CN118094398A - Power supply evaluation method based on Internet of things - Google Patents
Power supply evaluation method based on Internet of things Download PDFInfo
- Publication number
- CN118094398A CN118094398A CN202410512411.2A CN202410512411A CN118094398A CN 118094398 A CN118094398 A CN 118094398A CN 202410512411 A CN202410512411 A CN 202410512411A CN 118094398 A CN118094398 A CN 118094398A
- Authority
- CN
- China
- Prior art keywords
- demand
- user
- power supply
- operation parameters
- parameter
- 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
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 26
- 238000004146 energy storage Methods 0.000 claims abstract description 78
- 230000008859 change Effects 0.000 claims abstract description 7
- 238000003066 decision tree Methods 0.000 claims description 31
- 238000013507 mapping Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 17
- 238000005259 measurement Methods 0.000 claims description 11
- 230000005611 electricity Effects 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 7
- 230000003542 behavioural effect Effects 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 description 57
- 238000000034 method Methods 0.000 description 18
- 239000000047 product Substances 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 238000005457 optimization Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/35—Utilities, e.g. electricity, gas or water
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/20—Analytics; Diagnosis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Accounting & Taxation (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a power supply evaluation method based on the Internet of things, which relates to the technical field of energy storage power supply evaluation and comprises the following steps: s11, acquiring operation parameters corresponding to an energy storage power supply, wherein the operation parameters comprise capacity, an input voltage range, output voltage, output power, a charge-discharge power limit value and a state of charge; s12, predicting the acquired operation parameters, and determining the numerical value change range of the current operation parameters under different scenes; s13, dividing the scene information of the operation parameters according to the scene information corresponding to the operation parameters and the user requirements, and determining the operation parameters corresponding to different user requirements; s14, determining the correlation between corresponding operation parameters in different scenes, determining at least one demand deflection characteristic, and acquiring user behavior characteristics corresponding to at least one user demand; the flexibility and scene applicability of the stored energy power supply evaluation can be realized.
Description
Technical Field
The invention relates to the technical field of energy storage power supply evaluation, in particular to a power supply evaluation method based on the Internet of things.
Background
An energy storage power supply is a device that is capable of converting and storing electrical energy, and converting the stored electrical energy back to a power supply system when needed. The energy storage power supply can solve the problems of intermittence, instability and the like of renewable energy sources, so that the energy sources are more stable and reliable to supply. In the working process of the energy storage power supply, energy loss can be generated, the cycle life of the energy storage power supply is influenced, the scrapping of the energy storage power supply is accelerated, and the environment is influenced. The energy storage power supply is evaluated, so that the stability of voltage and frequency can be promoted, and the energy quality of electric power can be improved; the power supply requirement of the energy storage power supply is optimized, the utilization efficiency of energy in the energy storage power supply is maximized, waste is reduced, meanwhile, the power supply structure of the electric power energy can be optimized, the energy conservation and emission reduction of traditional fossil energy are realized.
The invention discloses an energy storage power supply evaluation method and system based on the Internet of things as disclosed in Chinese patent publication No. CN116738865A, and the method comprises the following steps: the method comprises the steps of obtaining a standard energy storage power supply prediction model and standard energy storage power supply prediction parameters through a decision tree model algorithm, obtaining the energy storage power supply prediction parameters through collecting operation parameters of an energy storage power supply, comparing and analyzing the standard energy storage power supply prediction parameters and the energy storage power supply prediction parameters to obtain abnormal sub-equipment and abnormal operation parameters, constructing an energy storage power supply dynamic simulation model based on the abnormal operation parameters, and screening an optimal debugging scheme of the energy storage power supply.
However, when the energy storage power supply is processed, if the energy storage power supply changes the power supply requirement and the energy utilization rate, the measured operation parameters and the optimal debugging scheme in the scene change correspondingly, and only the operation parameters and the abnormal operation parameters are referred, so that the optimal scheme required to be adopted by the current equipment cannot be accurately identified, and the energy utilization rate is reduced.
Disclosure of Invention
The embodiment of the application solves the problem that the operation parameters are difficult to determine due to different change ranges of different scenes in the prior art by providing the energy storage power supply evaluation method based on the Internet of things, realizes the personalized requirements of energy storage power supply evaluation, and improves the scene adaptability of energy storage power supply evaluation.
The embodiment of the application provides a power supply evaluation method based on the Internet of things, which comprises the following steps:
S11, acquiring operation parameters corresponding to an energy storage power supply, wherein the operation parameters comprise capacity, an input voltage range, output voltage, output power, a charge-discharge power limit value and a state of charge;
s12, predicting the acquired operation parameters, and determining the numerical value change range of the current operation parameters under different scenes;
s13, dividing the scene information of the operation parameters according to the scene information corresponding to the operation parameters and the user requirements, and determining the operation parameters corresponding to different user requirements;
s14, determining the correlation between corresponding operation parameters in different scenes, determining at least one demand deflection characteristic, and acquiring user behavior characteristics corresponding to at least one user demand;
S15, fusing the demand deviation characteristics with the user behavior characteristics corresponding to the user demands, and determining a power supply debugging scheme selected by the user.
