CN116070888A - Virtual power plant adjustable capacity analysis method, device and medium based on decision tree - Google Patents

Virtual power plant adjustable capacity analysis method, device and medium based on decision tree Download PDF

Info

Publication number
CN116070888A
CN116070888A CN202310355630.XA CN202310355630A CN116070888A CN 116070888 A CN116070888 A CN 116070888A CN 202310355630 A CN202310355630 A CN 202310355630A CN 116070888 A CN116070888 A CN 116070888A
Authority
CN
China
Prior art keywords
load
decision tree
adjustable capacity
power plant
demand response
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.)
Granted
Application number
CN202310355630.XA
Other languages
Chinese (zh)
Other versions
CN116070888B (en
Inventor
杜熠伯
马振宇
李毓
张旭东
张波
刘敦楠
付忠广
孟梁涛
邵帅
安玉涛
张建松
陈志华
林恺丰
赵凯美
卢旭倩
宋晨超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Huadian Energy Internet Research Institute Co ltd
North China Electric Power University
Jinhua Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Original Assignee
Beijing Huadian Energy Internet Research Institute Co ltd
North China Electric Power University
Jinhua Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Huadian Energy Internet Research Institute Co ltd, North China Electric Power University, Jinhua Power Supply Co of State Grid Zhejiang Electric Power Co Ltd filed Critical Beijing Huadian Energy Internet Research Institute Co ltd
Priority to CN202310355630.XA priority Critical patent/CN116070888B/en
Publication of CN116070888A publication Critical patent/CN116070888A/en
Application granted granted Critical
Publication of CN116070888B publication Critical patent/CN116070888B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • 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
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The invention discloses a decision tree-based virtual power plant adjustable capacity analysis method, device and medium, relating to the technical field of power grid data prediction, and mainly comprising the following steps: constructing a decision tree model according to the numerical table, and selecting the decision tree model based on the screening of the coefficient of the radix by the pruning optimization operation of the decision tree; constructing a consumer psychology association under the influence of the demand response subsidy price according to the load characteristic value set, and acquiring corresponding certainty parameters; acquiring historical uncertain parameter discrete distribution conditions of potential target users under the condition of change of demand response subsidy price based on the load change rate and each deterministic parameter; and calculating response potential according to the discrete step-by-step condition of the historical uncertain parameters and each deterministic parameter, and determining the adjustable capacity space under the target confidence interval when participating in demand response. The method can evaluate the load adjustable potential more accurately under the prediction of the load perceptibility and quantification, thereby more fully utilizing the resource at the demand side.

