A data interaction method and storage device for power Internet of Things terminals

Abstract

The present invention provides a power Internet of Things terminal data interaction method and storage device, which belongs to the field of Internet of Things technology, and specifically includes: determining the credibility based on the change amount, the number of occurrences, and the number of times the power equipment has been in an abnormal state in the past year of abnormal collected data within a first time threshold; when the credibility is greater than the first threshold, based on the suspected abnormalities in the collected data of other Internet of Things terminals of the power equipment as other abnormal collected data, and based on the number of other abnormal collected data, the ratio of other abnormal data to other collected data, and the sum of the weights of other abnormal data, an evaluation model based on a machine learning algorithm is used to obtain the evaluated credibility of the abnormal collected data; when the credibility is greater than a second threshold, a credibility evaluation value of the abnormal collected data is obtained based on the evaluated credibility and the credibility, and based on the credibility evaluation value, it is determined whether the abnormal collected data is in an abnormal state, thereby improving the accuracy of data interaction.

Description

Technical Field

[0001] The present invention belongs to the technical field of Internet of Things, and in particular relates to a data interaction method and storage device for a power Internet of Things terminal. Background Art

[0002] To achieve data interaction with IoT terminals, the invention patent publication number CN115086343A, "A Method and System for IoT Data Interaction Based on Artificial Intelligence," obtains the working status of IoT devices, divides the data collection tasks according to the working status, sends the divided data collection tasks to the corresponding IoT devices, receives the collected data fed back by each IoT device in real time, generates evaluation information for each IoT device based on the collected data, and sends the evaluation information to each IoT device. However, there are the following technical problems:

[0003] 1. The dynamic evaluation of the credibility of the data of IoT devices based on the evaluation information of IoT devices has been neglected. For IoT devices that reflect the operating status of power equipment, especially IoT devices that reflect the fault status of power equipment, if the credibility of the data collected cannot be evaluated, it may lead to the inability to accurately and reliably know the fault status of the power equipment.

[0004] 2. The credibility of the data collected by the IoT device is not evaluated in combination with other data of the power equipment monitored by the IoT device. For the same power equipment, such as a transformer, if the temperature data of the transformer monitored by the IoT device changes suddenly, while the current, voltage, power factor, operating status of the cooling fan of the transformer monitored by other IoT devices do not change suddenly, it can be concluded that the credibility of the temperature data monitored by the IoT device is significantly lower. Therefore, if the operating status cannot be evaluated in combination with other data monitored by the IoT device, the fault status of the power equipment cannot be accurately and reliably known.

[0005] In response to the above technical problems, the present invention provides a data interaction method and storage device for power Internet of Things terminals. Summary of the Invention

[0006] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0007] According to one aspect of the present invention, a method for interacting with terminal data of an electric power Internet of Things is provided.

[0008] A method for interacting with power Internet of Things terminal data, characterized by comprising:

[0009] S11 acquires the collected data of the Internet of Things terminal of the power equipment in real time, and when the collected data is in a suspected abnormal state, the collected data is regarded as abnormal collected data, and then enters step S12;

[0010] S12 determines the credibility of the abnormal collected data based on the amount of change of the abnormal collected data within the first time threshold, the number of occurrences of the abnormal collected data within the first time threshold, and the number of times the abnormal collected data of the power equipment is in an abnormal state in the past year, and determines whether the credibility of the abnormal collected data is greater than the first threshold. If so, proceed to step S13; if not, return to step S11;

[0011] S13 is based on the collected data of other IoT terminals of the power equipment, and the collected data of the other IoT terminals with suspected abnormalities are regarded as other abnormal collected data, and based on the correlation between the other abnormal data and the abnormal collected data, the weight of the other abnormal data is determined, and based on the number of the other abnormal collected data, the ratio of the other abnormal data to the other collected data, and the sum of the weights of the other abnormal data, an evaluation model based on a machine learning algorithm is used to obtain the evaluation credibility of the abnormal collected data, and determine whether the evaluation credibility of the abnormal collected data is greater than a second threshold. If so, it is determined that the abnormal collected data is abnormal; if not, the process proceeds to step S14;

[0012] S14 constructs a credibility evaluation value of the abnormal collected data based on the evaluation credibility and credibility of the abnormal collected data, and determines whether the abnormal collected data is in an abnormal state based on the credibility evaluation value of the abnormal collected data.