The method for acquiring the numerical variation range of the operation parameters comprises the following steps:
s21, acquiring various operation parameter data of the energy storage power supply in a normal operation state, wherein the data comprise parameter values in different scenes;
s22, for each operation parameter, calculating the maximum value and the minimum value of the operation parameter in the normal operation state, thereby determining the parameter range and the range size value; the range size value is the difference between the maximum value and the minimum value of each parameter;
S23, setting a plurality of classification thresholds according to the acquired parameter range and range size values of the operation parameters, wherein the classification thresholds are values of which the parameter range is increased according to a preset percentage value, and classifying the operation parameters into different categories;
s24, taking the operation parameters as nodes, and constructing a decision tree according to the relation between the residual errors of the operation parameters and the operation parameters in different scenes.
The method for dividing the operation parameters according to the user requirements comprises the following steps:
s31, obtaining user demands and determining specific requirements and dependency relations of operation parameters under different user demands;
s32, acquiring a history record of operation parameters and scene information related to the history record under the corresponding user requirements;
s33, identifying a mapping relation between each operation parameter and a specific scene;
s34, converting the user demand into the demand for the specific operation parameter based on the user demand and the mapping relation between the operation parameter and the scene, and taking the user demand as a demand conversion result;
S35, dividing the operation parameters into different user demand groups according to the user demand conversion result, and constructing a decision tree aiming at the user demand groups.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
By acquiring and analyzing the operation parameter requirements (such as capacity, voltage, power and the like) of the user, the method can ensure that the energy storage power supply meets the personalized requirements of the user; the numerical value change range of the operation parameters under different scenes is considered, so that the configuration of the energy storage power supply can adapt to various use scenes, and the flexibility and applicability of the energy storage power supply are enhanced; by constructing a scene-related decision tree and a user demand-related decision tree, the method can provide intelligent power supply debugging scheme selection support for the user, so that the decision burden of the user in the process of selecting and configuring the energy storage power supply is reduced; not only the demand deviation characteristics of the user are considered, but also the behavior characteristics (such as load mode, equipment use habit and the like) of the user are fused, so that the power supply debugging scheme is more close to the actual use habit and demand of the user.
Drawings
Fig. 1 is a schematic flow chart of a first embodiment of a power supply evaluation method based on the internet of things of the present invention;
fig. 2 is a schematic flow chart of a second embodiment of a power supply evaluation method based on the internet of things of the present invention;
Fig. 3 is a schematic flow chart of a third embodiment of a power supply evaluation method based on the internet of things.
Detailed Description
In order that the application may be readily understood, a more complete description of the application will be rendered by reference to the appended drawings; the preferred embodiments of the present application are illustrated in the drawings, but the present application can be embodied in many different forms and is not limited to the embodiments described herein; rather, these embodiments are provided so that this disclosure will be thorough and complete.
It should be noted that the terms "vertical", "horizontal", "upper", "lower", "left", "right", and the like are used herein for illustrative purposes only and do not represent the only embodiment.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs; the terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention; the term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Example 1
As shown in fig. 1, the power supply evaluation method based on the internet of things of the present application includes:
S11, acquiring operation parameters corresponding to the energy storage power supply, wherein the operation parameters comprise capacity, an input voltage range, output voltage, output power, a charge-discharge power limit value and a state of charge.
The capacity of the energy storage power supply is determined according to actual requirements, and various capacity selections such as 10kWh, 50kWh, 100kWh and the like can be provided, and the parameter determines the maximum energy value that the energy storage power supply can store.
The energy storage power supply should have a wide input voltage range, and be able to accommodate different power inputs, for example, an input voltage range of 220V to 440V, which represents a voltage range of an external power supply that the energy storage power supply can accept.
The output voltage of the energy storage power supply is also determined according to actual requirements, and is usually a Direct Current (DC) output, such as 48V, 110V, etc., and this parameter determines the voltage value of the electric energy output by the energy storage power supply.
The output power of the energy storage power supply should also be determined according to actual requirements, and various power selections such as 1kW, 5kW, 10kW and the like can be provided, and the parameter determines the maximum electric energy value that the energy storage power supply can output at the same time.
The limit value of the charge and discharge power of the energy storage power supply refers to the maximum power limit of the energy storage power supply when the energy storage power supply is charged or discharged, and the parameter ensures the stability and the safety of the energy storage power supply in the running process.
The State of Charge (SOC) is a parameter describing the ratio of the current power to the total capacity of the energy storage power source, through which the remaining power of the energy storage power source and whether a charging or discharging operation is required can be known.
S12, predicting the acquired operation parameters, and determining the numerical value change range of the current operation parameters under different scenes.
The required parameter ranges of the energy storage power supply are different in different scenes, and the different scenes can be a household energy storage system, a commercial energy storage system and an industrial energy storage system.
For home energy storage systems, the main requirements include standby power, peak clipping and valley filling, etc. In this case, the operating parameters vary relatively little, and in general, the voltage variation range may be within ±10% of the rated voltage, and the current and power may be adjusted according to the actual requirements, but generally do not exceed the maximum bearing capacity of the device; in addition, the household energy storage system has higher requirements on the safety and stability of the energy storage power supply, so that the circuit can be cut off in time when the voltage and the current are abnormal.
The main demands of commercial energy storage systems include reducing electricity rates, backup power supplies, etc. In a commercial environment, the voltage and current may vary widely than in a home environment to accommodate different consumers and peaks of electricity. For example, the input voltage range of a commercial energy storage power supply may be wider to accommodate voltage fluctuations of the commercial power grid; the output power may also be higher to meet the needs of the commercial plant. Meanwhile, commercial energy storage systems have certain requirements on the service life and maintainability of equipment.