Description

Virtual power plant adjustable capacity analysis method, device and medium based on decision tree
Technical Field
The invention relates to the technical field of power grid data prediction, in particular to a decision tree-based virtual power plant adjustable capacity analysis method, device and medium.
Background
Under the large background of the construction of the novel power system, the rapidly-increased power demand, the fluctuation and the anti-peak regulation of the wind power generation and the photovoltaic power generation enable the situation of power shortage to occur in China, and the requirements of safe and economic operation of a power grid are difficult to meet only by means of adjustment on the power generation side. Therefore, how to fully mine the capacity of the resources on the demand side to participate in the regulation of the power grid and to formulate a demand response management strategy of the virtual power plant to participate in the regulation and control operation of the power grid have great significance in guaranteeing the safety and economic operation of the power grid.
The demand side resource is an important regulation resource of the power system, and can be guided to carry out peak clipping and valley filling through time-sharing electricity price, so that the safety margin of electrical equipment is improved, the investment cost of the power grid system is reduced, and the electrical safety and the economical efficiency are further improved. And the distribution characteristics of electricity consumption behavior in time and the sensitivity degree to electricity price change are different for power users in different industries and even for different power users in the same industry. Therefore, the evaluation of the demand response potential is a primary condition for realizing effective demand response management, and the accuracy of the evaluation influences the feasibility and reliability of the subsequent demand response management strategy, so that the evaluation of the demand response potential of the power consumer is very significant.
Disclosure of Invention
Aiming at the difference of electricity utilization time and electricity price sensitivity of different industries and even different users, the invention provides a decision tree-based virtual power plant adjustable capacity analysis method for better calling demand side resources, which comprises the following steps:
s1: collecting historical load data and historical participation demand response data of potential target users;
s2: calculating a load characteristic value set and a load change rate of participation response time periods under a target time span according to the collected historical load data, and converting the collected historical participation demand response data into a numerical table through numerical conversion;
s3: constructing a decision tree model according to the numerical table, and selecting the decision tree model based on the screening of the coefficient of the radix by the pruning optimization operation of the decision tree;
s4: constructing a consumer psychology association under the influence of the demand response subsidy price according to the load characteristic value set, and acquiring corresponding certainty parameters;
s5: acquiring historical uncertain parameter discrete distribution conditions of potential target users under the condition of change of demand response subsidy price based on the load change rate and each deterministic parameter;
s6: acquiring and numerically converting corresponding data of participation demands of a target day, inputting the selected decision tree model to acquire a corresponding judgment result of the participation demands of the user, and entering the next step when judging participation;
s7: and calculating response potential according to the discrete step-by-step condition of the historical uncertain parameters and each deterministic parameter, and determining the adjustable capacity space under the target confidence interval when participating in demand response.
Further, in the step S1, the historical participation demand response data includes a demand response subsidy price, a demand response time period, a determination of whether to use holidays, and a determination of whether to participate in demand response.
Further, in the step S2, the load characteristic value set includes a peak Gu Chalv, a load cumulative change duty ratio, a power consumption duty ratio in a response period, a low load time duty ratio, and a high load time duty ratio.
Further, the peak Gu Chalv is obtained by the following formula,
Figure SMS_1
the duty cycle of the load cumulative change is obtained by the following formula,
Figure SMS_2
the response period power consumption ratio is obtained by the following formula,
Figure SMS_3
the low load time duty ratio and the high load time duty ratio are obtained by the following formula,
Figure SMS_4
in the method, in the process of the invention,
Figure SMS_7
peak Gu Chalv, +.>
Figure SMS_11
Accumulating the change duty ratio for the load, +.>
Figure SMS_15
For the response period the power usage is proportional, +.>
Figure SMS_8
Is a low load time duty ratio, +.>
Figure SMS_12
For a high load time duty cycle, +.>
Figure SMS_16
Maximum daily load, +.>
Figure SMS_18
Is the minimum daily load value->
Figure SMS_5
For the load of the nth time node of the day, < >>
Figure SMS_9
For the load of the mth time node of the day, N is the total time node number of the day,
Figure SMS_13
for low duty control amount, +.>
Figure SMS_17
For a load below a preset low load threshold +.>
Figure SMS_6
Time node number,/, of (2)>
Figure SMS_10
For the load exceeding the preset high load threshold +.>
Figure SMS_14
Is a time node of (a).
Further, the load change rate is obtained by the following formula,
Figure SMS_19
in the method, in the process of the invention,
Figure SMS_20
for the average load of Q days before the day of participation in demand response, +.>
Figure SMS_21
For the baseline load of Q days before the day of the participation in the demand, which do not participate in the demand, +.>
Figure SMS_22
Is the load change rate. />
Further, in the step S3, the coefficient of the kunity is expressed as the following formula,
Figure SMS_23
wherein t is a given decision tree node, i is a class number of the label,
Figure SMS_24
and c is the class number of the decision tree node, wherein the proportion of the label class number i on the node t is calculated.
Further, in the step S4, the deterministic parameter includes a sensitive excitation threshold, an adjustable capacity upper limit, and an excitation upper limit threshold, which are expressed by the following formulas:
Figure SMS_25
in the method, in the process of the invention,
Figure SMS_28
for the sensitive excitation threshold, ++>
Figure SMS_32
Is the upper limit of the adjustable capacity, < >>
Figure SMS_35
For the upper threshold of excitation, +.>
Figure SMS_27
、/>
Figure SMS_31
、/>
Figure SMS_34
、/>
Figure SMS_37
Sensitivity incentive threshold obtained for Consumer psychology correlation construction +.>
Figure SMS_26
Weight parameter of->
Figure SMS_30
Upper limit of adjustable capacity obtained for construction through consumer psychology association>
Figure SMS_33
Weight parameter of->
Figure SMS_36
Incentive upper threshold value obtained for Consumer psychology correlation construction>
Figure SMS_29
Weight parameters of (c).
Further, in the step S5, the obtaining of the discrete distribution of the history uncertain parameter specifically includes the following steps:
s51: determining an equivalent subsidy price according to the load change rate and the deterministic parameter;
s52: acquiring a load change rate uncertainty factor according to the equivalent patch price and the sensitive excitation threshold;
s53: and (3) calling an inverse cumulative distribution function of MATLAB to fit the mean value and the variance of the uncertain factors of the load change rate, and obtaining the upper and lower limit values of the target confidence coefficient corresponding to the inverse function of the normal probability density function.
Further, in the step S51, the equivalent patch price is obtained by the following formula,
Figure SMS_38
in the method, in the process of the invention,
Figure SMS_39
for the equivalent subsidy price, the M demand responds to the subsidy price.
Further, in the step S52, the load change rate uncertainty factor is obtained by the following formula,
Figure SMS_40