[0013] By determining the credibility of the abnormal collected data based on the amount of change in the abnormal collected data within the first time threshold, the number of occurrences of the abnormal collected data within the first time threshold, and the number of times the abnormal collected data of the power equipment has been in an abnormal state in the past year, the credibility of the abnormal collected data can be evaluated from multiple perspectives, and the accuracy and comprehensiveness of the judgment can be further improved, thereby achieving accurate judgment of the abnormal state from the perspective of data changes.

[0014] By further combining the collected data of other IoT terminals of power equipment, the credibility of the evaluation of abnormal collected data can be determined, thereby further realizing the judgment of the credibility of abnormal collected data from the perspective of associated data, further preventing the technical problem of misjudgment caused by data anomalies, and improving the reliability and accuracy of judgment.

[0015] The construction of the credibility evaluation value is achieved by comprehensively considering the evaluation credibility and trustworthiness, thereby achieving a comprehensive judgment from itself and related data, ensuring the reliability and accuracy of the credibility evaluation value, and also laying the foundation for accurate judgment of the status of abnormal collection data.

[0016] A further technical solution is to determine that the collected data is in a suspected abnormal state when the variation of the collected data within the second time threshold is greater than the first variation threshold or when the operating state of the power equipment reflected by the collected data is abnormal.

[0017] A further technical solution is that the first time threshold is determined according to the type of the abnormal collected data and the importance of the power equipment, wherein the more important the type of the abnormal collected data and the more important the power equipment are, the smaller the first time threshold is.

[0018] A further technical solution is that the specific steps of evaluating the credibility of the abnormal collected data are:

[0019] S21 obtains the number of occurrences of the abnormal collected data within the first time threshold, and determines whether the number of occurrences of the abnormal collected data within the first time threshold is greater than the first number threshold. If so, determines that the credibility of the abnormal collected data is 1; if not, proceeds to step S22;

[0020] S22 determines whether the number of occurrences of the abnormal collected data within the first time threshold is greater than the second number threshold and the change of the abnormal collected data within the first time threshold is less than the second change threshold, wherein the second number threshold is less than the first number threshold. If so, proceed to step S23; if not, proceed to step S24;

[0021] S23 is based on whether the number of times the collected data of the same type of power equipment in the past year has abnormal conditions is less than the third number threshold. If so, the credibility of the abnormal collected data is determined to be 1; if not, the process proceeds to step S24;

[0022] S24 determines the credibility of the abnormal collected data using an evaluation model based on a machine learning algorithm based on the change in the abnormal collected data within the first time threshold, the number of occurrences of the abnormal collected data within the first time threshold, and the number of times the collected data of the power equipment is in an abnormal state in the past year.

[0023] A further technical solution is that the power equipment of the same type is determined according to the voltage level, manufacturer, and application site of the power equipment.

[0024] A further technical solution is that the correlation between the other abnormal data and the abnormal collected data is determined by using a principal component analysis-based method to determine the correlation coefficient between the other abnormal data and the abnormal collected data, and the correlation coefficient is normalized to obtain the weight of the other abnormal data.

[0025] A further technical solution is that the specific steps of constructing the evaluation credibility of the abnormal collected data are:

[0026] S31 determines whether the number of the other abnormal data is greater than the first number threshold, if so, proceeds to step S34, if not, proceeds to step S32;

[0027] S32 determines whether the ratio of the other abnormal data to the other collected data is greater than a first ratio threshold, if so, proceeds to step S34, if not, proceeds to step S33;

[0028] S33 determines whether the sum of the weights of the other abnormal data is greater than a third threshold. If so, proceed to step S34. If not, take the ratio of the other abnormal data to the other collected data as the evaluation credibility of the abnormal collected data.