For industrial energy storage systems, the demand may be more complex and diverse, including balancing the grid, improving the efficiency of the equipment, etc. With this requirement, the range of voltage and current may be more flexible and variable, which needs to be determined according to specific industrial equipment and process flows. For example, for certain industrial devices requiring high power inputs, the stored energy power source may need to provide higher output voltages and currents; for some process flows with high requirements on the quality of electric energy, the stability of the output of the energy storage power supply needs to be ensured.
Besides the above-mentioned operating parameters in several scenes, there are some special scenes in which the operating parameter ranges are required to be considered, and these scenes are quantized to find the parameter ranges required in different scenes.
S13, dividing the scene information of the operation parameters according to the scene information corresponding to the operation parameters and the user requirements, and determining the operation parameters corresponding to different user requirements.
The consumer demand herein may be expressed as power supply stability demand, economic benefit demand, environmental and sustainability demand, extensibility and flexibility demand, safety and reliability demand.
Power supply stability requirements: users want energy storage power sources to provide emergency power support in the event of grid faults or outages, ensuring continuous power to critical devices or the entire system. Under the condition of fluctuation or unstable voltage of the power grid, the energy storage power supply can smoothly output, and the user equipment is protected from damage.
Economic benefit requirement: the user hopes to realize peak clipping and valley filling of the electric charge through the energy storage power supply, namely, the user charges when the electric charge is low and discharges when the electric charge is high, so that the expenditure of the electric charge is reduced. For commercial and industrial users, energy storage power supplies may be used in demand response projects to avoid or reduce demand charges by reducing peak loads.
Environmental and sustainability requirements: users may choose an energy storage power source for environmental reasons to reduce reliance on traditional fossil fuels and reduce carbon emissions. In remote areas or off-grid applications, the stored energy power source may be used as a supplement to renewable energy sources (e.g., solar energy, wind energy) to provide a stable and reliable power supply.
Expansibility and flexibility requirements: users may require the energy storage power supply system to be of modular design in order to expand capacity according to future demands. The energy storage power supply should have the capability of being compatible with a variety of energy management systems and devices in order to achieve intelligent control and optimization.
Security and reliability requirements: the safety performance of the energy storage power supply is strictly required by users, including the safety of a battery management system, the protection against overcharge and overdischarge, the short-circuit protection and the like. The energy storage power supply has high reliability, can stably operate under various environmental conditions, and has low maintenance cost.
S14, determining the correlation between corresponding operation parameters in different scenes, determining at least one demand deflection characteristic, and acquiring user behavior characteristics corresponding to at least one user demand.
The demand bias characteristics are characteristics related to the capacity, the charge and discharge power, the energy source and the energy loss of the energy storage power supply, which are acquired based on the demands of users.
The user behavior characteristics include the behavior characteristics of a stability pursuer, the behavior characteristics of an economic user, the behavior characteristics of an environment-friendly advocate, the behavior characteristics of a flexible configurator, the behavior characteristics of a security advocate, and the like.
1. Behavior characteristics of stability pursuers
Selection behavior: there is a trend to select stored energy power products with high capacity, high output power and fast response capability.
Configuration behavior: redundant configurations are important to ensure that critical equipment operation is maintained in extreme cases.
Usage behavior: the power supply status is often checked to ensure that it is ready for use and an automatic switching function may be provided to cope with grid faults.
2. Behavior characteristics of economic users
Selection behavior: price sensitive, cost effectiveness of different brands and models may be compared.
Configuration behavior: smaller initial capacities may be selected but require scalability of the power supply in order to increase capacity in the future.
Usage behavior: regarding the operation efficiency of the power supply, the charge and discharge strategy may be adjusted according to the power price fluctuation.
3. Behavior characteristics of environmental protection advocates
Selection behavior: preferably, the stored energy power source is charged using a renewable energy source.
Configuration behavior: it is possible to install a solar panel or a wind generator for use with the stored energy power source.
Usage behavior: focusing on the environmental label and recyclability of the power supply, it is possible to participate in the recycling program when it is no longer needed.
4. Behavior features of a flexible configurator
Selection behavior: the energy storage power supply of modular design tends to be selected to adjust the configuration as desired.
Configuration behavior: the setting of the power supply is often adjusted to adapt to the requirements of different equipment or application scenes.
Usage behavior: the mode of operation of the power supply may be frequently altered to maximize its flexibility and efficiency.
5. Behavior characteristics of security upper bound
Selection behavior: very important to the security record of the power supply, only authenticated brands and models may be selected.
Configuration behavior: additional safety devices and monitoring systems may be installed to ensure safe operation of the power supply.
Usage behavior: strictly following the operation rules, safety inspection and maintenance are carried out regularly.
S15, fusing the demand deviation characteristics with the user behavior characteristics corresponding to the user demands, and determining a power supply debugging scheme selected by the user.
By fusing different user behavior characteristics and demand preference characteristics, the power supply debugging scheme can more accurately meet the demand of a user on stable power supply. For example, by optimizing capacity configuration and charge-discharge strategies, it is ensured that critical equipment can continue to operate stably when a power grid fails or fluctuates, and production interruption risks caused by power problems are reduced. For customized demanders, the power supply debugging scheme fused with the behavior characteristics of the customized demanders can provide more accurate and personalized services. Through close cooperation and depth customization with the user, the power supply system is ensured to completely meet the requirements of specific application scenes of the user, and the satisfaction and loyalty of the user are improved.