in the method, in the process of the invention,
Figure SMS_41
is a factor of uncertainty in the rate of change of load.
Further, in the step S7, the obtaining of the adjustable capacity interval specifically includes the following steps:
s71: acquiring a load change rate under the corresponding confidence limit value according to the upper and lower limit values of the target confidence;
s72: and acquiring an adjustable capacity space under the target confidence interval according to the load change rate under the corresponding confidence limit value.
Further, in the step S71, the load change rate under the corresponding confidence limit value is obtained by the following formula,
Figure SMS_42
in the method, in the process of the invention,
Figure SMS_43
for the target confidence lower limit,/>
Figure SMS_44
For the upper limit value of the target confidence level, < >>
Figure SMS_45
Load change rate corresponding to target confidence lower limit value, < ->
Figure SMS_46
Load change rate corresponding to target confidence upper limit value, < ->
Figure SMS_47
Subsidized prices for determining demand response for participation in the day.
Further, in the step S72, the adjustable capacity space is expressed as the following formula:
Figure SMS_48
in the method, in the process of the invention,
Figure SMS_49
to determine the adjustable capacity interval for the day of participation, < > for>
Figure SMS_50
Is the baseline load.
Further, if there is a market rule requirement under a second time span longer than the target time span, the certainty parameter corresponding to the second time span may be obtained through the following steps after the step S4:
s41: obtaining the mapping relation between each deterministic parameter corresponding to the target time span and the load characteristic set thereof;
s42: and acquiring each deterministic parameter of the second time span according to the mapping relation and the load characteristic set corresponding to the second time span.
Further, in the step S41, the mapping relation is obtained by the following formula,
Figure SMS_51
in the method, in the process of the invention,
Figure SMS_52
for the mapping relation between the target deterministic parameter and the load characteristic set, F is a matrix with k multiplied by 5 size and composed of load characteristic values, k is the number of samples of historical load data, Y is an output vector with k multiplied by 1 dimension, and T is matrix transposition operation.
Further, in the step S42, the deterministic parameter of the second time span is obtained by the following formula,
Figure SMS_53
in the method, in the process of the invention,
Figure SMS_55
for a second time span, for a set of load characteristics corresponding to the second time span,/->
Figure SMS_58
Sensitive excitation threshold value in deterministic parameters for targets>
Figure SMS_60
Mapping relation between load characteristic sets thereof, < ->
Figure SMS_54
Is the object ofAdjustable capacity upper limit in deterministic parameter +.>
Figure SMS_57
Mapping relation between load characteristic sets thereof, < ->
Figure SMS_59
Excitation upper threshold value +.>
Figure SMS_61
Mapping relation between load characteristic sets thereof, < ->
Figure SMS_56
Is a deterministic parameter for the second time span.
Also included is a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method for decision tree based virtual power plant adjustable capacity analysis.
Also included is an apparatus for processing data, comprising:
a memory having a computer program stored thereon;
and the processor is used for executing the computer program in the memory to realize the steps of the virtual power plant adjustable capacity analysis method based on the decision tree.
Compared with the prior art, the invention at least has the following beneficial effects:
(1) According to the decision tree-based virtual power plant adjustable capacity analysis method, device and medium, by combining the decision tree with the discrete distribution condition of the historical data, the load adjustable potential can be accurately estimated under the prediction of the load perceptibility and quantification, so that the demand side resources can be fully utilized, and planning can be made in advance;
(2) The relevant factor threshold value affecting the user parameter demand response is obtained through the psychology of the consumer, so that the finally obtained uncertainty parameter discrete distribution situation can better meet the actual market demand;
(3) Based on the acquisition of the mapping relation between the deterministic parameter and the corresponding load feature set under the reference time span, the deterministic parameter under the longer time span can be acquired more easily, so that the acquisition steps and difficulty of the deterministic parameter under the long time span are simplified, and different market rule requirements can be adapted.
Drawings
FIG. 1 is a step diagram of a decision tree-based method for variable capacity analysis in a virtual power plant;
FIG. 2 is a dataset representation of a trained decision tree model.
Detailed Description
The following are specific embodiments of the present invention and the technical solutions of the present invention will be further described with reference to the accompanying drawings, but the present invention is not limited to these embodiments.
Example 1
Considering power users in different industries, even different power users in the same industry, the distribution characteristics of electricity consumption behavior in time and the sensitivity degree to electricity price are different. Meanwhile, most of the current multi-phase research is only directed to a single load resource, so that the evaluation method thereof has a limitation in the range of applicable objects. Therefore, the invention is suitable for different types of power users, and analyzes based on the historical load data and the corresponding conditions of the historical participation demands, so that quantitative evaluation of user demand response is realized, and the demand side resource management capability of the virtual power plant is enhanced. Specifically, as shown in fig. 1, the invention provides a decision tree-based method for analyzing the adjustable capacity of a virtual power plant, which comprises the following steps:
s1: collecting historical load data and historical participation demand response data of potential target users;
s2: calculating a load characteristic value set and a load change rate of participation response time periods under a target time span according to the collected historical load data, and converting the collected historical participation demand response data into a numerical table through numerical conversion;
s3: constructing a decision tree model according to the numerical table, and selecting the decision tree model based on the screening of the coefficient of the radix by the pruning optimization operation of the decision tree;
s4: constructing a consumer psychology association under the influence of the demand response subsidy price according to the load characteristic value set, and acquiring corresponding certainty parameters;
s5: acquiring historical uncertain parameter discrete distribution conditions of potential target users under the condition of change of demand response subsidy price based on the load change rate and each deterministic parameter;
s6: acquiring and numerically converting corresponding data of participation demands of a target day, inputting the selected decision tree model to acquire a corresponding judgment result of the participation demands of the user, and entering the next step when judging participation;
s7: and calculating response potential according to the discrete step-by-step condition of the historical uncertain parameters and each deterministic parameter, and determining the adjustable capacity space under the target confidence interval when participating in demand response.
Firstly, the construction of a high-reliability model is not independent of the support of real data, so that the historical load data of potential target users and the corresponding situations of the historical participation demands of the potential target users are required to be collected from a virtual power plant platform, and the conditions comprise a power load curve of a plurality of historical days, whether holidays exist, a demand response subsidy price for executing the demand response, a time period for executing the demand response and whether the users participate in the demand response.
