Dynamic Response Early Warning System and Method for Wind, Solar and Storage Equipment Based on Digital Twin Technology

By constructing a response twin matrix for wind, solar, and energy storage equipment using digital twin technology, analyzing the degree of coordination and probability, and periodically updating the matrix slice set, the problem of insufficient identification of the coordinated response relationship between wind, solar, and energy storage equipment is solved, enabling dynamic risk assessment and timely early warning of the wind, solar, and energy storage system.

CN120896113BActive Publication Date: 2026-11-17XINJIANG SHAANXI INVESTMENT NEW ENERGY CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202510913568.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-07-03
Publication Date
2026-11-17
Estimated Expiration
2045-07-03

AI Technical Summary

Technical Problem

Existing early warning technologies ignore the coordinated response relationship between wind, solar and energy storage equipment. Data analysis is static and cannot dynamically track changes in equipment response, resulting in delayed early warnings and insufficient risk identification.

Method used

Based on digital twin technology, a device response twin matrix is ​​constructed to analyze the degree of coordination and probability between devices. By periodically updating the matrix slice set, the risk of coordination interruption is assessed and an early warning is issued.

Benefits of technology

It improves the accuracy and timeliness of early warning response for wind, solar and energy storage equipment, can identify risks of collaborative imbalance, reduce delayed early warning, and is suitable for safety monitoring of wind, solar and energy storage systems under complex operating conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120896113B_ABST
    Figure CN120896113B_ABST
Patent Text Reader

Abstract

This invention discloses a dynamic response early warning system and method for wind, solar, and energy storage equipment based on digital twin technology, belonging to the field of energy storage equipment early warning technology. It maps the operating data of wind, solar, and energy storage equipment using digital twin technology to construct an equipment response twin matrix; analyzes the coordination consistency and probability between equipment to generate a coordinated response feature set; periodically updates the matrix to form a slice set, assesses the risk of coordination interruption between equipment, and issues early warnings. This invention considers the coordination relationship between equipment, enabling the identification of risks caused by coordination imbalance (such as the energy storage equipment not responding synchronously when photovoltaic power fluctuates), avoiding "missed warnings." By capturing equipment coordination relationships and dynamically updating data, it improves the accuracy and timeliness of wind, solar, and energy storage equipment response early warnings. Through periodic updates of the matrix and slice set, it can dynamically track changes in equipment response, detect trend risks in advance (such as a decrease in the coordination efficiency of wind power and energy storage within three consecutive cycles), and reduce "lagging early warnings."
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of early warning technology for energy storage equipment, specifically to a dynamic response early warning system and method for wind, solar and energy storage equipment based on digital twin technology. Background Technology

[0002] With the rapid development of the new energy industry, wind-solar-storage (wind power generation, photovoltaic power generation, and energy storage equipment) systems have become an important part of energy supply. However, the operating environment of wind-solar-storage equipment is complex, and there are strong coupling relationships between the equipment (such as power matching between wind power generation and energy storage equipment, and coordinated response between photovoltaic power generation and the power grid). An abnormality in a single device may trigger a chain of failures.

[0003] Existing early warning technologies mostly rely on independent operating data (such as temperature and voltage) from single devices to make threshold judgments, which has the following shortcomings: First, they ignore the coordinated response relationship between devices, making it difficult to identify potential risks caused by coordination imbalances (such as energy storage devices failing to replenish energy in time when wind power drops sharply); second, they are mainly based on static data analysis and cannot dynamically track the response changes of devices in different cycles, resulting in delayed early warnings; third, they lack correlation analysis of multiple types of operating data (such as power, frequency, and energy storage capacity), making it difficult to locate the root cause of risks. Summary of the Invention