Example 2
In order to obtain an accurate operating parameter range, the obtained power debugging scheme can meet the requirements of scenes and users under the conditions of subsequent scene analysis and user behavior processing, the obtained operating parameters are used as nodes according to range values and prominent values in different scenes, the relation among the values is represented through an integral decision tree, and the tree structure after the operating parameters are classified is obtained through the association of the values among the decision trees.
And acquiring the range value of the operation parameter by acquiring the data of the operation parameter under normal operation, and acquiring the corresponding related parameter range of the energy storage power supply and the difference value between the maximum value and the minimum value of the parameter range to determine the current classification.
Specifically, as shown in fig. 2, the method for obtaining the numerical variation range of the operation parameter includes:
s21, acquiring various operation parameter data of the energy storage power supply in a normal operation state, wherein the data comprise parameter values in different scenes;
s22, for each operation parameter, calculating the maximum value and the minimum value of the operation parameter in the normal operation state, thereby determining the parameter range and the range size value; the range size value is the difference between the maximum value and the minimum value of each parameter;
S23, setting a plurality of classification thresholds according to the acquired parameter range and range size values of the operation parameters, wherein the classification thresholds are values of which the parameter range is increased according to a preset percentage value, and classifying the operation parameters into different categories;
s24, taking the operation parameters as nodes, and constructing a decision tree according to the relation between the residual errors of the operation parameters and the operation parameters in different scenes.
Constructing a scenario-related decision tree includes: and taking the operation parameter with the minimum residual as a root node, selecting an internal node according to the residual of the operation parameter, and dividing leaf nodes according to the Pearson product difference correlation coefficient of the internal node.
Residual generally refers to the difference between observed and predicted values (or model estimates), and when constructing a decision tree based on an operating parameter, residual is understood to be the deviation between the actual value and the expected value (or baseline value) of the operating parameter in different scenarios. This deviation reflects the degree of variation of the parameter in a particular scenario, helping to understand the behavior patterns of the parameter in different scenarios.
For the Pearson product difference correlation coefficient between the determined operation parameters, taking the Pearson product difference correlation coefficient as the relation between the operation parameters; according to the method, the nodes corresponding to the operation parameters are trained on different decision trees, the prediction accuracy is improved by constructing a plurality of decision trees and combining the outputs of the decision trees, and each node splitting is realized by considering only one random feature subset, so that the decision trees are more robust and are not easy to fit.
The calculation formula of the Pearson product difference correlation coefficient is as follows:
r=(n×Σ(xy)–Σx×Σy)/sqrt((n×Σx²-(Σx)²)×(nΣy²-(Σy)²))
Where n is the data sample capacity, i.e., the number of observations; x and y are observations of two variables, respectively; Σ represents the sum of all observations; Σ (xy) represents the sum of the products of each x and y; Σx and Σy represent the sum of all observations of x and y, respectively; Σx and Σy denote the sum of the squares of each observation of x and y, respectively.
When a scene-related decision tree is constructed, the operation parameter with the minimum residual error is taken as a root node, and the operation parameter with the minimum residual error is selected as the root node, which means that the interpretation capability of the parameter to a target variable is strongest in the current scene, so that the decision tree constructed based on the parameter possibly has higher prediction accuracy, and is beneficial to reducing the depth of the tree, thereby simplifying the model structure and reducing the risk of overfitting.
Assuming a set of operating parameters, each parameter has a residual associated with it, the residual being the difference between the observed value and the predicted value, the parameter with the smallest residual is selected as the root node.
Operating parameter a: residual = 10;
operating parameter B: residual = 5;
Operating parameter C: residual = 8;
in this example, the operating parameter B has the smallest residual, so it is selected as the root node.
Once the root node is selected, it is necessary to continue to select the internal nodes, which can be done by taking into account the residual of each remaining parameter, the parameter with the smallest residual being selected as the next internal node.
Example (continuing with the example above):
after excluding parameter B, the remaining parameters a and C are considered.
Operating parameter a: residual = 10
Operating parameter C: residual = 8
In this example, the operating parameter C now has the smallest residual, so it is selected as the next internal node.
For each internal node, a Pearson product difference correlation coefficient between it and the remaining operating parameters needs to be calculated, this coefficient measures the strength and direction of the linear relationship between the two variables, and parameters with high correlation coefficients may be used to divide the leaf nodes.
Let us assume that the node is now at parameter C and consider dividing it into leaf nodes.
The Pearson product difference correlation coefficient between the parameter C and the other remaining parameters (parameter a in this example) is calculated.
If the Pearson coefficients show a strong correlation (whether positive or negative) between parameter C and parameter a, then the leaf nodes may be partitioned according to this correlation.
Assuming that the calculated Pearson coefficient is high (near 1 or-1), then it is possible to use the parameter a as a partitioning criterion to create two leaf nodes: one containing an instance of a high a value and the other containing an instance of a low a value.
It should be noted that this process may require multiple iterations and adjustments depending on the actual data and complexity of the problem. Moreover, since this approach is not a standard approach to decision tree construction, additional verification and optimization may be required in practical applications.