Of course, these data cannot be used directly for the construction of the correlation model, and further processing of the data is required to obtain a data set for training the decision tree model and a data set for fitting the load change rate model, respectively. Firstly, the data are cleaned, error values and repeated values are removed, and missing values are complemented.
For the data set used for fitting the load change rate model, the definition and acquisition and calculation methods of the included variables are as follows. First, 5 load characteristic values for different time spans are calculated based on historical load data: peak Gu Chalv
Figure SMS_62
Load cumulative change ratio->
Figure SMS_63
Power consumption ratio in response period>
Figure SMS_64
Low load time ratio->
Figure SMS_65
High load time ratio->
Figure SMS_66
. By these five:
the peak Gu Chalv is obtained by the following formula,
Figure SMS_67
the duty cycle of the cumulative load change is obtained by the following formula,
Figure SMS_68
the response period power usage ratio is obtained by the following formula,
Figure SMS_69
the low load time duty ratio and the high load time duty ratio are obtained by the following formula,
Figure SMS_70
in the method, in the process of the invention,
Figure SMS_72
maximum daily load, +.>
Figure SMS_75
Is the minimum daily load value->
Figure SMS_78
For the load of the nth time node of the day, < >>
Figure SMS_73
For the load of the mth time node of the day, N is the total time node number of the day, < ->
Figure SMS_74
For a low duty cycle control amount,
Figure SMS_77
for a load below a preset low load threshold +.>
Figure SMS_79
Time node number,/, of (2)>
Figure SMS_71
For the load exceeding the preset high load threshold +.>
Figure SMS_76
Is a time node of (a).
As to why the concept of time span is proposed, this is due to the difference in data accuracy requirements of different market rule requirements, which results in that the different market rule requirements need to employ multi-day average data at different time spans as the load characteristic value. The load characteristic value is acquired with the time span of 5 days as the target time span. That is, the load characteristic value set of the target baseline day is obtained by averaging the data of the above 5 load characteristic values over the target time span. For example, a target baseline daily peak Gu Chalv of 1 month 10 days means: the peak-valley difference ratios were calculated and averaged respectively on the first 5 days of the day of participation in the demand response (1 month, 10 days) without participation in the demand response.
The load change rate is as follows:
Figure SMS_80
also, in the case of 5 days, the value of Q in the formula is 5,
Figure SMS_81
for the average load of the day 5 before the day of participation in demand response, +.>
Figure SMS_82
For the baseline load of Q days before the day of the participation in the demand, which do not participate in the demand, +.>
Figure SMS_83
Is the load change rate.
For the data set for training the decision tree model, as shown in fig. 2, the variables are defined, acquired and calculated as follows:
the date and whether the holiday are obtained according to the calendar record of the virtual power plant, wherein 2 represents the legal holiday of the country, 1 represents the weekend and 0 represents the working day;
if a demand response plan exists, whether the electric power user is required to participate in the demand response to cut peaks and fill valleys or not is indicated in the time period, if the demand response plan does not exist, the user does not participate in the demand response, if the demand response plan exists, the user can select whether to participate according to the self condition and the demand response subsidy price, wherein 1 indicates that the demand response plan exists, and 0 indicates that the demand response plan does not exist; (wherein demand response time period is typically a peak or valley period of grid load, and demand response subsidies are relatively fixed for a short period of time, and demand response subsidies are subsidies provided to participating demand response users by the virtual power plant platform, and demand response subsidies price represents a subsidies for which a user can obtain a price every time the user uses one degree less than the baseline day period)
Whether to participate in the demand response indicates whether the user has participated in the demand response for this period of time, where 1 indicates that the demand response has been participated in and 0 indicates that the demand response has not been participated in.
Through the numerical conversion operation, the historical participation demand response data can be better used for training the decision tree model in the step S3. Here, the present invention uses the data of the first 80% of the date of the dataset as a training dataset for training the decision tree model; the data from the last 20% of the date was used as a test dataset for evaluating the accuracy of model predictions. The training data set and the test data set both comprise a feature data set and a result data set, the feature data set comprising each date pair of the userWhether the user should be on a holiday, a demand response time period, whether there is a demand response program, a demand response subsidy price, and the resulting data set contains whether the user has participated in the demand response for the corresponding time period of the date. Next, the SK-learn library of Python is called, and the training data set is read
Figure SMS_84
And->
Figure SMS_85
And training the model to obtain a trained decision tree model. Characteristic data of the test dataset +.>
Figure SMS_86
Inputting the trained models to output the user test data set whether to participate in the demand response in each time period>
Figure SMS_87
. Will->
Figure SMS_88
And->
Figure SMS_89
If the difference degree is too high, the model is possibly overfitted, pruning operation is needed to be carried out on the decision tree, so that the coefficient of the foundation is not too small, and finally, the decision tree with the coefficient of the foundation meeting the preset standard is selected as a final decision tree model, and the decision tree model is built. Wherein, the coefficient of the Kernine is expressed as the following formula,
Figure SMS_90
wherein t is a given decision tree node, i is a class number of the label,
Figure SMS_91
and c is the class number of the decision tree node, wherein the proportion of the label class number i on the node t is calculated.
And in the step S4, for the construction of the load change rate model,the invention constructs the psychological association relation of the consumer under the influence of the demand response subsidy price according to the load characteristic value set (obtained by means of observation, interview, questionnaire, comprehensive investigation and the like), thereby obtaining deterministic parameters: sensitive excitation threshold
Figure SMS_92
(prompting the user to decide the lowest demand response subsidy price corresponding to the participation demand), the adjustable capacity upper limit +.>
Figure SMS_93
Excitation upper threshold +.>
Figure SMS_94
(the minimum demand response subsidy price that no longer has an impact on the user's participation in the demand response). These three deterministic parameters can be obtained by the following formula:
Figure SMS_95
in the method, in the process of the invention,
Figure SMS_96
sensitivity incentive threshold obtained for Consumer psychology correlation construction +.>
Figure SMS_97
Weight parameter of->
Figure SMS_98
Upper limit of adjustable capacity obtained for construction through consumer psychology association>
Figure SMS_99
Weight parameter of->
Figure SMS_100
Incentive upper threshold obtained for consumer psychology association construction
Figure SMS_101
Weight parameters of (c).
Then, according to the discrete distribution of the uncertain parameter of deterministic parameter acquisition history, specifically comprising the following steps:
s51: determining an equivalent subsidy price according to the load change rate and the deterministic parameter;
s52: acquiring a load change rate uncertainty factor according to the equivalent patch price and the sensitive excitation threshold;
