superposing the primary forecast power and the forecast compensation value to obtain a final power forecast value, thereby realizing rolling optimization of power forecast.
Based on the scheme, in the step A, the preprocessing process of the collected data is as follows: and performing deficiency supplement on the historical active output power data and the historical numerical weather forecast data of the photovoltaic electric field with the resolution of 15min according to the time sequence, and finally forming a matrix with one-to-one correspondence between the numerical weather forecast data and the photovoltaic power data.
On the basis of the scheme, in the step A, the section threshold value of weather is determined according to the national standard of short-term weather forecast, firstly, data preprocessing is carried out on the weather forecast time sequence of the historical numerical value of the photovoltaic electric field, and the processing formula is as follows:
in nwp cls,lag Refers to the value of the cls number weather forecast factor at lag moment in the historical number weather forecast time sequence of the photovoltaic electric field, nwp cls,lag Cls=1, 2,3,4 refers to four numerical weather predictors of cloud cover, humidity, large-scale precipitation, convection precipitation, respectively; n is n d Indicating the number of time points in the day under the forecast with 15min as the time interval;the method is characterized in that the method refers to a single day daytime average value of a cls number weather forecast factor in a photovoltaic electric field historical number weather forecast time sequence;
secondly, defining single day daytime precipitation time according to large-scale precipitation and convection precipitation:
wherein p is l la The precipitation amount of the large-scale precipitation at the time la is in millimeters; p is p s lb The unit is millimeter for the precipitation amount of convection precipitation at lb time; t is t pl Counting when the large-scale precipitation amount is larger than 0 for the number of time points of large-scale precipitation in a single day; t is t ps Counting when the convection precipitation amount is more than 0; t is t p Taking t as the number of time points of precipitation in daytime on a single day pl And t ps Maximum value of (2);
finally, according to the historical numerical weather forecast time sequence preprocessing method and precipitation time definition, a parting formula of an ideal day prediction model and a non-ideal day prediction model is given by combining the short-term weather forecast national standard:
ideal day prediction model:
non-ideal day prediction model:
or (b)
t p ∈(0,∞) (5)
In the method, in the process of the invention,c is the average value of cloud amount in daytime on a single day 1 C, referring to the national standard of short-term weather forecast for the upper threshold limit of the single-day daytime average value of cloud cover in an ideal day prediction model 1 ＝0.3。
On the basis of the scheme, in the step B, the process of defining the fluctuation process of the single-day historical active output power sequence is as follows: analyzing the historical active output power sequence of 96 points in a single day by taking 15min as resolution, and carrying out normalization processing on the historical active output power sequence before analysis:
wherein:for normalizing the photovoltaic electric field power sequence, +.>Wherein P is max ,P min The maximum value and the minimum value in the single day history active output power sequence P are respectively.
On the basis of the scheme, in the step B, the photovoltaic daily power sequence refers to a photovoltaic electric field single-day historical active output power sequence, wherein the photovoltaic daily power sequence fluctuates to peak value R m The following formula is shown:
in the method, in the process of the invention,output power value representing instant i in normalized photovoltaic solar power sequence,/>Representing the output power value, t, at the moment i+1 in the normalized photovoltaic solar power sequence nw Representing a time value corresponding to an extreme point of the photovoltaic daily power sequence;
the photovoltaic solar power sequence fluctuation frequency f is shown as follows:
wherein n is tw Representing the number of extreme points, n, of normalized photovoltaic solar power sequences t Represents the total number of time points of the normalized photovoltaic daily power sequence, n t The value is 96;
photovoltaic solar power sequence fluctuation mutation rate eta m The following formula is shown:
η m ＝max{tl s },s＝1,2,…,n tw (10)
wherein t is 1 Representing a time value, t, corresponding to an extreme point 1 of a normalized photovoltaic solar power sequence s-1 Representing a time value, t, corresponding to an extreme point s-1 of a normalized photovoltaic solar power sequence s Representing the time value corresponding to the extreme point s of the normalized photovoltaic solar power sequence, tl s Representing the time interval between two adjacent extreme points of the normalized photovoltaic daily power sequence;
photovoltaic solar power sequence fluctuation symmetry degree D P The following formula is shown:
in the method, in the process of the invention,refers to the maximum value of the normalized photovoltaic daily power sequence,/-or%>Respectively refers to minimum values at the left and right sides of the maximum value of the normalized photovoltaic solar power sequence, t max Refers to the time t corresponding to the maximum value of the normalized photovoltaic daily power sequence min1 Refers to the time t corresponding to the minimum value at the left side of the maximum value of the normalized photovoltaic solar power sequence min2 The time corresponding to the minimum value on the right of the maximum value of the normalized photovoltaic daily power sequence is referred.