[0004] The purpose of this invention is to provide a dynamic response early warning system and method for wind, solar, and energy storage equipment based on digital twin technology, in order to solve the problems mentioned in the background. In terms of technical structure, this invention, based on digital twin technology, achieves early warning through a logic of "data mapping - collaborative analysis - dynamic update - risk assessment." Specifically, firstly, the physical operating status of wind, solar, and energy storage equipment (such as power output, energy storage capacity, etc.) is transformed into computable operating data using digital twin technology, constructing an equipment response twin matrix to quantify the response status of the equipment at different times; then, by comparing the response behaviors between equipment, the degree of coordination and probability are calculated, key collaborative features are screened, and the dependencies between equipment are captured; next, the matrix is ​​continuously updated within a fixed period to form a periodic slice set to reflect the temporal changes in equipment response; finally, based on the slice set, the risk of collaborative interruption between different operating data is analyzed to locate the cycle and data type of risk occurrence, achieving accurate early warning.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] The dynamic response and early warning system for wind, solar and energy storage equipment based on digital twin technology includes: a data acquisition and matrix construction module, a collaborative analysis module, a periodic matrix update module, and a risk assessment and early warning module. Each module is connected in sequence via wireless signals.

[0007] The data acquisition and matrix construction module is used to collect the operation data of wind, solar and energy storage equipment, construct an operation behavior set based on the data type, and map the operation behavior set to the equipment response twin matrix through digital twin technology.

[0008] The collaborative analysis module is used to select different response behavior clusters in the device response twin matrix as collaborative analysis samples and collaborative control samples, respectively, to analyze the degree of collaboration and probability of collaboration between samples, and to screen the collaborative control samples that meet the conditions to form a collaborative response feature set.

[0009] The periodic matrix update module updates the device response twin matrix based on the collaborative response feature set, and collects the updated device response twin matrix under a fixed response cycle to form a periodic twin matrix slice set.

[0010] The risk assessment and early warning module, based on a periodic twin matrix slice set, assesses the risk of collaborative interruption among wind, solar and energy storage equipment corresponding to different types of operational data, and outputs early warning information based on the risk assessment results.

[0011] Furthermore, the data acquisition and matrix construction module includes an operational data acquisition unit and a twin matrix construction unit, with each unit connected sequentially via wireless signals. The operational data acquisition unit is used to collect operational data from wind, solar, and energy storage equipment and construct an operational behavior set based on the data type. The twin matrix construction unit is used to construct a device response twin matrix based on the operational behavior set, with the matrix row number corresponding to the device number and the column number corresponding to the response time node.

[0012] Furthermore, the collaborative analysis module includes a sample selection unit, a collaborative consistency analysis unit, and a collaborative response feature set generation unit, which are connected in sequence via wireless signals. The sample selection unit is used to select response behavior samples of the device as collaborative analysis samples and collaborative control samples. The collaborative consistency analysis unit is used to analyze the collaborative consistency between two samples and calculate the collaborative probability value. The collaborative response feature set generation unit is used to filter samples whose collaborative probability values ​​meet the threshold to form a collaborative response feature set.

[0013] Furthermore, the periodic matrix update module includes a matrix update unit and a slice set generation unit, which are connected in sequence via wireless signals. The matrix update unit updates the device response twin matrix based on the cooperative response feature set. The slice set generation unit is used to collect the updated matrix at the end of each cycle under a fixed response cycle to form a periodic twin matrix slice set.

[0014] Furthermore, the risk assessment and early warning module includes a risk assessment unit and an early warning output unit, which are connected in sequence via wireless signals. The risk assessment unit assesses the risk value of collaborative interruption between devices corresponding to different types of operational data based on a periodic twin matrix slice set. The early warning output unit is used to compare the risk value with a preset threshold, output the period and type of operational data where collaborative interruption risk exists, and send it to the staff port for early warning.

[0015] A dynamic response early warning method for wind, solar, and energy storage equipment based on digital twin technology, comprising the following steps:

[0016] Step S1: Collect operational data of wind, solar and energy storage equipment, construct an operational behavior set based on data types, and map the operational behavior set to the equipment response twin matrix using digital twin technology;

[0017] Step S2: In the device response twin matrix, select different response behavior clusters as collaborative analysis samples and collaborative control samples respectively, in order to analyze the degree of collaboration and probability of collaboration between samples, and screen the collaborative control samples that meet the conditions to form a collaborative response feature set;

[0018] Step S3: Update the device response twin matrix based on the collaborative response feature set, and collect the updated device response twin matrix under a fixed response cycle to form a periodic twin matrix slice set;

[0019] Step S4: Based on the periodic twin matrix slice set, assess the risk of collaborative interruption between wind, solar and energy storage equipment corresponding to different types of operating data, and output early warning information based on the risk assessment results.