s53: and (3) calling an inverse cumulative distribution function of MATLAB to fit the mean value and the variance of the uncertain factors of the load change rate, and obtaining the upper and lower limit values of the target confidence coefficient corresponding to the inverse function of the normal probability density function.
Wherein the equivalent patch price is obtained by the following formula,
Figure SMS_102
in the method, in the process of the invention,
Figure SMS_103
for the equivalent subsidy price, the M demand responds to the subsidy price.
Further, the load change rate uncertainty factor is obtained by the following formula,
Figure SMS_104
in the method, in the process of the invention,
Figure SMS_105
is a factor of uncertainty in the rate of change of load.
Finally, in step S7, the obtaining of the adjustable capacity interval specifically includes the following steps:
s71: acquiring a load change rate under the corresponding confidence limit value according to the upper and lower limit values of the target confidence;
s72: and acquiring an adjustable capacity space under the target confidence interval according to the load change rate under the corresponding confidence limit value.
Then, the load change rate uncertainty factor is calculated
Figure SMS_106
Fitting the inverse function of the normal distribution probability density function by using the Inverse Cumulative Distribution Function (ICDF) of MATLAB, and determining the point(s) corresponding to the lowest confidence level and the highest confidence level>
Figure SMS_107
Value->
Figure SMS_108
And->
Figure SMS_109
。
And finally, evaluating the participation condition and the load change rate of a user in a period corresponding to a certain demand on a certain day according to the constructed decision tree model and the load change rate model. The method comprises the steps of converting the holiday, the demand response plan, the demand response time period and the demand response subsidy of the day into a format required by a decision tree model through numerical conversion, and inputting the trained decision tree model to obtain the judgment of whether the user participates in the demand response. And after judging the user participation demand response, inputting the current demand response subsidy price into a load change rate model to obtain the load change rate (shown in the following formula) of the user participation demand response under the upper and lower limit values of the target confidence coefficient,
Figure SMS_110
in the method, in the process of the invention,
Figure SMS_111
for the target confidence lower limit,/>
Figure SMS_112
For the upper limit value of the target confidence level, < >>
Figure SMS_113
Load change rate corresponding to target confidence lower limit value, < ->
Figure SMS_114
Load change rate corresponding to target confidence upper limit value, < ->
Figure SMS_115
Subsidized prices for determining demand response for participation in the day.
Finally, the load change rate formula mentioned before is adjusted, and the adjustable capacity space can be obtained:
Figure SMS_116
in the method, in the process of the invention,
Figure SMS_117
to determine the adjustable capacity interval for the day of participation, < > for>
Figure SMS_118
Is the baseline load.
In a preferred embodiment, in consideration of the requirement of the duration rule under the longer time span (named as the second time span), the step S4 further includes the steps of:
s41: obtaining the mapping relation between each deterministic parameter corresponding to the target time span and the load characteristic set thereof;
s42: and acquiring each deterministic parameter of the second time span according to the mapping relation and the load characteristic set corresponding to the second time span.
Wherein, in the step S41, the mapping relation is obtained by the following formula,
Figure SMS_119
in the method, in the process of the invention,
Figure SMS_120
for the mapping relation between the target deterministic parameter and the load characteristic set, F is a matrix with k multiplied by 5 and composed of load characteristic values, k is the number of samples of historical load data, and Y is the size of k multiplied by 1 dimensionAnd outputting a vector, wherein T is a matrix transposition operation.
In step S42, the deterministic parameter of the second time span is obtained by the following formula,
Figure SMS_121
in the method, in the process of the invention,
Figure SMS_124
for a second time span, for a set of load characteristics corresponding to the second time span,/->
Figure SMS_126
Sensitive excitation threshold value in deterministic parameters for targets>
Figure SMS_128
Mapping relation between load characteristic sets thereof, < ->
Figure SMS_122
For the upper limit of adjustable capacity in the target deterministic parameter +.>
Figure SMS_125
Mapping relation between load characteristic sets thereof, < ->
Figure SMS_127
Excitation upper threshold value +.>
Figure SMS_129
Mapping relation between load characteristic sets thereof, < ->
Figure SMS_123
Is a deterministic parameter for the second time span.
The adjustable capacity analysis under longer time span is convenient by acquiring the mapping relation, so that the method can adapt to different market rule requirements.
Also included is a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method for decision tree based virtual power plant adjustable capacity analysis.
Also included is an apparatus for processing data, comprising:
a memory having a computer program stored thereon;
and the processor is used for executing the computer program in the memory to realize the steps of the virtual power plant adjustable capacity analysis method based on the decision tree.
In summary, according to the method, the device and the medium for analyzing the adjustable capacity of the virtual power plant based on the decision tree, through the combination of the decision tree and the discrete distribution condition of the historical data, the adjustable potential of the load can be accurately estimated under the prediction of the perceivable and quantifiable load, so that the resource on the demand side can be fully utilized, and the planning can be made in advance.
And acquiring a relevant factor threshold value affecting the user parameter demand response through consumer psychology, so that the finally acquired uncertainty parameter discrete distribution situation can better meet the actual market demand.
Based on the acquisition of the mapping relation between the deterministic parameter and the corresponding load feature set under the reference time span, the deterministic parameter under the longer time span can be acquired more easily, so that the acquisition steps and difficulty of the deterministic parameter under the long time span are simplified, and different market rule requirements can be adapted.
It should be noted that all directional indicators (such as up, down, left, right, front, and rear … …) in the embodiments of the present invention are merely used to explain the relative positional relationship, movement, etc. between the components in a particular posture (as shown in the drawings), and if the particular posture is changed, the directional indicator is changed accordingly.
Furthermore, descriptions such as those referred to herein as "first," "second," "a," and the like are provided for descriptive purposes only and are not to be construed as indicating or implying a relative importance or an implicit indication of the number of features being indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
In the present invention, unless specifically stated and limited otherwise, the terms "connected," "affixed," and the like are to be construed broadly, and for example, "affixed" may be a fixed connection, a removable connection, or an integral body; can be mechanically or electrically connected; either directly or indirectly, through intermediaries, or both, may be in communication with each other or in interaction with each other, unless expressly defined otherwise. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
In addition, the technical solutions of the embodiments of the present invention may be combined with each other, but it is necessary to be based on the fact that those skilled in the art can implement the technical solutions, and when the technical solutions are contradictory or cannot be implemented, the combination of the technical solutions should be considered as not existing, and not falling within the scope of protection claimed by the present invention.