Based on the above scheme, in step C, the discriminant of the ideal solar fluctuation type is:
wherein R is m Is the fluctuation peak value of the photovoltaic solar power sequence, D P The symmetry degree of fluctuation of the photovoltaic solar power sequence is f the fluctuation frequency of the photovoltaic solar power sequence, P N Rated output power of the photovoltaic electric field; lambda (lambda) 1 Refers to the upper threshold limit, mu, of the fluctuation peak value of the photovoltaic solar power sequence in an ideal solar fluctuation model 0 Refers to the threshold lower limit, mu, of the fluctuation symmetry degree of the photovoltaic solar power sequence in an ideal solar fluctuation model 1 Refers to the upper threshold limit epsilon of the fluctuation symmetry degree of the photovoltaic solar power sequence in an ideal solar fluctuation model 0 The photovoltaic solar power sequence fluctuation frequency threshold upper limit in the ideal solar fluctuation model is referred;
discriminant of the small fluctuation type:
wherein eta is m For photovoltaic solar power sequence fluctuating mutation rate, lambda 2 Refers to the upper threshold limit, mu, of the fluctuation peak value of the photovoltaic solar power sequence in the small fluctuation model 2 Refers to photovoltaic solar power sequence in a small fluctuation modelUpper threshold of column fluctuation symmetry, delta 1 Refers to the threshold upper limit epsilon of the fluctuation mutation rate of the photovoltaic solar power sequence in the small, medium and large fluctuation models 1 The upper threshold value of the fluctuation frequency of the photovoltaic solar power sequence in the small and medium fluctuation models is referred;
the discriminant of the medium fluctuation type:
wherein lambda is 3 Refers to the upper threshold limit, mu, of the fluctuation peak value of the photovoltaic solar power sequence in the medium fluctuation model 3 The upper threshold value limit of the fluctuation symmetry degree of the photovoltaic solar power sequence in the medium fluctuation model is referred;
discriminant of the large fluctuation type:
wherein mu is 4 The upper threshold limit of the fluctuation symmetry degree of the photovoltaic solar power sequence in the large fluctuation model is referred;
discriminant of the complex strong fluctuation type:
based on the above scheme, the expression of the mapping model in the step D is:
wherein,refers to the parameter value, P, of the nth numerical weather forecast factor at the m time m Refers to the measured power at m time.
Based on the above scheme, in the step D, the specific determination mode of the matching error value is as follows:
wherein,refers to the parameter value of the u normalized value weather forecast factor at the v moment,/> Refers to the parameter value of the u-th numerical weather forecast factor at the moment v, max (x (u) )、min(x (u) ) Respectively the (u) th numerical weather forecast factor sequence x (u) Maximum and minimum of>The u normalized value weather forecast factor sequence +.>Maximum and minimum of>The matching error value of the u-th numerical weather forecast factor;
wherein,refers to the forecast value of the u-th normalized numerical weather forecast factor at the moment v of the day to be forecast,refers to the value of the u-th historical normalized value weather predictor at the k moment, mark v,k The matching degree score of the numerical weather forecast factor of the day to be predicted at the moment v and the numerical value at the moment k in the historical numerical weather forecast factor is indicated.
Based on the above scheme, in the step D, the specific expression of the primary forecast power is as follows:
wherein, xi r Refers to a match error threshold;the value of the kr moment in the historical power sequence matched with the time of day v to be predicted is referred; />The weighting coefficient of the matched historical power at the kr moment in the power at the time of day v to be predicted;is the primary forecast power value at the time of day v to be predicted.
Based on the above scheme, the expression of the final predicted value of power in step E is as follows:
wherein err is v Refers to the predicted compensation value at the time of day v to be predicted,refers to the actual power value of v in hr days before day to be predicted, < >>Refers to the predicted value of power at time v in hr days before day to be predicted,/day>Is the final predicted value of the power at the time of day v to be predicted.
Based on the above scheme, the rolling optimization of the power prediction in step E refers to: the final predicted value of the power after the prediction optimization process becomes the object to be matched of the historical database in the prediction optimization process of the next moment, so that a data foundation is laid for the optimization of the predicted power of the next moment.
Drawings
The invention has the following drawings:
fig. 1 is a photovoltaic electric field power prediction method based on weather process and power fluctuation process correlation mining.
Detailed Description
The present invention will be described in further detail with reference to fig. 1.