[0029] S34 obtains the evaluation credibility of the abnormal collected data by using an evaluation model based on a machine learning algorithm based on the number of the other abnormal collected data, the ratio of the other abnormal data to the other collected data, and the sum of the weights of the other abnormal data.

[0030] A further technical solution is that the credibility evaluation value is determined based on the evaluation credibility and credibility of the abnormal collected data using a mathematical model based on the hierarchical analysis method.

[0031] A further technical solution is that when and only when the trustworthy evaluation value is greater than a set threshold, it is determined that the abnormal data is in an abnormal state, and when the abnormal data is in an abnormal state, data interaction is performed with the Internet of Things terminal based on the server, and the collected data of the Internet of Things terminal is obtained again based on at least a third time threshold.

[0032] On the other hand, a computer device is provided in an embodiment of the present application, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned method for interacting with data of an electric power Internet of Things terminal.

[0033] On the other hand, the present invention provides a computer storage device having a computer program stored thereon. When the computer program is executed in a computer, the computer is caused to execute the above-mentioned method for interacting with terminal data of an electric power Internet of Things.

[0034] Other features and advantages will be described in the following description, and in part will become apparent from the description, or understood by practicing the invention. The objects and other advantages of the invention are realized and obtained by the structures particularly pointed out in the description.

[0035] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail as follows. DETAILED DESCRIPTION

[0036] Example embodiments will now be described more fully. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concept of the example embodiments to those skilled in the art.

[0037] The terms "a", "an", "the", and "said" are used to indicate the presence of one or more elements / components / etc.; the terms "including" and "having" are used to express an open-ended inclusive meaning and mean that additional elements / components / etc. may be present in addition to the listed elements / components / etc.

[0038] Example 1

[0039] To solve the above problems, according to one aspect of the present invention, a method for interacting with power Internet of Things terminal data is provided.

[0040] A method for interacting with power Internet of Things terminal data, characterized by comprising:

[0041] S11 acquires the collected data of the Internet of Things terminal of the power equipment in real time, and when the collected data is in a suspected abnormal state, the collected data is regarded as abnormal collected data, and then enters step S12;

[0042] Specifically, when the variation of the collected data within the second time threshold is greater than the first variation threshold or when the operating state of the power equipment reflected by the collected data is abnormal, it is determined that the collected data is in a suspected abnormal state.

[0043] Specifically, if the rated value of the operating temperature of the transformer is 70 degrees Celsius, when the collected data is 150 degrees Celsius, it is determined that the collected data is in a suspected abnormal state.

[0044] S12 determines the credibility of the abnormal collected data based on the amount of change of the abnormal collected data within the first time threshold, the number of occurrences of the abnormal collected data within the first time threshold, and the number of times the abnormal collected data of the power equipment is in an abnormal state in the past year, and determines whether the credibility of the abnormal collected data is greater than the first threshold. If so, proceed to step S13; if not, return to step S11;

[0045] Specifically, the first time threshold is determined according to the type of the abnormal collected data and the importance of the power equipment. The more important the type of the abnormal collected data and the more important the power equipment are, the smaller the first time threshold is.

[0046] Specifically, the specific steps of evaluating the credibility of the abnormal collected data are:

[0047] S21 obtains the number of occurrences of the abnormal collected data within the first time threshold, and determines whether the number of occurrences of the abnormal collected data within the first time threshold is greater than the first number threshold. If so, determines that the credibility of the abnormal collected data is 1; if not, proceeds to step S22;

[0048] In another possible embodiment, when the value is greater than the first number threshold, the process directly proceeds to step S24 to evaluate the credibility of the abnormal collected data in combination with multiple factors.