Claims (18)

1. The method for analyzing the adjustable capacity of the virtual power plant based on the decision tree is characterized by comprising the following steps of:
s1: collecting historical load data and historical participation demand response data of potential target users;
s2: calculating a load characteristic value set and a load change rate of participation response time periods under a target time span according to the collected historical load data, and converting the collected historical participation demand response data into a numerical table through numerical conversion;
s3: constructing a decision tree model according to the numerical table, and selecting the decision tree model based on the screening of the coefficient of the radix by the pruning optimization operation of the decision tree;
s4: constructing a consumer psychology association under the influence of the demand response subsidy price according to the load characteristic value set, and acquiring corresponding certainty parameters;
s5: acquiring historical uncertain parameter discrete distribution conditions of potential target users under the condition of change of demand response subsidy price based on the load change rate and each deterministic parameter;
s6: acquiring and numerically converting corresponding data of participation demands of a target day, inputting the selected decision tree model to acquire a corresponding judgment result of the participation demands of the user, and entering the next step when judging participation;
s7: and calculating response potential according to the discrete step-by-step condition of the historical uncertain parameters and each deterministic parameter, and determining the adjustable capacity space under the target confidence interval when participating in demand response.
2. The method for analyzing adjustable capacity of a virtual power plant based on a decision tree according to claim 1, wherein in step S1, the historical participation demand response data includes a demand response subsidy price, a demand response time period, a determination of whether a holiday is or not, and a determination of whether a user participates in a demand response.
3. The method for analyzing adjustable capacity of a virtual power plant based on a decision tree according to claim 1, wherein in the step S2, the load characteristic value set includes a peak Gu Chalv, a load cumulative change duty ratio, a response period power consumption duty ratio, a low load time duty ratio, and a high load time duty ratio.
4. A method for decision tree based variable capacity analysis of a virtual power plant according to claim 3, wherein the peak Gu Chalv is obtained by the following formula,
Figure QLYQS_1
the duty cycle of the load cumulative change is obtained by the following formula,
Figure QLYQS_2
the response period power consumption ratio is obtained by the following formula,
Figure QLYQS_3
the low load time duty ratio and the high load time duty ratio are obtained by the following formula,
Figure QLYQS_4
/>
in the method, in the process of the invention,
Figure QLYQS_8
peak Gu Chalv, +.>
Figure QLYQS_12
Accumulating the change duty ratio for the load, +.>
Figure QLYQS_16
For the response period the power usage is proportional, +.>
Figure QLYQS_6
Is a low load time duty ratio, +.>
Figure QLYQS_9
For a high load time duty cycle, +.>
Figure QLYQS_13
Maximum daily load, +.>
Figure QLYQS_17
Is the minimum daily load value->
Figure QLYQS_5
For the load of the nth time node of the day, < >>
Figure QLYQS_11
For the load of the mth time node of the day, N is the total time node number of the day, < ->
Figure QLYQS_15
For low duty control amount, +.>
Figure QLYQS_18
For a load below a preset low load threshold +.>
Figure QLYQS_7
Time node number,/, of (2)>
Figure QLYQS_10
For the load exceeding the preset high load threshold +.>
Figure QLYQS_14
Is a time node of (a).
5. A method for decision tree based variable capacity analysis of a virtual power plant according to claim 4, wherein the load rate is obtained by the following equation,
Figure QLYQS_19
in the method, in the process of the invention,
Figure QLYQS_20
for the average load of Q days before the day of participation in demand response, +.>
Figure QLYQS_21
For the baseline load of Q days before the day of the participation in the demand, which do not participate in the demand, +.>
Figure QLYQS_22
Is the load change rate.
6. A method for analyzing the adjustable capacity of a virtual power plant based on a decision tree according to claim 1, wherein in the step S3, the coefficient of Kerning is expressed as the following formula,
Figure QLYQS_23
wherein t is a given decision tree node, i is a class number of the label,
Figure QLYQS_24
and c is the class number of the decision tree node, wherein the proportion of the label class number i on the node t is calculated.
7. The method for analyzing adjustable capacity of a virtual power plant based on a decision tree according to claim 1, wherein in the step S4, the deterministic parameter includes a sensitive excitation threshold, an adjustable capacity upper limit, and an excitation upper limit threshold, which are expressed by the following formulas:
Figure QLYQS_25
in the method, in the process of the invention,
Figure QLYQS_27
for the sensitive excitation threshold, ++>
Figure QLYQS_33
Is the upper limit of the adjustable capacity, < >>
Figure QLYQS_39
For the upper threshold of excitation, +.>
Figure QLYQS_31
、/>
Figure QLYQS_34
、/>
Figure QLYQS_37
、/>
Figure QLYQS_42
Sensitivity incentive threshold obtained for Consumer psychology correlation construction +.>
Figure QLYQS_28
Weight parameter of->
Figure QLYQS_38
、/>
Figure QLYQS_26
、/>
Figure QLYQS_36
、/>
Figure QLYQS_29
、/>
Figure QLYQS_40
Upper limit of adjustable capacity obtained for construction through consumer psychology association>
Figure QLYQS_30
Weight parameter of->
Figure QLYQS_41
、/>
Figure QLYQS_32
Incentive upper threshold value obtained for Consumer psychology correlation construction>
Figure QLYQS_35
Weight parameters of (c).