The Pearson product difference correlation coefficient can quantify the linear relation strength between the operation parameters, and by using the coefficient in a decision tree, the parameters with strong correlation and the parameters with weak correlation or irrelevant can be intuitively displayed; the residual error reflects the deviation between the running parameter and the baseline value or the expected value under different scenes, and the residual error is used as the distance between the nodes, so that the influence degree of the different scenes on the running parameter can be revealed, and if the residual error of a certain parameter under a plurality of scenes is large, the parameter can be a key parameter which is very sensitive to scene changes; by observing the decision tree, a decision maker can quickly identify which operation parameters are interrelated under different scenes and how their relationship strength is, and the information is very valuable for tasks such as making a power supply debugging scheme, optimizing system performance or performing fault diagnosis.
Example 3
After the operation parameters are classified, the operation parameters which are classified are matched with the user demands according to the operation parameters, the operation parameters corresponding to the user demands are determined, and the obtained user demands are distinguished according to the energy storage value and the maintenance demands related to the equipment so as to obtain the operation parameters which meet the use and maintenance demands.
Specifically, as shown in fig. 3, the method for dividing the operation parameters according to the user requirement includes:
s31, obtaining user demands and determining specific requirements and dependency relations of operation parameters under different user demands;
s32, acquiring a history record of operation parameters and scene information related to the history record under the corresponding user requirements;
s33, identifying a mapping relation between each operation parameter and a specific scene;
s34, converting the user demand into the demand for the specific operation parameter based on the user demand and the mapping relation between the operation parameter and the scene, and taking the user demand as a demand conversion result;
S35, dividing the operation parameters into different user demand groups according to the user demand conversion result, and constructing a decision tree aiming at the user demand groups.
First, it is necessary to clarify and collect the different needs of the user. This may include various specific application objectives such as performance optimization, energy efficiency improvement, fault detection, etc.; the requirements are analyzed in detail, and the specific requirements and the dependency relationship of the requirements on the operation parameters are known; collecting historical data, including a historical record of operation parameters and scene information related to the historical data, and preprocessing the collected data, such as data cleaning, normalization and the like, so as to ensure the effectiveness of subsequent analysis; the mapping relationship between each operating parameter and a specific scene is identified and analyzed. This may involve the use of statistical analysis, machine learning algorithms, etc., the purpose of this step being to establish a correspondence between parameter values or parameter changes and specific scenarios; converting the user demand into the demand for the specific operation parameter based on the user demand and the mapping relation between the parameter and the scene; dividing the operation parameters into different user demand groups according to the user demand conversion result; for each user demand, determining a set of key operating parameters thereof; for each user requirement or user group, a customized decision tree can be constructed to intuitively demonstrate the relationship between its key operating parameters.
And identifying the mapping relation between each operation parameter and the specific scene, wherein the mapping relation can be obtained through a decision tree constructed according to the scene information, and determining the mapping relation between the operation parameters and the scene.
Based on the mapping relation between the user requirement and the operation parameter and the scene, the mainly used scene and the operation parameter are selected according to the type of the user requirement, so that the corresponding mapping relation is determined, and when the mapping relation between the user requirement and the scene is determined, the user requirement and the required scene can be matched in a statistical mode, so that the mapping relation between the user requirement and the scene is obtained.
When constructing a decision tree related to user demands, taking the largest user demand group as a root node, creating child nodes according to the mapping relation between the user demands and scenes, and constructing leaf nodes according to operation parameters corresponding to the user demands.
When constructing a decision tree related to user demands, the largest user demand group is taken as a root node, which means that the decision tree will pay attention to and meet the demands of the most extensive users first, which helps to ensure that the solution can meet the core demands of most users, thereby improving the overall user satisfaction.
Through detailed collection and analysis of the user demands and identification of the mapping relation between the operation parameters and the specific scenes, the user demands can be ensured to be accurately converted into the demands for the specific operation parameters, so that specific targets of performance optimization, energy efficiency improvement, fault detection and the like of the user can be more effectively met; according to different user demands, the operation parameters are divided into different user demand groups, and a customized decision tree is constructed for the operation parameters, so that the customized decision support mode can be better adapted to the demands and application scenes of different users, and a more targeted solution is provided.
Example 4
After the decision tree corresponding to the scene information and the user demand is obtained, extracting the demand deviation characteristics related to the demand deviation and the user behavior characteristics corresponding to the user behavior from the obtained operation parameters; these extracted features are analyzed here to identify how they affect the performance of the system or the user's experience, understanding the user's needs and behavioral characteristics in depth, thereby meeting the user's expectations more precisely.
Demand bias features common and differential features are extracted by sorting and analyzing the collected user demand data, which may include user preferences in terms of functionality, performance, price, etc.
User behavior features key behavior features are extracted by preprocessing and analyzing the collected user behavior data, and the features may include frequency of use, time of use, access path, operation habit and the like.
The collected and analyzed information is integrated to form a comprehensive view containing scene, operation parameters, user demand bias and user behavior characteristics, and the parameters required by the user can be positioned according to the comprehensive view so as to facilitate subsequent processing.
When the demand deviation feature is acquired, acquiring a first demand feature of a training sample based on user demands; inputting the first demand features into a deep semantic model to obtain second demand features containing user demands, and taking the second demand features as demand text features of training samples;
and acquiring first category features of the training sample based on the requirement category, inputting the first category features into a depth semantic model to obtain second category features containing the requirement category, and taking the second category features as category features of the training sample.