[0049] S22 determines whether the number of occurrences of the abnormal collected data within the first time threshold is greater than the second number threshold and the change of the abnormal collected data within the first time threshold is less than the second change threshold, wherein the second number threshold is less than the first number threshold. If so, proceed to step S23; if not, proceed to step S24;

[0050] S23 is based on whether the number of times the collected data of the same type of power equipment in the past year has abnormal conditions is less than the third number threshold. If so, the credibility of the abnormal collected data is determined to be 1; if not, the process proceeds to step S24;

[0051] S24 determines the credibility of the abnormal collected data using an evaluation model based on a machine learning algorithm based on the change in the abnormal collected data within the first time threshold, the number of occurrences of the abnormal collected data within the first time threshold, and the number of times the collected data of the power equipment is in an abnormal state in the past year.

[0052] For example, the machine learning-based evaluation model employs a GSO-BPNN algorithm-based evaluation model. The improved firefly algorithm optimizes the BP neural network by designing the BP neural network structure based on the required output and output parameters, thereby determining the encoding length of the individual firefly algorithms. Each individual firefly contains the weights and thresholds in the BP neural network. The improved firefly algorithm then updates the position, decision radius, and luciferin of the firefly population. Simultaneously, the fitness values ​​of the individual fireflies are calculated based on the proposed fitness function, thereby finding the individual with the optimal objective function value. This results in better initial weights and thresholds for the BP neural network, which are then further optimized using the BP neural network to obtain the optimal BP neural network prediction value.

[0053] In another possible embodiment, if the set of individual firefly neighborhoods is an empty set, then the position update formula is:

[0054] x i (t+1)=x best (t+1)

[0055] Where xbest(t+1) is the value obtained by randomly searching M times in the neighborhood when the firefly territory space is empty, and the evaluation formula of M is as follows:

[0056]

[0057] Where round() is a rounding function, σ is a constant, tmax is the maximum number of iterations, and t is the current iteration number. Because the Firefly Algorithm approaches its peak value as the number of iterations increases, M is designed to decrease exponentially with the number of iterations. When the number of iterations reaches or approaches the maximum number of iterations set by the algorithm, the result of the round() function is close to 1, and the result of M is close to 2, ensuring that the Firefly can also choose a relatively optimal position in the later iterations.

[0058] Specifically, the power equipment of the same type is determined according to the voltage level, manufacturer, and application location of the power equipment.

[0059] S13 is based on the collected data of other IoT terminals of the power equipment, and the collected data of the other IoT terminals with suspected abnormalities are regarded as other abnormal collected data, and based on the correlation between the other abnormal data and the abnormal collected data, the weight of the other abnormal data is determined, and based on the number of the other abnormal collected data, the ratio of the other abnormal data to the other collected data, and the sum of the weights of the other abnormal data, an evaluation model based on a machine learning algorithm is used to obtain the evaluation credibility of the abnormal collected data, and determine whether the evaluation credibility of the abnormal collected data is greater than a second threshold. If so, it is determined that the abnormal collected data is abnormal; if not, the process proceeds to step S14;

[0060] Specifically, the correlation between the other abnormal data and the abnormal collected data is determined by using a principal component analysis-based method to determine a correlation coefficient between the other abnormal data and the abnormal collected data, and normalizing the correlation coefficient to obtain a weight of the other abnormal data.

[0061] Specifically, the specific steps for constructing the evaluation credibility of the abnormal collected data are:

[0062] S31 determines whether the number of the other abnormal data is greater than the first number threshold, if so, proceeds to step S34, if not, proceeds to step S32;

[0063] S32 determines whether the ratio of the other abnormal data to the other collected data is greater than a first ratio threshold, if so, proceeds to step S34, if not, proceeds to step S33;

[0064] S33 determines whether the sum of the weights of the other abnormal data is greater than a third threshold. If so, proceed to step S34. If not, take the ratio of the other abnormal data to the other collected data as the evaluation credibility of the abnormal collected data.

[0065] S34 obtains the evaluation credibility of the abnormal collected data by using an evaluation model based on a machine learning algorithm based on the number of the other abnormal collected data, the ratio of the other abnormal data to the other collected data, and the sum of the weights of the other abnormal data.