8. The method for analyzing adjustable capacity of a virtual power plant based on a decision tree according to claim 7, wherein in the step S5, the obtaining of the discrete distribution of the history uncertainty parameter specifically includes the steps of:
s51: determining an equivalent subsidy price according to the load change rate and the deterministic parameter;
s52: acquiring a load change rate uncertainty factor according to the equivalent patch price and the sensitive excitation threshold;
s53: and (3) calling an inverse cumulative distribution function of MATLAB to fit the mean value and the variance of the uncertain factors of the load change rate, and obtaining the upper and lower limit values of the target confidence coefficient corresponding to the inverse function of the normal probability density function.
9. The method for analyzing adjustable capacity of virtual power plant based on decision tree as claimed in claim 8, wherein in step S51, the equivalent subsidy price is obtained by the following formula,
Figure QLYQS_43
in the method, in the process of the invention,
Figure QLYQS_44
for the equivalent subsidy price, the M demand responds to the subsidy price.
10. The method for analyzing adjustable capacity of virtual power plant based on decision tree as recited in claim 9, wherein in step S52, the uncertainty factor of the load change rate is obtained by the following formula,
Figure QLYQS_45
in the method, in the process of the invention,
Figure QLYQS_46
is a factor of uncertainty in the rate of change of load.
11. The method for analyzing adjustable capacity of a virtual power plant based on a decision tree according to claim 8, wherein in the step S7, the obtaining of the adjustable capacity interval specifically includes the steps of:
s71: acquiring a load change rate under the corresponding confidence limit value according to the upper and lower limit values of the target confidence;
s72: and acquiring an adjustable capacity space under the target confidence interval according to the load change rate under the corresponding confidence limit value.
12. The method for analyzing adjustable capacity of virtual power plant based on decision tree as claimed in claim 11, wherein in step S71, the load change rate under the corresponding confidence limit is obtained by the following formula,
Figure QLYQS_47
in the method, in the process of the invention,
Figure QLYQS_48
for the target confidence lower limit,/>
Figure QLYQS_49
For the upper limit value of the target confidence level, < >>
Figure QLYQS_50
Load change rate corresponding to target confidence lower limit value, < ->
Figure QLYQS_51
Load change rate corresponding to target confidence upper limit value, < ->
Figure QLYQS_52
Subsidized prices for determining demand response for participation in the day.
13. The method for analyzing adjustable capacity of a virtual power plant according to claim 11, wherein in step S72, the adjustable capacity space is expressed as the following formula:
Figure QLYQS_53
in the method, in the process of the invention,
Figure QLYQS_54
to determine the adjustable capacity interval for the day of participation, < > for>
Figure QLYQS_55
Is the baseline load. />
14. The method of decision tree based virtual power plant adjustable capacity analysis according to claim 7, wherein if there is a market rule requirement at a second time span longer than the target time span, the deterministic parameter corresponding to the second time span is obtained by the following steps after step S4:
s41: obtaining the mapping relation between each deterministic parameter corresponding to the target time span and the load characteristic set thereof;
s42: and acquiring each deterministic parameter of the second time span according to the mapping relation and the load characteristic set corresponding to the second time span.
15. The method for analyzing adjustable capacity of virtual power plant based on decision tree as recited in claim 14, wherein in step S41, the mapping relation is obtained by the following formula,
Figure QLYQS_56
in the method, in the process of the invention,
Figure QLYQS_57
for the mapping relation between the target deterministic parameter and the load characteristic set, F is a matrix with k multiplied by 5 size and composed of load characteristic values, k is the number of samples of historical load data, Y is an output vector with k multiplied by 1 dimension, and T is matrix transposition operation.
16. The method for decision tree based virtual power plant adjustable capacity analysis as recited in claim 15, wherein in step S42, the deterministic parameter of the second time span is obtained by the following formula,
Figure QLYQS_58
in the method, in the process of the invention,
Figure QLYQS_59
for a second time span, for a set of load characteristics corresponding to the second time span,/->
Figure QLYQS_63
Sensitive excitation threshold value in deterministic parameters for targets>
Figure QLYQS_65
Mapping relation between load characteristic sets thereof, < ->
Figure QLYQS_61
For the upper limit of adjustable capacity in the target deterministic parameter
Figure QLYQS_62
Mapping relation between load characteristic sets thereof, < ->
Figure QLYQS_64
Excitation upper threshold value +.>
Figure QLYQS_66
Mapping relation between load characteristic sets thereof, < ->
Figure QLYQS_60
Is a deterministic parameter for the second time span.
17. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the analysis method according to any one of claims 1 to 16.
18. An apparatus for processing data, comprising:
a memory having a computer program stored thereon;
a processor for executing a computer program in the memory to implement the steps of the analysis method of any one of claims 1 to 16.
CN202310355630.XA 2023-04-06 2023-04-06 Virtual power plant adjustable capacity analysis method, device and medium based on decision tree Active CN116070888B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310355630.XA CN116070888B (en) 2023-04-06 2023-04-06 Virtual power plant adjustable capacity analysis method, device and medium based on decision tree