Upon acquiring the demand bias feature, the user may enter their demand through a system interface or voice, such as "a portable battery suitable for outdoor camping is required" or "the energy storage battery capacity is reduced"; the system will first pre-process and initially extract features of the desired text. The system has a series of battery categories, such as an outdoor portable battery, a household energy storage battery, an industrial large-capacity battery and the like, and each category has corresponding description and characteristic information. The system respectively inputs the demand text features and the battery category features of the user into a deep semantic model to acquire second demand features and second category features containing rich semantic information; for example, the model may understand that "light" and "camping outdoors" are keywords related to portability and durability, while "capacity degradation" may be associated with battery aging or maintenance issues, based on which the resulting features may provide a user with advice, fault solutions, and the like.
The acquired demand category may be expressed as a corresponding classification formed for keywords of high capacity, long endurance, high energy density, transient response, etc.
When the behavior characteristics of the user are acquired, the processing mode comprises the steps of acquiring at least one behavior measurement data under the category corresponding to the user demand, wherein the behavior measurement data comprise a load mode, equipment use, electricity management behaviors and demand response; a behavioral metric characteristic of the user is determined from the behavioral metric data.
Wherein the power demand of the load mode users varies in different time periods to form a specific load mode, for example, the power demand of a commercial district is high in the daytime, and the power demand of a residential district is increased in the evening; such load pattern variations can directly affect the voltage and current distribution within the power system, resulting in loss variations.
Device usage indicates the type and number of electrical devices used by the user; frequent use of high power devices increases current consumption, while use of energy-saving devices reduces consumption.
The electricity management actions indicate that if the user takes energy-saving measures, such as peak-shifting electricity consumption, using electric appliances with higher energy efficiency, etc., the actions can lighten the load of the power system, and further reduce the loss of voltage and current, otherwise, if the user uses the electric power without restriction, the loss of the power system can be increased, especially in peak time.
Demand response means that in some power systems implementing demand response plans, users will adjust their own electricity usage behavior based on electricity price signals or system demand, which helps balance grid load and reduce losses.
By regulating and controlling the behavior measurement data, when a user uses electric power, the operation parameters of the energy storage power supply can use different values of current and voltage according to different choices, so as to complete the regulation and control of the user behavior.
In acquiring the demand bias characteristics, further comprising: and vector splicing is carried out on the demand text features and at least one behavior measurement data, so that demand deviation features of the training text are obtained.
When the user behavior characteristics are acquired, the method further comprises the following steps: and acquiring the selection probability of each demand category under the condition that the training sample corresponds to the demand category, acquiring at least one behavior measurement data under each demand category, and vector-splicing the behavior measurement data with category characteristics of the training sample according to the size of the selection probability to obtain the user behavior characteristics of the training sample.
The method for determining the correlation degree data of the demand deflection feature and the user behavior feature under the current corresponding demand category comprises the following steps of: inputting the demand deflection characteristics and the user behavior characteristics into the full-connection layer with the preset layer number respectively; and the cosine similarity of the demand deflection characteristics and the user behavior characteristics is calculated through the full connection layer and is used as the correlation degree data.
And taking the demand deviation characteristic and the user behavior characteristic corresponding to the maximum correlation degree data as the basis for selecting the power supply debugging scheme, and outputting the optimal power supply debugging scheme based on big data detection.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The power supply evaluation method based on the Internet of things is characterized in that the power supply is an energy storage power supply and comprises the following steps: s11, acquiring operation parameters corresponding to an energy storage power supply, wherein the operation parameters comprise capacity, an input voltage range, output voltage, output power, a charge-discharge power limit value and a state of charge;
s12, predicting the acquired operation parameters, and determining the numerical value change range of the current operation parameters under different scenes;
s13, dividing the scene information of the operation parameters according to the scene information corresponding to the operation parameters and the user requirements, and determining the operation parameters corresponding to different user requirements;
s14, determining the correlation between corresponding operation parameters in different scenes, determining at least one demand deflection characteristic, and acquiring user behavior characteristics corresponding to at least one user demand;
S15, fusing the demand deviation characteristics with the user behavior characteristics corresponding to the user demands, and determining a power supply debugging scheme selected by the user.
2. The power supply evaluation method based on the internet of things according to claim 1, wherein the acquiring manner of the numerical variation range of the operation parameter comprises:
s21, acquiring various operation parameter data of the energy storage power supply in a normal operation state, wherein the data comprise parameter values in different scenes;
s22, for each operation parameter, calculating the maximum value and the minimum value of the operation parameter in the normal operation state, thereby determining the parameter range and the range size value; the range size value is the difference between the maximum value and the minimum value of each parameter;
S23, setting a plurality of classification thresholds according to the acquired parameter range and range size values of the operation parameters, wherein the classification thresholds are values of which the parameter range is increased according to a preset percentage value, and classifying the operation parameters into different categories;
s24, taking the operation parameters as nodes, and constructing a decision tree according to the relation between the residual errors of the operation parameters and the operation parameters in different scenes.
3. The power supply evaluation method based on the internet of things as set forth in claim 2, wherein constructing a scene-related decision tree comprises: and taking the operation parameter with the minimum residual as a root node, selecting an internal node according to the residual of the operation parameter, and dividing leaf nodes according to the Pearson product difference correlation coefficient of the internal node.