A photovoltaic power prediction method based on association of meteorological processes and power fluctuation comprises the following steps:
A. data processing layer: collecting a photovoltaic electric field historical active output power sequence and a numerical weather forecast time sequence, preprocessing collected data, dividing daily historical numerical weather forecast data based on cloud cover, humidity, large-scale precipitation and convection precipitation, determining a weather interval threshold according to a short-term weather forecast national standard, and dividing a photovoltaic electric field power prediction model into an ideal day prediction model and a non-ideal day prediction model;
B. wave definition layer: determining fluctuation process of single-day historical active output power sequenceThe fluctuation process is then depicted with photovoltaic power fluctuation parameters including: photovoltaic solar power sequence fluctuation peak value R m The fluctuation frequency f of the photovoltaic solar power sequence and the fluctuation mutation rate eta of the photovoltaic solar power sequence m And photovoltaic solar power sequence fluctuation symmetry degree D P ；
C. Wave division layer: respectively identifying power data under an ideal day prediction model and a non-ideal day prediction model according to photovoltaic power fluctuation parameters, carrying out statistical analysis on the power data and the numerical weather forecast data in the ideal day prediction model, removing data which are not matched with the power data and the numerical weather forecast data, defining the power data and the numerical weather forecast data in the ideal day prediction model as ideal day fluctuation types according to the size of the photovoltaic power fluctuation parameters, and obtaining weather parting thresholds under ideal days; carrying out mathematical statistical analysis on the power data and the numerical weather forecast data in the non-ideal daily prediction model, dividing the power data and the numerical weather forecast data in the non-ideal daily prediction model into small fluctuation types, medium fluctuation types, large fluctuation types and complex strong fluctuation types according to the size of the photovoltaic power fluctuation parameters, and obtaining parting thresholds under each type;
D. prediction layer: respectively constructing a mapping model of weather factors and photovoltaic power fluctuation parameters under an ideal day prediction model and a non-ideal day prediction model; defining a matching error value according to the extreme differences of weather factors in an ideal day prediction model and a non-ideal day prediction model, then constructing a matching error sequence according to a time sequence, setting a matching error threshold, selecting numerical weather forecast data and photovoltaic power data which are smaller than or equal to the matching error threshold in a historical database, and carrying out weighted average on the selected photovoltaic power data according to the matching error value to serve as primary forecast power of a day to be predicted;
E. optimization layer: and D, according to the numerical weather forecast data of the day to be predicted and the weather factor error matching principle in the step D, carrying out optimization matching on the numerical weather forecast data of 72 hours before the day to be predicted by taking 15min as a unit, taking the power forecast error at the moment with the highest optimization matching degree as a forecast compensation value at the moment, and superposing the primary forecast power and the forecast compensation value to obtain a final power forecast value, thereby realizing rolling optimization of power forecast.
Based on the scheme, in the step A, the preprocessing process of the collected data is as follows: and performing deficiency supplement on the historical active output power data and the historical numerical weather forecast data of the photovoltaic electric field with the resolution of 15min according to the time sequence, and finally forming a matrix with one-to-one correspondence between the numerical weather forecast data and the photovoltaic power data.
On the basis of the scheme, in the step A, the section threshold value of weather is determined according to the national standard of short-term weather forecast, firstly, data preprocessing is carried out on the weather forecast time sequence of the historical numerical value of the photovoltaic electric field, and the processing formula is as follows:
in nwp cls,lag Refers to the value of the cls number weather forecast factor at lag moment in the historical number weather forecast time sequence of the photovoltaic electric field, nwp cls,lag Cls=1, 2,3,4 refers to four numerical weather predictors of cloud cover, humidity, large-scale precipitation, convection precipitation, respectively; n is n d Indicating the number of time points in the day under the forecast with 15min as the time interval;the method is characterized in that the method refers to a single day daytime average value of a cls number weather forecast factor in a photovoltaic electric field historical number weather forecast time sequence;
secondly, defining single day daytime precipitation time according to large-scale precipitation and convection precipitation:
wherein p is l la The precipitation amount of the large-scale precipitation at the time la is in millimeters; p is p s lb Is convection currentPrecipitation amount of precipitation at lb time, wherein the unit is millimeter; t is t pl Counting when the large-scale precipitation amount is larger than 0 for the number of time points of large-scale precipitation in a single day; t is t ps Counting when the convection precipitation amount is more than 0; t is t p Taking t as the number of time points of precipitation in daytime on a single day pl And t ps Maximum value of (2);
finally, according to the historical numerical weather forecast time sequence preprocessing method and precipitation time definition, a parting formula of an ideal day prediction model and a non-ideal day prediction model is given by combining the short-term weather forecast national standard:
ideal day prediction model:
non-ideal day prediction model:
or (b)
t p ∈(0,∞) (5)
In the method, in the process of the invention,c is the average value of cloud amount in daytime on a single day 1 C, referring to the national standard of short-term weather forecast for the upper threshold limit of the single-day daytime average value of cloud cover in an ideal day prediction model 1 ＝0.3。
On the basis of the scheme, in the step B, the process of defining the fluctuation process of the single-day historical active output power sequence is as follows: analyzing the historical active output power sequence of 96 points in a single day by taking 15min as resolution, and carrying out normalization processing on the historical active output power sequence before analysis:
wherein:for normalizing the photovoltaic electric field power sequence, +.>Wherein P is max ,P min The maximum value and the minimum value in the single day history active output power sequence P are respectively.