[0020] Furthermore, the specific implementation process of step S1 includes:

[0021] Collect wind, solar, and energy storage operation data mapped by digital twins, where each twin node has the function of mapping one type of wind, solar, and energy storage operation data; based on the number of types of wind, solar, and energy storage operation data, construct an operation behavior set, denoted as WD. i ={wd n |n∈[1,N]}, where WD i wd represents the set of operational behaviors consisting of the i-th type of wind, solar, and energy storage operation data. n Let wd represent the cluster of response behaviors of the nth wind, solar, and energy storage device. n ={t m |m∈[1,M]},t mThe m-th response time node is represented by N, the total number of wind, solar and energy storage devices, and M, the total number of response time nodes. The response time node refers to the time node when the operating status of the wind, solar and energy storage devices reaches the preset response parameters during the response process. The time nodes are uniformly divided and configured within a fixed response period.

[0022] Based on the set of operational behaviors, a device response twin matrix is ​​constructed. The row and column numbers of the device response twin matrix correspond to the index numbers of the wind, solar, and energy storage devices and the response time nodes, respectively. The device response twin matrix generated corresponding to the set of operational behaviors is denoted as WD. ig (N, M), where g is the sequence number of the fixed response period, let the matrix element in the nth row and mth column of the device response twin matrix be 1 or 0. If it is 1, it means t m ∈wd n If it is 0, it means

[0023] Furthermore, the specific implementation process of step S2 includes:

[0024] In the device response twin matrix, select the response behavior cluster wd n and wd v The coherence between the co-analysis sample and the co-control sample is given by the Kth iteration, where v∈[1,N] and v≠n. The coherence is calculated when the operating status of the wind, solar, and energy storage equipment reaches the preset response parameters.

[0025] In the formula, |wd n ∩wd v | Represents the response behavior cluster wd n and wd v The number of nodes with the same response time contained in the intersection set between them, |wd n ∪wd v | Represents the response behavior cluster wd n and wd v The number of nodes with the same or different response times contained in the union set;

[0026] Based on the degree of coherence, the probability of coherence between the coherent analysis samples and the coherent control samples is evaluated.

[0027] In the formula,

[0028] If the collaborative probability value is greater than or equal to the collaborative probability threshold, then the response behavior cluster wd is selected. vLet v = v+1, v+1 ∈ [1, N] and v+1 ≠ n, and construct a screening control set Q from all the selected response behavior clusters to obtain the collaborative response feature set of the Kth iteration.

[0029] If K = N, then the iteration stops.

[0030] Furthermore, the specific implementation process of step S3 includes:

[0031] Based on the construction method of device response twin matrix, the collaborative response feature set RC(n) is replaced with the response behavior cluster wd n To respond to the device's twin matrix WD ig Update (N, M), and denote the updated device response twin matrix as...

[0032] Under a fixed response cycle, the updated device response twin matrix is ​​collected at the end of each fixed response cycle to form a periodic twin matrix slice set of the i-th type of wind, solar and energy storage operation data, denoted as F. i ={WD ig (N, M)|g∈[1, G]}, where G is the index number of the current fixed response period.

[0033] Furthermore, the specific implementation process of step S4 includes:

[0034] Based on a periodic twin matrix slice set, and inputting the index numbers of different types of wind, solar, and energy storage operation data, assess the risk value of coordinated interruption among wind, solar, and energy storage equipment:

[0035]

[0036] In the formula, i and j are the type index numbers of the input wind, solar and energy storage operation data. This represents the updated device response twin matrix. and The number of 1s contained in the result of a Boolean logical AND operation. This represents the updated device response twin matrix. and The number of 1s contained after a Boolean logical OR operation between them;

[0037] A preset collaborative interruption risk threshold is set. If the collaborative interruption risk value RV[(i,j)|g] is greater than or equal to the collaborative interruption risk threshold, it means that there is a collaborative interruption risk between the wind, solar and energy storage equipment in the i-th type of wind, solar and energy storage operation data and the j-th type of wind, solar and energy storage operation data in the g-th fixed period. Otherwise, there is no collaborative interruption risk.