4. The power supply evaluation method based on the internet of things according to claim 1, wherein the dividing the operation parameters according to the user requirements comprises:
s31, obtaining user demands and determining specific requirements and dependency relations of operation parameters under different user demands;
s32, acquiring a history record of operation parameters and scene information related to the history record under the corresponding user requirements;
s33, identifying a mapping relation between each operation parameter and a specific scene;
s34, converting the user demand into the demand for the specific operation parameter based on the user demand and the mapping relation between the operation parameter and the scene, and taking the user demand as a demand conversion result;
S35, dividing the operation parameters into different user demand groups according to the user demand conversion result, and constructing a decision tree aiming at the user demand groups.
5. The power supply evaluation method based on the Internet of things according to claim 4, wherein when constructing a decision tree related to user demands, a maximum user demand group is taken as a root node, child nodes are created according to a mapping relation between the user demands and scenes, and leaf nodes are constructed according to operation parameters corresponding to the user demands.
6. The power supply evaluation method based on the internet of things according to claim 1, further comprising, when the demand bias feature is acquired, acquiring a first demand feature of a training sample based on a user demand; inputting the first demand features into a deep semantic model to obtain second demand features containing user demands, and taking the second demand features as demand text features of training samples;
and acquiring first category features of the training sample based on the requirement category, inputting the first category features into a depth semantic model to obtain second category features containing the requirement category, and taking the second category features as category features of the training sample.
7. The power supply evaluation method based on the internet of things according to claim 6, wherein at least one behavior measurement data under the category corresponding to the user demand is obtained, and the behavior measurement data comprises a load mode, equipment use, electricity management behavior and demand response; a behavioral metric characteristic of the user is determined from the behavioral metric data.
8. The power supply evaluation method based on the internet of things according to claim 7, wherein the demand text features and the at least one behavior measurement data are subjected to vector splicing to obtain the demand deviation features of the training text.
9. The power supply evaluation method based on the internet of things according to claim 8, wherein the selection probability of each demand category under the corresponding demand category of the training sample is obtained, at least one behavior measurement data under each demand category is obtained, and the behavior measurement data is subjected to vector splicing according to the size of the selection probability and category characteristics of the training sample, so that the user behavior characteristics of the training sample are obtained.
10. The power supply evaluation method based on the internet of things according to claim 9, wherein determining the correlation degree data of the demand bias feature and the user behavior feature under the currently corresponding demand category according to the distance between the demand bias feature and the user behavior feature of the training sample comprises: inputting the demand deflection characteristics and the user behavior characteristics into the full-connection layer with the preset layer number respectively; cosine similarity between the demand deflection characteristics and the user behavior characteristics is calculated through the full connection layer and is used as correlation degree data;
And taking the demand deviation characteristic and the user behavior characteristic corresponding to the maximum correlation degree data as the basis for selecting the power supply debugging scheme, and outputting the optimal power supply debugging scheme based on big data detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410512411.2A CN118094398B (en) | 2024-04-26 | 2024-04-26 | Power supply evaluation method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410512411.2A CN118094398B (en) | 2024-04-26 | 2024-04-26 | Power supply evaluation method based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118094398A true CN118094398A (en) | 2024-05-28 |
| CN118094398B CN118094398B (en) | 2024-07-26 |
Family
ID=91157691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410512411.2A Active CN118094398B (en) | 2024-04-26 | 2024-04-26 | Power supply evaluation method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118094398B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060085738A (en) * | 2005-01-25 | 2006-07-28 | 한국전기연구원 | System for demand side management evaluation in the electric power industry through internet |
| US20170338653A1 (en) * | 2014-11-27 | 2017-11-23 | Nec Corporation | Demand control apparatus, group generation apparatus, and group generation method |
| JP2019097327A (en) * | 2017-11-24 | 2019-06-20 | 株式会社Ｎｔｔファシリティーズ | Power demand forecasting device, power demand forecasting method, and program |
| CN112329988A (en) * | 2020-10-16 | 2021-02-05 | 杭州鸿晟电力设计咨询有限公司 | Demand side response calculation method based on park adjustability analysis |
| CN113610351A (en) * | 2021-07-13 | 2021-11-05 | 国网浙江省电力有限公司电力科学研究院 | User demand response capability assessment method, system, terminal and medium |
| WO2022246966A1 (en) * | 2021-05-27 | 2022-12-01 | 四川中电启明星信息技术有限公司 | Competitive-map-based charging station demand response method for electric vehicle |
| CN116384155A (en) * | 2023-05-25 | 2023-07-04 | 天津大学 | Household energy management optimization method considering uncertainty of user behavior |