On the basis of the scheme, in the step B, the photovoltaic daily power sequence refers to a photovoltaic electric field single-day historical active output power sequence, wherein the photovoltaic daily power sequence fluctuates to peak value R m The following formula is shown:
in the method, in the process of the invention,output power value representing instant i in normalized photovoltaic solar power sequence,/>Representing the output power value, t, at the moment i+1 in the normalized photovoltaic solar power sequence nw Representing a time value corresponding to an extreme point of the photovoltaic daily power sequence;
the photovoltaic solar power sequence fluctuation frequency f is shown as follows:
wherein n is tw Representing the number of extreme points, n, of normalized photovoltaic solar power sequences t Represents the total number of time points of the normalized photovoltaic daily power sequence, n t The value is 96;
photovoltaic solar power sequence fluctuation mutation rate eta m As followsThe illustration is:
η m ＝max{tl s },s＝1,2,…,n tw (10)
wherein t is 1 Representing a time value, t, corresponding to an extreme point 1 of a normalized photovoltaic solar power sequence s-1 Representing a time value, t, corresponding to an extreme point s-1 of a normalized photovoltaic solar power sequence s Representing the time value corresponding to the extreme point s of the normalized photovoltaic solar power sequence, tl s Representing the time interval between two adjacent extreme points of the normalized photovoltaic daily power sequence;
photovoltaic solar power sequence fluctuation symmetry degree D P The following formula is shown:
in the method, in the process of the invention,refers to the maximum value of the normalized photovoltaic daily power sequence,/-or%>Respectively refers to minimum values at the left and right sides of the maximum value of the normalized photovoltaic solar power sequence, t max Refers to the time t corresponding to the maximum value of the normalized photovoltaic daily power sequence min1 Refers to the time t corresponding to the minimum value at the left side of the maximum value of the normalized photovoltaic solar power sequence min2 The time corresponding to the minimum value on the right of the maximum value of the normalized photovoltaic daily power sequence is referred.
Based on the above scheme, in step C, the discriminant of the ideal solar fluctuation type is:
wherein R is m Is the fluctuation peak value of the photovoltaic solar power sequence, D P The symmetry degree of fluctuation of the photovoltaic solar power sequence is f the fluctuation frequency of the photovoltaic solar power sequence, P N Rated output power of the photovoltaic electric field; lambda (lambda) 1 Refers to the upper threshold limit, mu, of the fluctuation peak value of the photovoltaic solar power sequence in an ideal solar fluctuation model 0 Refers to the threshold lower limit, mu, of the fluctuation symmetry degree of the photovoltaic solar power sequence in an ideal solar fluctuation model 1 Refers to the upper threshold limit epsilon of the fluctuation symmetry degree of the photovoltaic solar power sequence in an ideal solar fluctuation model 0 The photovoltaic solar power sequence fluctuation frequency threshold upper limit in the ideal solar fluctuation model is referred;
discriminant of the small fluctuation type:
wherein eta is m For photovoltaic solar power sequence fluctuating mutation rate, lambda 2 Refers to the upper threshold limit, mu, of the fluctuation peak value of the photovoltaic solar power sequence in the small fluctuation model 2 Refers to the threshold upper limit, delta of the fluctuation symmetry degree of the photovoltaic solar power sequence in the small fluctuation model 1 Refers to the threshold upper limit epsilon of the fluctuation mutation rate of the photovoltaic solar power sequence in the small, medium and large fluctuation models 1 The upper threshold value of the fluctuation frequency of the photovoltaic solar power sequence in the small and medium fluctuation models is referred;
the discriminant of the medium fluctuation type:
wherein lambda is 3 Refers to the upper threshold limit, mu, of the fluctuation peak value of the photovoltaic solar power sequence in the medium fluctuation model 3 The upper threshold value limit of the fluctuation symmetry degree of the photovoltaic solar power sequence in the medium fluctuation model is referred;
discriminant of the large fluctuation type:
wherein mu is 4 The upper threshold limit of the fluctuation symmetry degree of the photovoltaic solar power sequence in the large fluctuation model is referred;
discriminant of the complex strong fluctuation type:
based on the above scheme, the expression of the mapping model in the step D is:
wherein,refers to the parameter value, P, of the nth numerical weather forecast factor at the m time m Refers to the measured power at m time.
Based on the above scheme, in the step D, the specific determination mode of the matching error value is as follows:
wherein,refers to the parameter value of the u normalized value weather forecast factor at the v moment,/> Refers to the parameter value of the u-th numerical weather forecast factor at the moment v, max (x (u) )、min(x (u) ) Respectively the (u) th numerical weather forecast factor sequence x (u) Maximum and minimum of>The u normalized value weather forecast factor sequence +.>Maximum and minimum of>The matching error value of the u-th numerical weather forecast factor;
wherein,refers to the forecast value of the u-th normalized numerical weather forecast factor at the moment v of the day to be forecast,refers to the value of the u-th historical normalized value weather predictor at the k moment, mark v,k The matching degree score of the numerical weather forecast factor of the day to be predicted at the moment v and the numerical value at the moment k in the historical numerical weather forecast factor is indicated.