[0038] Output the index number of the fixed-cycle and wind, solar and energy storage operation data types that have a risk of collaborative interruption, and send it to the staff port for early warning.

[0039] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: The wind, solar, and energy storage dynamic response early warning system and method based on digital twin technology provided by this invention maps the operating data of wind, solar, and energy storage equipment using digital twin technology to construct an equipment response twin matrix; analyzes the coordination consistency and probability between equipment to generate a coordinated response feature set; periodically updates the matrix to form a slice set, assesses the risk of coordination interruption between equipment, and provides early warning; this invention considers the coordination relationship between equipment, can identify risks caused by coordination imbalance (such as the energy storage equipment not responding synchronously when photovoltaic power fluctuates), avoids "missed reports," and improves the accuracy and timeliness of wind, solar, and energy storage equipment response early warning by capturing equipment coordination relationships and dynamically updating data. By periodically updating the matrix and slice set, it can dynamically track changes in equipment response, detect trend risks in advance (such as the decrease in coordination efficiency between wind power and energy storage within three consecutive cycles), reduce "lagging early warnings," and thus make this invention applicable to the safety monitoring of wind, solar, and energy storage systems under complex operating conditions. Attached Figure Description

[0040] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0041] Figure 1 This is a schematic diagram illustrating the steps of the dynamic response early warning method for wind, solar and energy storage equipment based on digital twin technology according to the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] In this first embodiment: a dynamic response early warning system for wind, solar and energy storage equipment based on digital twin technology is provided. The system includes: a data acquisition and matrix construction module, a collaborative analysis module, a periodic matrix update module, and a risk assessment and early warning module. Each module is connected in sequence via wireless signal.

[0044] The data acquisition and matrix construction module is used to collect operational data from wind, solar and energy storage equipment, construct operational behavior sets based on data types, and map the operational behavior sets to the equipment response twin matrix through digital twin technology.

[0045] The data acquisition and matrix construction module includes an operational data acquisition unit and a twin matrix construction unit, which are connected in sequence via wireless signals. The operational data acquisition unit is used to collect operational data of wind, solar and energy storage equipment and construct an operational behavior set based on the data type. The twin matrix construction unit is used to construct a twin matrix of equipment response based on the operational behavior set, with the matrix row number corresponding to the equipment number and the column number corresponding to the response time node.

[0046] The collaborative analysis module is used to select different clusters of response behaviors in the device response twin matrix as collaborative analysis samples and collaborative control samples, respectively, to analyze the degree of collaboration and probability of collaboration between samples, and to screen the collaborative control samples that meet the conditions to form a collaborative response feature set.

[0047] The collaborative analysis module includes a sample selection unit, a collaborative consistency analysis unit, and a collaborative response feature set generation unit, which are connected in sequence via wireless signals. The sample selection unit is used to select response behavior samples of the devices as collaborative analysis samples and collaborative control samples. The collaborative consistency analysis unit is used to analyze the collaborative consistency between two samples and calculate the collaborative probability value. The collaborative response feature set generation unit is used to screen samples whose collaborative probability values ​​meet the threshold to form a collaborative response feature set.

[0048] The periodic matrix update module updates the device response twin matrix based on the collaborative response feature set, and collects the updated device response twin matrix under a fixed response cycle to form a periodic twin matrix slice set;

[0049] The periodic matrix update module includes a matrix update unit and a slice set generation unit, which are connected in sequence via wireless signals. The matrix update unit updates the device response twin matrix based on the cooperative response feature set. The slice set generation unit is used to collect the updated matrix at the end of each cycle under a fixed response cycle to form a periodic twin matrix slice set.