| CN116404655A (en) * | 2023-01-29 | 2023-07-07 | 国网河南省电力公司焦作供电公司 | Distribution network load flexible regulation and control method and system |
| CN116739347A (en) * | 2023-06-09 | 2023-09-12 | 广东电网有限责任公司广州供电局 | Power grid risk assessment method and device, storage medium and computer equipment |
| CN116896086A (en) * | 2023-05-31 | 2023-10-17 | 国网山东省电力公司经济技术研究院 | Virtual power plant adjustable resource regulation and control system and method considering demand response |
| CN117592678A (en) * | 2023-10-25 | 2024-02-23 | 国网综合能源服务集团有限公司 | Comprehensive energy scheduling method and system based on electricity consumption demand analysis |
| CN117875752A (en) * | 2023-12-06 | 2024-04-12 | 国网四川省电力公司经济技术研究院 | Power system flexible operation domain assessment method based on self-organizing map decision tree |
-
2024
- 2024-04-26 CN CN202410512411.2A patent/CN118094398B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060085738A (en) * | 2005-01-25 | 2006-07-28 | 한국전기연구원 | System for demand side management evaluation in the electric power industry through internet |
| US20170338653A1 (en) * | 2014-11-27 | 2017-11-23 | Nec Corporation | Demand control apparatus, group generation apparatus, and group generation method |
| JP2019097327A (en) * | 2017-11-24 | 2019-06-20 | 株式会社Ｎｔｔファシリティーズ | Power demand forecasting device, power demand forecasting method, and program |
| CN112329988A (en) * | 2020-10-16 | 2021-02-05 | 杭州鸿晟电力设计咨询有限公司 | Demand side response calculation method based on park adjustability analysis |
| WO2022246966A1 (en) * | 2021-05-27 | 2022-12-01 | 四川中电启明星信息技术有限公司 | Competitive-map-based charging station demand response method for electric vehicle |
| CN113610351A (en) * | 2021-07-13 | 2021-11-05 | 国网浙江省电力有限公司电力科学研究院 | User demand response capability assessment method, system, terminal and medium |
| CN116404655A (en) * | 2023-01-29 | 2023-07-07 | 国网河南省电力公司焦作供电公司 | Distribution network load flexible regulation and control method and system |
| CN116384155A (en) * | 2023-05-25 | 2023-07-04 | 天津大学 | Household energy management optimization method considering uncertainty of user behavior |
| CN116896086A (en) * | 2023-05-31 | 2023-10-17 | 国网山东省电力公司经济技术研究院 | Virtual power plant adjustable resource regulation and control system and method considering demand response |
| CN116739347A (en) * | 2023-06-09 | 2023-09-12 | 广东电网有限责任公司广州供电局 | Power grid risk assessment method and device, storage medium and computer equipment |
| CN117592678A (en) * | 2023-10-25 | 2024-02-23 | 国网综合能源服务集团有限公司 | Comprehensive energy scheduling method and system based on electricity consumption demand analysis |
| CN117875752A (en) * | 2023-12-06 | 2024-04-12 | 国网四川省电力公司经济技术研究院 | Power system flexible operation domain assessment method based on self-organizing map decision tree |
Non-Patent Citations (3)
| Title |
|---|
| AYA SAYED等: "Intelligent edge-based recommender system for internet of energy applications", 《IEEE》, 25 November 2021 (2021-11-25), pages 1 - 10 * |
| 张凯瑞等: "基于CPSS视角的需求响应能力评估综述", 《电力科学与技术学报》, 28 January 2024 (2024-01-28), pages 28 - 46 * |
| 王毅等: "电力用户行为模型：基本概念与研究框架", 《电工技术学报》, 10 May 2019 (2019-05-10), pages 056 - 2068 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118094398B (en) | 2024-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9235825B2 (en) | Processing load profiles for consumption management systems | |
| KR102187327B1 (en) | Dynamic management and control system for a building electric demand based on automated machine learning scheme | |
| Kang et al. | How to better share energy towards a carbon-neutral city? A review on application strategies of battery energy storage system in city | |
| Roslan et al. | Microgrid control methods toward achieving sustainable energy management: A bibliometric analysis for future directions | |
| EP3343496A1 (en) | Method and system for energy management in a facility | |
| US20130232151A1 (en) | Aggregation of Load Profiles for Consumption Management Systems | |
| Liu et al. | Fast stability scanning for future grid scenario analysis | |
| CN116821660A (en) | Power management method, system, terminal equipment and storage medium | |
| CN117595391A (en) | Coordination control method of power grid system | |
| Lorente et al. | Energy storage allocation in power networks–A state-of-the-art review | |
| CN115514100A (en) | Hybrid energy storage system based on multi-element energy storage and control | |
| Bektas et al. | Review and clustering of optimal energy management problem studies for industrial microgrids | |
| Miah et al. | Energy storage controllers and optimization schemes integration to microgrid: an analytical assessment towards future perspectives | |
| CN117543791B (en) | Power supply detection method, device, equipment and storage medium for power supply | |
| Ponoćko | Data analytics-based demand profiling and advanced demand side management for flexible operation of sustainable power networks | |
| CN118094398B (en) | Power supply evaluation method based on Internet of things | |
| Kaplun et al. | About using electricity pricing for smart grid dynamic management with renewable sources | |
| Tian | Grid-connected energy storage systems: benefits, planning and operation | |
| Ding et al. | Reliability evaluation of direct current distribution system for intelligent buildings based on big data analysis | |
| Ponocko | Data Analytics Based Demand Profiling and Advanced Demand Side Management for Flexible Operation of Sustainable Power Networks | |
| Li et al. | Analysis of distribution network planning with distributed power supply based on ELM algorithm | |
| Lin et al. | Research on Operation Strategy of User-side Energy System Based on Data Driving | |
| Salameh et al. | Microgrid components clustering in a digital ecosystem cooperative framework | |
| Leng et al. | A Comprehensive Literature Review for Optimal Planning of Distributed Energy Resources in Distribution Grids | |
| CN117175639B (en) | Power distribution automation method and system matched with energy storage unit in coordination |
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 |