Based on the above scheme, in the step D, the specific expression of the primary forecast power is as follows:
wherein, xi r Refers to a match error threshold;the value of the kr moment in the historical power sequence matched with the time of day v to be predicted is referred; />The weighting coefficient of the matched historical power at the kr moment in the power at the time of day v to be predicted; />Is the primary forecast power value at the time of day v to be predicted. />
Based on the above scheme, the expression of the final predicted value of power in step E is as follows:
wherein err is v Refers to the predicted compensation value at the time of day v to be predicted,refers to the actual power value of v in hr days before day to be predicted, < >>Refers to the predicted value of power at time v in hr days before day to be predicted,/day>Is the final predicted value of the power at the time of day v to be predicted.
Based on the above scheme, the rolling optimization of the power prediction in step E refers to: the final predicted value of the power after the prediction optimization process becomes the object to be matched of the historical database in the prediction optimization process of the next moment, so that a data foundation is laid for the optimization of the predicted power of the next moment.
What is not described in detail in this specification is prior art known to those skilled in the art.
Claims (10)
1. The photovoltaic power prediction method based on the association of the meteorological process and the power fluctuation is characterized by comprising the following steps of:
A. data processing layer: collecting a photovoltaic electric field historical active output power sequence and a numerical weather forecast time sequence, preprocessing collected data, dividing daily historical numerical weather forecast data based on cloud cover, humidity, large-scale precipitation and convection precipitation, determining a weather interval threshold according to a short-term weather forecast national standard, and dividing a photovoltaic electric field power prediction model into an ideal day prediction model and a non-ideal day prediction model;
B. wave definition layer: defining a fluctuation process of a single-day historical active output power sequence, and then describing the fluctuation process by using photovoltaic power fluctuation parameters, wherein the photovoltaic power fluctuation parameters comprise: photovoltaic solar power sequence fluctuation peak value R m The fluctuation frequency f of the photovoltaic solar power sequence and the fluctuation mutation rate h of the photovoltaic solar power sequence m And photovoltaic solar power sequence fluctuation symmetry degree D P ；
C. Wave division layer: respectively identifying power data under an ideal day prediction model and a non-ideal day prediction model according to photovoltaic power fluctuation parameters, carrying out statistical analysis on the power data and the numerical weather forecast data in the ideal day prediction model, removing data which are not matched with the power data and the numerical weather forecast data, defining the power data and the numerical weather forecast data in the ideal day prediction model as ideal day fluctuation types according to the size of the photovoltaic power fluctuation parameters, and obtaining weather parting thresholds under ideal days; carrying out mathematical statistical analysis on the power data and the numerical weather forecast data in the non-ideal daily prediction model, dividing the power data and the numerical weather forecast data in the non-ideal daily prediction model into small fluctuation types, medium fluctuation types, large fluctuation types and complex strong fluctuation types according to the size of the photovoltaic power fluctuation parameters, and obtaining parting thresholds under each type;
D. prediction layer: respectively constructing a mapping model of weather factors and photovoltaic power fluctuation parameters under an ideal day prediction model and a non-ideal day prediction model; defining a matching error value according to the extreme differences of weather factors in an ideal day prediction model and a non-ideal day prediction model, then constructing a matching error sequence according to a time sequence, setting a matching error threshold, selecting numerical weather forecast data and photovoltaic power data which are smaller than or equal to the matching error threshold in a historical database, and carrying out weighted average on the selected photovoltaic power data according to the matching error value to serve as primary forecast power of a day to be predicted;
E. optimization layer: and D, according to the numerical weather forecast data of the day to be forecast, and the processing step of the forecast layer, carrying out optimization matching on the numerical weather forecast data of 72 hours before the day to be forecast by taking 15min as a unit, taking the power forecast error at the moment with the highest optimization matching degree as a forecast compensation value at the moment, and superposing the primary forecast power and the forecast compensation value to obtain a final power forecast value, thereby realizing rolling optimization of power forecast.
2. The photovoltaic power prediction method based on the association of meteorological processes with power fluctuations according to claim 1, wherein in step a, the process of preprocessing the collected data is: and performing deficiency supplement on the historical active output power data and the historical numerical weather forecast data of the photovoltaic electric field with the resolution of 15min according to the time sequence, and finally forming a matrix with one-to-one correspondence between the numerical weather forecast data and the photovoltaic power data.