[0050] The risk assessment and early warning module, based on a periodic twin matrix slice set, assesses the risk of collaborative interruption among wind, solar and energy storage equipment corresponding to different types of operational data, and outputs early warning information based on the risk assessment results;

[0051] The risk assessment and early warning module includes a risk assessment unit and an early warning output unit, which are connected in sequence via wireless signals. The risk assessment unit assesses the risk value of collaborative interruption between devices corresponding to different types of operational data based on a periodic twin matrix slice set. The early warning output unit compares the risk value with a preset threshold, outputs the period and type of operational data where collaborative interruption risk exists, and sends it to the staff port for early warning.

[0052] Please see Figure 1In this second embodiment: a dynamic response early warning method for wind, solar and energy storage equipment based on digital twin technology is provided to be applicable to the first embodiment above. The method includes the following steps:

[0053] Step S1: Collect operational data of wind, solar and energy storage equipment, construct an operational behavior set based on data types, and map the operational behavior set to the equipment response twin matrix using digital twin technology;

[0054] For example, wind, solar, and energy storage operation data are collected via digital twin mapping. Each twin node has the function of mapping one type of wind, solar, and energy storage operation data. Four types of operation data (power output, energy storage capacity, and grid frequency) are collected through the digital twin nodes, with each type of data corresponding to one twin node. Based on the number of types of wind, solar, and energy storage operation data, an operation behavior set is constructed, denoted as WD. i ={wd n |n∈[1,N]}, where WD i wd represents the set of operational behaviors consisting of the i-th type of wind, solar, and energy storage operation data. n Let wd represent the cluster of response behaviors of the nth wind, solar, and energy storage device. n ={t m |m∈[1,M]},t m The m-th response time node is represented by N, the total number of wind, solar and energy storage devices, and M, the total number of response time nodes. The response time node refers to the moment when the operating status of the wind, solar and energy storage devices reaches the preset response parameters during the response behavior. The time nodes are uniformly divided and configured within a fixed response period. For example, the "power output behavior set" contains the power response data of 10 wind turbines and 20 photovoltaic panels.

[0055] Based on the set of operational behaviors, a twin matrix of device responses is constructed. The row and column numbers of the twin matrix correspond to the index numbers of the wind, solar, and energy storage devices and the response time nodes, respectively. The twin matrix of device responses generated corresponding to the set of operational behaviors is denoted as WD. ig (N, M), where g is the index of a fixed response period. The element in the nth row and mth column of the device response twin matrix is ​​set to either 1 or 0. If it is 1, it indicates that t... m ∈wd n If it is 0, it means For example, the matrix row numbers correspond to 35 devices, and the column numbers correspond to 12 time nodes. If the response parameters of a device at a certain time reach a preset value (such as wind turbine power ≥ 1.8MW), the matrix element is recorded as 1; otherwise, it is recorded as 0.

[0056] Step S2: In the device response twin matrix, select different response behavior clusters as collaborative analysis samples and collaborative control samples respectively, in order to analyze the degree of collaboration and probability of collaboration between samples, and screen the collaborative control samples that meet the conditions to form a collaborative response feature set;

[0057] For example, in the device response twin matrix, the response behavior cluster wd is selected. n and wd v The coherence between the co-analysis sample and the co-control sample is given by the Kth iteration, where v∈[1,N] and v≠n. The coherence is calculated when the operating status of the wind, solar, and energy storage equipment reaches the preset response parameters. For example, taking wind turbine No. 1 as the collaborative analysis sample and the other 34 devices as the control sample, the intersection of the response times of wind turbine No. 1 and energy storage battery No. 1 is 8, the union is 10, and the degree of collaboration is 8 / 10 = 0.8.

[0058] In the formula, |wd n ∩wd v | Represents the response behavior cluster wd n and wd v The number of nodes with the same response time contained in the intersection set between them, |wd n ∪wd v | Represents the response behavior cluster wd n and wd v The number of nodes with the same or different response times contained in the union set;

[0059] Based on the degree of coherence, the probability of coherence between the coherent analysis samples and the coherent control samples is evaluated.