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310355630.XA CN116070888B (en) 2023-04-06 2023-04-06 Virtual power plant adjustable capacity analysis method, device and medium based on decision tree

Publications (2)

Publication Number Publication Date
CN116070888A true CN116070888A (en) 2023-05-05
CN116070888B CN116070888B (en) 2023-07-04

Family

ID=86173521

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310355630.XA Active CN116070888B (en) 2023-04-06 2023-04-06 Virtual power plant adjustable capacity analysis method, device and medium based on decision tree

Country Status (1)

Country Link
CN (1) CN116070888B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116523273A (en) * 2023-07-04 2023-08-01 广东电网有限责任公司广州供电局 Demand response characteristic analysis method for industrial users
CN116760122A (en) * 2023-08-21 2023-09-15 国网浙江省电力有限公司宁波供电公司 Virtual power plant resource management and control method and device, computer equipment and storage medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107590618A (en) * 2017-09-27 2018-01-16 中国农业大学 Workload demand response model based on consumer psychology under Spot Price background
CN111340597A (en) * 2020-03-06 2020-06-26 国网冀北电力有限公司 Virtual power plant internal multi-element main body bidding method, device and equipment
CN111598721A (en) * 2020-05-08 2020-08-28 天津大学 Load real-time scheduling method based on reinforcement learning and LSTM network
CN113191804A (en) * 2021-04-28 2021-07-30 西安交通大学 Optimal bidding strategy solving method
WO2022077588A1 (en) * 2020-10-12 2022-04-21 中国电力科学研究院有限公司 Method, system and apparatus for calling adjustable load to participate in demand response
CN114997665A (en) * 2022-06-08 2022-09-02 国网山西省电力公司电力科学研究院 Virtual power plant optimal scheduling method and system considering controllable load response performance difference
CN115018198A (en) * 2022-06-30 2022-09-06 国网河南省电力公司经济技术研究院 Residential user electricity utilization optimization strategy considering differentiated demand response scheme
CN115438922A (en) * 2022-08-17 2022-12-06 中国电力科学研究院有限公司 Large-scale demand side flexible resource demand response potential evaluation method and system

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107590618A (en) * 2017-09-27 2018-01-16 中国农业大学 Workload demand response model based on consumer psychology under Spot Price background
CN111340597A (en) * 2020-03-06 2020-06-26 国网冀北电力有限公司 Virtual power plant internal multi-element main body bidding method, device and equipment
CN111598721A (en) * 2020-05-08 2020-08-28 天津大学 Load real-time scheduling method based on reinforcement learning and LSTM network
WO2022077588A1 (en) * 2020-10-12 2022-04-21 中国电力科学研究院有限公司 Method, system and apparatus for calling adjustable load to participate in demand response
CN113191804A (en) * 2021-04-28 2021-07-30 西安交通大学 Optimal bidding strategy solving method
CN114997665A (en) * 2022-06-08 2022-09-02 国网山西省电力公司电力科学研究院 Virtual power plant optimal scheduling method and system considering controllable load response performance difference
CN115018198A (en) * 2022-06-30 2022-09-06 国网河南省电力公司经济技术研究院 Residential user electricity utilization optimization strategy considering differentiated demand response scheme
CN115438922A (en) * 2022-08-17 2022-12-06 中国电力科学研究院有限公司 Large-scale demand side flexible resource demand response potential evaluation method and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Z. WANG, X. KONG, S. ZHANG, K. CHEN, S. CHEN ， D. LI: "Source-load-storage Coordinated Optimal Scheduling of Virtual Power Plant Participating Demand Response", 《2020 23RD INTERNATIONAL CONFERENCE ON ELECTRICAL MACHINES AND SYSTEMS (ICEMS)》, pages 472 - 477 *
刘博: "计及电动汽车充电的居民分时电价方案研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, pages 042 - 2682 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116523273A (en) * 2023-07-04 2023-08-01 广东电网有限责任公司广州供电局 Demand response characteristic analysis method for industrial users
CN116523273B (en) * 2023-07-04 2023-09-22 广东电网有限责任公司广州供电局 Demand response characteristic analysis method for industrial users
CN116760122A (en) * 2023-08-21 2023-09-15 国网浙江省电力有限公司宁波供电公司 Virtual power plant resource management and control method and device, computer equipment and storage medium
CN116760122B (en) * 2023-08-21 2023-12-26 国网浙江省电力有限公司宁波供电公司 Virtual power plant resource management and control method and device, computer equipment and storage medium

Also Published As

Publication number Publication date
CN116070888B (en) 2023-07-04

Similar Documents

Publication Publication Date Title
CN116070888B (en) Virtual power plant adjustable capacity analysis method, device and medium based on decision tree
Celik On the distributional parameters used in assessment of the suitability of wind speed probability density functions
Petrov et al. Prediction of extreme significant wave heights using maximum entropy
CN109657913B (en) Transmission and distribution network joint risk assessment method considering distributed power supply
CN113537697A (en) Method and system for performance evaluation of supervisors in city management
CN116933034A (en) Method, system, electronic equipment and medium for determining carbon reserve change of ecosystem
CN112651560A (en) Ultra-short-term wind power prediction method, device and equipment
CN116861306A (en) Abnormal electricity utilization detection method based on electricity utilization trend quantification network
JP5946742B2 (en) Fluctuation estimation method, fluctuation estimation apparatus and fluctuation estimation program for total output of natural energy type distributed power supply group
CN105279706A (en) Method for determining operation security state of power network
Dai et al. A data-driven load fluctuation model for multi-region power systems
CN114254965A (en) Country happy power monitoring method and device, electronic equipment and storage medium
Milligan Variance estimates of wind plant capacity credit
Hor et al. Assessing load forecast uncertainty using extreme value theory
CN112258024B (en) Mixed energy storage capacity configuration method and system based on entropy weight method
CN115358495B (en) Calculation method for wind power prediction comprehensive deviation rate
CN117543702A (en) Data-driven power distribution network distributed new energy consumption capability assessment method
CN117521025A (en) Method and device for determining irrigation electric quantity of hybrid agriculture row user
Zhao et al. Evaluation method for security and economic operation of power system with high penetration of renewable energy
CN115907293A (en) Distributed photovoltaic power quality evaluation method and system based on time probability distribution
Biel Probabilistic analysis of coincident sums of precipitation at two measurement stations. Introduction to the method and an example
CN117114734A (en) Benefit data analysis method, device, storage medium and equipment
Dziadak et al. The quality engineering in designing a mobile measurement station
CN117933453A (en) Regional power grid electric power carbon emission prediction method, system, equipment and storage medium
CN117495056A (en) Power consumption data monitoring and optimizing method and system

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