3. The photovoltaic power prediction method based on the association of meteorological processes and power fluctuation according to claim 1, wherein in the step a, a weather interval threshold is determined according to a short-term weather forecast national standard, and data preprocessing is firstly performed on a photovoltaic electric field historical numerical weather forecast time sequence, and a processing formula is as follows:
in nwp cls,lag Refers to the value of the cls number weather forecast factor at lag moment in the historical number weather forecast time sequence of the photovoltaic electric field, nwp cls,lag Cls=1, 2,3,4 refers to four numerical weather predictors of cloud cover, humidity, large-scale precipitation, convection precipitation, respectively; n is n d Indicating the number of time points in the day under the forecast with 15min as the time interval;the method is characterized in that the method refers to a single day daytime average value of a cls number weather forecast factor in a photovoltaic electric field historical number weather forecast time sequence;
secondly, defining single day daytime precipitation time according to large-scale precipitation and convection precipitation:
wherein p is l la The precipitation amount of the large-scale precipitation at the time la is in millimeters; p is p s lb The unit is millimeter for the precipitation amount of convection precipitation at lb time; t is t pl Counting when the large-scale precipitation amount is larger than 0 for the number of time points of large-scale precipitation in a single day; t is t ps Counting when the convection precipitation amount is more than 0; t is t p Taking t as the number of time points of precipitation in daytime on a single day pl And t ps Maximum value of (2);
finally, according to the historical numerical weather forecast time sequence preprocessing method and precipitation time definition, a parting formula of an ideal day prediction model and a non-ideal day prediction model is given by combining the short-term weather forecast national standard:
ideal day prediction model:
non-ideal day prediction model:
or (b)
t p ∈(0,∞) (5)
In the method, in the process of the invention,c is the average value of cloud amount in daytime on a single day 1 C, referring to the national standard of short-term weather forecast for the upper threshold limit of the single-day daytime average value of cloud cover in an ideal day prediction model 1 ＝0.3。
4. The photovoltaic power prediction method based on the association of meteorological processes and power fluctuation according to claim 1, wherein in the step B, the process of defining the fluctuation process of the single day history active output power sequence is: analyzing the historical active output power sequence of 96 points in a single day by taking 15min as resolution, and carrying out normalization processing on the historical active output power sequence before analysis:
wherein:for normalizing the photovoltaic electric field power sequence, +.>Wherein P is max ,P min The maximum value and the minimum value in the single day history active output power sequence P are respectively.
5. The photovoltaic power prediction method based on the association of meteorological processes with power fluctuations according to claim 1, wherein in step B, theThe photovoltaic daily power sequence refers to a single-day historical active output power sequence of a photovoltaic electric field, wherein the photovoltaic daily power sequence fluctuates and peak value R m The following formula is shown:
in the method, in the process of the invention,output power value representing instant i in normalized photovoltaic solar power sequence,/>Representing the output power value, t, at the moment i+1 in the normalized photovoltaic solar power sequence nw Representing a time value corresponding to an extreme point of the photovoltaic daily power sequence;
the photovoltaic solar power sequence fluctuation frequency f is shown as follows:
wherein n is tw Representing the number of extreme points, n, of normalized photovoltaic solar power sequences t Represents the total number of time points of the normalized photovoltaic daily power sequence, n t The value is 96;
photovoltaic solar power sequence fluctuation mutation rate h m The following formula is shown:
h m ＝max{tl s },s＝1,2,...,n nw (10)
wherein t is 1 Representing a time value, t, corresponding to an extreme point 1 of a normalized photovoltaic solar power sequence s-1 Representing a time value, t, corresponding to an extreme point s-1 of a normalized photovoltaic solar power sequence s Representing the time value corresponding to the extreme point s of the normalized photovoltaic solar power sequence, tl s Representing the time interval between two adjacent extreme points of the normalized photovoltaic daily power sequence;
photovoltaic solar power sequence fluctuation symmetry degree D P The following formula is shown:
in the method, in the process of the invention,refers to the maximum value of the normalized photovoltaic daily power sequence,/-or%>Respectively refers to minimum values at the left and right sides of the maximum value of the normalized photovoltaic solar power sequence, t max Refers to the time t corresponding to the maximum value of the normalized photovoltaic daily power sequence min1 Refers to the time t corresponding to the minimum value at the left side of the maximum value of the normalized photovoltaic solar power sequence min2 The time corresponding to the minimum value on the right of the maximum value of the normalized photovoltaic daily power sequence is referred.