[0060] In the formula,

[0061] If the collaborative probability value is greater than or equal to the collaborative probability threshold, then the response behavior cluster wd is selected. v Let v = v+1, v+1 ∈ [1, N] and v+1 ≠ n, and construct a screening control set Q from all the selected response behavior clusters to obtain the collaborative response feature set of the Kth iteration. For example, based on the mean (β = 0.6) and variance (α = 0.1) of the consistency of 34 control samples, the probability of coordination between wind turbine No. 1 and energy storage battery No. 1 is 0.92 (greater than the threshold of 0.7), and it is included in the feature set;

[0062] If K = N, then the iteration stops.

[0063] Step S3: Update the device response twin matrix based on the collaborative response feature set, and collect the updated device response twin matrix under a fixed response cycle to form a periodic twin matrix slice set;

[0064] For example, based on the construction method of the device response twin matrix, the collaborative response feature set RC(n) is replaced with the response behavior cluster wd n To respond to the device's twin matrix WD ig Update (N, M), and denote the updated device response twin matrix as... For example, the response behavior of wind turbine No. 1 in the original matrix can be replaced with the collaborative response feature set to obtain the updated matrix;

[0065] Under a fixed response cycle, the updated device response twin matrix is ​​collected at the end of each fixed response cycle to form a periodic twin matrix slice set of the i-th type of wind, solar and energy storage operation data, denoted as F. i ={WD ig (N, M)|g∈[1,G]}, where G is the index number of the current fixed response period. For example, the updated matrix is ​​collected once per hour, and 8 slices are obtained after 8 consecutive hours. Each slice reflects the equipment coordination status within the period. The slice set is compared with the actual operation log to make the matrix changes in the slice set (such as the matrix element changes of energy storage charging behavior during the peak photovoltaic power at noon) consistent with the actual situation.

[0066] Step S4: Based on the periodic twin matrix slice set, assess the risk of collaborative interruption between wind, solar and storage equipment corresponding to different types of operating data, and output early warning information based on the risk assessment results;

[0067] For example, based on a periodic twin matrix slice set, inputting the index numbers of different types of wind, solar, and energy storage operation data, the risk value of coordinated interruption among wind, solar, and energy storage equipment can be assessed:

[0068]

[0069] In the formula, i and j are the type index numbers of the input wind, solar and energy storage operation data. This represents the updated device response twin matrix. and The number of 1s contained in the result of a Boolean logical AND operation. This represents the updated device response twin matrix. and The number of 1s contained after a Boolean logical OR operation between them;

[0070] A preset threshold for collaborative interruption risk is set. If the collaborative interruption risk value RV[(i,j)|g] is greater than or equal to the collaborative interruption risk threshold, it indicates that there is a collaborative interruption risk between the wind, solar and energy storage equipment in the i-th type of wind, solar and energy storage operation data and the j-th type of wind, solar and energy storage operation data in the g-th fixed period. Otherwise, there is no collaborative interruption risk. For example, if we select two types of data, "wind power" and "energy storage capacity", and calculate the collaborative interruption risk value in the 5th period, the intersection element of the two matrices is 3, the union element is 15, the historical average is 0.3, and the risk value RV = 1 - 3 / 15 ÷ 0.3 = 0.33. The preset threshold is 0.5. Since 0.3 < 0.5, it is determined that there is no risk. In the 6th period, the intersection element is 1, and the risk value RV = 1 - 1 / 15 ÷ 0.3 = 0.78 > 0.5, so it is determined that there is a risk.

[0071] Output the index number of the fixed-cycle and wind, solar and energy storage operation data types that have a risk of collaborative interruption, and send it to the staff port for early warning.