[0066] S14 constructs a credibility evaluation value of the abnormal collected data based on the evaluation credibility and credibility of the abnormal collected data, and determines whether the abnormal collected data is in an abnormal state based on the credibility evaluation value of the abnormal collected data.

[0067] Specifically, the credibility evaluation value is determined based on the evaluation credibility and credibility of the abnormal collected data, using a mathematical model based on the hierarchical analysis method.

[0068] Specifically, when and only when the trustworthy evaluation value is greater than the set threshold, it is determined that the abnormal data is in an abnormal state, and when the abnormal data is in an abnormal state, data interaction is performed with the Internet of Things terminal based on the server, and the collected data of the Internet of Things terminal is obtained again based on at least a third time threshold.

[0069] By determining the credibility of the abnormal collected data based on the amount of change in the abnormal collected data within the first time threshold, the number of occurrences of the abnormal collected data within the first time threshold, and the number of times the abnormal collected data of the power equipment has been in an abnormal state in the past year, the credibility of the abnormal collected data can be evaluated from multiple perspectives, and the accuracy and comprehensiveness of the judgment can be further improved, thereby achieving accurate judgment of the abnormal state from the perspective of data changes.

[0070] By further combining the collected data of other IoT terminals of power equipment, the credibility of the evaluation of abnormal collected data can be determined, thereby further realizing the judgment of the credibility of abnormal collected data from the perspective of associated data, further preventing the technical problem of misjudgment caused by data anomalies, and improving the reliability and accuracy of judgment.

[0071] The construction of the credibility evaluation value is achieved by comprehensively considering the evaluation credibility and trustworthiness, thereby achieving a comprehensive judgment from itself and related data, ensuring the reliability and accuracy of the credibility evaluation value, and also laying the foundation for accurate judgment of the status of abnormal collection data.

[0072] Example 2

[0073] A computer device is provided in an embodiment of the present application, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, the above-mentioned method for interacting with power Internet of Things terminal data is executed.

[0074] Example 3

[0075] The present invention provides a computer storage device having a computer program stored thereon. When the computer program is executed in a computer, the computer is caused to execute the above-mentioned method for interacting with terminal data of an electric power Internet of Things.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative.

[0077] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0078] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage device. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage device and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage device includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0079] With the above-described preferred embodiments of the present invention as a guide, and with reference to the above description, relevant personnel are fully capable of making various changes and modifications without departing from the technical scope of this invention. The technical scope of this invention is not limited to the contents of the specification and must be determined according to the scope of the claims.

Claims

1. A method for interacting with power Internet of Things terminal data, characterized in that: Specifically include: S11 acquires data collected from the IoT terminal of the power equipment in real time, and when the collected data is in a suspected abnormal state, the collected data is treated as abnormal collected data, then proceeds to step S12; S12 determines the credibility of the abnormal collected data based on the amount of change of the abnormal collected data within the first time threshold, the number of occurrences of the abnormal collected data within the first time threshold, and the number of times the abnormal collected data of the power equipment is in an abnormal state in the past year, and determines whether the credibility of the abnormal collected data is greater than the first threshold. If so, proceed to step S13; if not, return to step S11; S13 is based on the collected data of other IoT terminals of the power equipment, and the collected data of the other IoT terminals with suspected abnormalities are regarded as other abnormal collected data, and based on the correlation between the other abnormal data and the abnormal collected data, the weight of the other abnormal data is determined, and based on the number of the other abnormal collected data, the ratio of the other abnormal data to the other collected data, and the sum of the weights of the other abnormal data, an evaluation model based on a machine learning algorithm is used to obtain the evaluation credibility of the abnormal collected data, and determine whether the evaluation credibility of the abnormal collected data is greater than a second threshold. If so, it is determined that the abnormal collected data is abnormal; if not, the process proceeds to step S14; S14 constructs a credibility evaluation value of the abnormal collected data based on the evaluation credibility and credibility of the abnormal collected data, and determines whether the abnormal collected data is in an abnormal state based on the credibility evaluation value of the abnormal collected data.

2. The electric power Internet of Things terminal data interaction method according to claim 1, characterized in that: When the variation of the collected data within the second time threshold is greater than the first variation threshold or when the operating state of the power equipment reflected by the collected data is abnormal, it is determined that the collected data is in a suspected abnormal state.

3. The electric power Internet of Things terminal data interaction method according to claim 1, characterized in that: The first time threshold is determined according to the type of the abnormal collected data and the importance of the power equipment. The more important the type of the abnormal collected data and the more important the power equipment are, the smaller the first time threshold is.

4. The electric power Internet of Things terminal data interaction method according to claim 1, characterized in that: The specific steps of evaluating the credibility of the abnormal collected data are: S21 obtains the number of occurrences of the abnormal collected data within the first time threshold, and determines whether the number of occurrences of the abnormal collected data within the first time threshold is greater than the first number threshold. If so, determines that the credibility of the abnormal collected data is 1; if not, proceeds to step S22; S22 determines whether the number of occurrences of the abnormal collected data within the first time threshold is greater than the second number threshold and the change of the abnormal collected data within the first time threshold is less than the second change threshold, wherein the second number threshold is less than the first number threshold. If so, proceed to step S23; if not, proceed to step S24; S23 is based on whether the number of times the collected data of the same type of power equipment in the past year has abnormal conditions is less than the third number threshold. If so, the credibility of the abnormal collected data is determined to be 1; if not, the process proceeds to step S24; S24 determines the credibility of the abnormal collected data using an evaluation model based on a machine learning algorithm based on the change in the abnormal collected data within the first time threshold, the number of occurrences of the abnormal collected data within the first time threshold, and the number of times the collected data of the power equipment is in an abnormal state in the past year.

5. The electric power Internet of Things terminal data interaction method according to claim 4, characterized in that: The same type of electrical equipment is determined based on the voltage level, manufacturer, and application location of the electrical equipment.

6. The electric power Internet of Things terminal data interaction method according to claim 1, characterized in that: The correlation between the other abnormal data and the abnormal collected data is determined by using a principal component analysis-based method to determine the correlation coefficient between the other abnormal data and the abnormal collected data, and normalizing the correlation coefficient to obtain the weight of the other abnormal data.

7. The electric power Internet of Things terminal data interaction method according to claim 1, characterized in that: The specific steps of constructing the evaluation credibility of the abnormal collected data are: S31 determines whether the number of the other abnormal data is greater than the first number threshold, if so, proceeds to step S34, if not, proceeds to step S32; S32 determines whether the ratio of the other abnormal data to the other collected data is greater than the first ratio threshold, and if so, proceeds to step S34, if not, proceeds to step S33; S33 determines whether the sum of the weights of the other abnormal data is greater than a third threshold value. If so, proceed to step S34. If not, take the ratio of the other abnormal data to the other collected data as the evaluation credibility of the abnormal collected data. S34 obtains the evaluation credibility of the abnormal collected data by using an evaluation model based on a machine learning algorithm based on the number of the other abnormal collected data, the ratio of the other abnormal data to the other collected data, and the sum of the weights of the other abnormal data.

8. The method for interacting with power Internet of Things terminals according to claim 1, wherein: The credibility evaluation value is determined based on the evaluation credibility and credibility of the abnormal collected data, using a mathematical model based on the hierarchical analysis method.

9. The electric power Internet of Things terminal data interaction method according to claim 1, characterized in that: If and only if the credibility evaluation value is greater than a set threshold, it is determined that the abnormal data is in an abnormal state, and when the abnormal data is in an abnormal state, data interaction is performed with the Internet of Things terminal based on the server, and the collected data of the Internet of Things terminal is obtained again based on at least a third time threshold.

10. A computer storage device having a computer program stored thereon, which, when executed in a computer, causes the computer to execute the power Internet of Things terminal data interaction method according to any one of claims 1 to 9.

Images