6. The photovoltaic power prediction method based on meteorological process and power fluctuation association of claim 5, wherein in step C, the discriminant of ideal solar fluctuation type:
wherein R is m Is the fluctuation peak value of the photovoltaic solar power sequence, D P The symmetry degree of fluctuation of the photovoltaic solar power sequence is f the fluctuation frequency of the photovoltaic solar power sequence, P N Rated output power of the photovoltaic electric field; lambda (lambda) 1 Refers to the upper threshold limit, mu, of the fluctuation peak value of the photovoltaic solar power sequence in an ideal solar fluctuation model 0 Refers to the threshold lower limit, mu, of the fluctuation symmetry degree of the photovoltaic solar power sequence in an ideal solar fluctuation model 1 Refers to photovoltaic solar power sequence fluctuation in an ideal solar fluctuation modelUpper threshold of symmetry, ε 0 The photovoltaic solar power sequence fluctuation frequency threshold upper limit in the ideal solar fluctuation model is referred;
discriminant of the small fluctuation type:
in the formula, h m For photovoltaic solar power sequence fluctuating mutation rate, lambda 2 Refers to the upper threshold limit, mu, of the fluctuation peak value of the photovoltaic solar power sequence in the small fluctuation model 2 Refers to the threshold upper limit, delta of the fluctuation symmetry degree of the photovoltaic solar power sequence in the small fluctuation model 1 Refers to the threshold upper limit epsilon of the fluctuation mutation rate of the photovoltaic solar power sequence in the small, medium and large fluctuation models 1 The upper threshold value of the fluctuation frequency of the photovoltaic solar power sequence in the small and medium fluctuation models is referred;
the discriminant of the medium fluctuation type:
wherein lambda is 3 Refers to the upper threshold limit, mu, of the fluctuation peak value of the photovoltaic solar power sequence in the medium fluctuation model 3 The upper threshold value limit of the fluctuation symmetry degree of the photovoltaic solar power sequence in the medium fluctuation model is referred;
discriminant of the large fluctuation type:
wherein mu is 4 The upper threshold limit of the fluctuation symmetry degree of the photovoltaic solar power sequence in the large fluctuation model is referred;
discriminant of the complex strong fluctuation type:
7. the photovoltaic power prediction method based on the association of meteorological processes with power fluctuations according to claim 6, wherein the expression of the mapping model in step D is:
wherein,refers to the parameter value, P, of the nth numerical weather forecast factor at the m time m Refers to the measured power at m time.
8. The photovoltaic power prediction method based on the association of meteorological processes and power fluctuations according to claim 7, wherein in step D, the matching error value is specifically determined as follows:
wherein,refers to the parameter value of the u normalized value weather forecast factor at the v moment,/>Refers to the parameter value of the u-th numerical weather forecast factor at the moment v, max (x (u) )、min(x (u) ) Respectively the (u) th numerical weather forecast factor sequence x (u) Maximum and minimum of>The u normalized value weather forecast factor sequence +.>Maximum and minimum of>The matching error value of the u-th numerical weather forecast factor;
wherein,means the forecast value of the u-th normalized value weather forecast factor at the moment v of the day to be forecast,/>Refers to the value of the u-th historical normalized value weather predictor at the k moment, mark v,k The matching degree score of the numerical weather forecast factor of the day to be predicted at the moment v and the numerical value at the moment k in the historical numerical weather forecast factor is indicated.
9. The photovoltaic power prediction method based on the association of meteorological processes and power fluctuations according to claim 8, wherein in step D, the specific expression of the primary prediction power is as follows:
wherein x is r Refers to a match error threshold;the value of the kr moment in the historical power sequence matched with the time of day v to be predicted is referred; />The weighting coefficient of the matched historical power at the kr moment in the power at the time of day v to be predicted; />The primary forecast power value at the time of day v to be predicted;
the expression of the final predicted value of the power in step E is as follows:
wherein err is v Refers to the predicted compensation value at the time of day v to be predicted,refers to the actual power value of v in hr days before day to be predicted, < >>Refers to the predicted value of power at time v in hr days before day to be predicted,/day>Is the final predicted value of the power at the time of day v to be predicted.