[0072] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0073] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A dynamic response early warning method for wind, solar, and energy storage equipment based on digital twin technology, characterized in that, The method includes the following steps: Step S1: Based on the number of types of wind, solar, and energy storage operation data, construct an operation behavior set, denoted as... ,in, This represents the set of operational behaviors comprised of the i-th type of wind, solar, and energy storage operational data. Let represent the cluster of response behaviors for the nth wind, solar, and energy storage device, and , Let M represent the m-th response time node, N represent the total number of wind, solar and storage devices, and M represent the total number of response time nodes; through digital twin technology, the set of operating behaviors is mapped to the device response twin matrix, and the row number and column number of the device response twin matrix correspond to the index number of the wind, solar and storage devices and the response time node, respectively. Step S2: Select the response behavior cluster in the device response twin matrix. and These are the co-analysis sample and the co-control sample from the Kth iteration, respectively. and To analyze the degree of coordination and probability of coordination among samples, and to screen out the coordination control samples that meet the conditions, forming a coordination response feature set; Step S3: Update the device response twin matrix based on the collaborative response feature set, and collect the updated device response twin matrix under a fixed response cycle to form a periodic twin matrix slice set; Step S4: Based on the periodic twin matrix slice set, assess the risk of collaborative interruption between wind, solar and energy storage equipment corresponding to different types of operating data, and output early warning information based on the risk assessment results.

2. The dynamic response early warning method for wind, solar, and energy storage equipment based on digital twin technology according to claim 1, characterized in that, The specific implementation process of step S1 includes: Collect wind, solar and energy storage operation data mapped by digital twins, wherein one twin node has the function of mapping one type of wind, solar and energy storage operation data; the response time node refers to the time node when the operation status of the wind, solar and energy storage equipment reaches the preset response parameters during the response behavior of the wind, solar and energy storage equipment, and the time node is uniformly divided and configured within a fixed response period. Based on the set of operational behaviors, a device response twin matrix is ​​constructed. The device response twin matrix generated corresponding to the set of operational behaviors is denoted as... Let g be the sequence number of the fixed response period. Let the element in the nth row and mth column of the device response twin matrix be 1 or 0. If it is 1, it indicates... If it is 0, it means .

3. The dynamic response early warning method for wind, solar, and energy storage equipment based on digital twin technology according to claim 2, characterized in that, The specific implementation process of step S2 includes: When the operating status of wind, solar, and energy storage equipment reaches the preset response parameters, the degree of consistency between the collaborative analysis sample and the collaborative control sample is calculated. ; In the formula, Represents a cluster of response behaviors and The number of nodes with the same response time contained in the intersection set between them. Represents a cluster of response behaviors and The number of nodes with the same or different response times contained in the union set; Based on the degree of coherence, the probability of coherence between the coherent analysis samples and the coherent control samples is evaluated. ; In the formula, , ; If the collaboration probability value is greater than or equal to the collaboration probability threshold, then the response behavior cluster is selected. And let v = v + 1, and The selected clusters of response behaviors are combined to form a screening control set Q, resulting in the collaborative response feature set for the Kth iteration. If K=N, then the iteration stops.

4. The dynamic response early warning method for wind, solar, and energy storage equipment based on digital twin technology according to claim 3, characterized in that, The specific implementation process of step S3 includes: Based on the construction method of device response twin matrix, the collaborative response feature set is... Replace with response behavior cluster To respond to the device twin matrix Perform an update, and record the updated device response twin matrix as follows: ; Under a fixed response cycle, the updated device response twin matrix is ​​collected at the end of each fixed response cycle, forming a periodic twin matrix slice set of the i-th type of wind, solar, and energy storage operation data, denoted as . G is the index number of the current fixed response period.

5. The dynamic response early warning method for wind, solar, and energy storage equipment based on digital twin technology according to claim 4, characterized in that, The specific implementation process of step S4 includes: Based on a periodic twin matrix slice set, and inputting the index numbers of different types of wind, solar, and energy storage operation data, assess the risk value of coordinated interruption among wind, solar, and energy storage equipment: ; In the formula, i and j are the type index numbers of the input wind, solar and energy storage operation data. This represents the updated device response twin matrix. and The number of 1s contained in the result of a Boolean logical AND operation. This represents the updated device response twin matrix. and The number of 1s contained after a Boolean logical OR operation between them; A preset threshold for collaborative interruption risk is set; if the collaborative interruption risk value is... If the threshold for collaborative interruption risk is greater than or equal to the threshold, it means that there is a risk of collaborative interruption between the wind, solar and energy storage equipment in the i-th type of wind, solar and energy storage operation data and the j-th type of wind, solar and energy storage operation data in the g-th fixed period; otherwise, there is no risk of collaborative interruption. Output the index number of the fixed-cycle and wind, solar and energy storage operation data types that have a risk of collaborative interruption, and send it to the staff port for early warning.

6. A dynamic response early warning system for wind, solar, and energy storage equipment based on digital twin technology, executing the dynamic response early warning method for wind, solar, and energy storage equipment as described in any one of claims 1-5, characterized in that, The system includes: a data acquisition and matrix construction module, a collaborative analysis module, a periodic matrix update module, and a risk assessment and early warning module, with each module connected in sequence via wireless signals; The data acquisition and matrix construction module is used to collect the operation data of wind, solar and energy storage equipment, construct an operation behavior set based on the data type, and map the operation behavior set to the equipment response twin matrix through digital twin technology. The collaborative analysis module is used to select different clusters of response behaviors in the device response twin matrix as collaborative analysis samples and collaborative control samples, respectively, to analyze the degree of collaboration and probability of collaboration between samples, and to screen the collaborative control samples that meet the conditions to form a collaborative response feature set. The periodic matrix update module updates the device response twin matrix based on the collaborative response feature set, and collects the updated device response twin matrix under a fixed response cycle to form a periodic twin matrix slice set. The risk assessment and early warning module, based on a periodic twin matrix slice set, assesses the risk of collaborative interruption among wind, solar and energy storage equipment corresponding to different types of operational data, and outputs early warning information based on the risk assessment results.

7. The dynamic response early warning system for wind, solar, and energy storage equipment based on digital twin technology according to claim 6, characterized in that: The data acquisition and matrix construction module includes an operational data acquisition unit and a twin matrix construction unit, which are connected in sequence via wireless signals. The operational data acquisition unit is used to collect operational data from wind, solar and energy storage equipment and construct an operational behavior set based on the data type. The twin matrix construction unit is used to construct a device response twin matrix based on the set of operating behaviors, where the matrix row number corresponds to the device number and the column number corresponds to the response time node.

8. The dynamic response early warning system for wind, solar, and energy storage equipment based on digital twin technology according to claim 6, characterized in that: The collaborative analysis module includes a sample selection unit, a collaborative consistency analysis unit, and a collaborative response feature set generation unit, which are connected in sequence via wireless signals. The sample selection unit is used to select response behavior samples of the devices as collaborative analysis samples and collaborative control samples. The collaborative consistency analysis unit is used to analyze the collaborative consistency between two samples and calculate the collaborative probability value. The collaborative response feature set generation unit is used to filter samples whose collaborative probability values ​​meet the threshold to form a collaborative response feature set.

9. The dynamic response early warning system for wind, solar, and energy storage equipment based on digital twin technology according to claim 6, characterized in that: The periodic matrix update module includes a matrix update unit and a slice set generation unit, which are connected in sequence via wireless signals. The matrix update unit updates the device response twin matrix based on the cooperative response feature set. The slice set generation unit is used to collect the updated matrix at the end of each cycle under a fixed response cycle to form a periodic twin matrix slice set.

10. The dynamic response early warning system for wind, solar, and energy storage equipment based on digital twin technology according to claim 6, characterized in that: The risk assessment and early warning module includes a risk assessment unit and an early warning output unit, which are connected in sequence via wireless signals. The risk assessment unit assesses the risk value of collaborative interruption between devices corresponding to different types of operational data based on a periodic twin matrix slice set. The early warning output unit is used to compare the risk value with a preset threshold, output the cycle and type of operational data where there is a risk of collaborative interruption, and send the warning to the staff port.

Citation Information

Patent Citations

  • Hydraulic engineering operation supervision system and method based on digital twinborn technology

    CN119106572A

  • SMT production line operation and maintenance method and system based on digital twinning technology

    CN119536181A