10. The photovoltaic power prediction method based on the association of meteorological processes with power fluctuations according to claim 1, wherein the rolling optimization of power prediction in step E means: the final predicted value of the power after the prediction optimization process becomes the object to be matched of the historical database in the prediction optimization process of the next moment, so that a data foundation is laid for the optimization of the predicted power of the next moment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010840478.0A CN112116127B (en) | 2020-08-20 | 2020-08-20 | Photovoltaic power prediction method based on association of meteorological process and power fluctuation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010840478.0A CN112116127B (en) | 2020-08-20 | 2020-08-20 | Photovoltaic power prediction method based on association of meteorological process and power fluctuation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112116127A CN112116127A (en) | 2020-12-22 |
| CN112116127B true CN112116127B (en) | 2024-04-02 |
Family
ID=73805254
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010840478.0A Active CN112116127B (en) | 2020-08-20 | 2020-08-20 | Photovoltaic power prediction method based on association of meteorological process and power fluctuation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112116127B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113537575B (en) * | 2021-06-25 | 2023-11-21 | 中国农业大学 | Trend load prediction method containing distributed photovoltaic and electric automobile grid connection |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117975A (en) * | 2015-08-06 | 2015-12-02 | 国家电网公司 | Frequency division prediction method of photovoltaic output power value |
| WO2017054537A1 (en) * | 2015-09-30 | 2017-04-06 | 中国电力科学研究院 | Long-time scale photovoltaic output time sequence modelling method and apparatus |
| WO2018129828A1 (en) * | 2017-01-11 | 2018-07-19 | 沃太能源南通有限公司 | Photovoltaic power generation predicting system and prediction method |
| CN108388956A (en) * | 2018-01-18 | 2018-08-10 | 华北电力大学 | Consider the photovoltaic power prediction technique of attenuation |
| CN109615131A (en) * | 2018-12-07 | 2019-04-12 | 国能日新科技股份有限公司 | Photovoltaic power prediction technique and device |
| CN110705789A (en) * | 2019-09-30 | 2020-01-17 | 国网青海省电力公司经济技术研究院 | Photovoltaic power station short-term power prediction method |
-
2020
- 2020-08-20 CN CN202010840478.0A patent/CN112116127B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117975A (en) * | 2015-08-06 | 2015-12-02 | 国家电网公司 | Frequency division prediction method of photovoltaic output power value |
| WO2017054537A1 (en) * | 2015-09-30 | 2017-04-06 | 中国电力科学研究院 | Long-time scale photovoltaic output time sequence modelling method and apparatus |
| WO2018129828A1 (en) * | 2017-01-11 | 2018-07-19 | 沃太能源南通有限公司 | Photovoltaic power generation predicting system and prediction method |
| CN108388956A (en) * | 2018-01-18 | 2018-08-10 | 华北电力大学 | Consider the photovoltaic power prediction technique of attenuation |
| CN109615131A (en) * | 2018-12-07 | 2019-04-12 | 国能日新科技股份有限公司 | Photovoltaic power prediction technique and device |
| CN110705789A (en) * | 2019-09-30 | 2020-01-17 | 国网青海省电力公司经济技术研究院 | Photovoltaic power station short-term power prediction method |
Non-Patent Citations (2)
| Title |
|---|
| 一种光伏系统短期功率预测模型;刘沛汉;吐尔逊·伊不拉音;赵力;四川电力技术;20151231(第001期);全文 * |
| 风光水多能互补发电系统日内时间尺度运行特性分析;叶林;屈晓旭;么艳香;张节潭;王跃峰;黄越辉;王伟胜;;电力系统自动化;20171229(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112116127A (en) | 2020-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112257941B (en) | Photovoltaic power station short-term power prediction method based on improved Bi-LSTM | |
| CN107766990B (en) | Method for predicting power generation power of photovoltaic power station | |
| CN109002915B (en) | Photovoltaic power station short-term power prediction method based on Kmeans-GRA-Elman model | |
| CN106529814B (en) | Distributed photovoltaic ultra-short term prediction method based on Adaboost clustering and Markov chain | |
| CN110880789B (en) | Economic dispatching method for wind power and photovoltaic combined power generation system | |
| CN110909919A (en) | Photovoltaic power prediction method of depth neural network model with attention mechanism fused | |
| Melzi et al. | Hourly solar irradiance forecasting based on machine learning models | |
| CN105631558A (en) | BP neural network photovoltaic power generation system power prediction method based on similar day | |
| CN109934395B (en) | Multi-hydropower-region short-term power load prediction method based on time-sharing and regional meteorological data | |
| CN107403015B (en) | Short-term optical power prediction method based on time series similarity | |
| CN111626473A (en) | Two-stage photovoltaic power prediction method considering error correction | |
| CN112418346B (en) | Numerical weather forecast total radiation system error classification calculation method | |
| CN115829105A (en) | Photovoltaic power prediction method based on historical data feature search | |
| CN115441447B (en) | New energy power generation power prediction method | |
| Yang et al. | Photovoltaic power forecasting with a rough set combination method | |
| Wang et al. | Solar power prediction with data source weighted nearest neighbors | |
| CN107256437B (en) | Photovoltaic power station ultra-short-term irradiance prediction method and system | |
| CN115481918A (en) | Active sensing and predictive analysis system for unit state based on source network load storage | |
| CN112116127B (en) | Photovoltaic power prediction method based on association of meteorological process and power fluctuation | |
| CN104915727A (en) | Multi-dimensional isomorphic heterogeneous BP neural network optical power ultrashort-term prediction method | |
| CN108694475B (en) | Short-time-scale photovoltaic cell power generation capacity prediction method based on hybrid model | |
| CN111967660B (en) | Ultra-short-term photovoltaic prediction residual error correction method based on SVR | |
| CN112348236B (en) | Abnormal daily load demand prediction system and method for intelligent electricity consumption monitoring terminal | |
| CN116484998A (en) | Distributed photovoltaic power station power prediction method and system based on meteorological similar day | |
| CN116611702A (en) | Integrated learning photovoltaic power generation prediction method for building integrated energy management |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |