Abnormal Power Grid Data Alarm Method, Device, Equipment and Computer Readable Medium

Abstract

Embodiments of the present disclosure disclose an abnormal power grid data warning method, apparatus, device, and computer-readable medium. A specific implementation of the method includes: obtaining a power data set sequence; performing data preprocessing on each power data in the power data set sequence to generate a preprocessed power data set sequence; extracting power attribute information corresponding to each preprocessed power data to obtain a power attribute information set sequence; for each power attribute information set, performing a first generation step: performing clustering processing to generate a power attribute information cluster set; inputting each power attribute information into a power usage classification model to generate initial power usage information; generating predicted power usage information corresponding to each power attribute information; performing a power usage verification on a target power area to generate power usage verification information; and performing data warning processing. This implementation can accurately and efficiently verify the power usage and perform data warning in the target power area.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technologies, and particularly to methods, devices, equipment, and computer-readable media for warning of abnormal power grid data. Background Art

[0002] Currently, in the power field, it is of great significance to determine the uses of electricity (such as commercial electricity and residential electricity) to achieve the rational distribution of electricity. For the verification of electricity uses within a region, the commonly used method is to manually verify the electricity consumption data within the region by relevant experts to determine whether the electricity uses within the region are abnormal.

[0003] However, when using the above method to verify electricity uses, the following technical problems often exist:

[0004] The workload of manually verifying electricity uses is large, and the determination of abnormalities is relatively cumbersome, resulting in low verification efficiency. There may be a large number of power equipment with abnormal uses, leading to power usage risks.

[0005] The above information disclosed in this background art section is only used to enhance the understanding of the background of the inventive concept, and thus, it may include information that does not constitute the prior art known to those of ordinary skill in the art in this country. Summary of the Invention

[0006] The content part of the present disclosure is used to briefly introduce the concepts, which will be described in detail in the subsequent detailed implementation part. The content part of the present disclosure is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] Some embodiments of the present disclosure propose methods, devices, equipment, and media for warning of abnormal power grid data to solve one or more of the technical problems mentioned in the above background art section.

[0008] In a first aspect, some embodiments of the present disclosure provide an abnormal power grid data warning method, including: obtaining a sequence of power data sets corresponding to a target power region, where there is a corresponding power acquisition time for each power data set in the sequence of power data sets, and the power data is the power detection data of each power device in the power sub-region at the corresponding power acquisition time, and the target power region includes: each power sub-region; performing data preprocessing on each power data in the sequence of power data sets to generate a sequence of preprocessed power data sets; extracting the power attribute information corresponding to each preprocessed power data in the sequence of preprocessed power data sets to obtain a sequence of power attribute information sets; for each power attribute information set, performing the following first generation step: performing clustering processing on the power attribute information set to generate a set of power attribute information clusters; inputting each power attribute information in the power attribute information set into a power usage classification model to generate initial power usage information; generating predicted power usage information corresponding to each power attribute information in the power attribute information set according to the obtained initial power usage information set and the set of power attribute information clusters; performing a power usage verification on the target power region according to the obtained sequence of predicted power usage information sets to generate power usage verification information; and performing a data warning process on the power usage verification information.

[0009] In a second aspect, some embodiments of the present disclosure provide an abnormal power grid data warning device, including: an obtaining unit configured to obtain a sequence of power data sets corresponding to a target power region, where there is a corresponding power acquisition time for each power data set in the sequence of power data sets, and the power data is the power detection data of each power device in the power sub-region at the corresponding power acquisition time, and the target power region includes: each power sub-region; a preprocessing unit configured to perform data preprocessing on each power data in the sequence of power data sets to generate a sequence of preprocessed power data sets; an extraction unit configured to extract the power attribute information corresponding to each preprocessed power data in the sequence of preprocessed power data sets to obtain a sequence of power attribute information sets; an execution unit configured to, for each power attribute information set, perform the following first generation step: performing clustering processing on the power attribute information set to generate a set of power attribute information clusters; inputting each power attribute information in the power attribute information set into a power usage classification model to generate initial power usage information; generating predicted power usage information corresponding to each power attribute information in the power attribute information set according to the obtained initial power usage information set and the set of power attribute information clusters; a verification unit configured to perform a power usage verification on the target power region according to the obtained sequence of predicted power usage information sets to generate power usage verification information; and an alarm unit configured to perform a data warning process on the power usage verification information.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device storing one or more programs thereon, and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method described in any implementation manner of the first aspect.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium storing a computer program thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the first aspect is implemented.

[0012] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the abnormal power grid data warning method of some embodiments of the present disclosure, the electricity usage in the target power area can be verified accurately and efficiently. Specifically, the reason for the inefficient verification of relevant electricity usage is that the workload of manually verifying electricity usage is large and the determination of abnormalities is relatively cumbersome, resulting in low verification efficiency. Based on this, the abnormal power grid data warning method of some embodiments of the present disclosure first obtains a sequence of power data sets corresponding to the target power area. Among them, there is a corresponding power acquisition time for the power data sets in the above-mentioned sequence of power data sets. The power data is the power detection data of each power device in the corresponding power sub-area at the corresponding power acquisition time. The above-mentioned target power area includes: each power sub-area. Here, by obtaining the power data at each power acquisition time in the target power area, sufficient data support can be provided for the subsequent verification of the electricity usage in the target power area. Then, data preprocessing is performed on each power data in the above-mentioned sequence of power data sets to generate a sequence of preprocessed power data sets, so as to remove the data noise existing in each power data and ensure the data accuracy of subsequent electricity usage. Next, the power attribute information corresponding to each preprocessed power data in the above-mentioned sequence of preprocessed power data sets is extracted to obtain a sequence of power attribute information sets, so as to extract the feature information under each power attribute feature, which is convenient for accurately determining the electricity usage information from the attribute features in the subsequent process. Then, for each power attribute information set, the following first generation steps are performed: The first step is to perform clustering processing on the above-mentioned power attribute information set to generate a set of power attribute information clusters. Here, through clustering processing, the power attribute information belonging to the same type of electricity usage can be accurately classified into one category, which is convenient for determining the corresponding electricity usage in the subsequent process. The second step is to input each power attribute information in the above-mentioned power attribute information set into the electricity usage classification model to accurately and efficiently generate the initial electricity usage information. The third step is to accurately generate the predicted electricity usage information corresponding to each power attribute information in the above-mentioned power attribute information set according to the obtained initial electricity usage information set and the above-mentioned set of power attribute information clusters. Here, through the set of power attribute information clusters after clustering processing and the initial electricity usage information output by the electricity usage classification model, the accuracy of the predicted electricity usage information can be ensured under the mutual verification of the two. Finally, according to the obtained sequence of predicted electricity usage information sets, the electricity usage in the above-mentioned target power area can be quickly verified to generate electricity usage verification information for data warning processing. In summary, through clustering processing and the electricity usage classification model, the electricity usage in the target power area can be accurately and efficiently verified under mutual verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the elements and elements are not necessarily drawn to scale.

[0014] Figure 1 is a flowchart of some embodiments of an abnormal power grid data warning method according to the present disclosure;

[0015] Figure 2 is a schematic structural diagram of some embodiments of an abnormal power grid data warning device according to the present disclosure;

[0016] Figure 3 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. Specific Embodiments

[0017] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0018] In addition, it should be noted that for the sake of convenience of description, only the parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

[0019] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules, or units, and are not used to limit the order or interdependence relationship of the functions performed by these devices, modules, or units.

[0020] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly stated in the context, it should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] The present disclosure will be described in detail below with reference to the drawings and in combination with the embodiments.

[0023] Reference Figure 1, which shows the process 100 of some embodiments of the abnormal power grid data warning method according to the present disclosure. The abnormal power grid data warning method includes the following steps:

[0024] Step 101, obtaining a sequence of power data sets corresponding to a target power area.

[0025] In some embodiments, the execution subject (e.g., an electronic device) of the above abnormal power grid data warning method can obtain a sequence of power data sets corresponding to a target power area through a wired connection method or a wireless connection method. Among them, the target power area can be an area to be audited for electricity usage purposes. For example, the target power area can be Tianjin. The electricity usage purpose audit can be to audit the purpose of electricity usage. For example, the purpose of electricity usage can be one of the following: commercial electricity usage, residential electricity usage. There is a corresponding power acquisition time for each power data set in the above sequence of power data sets. There is a one-to-one correspondence between the power data sets in the sequence of power data sets and the power acquisition times in the sequence of power acquisition times. The power acquisition times in the sequence of power acquisition times are sorted in ascending order from early to late. In practice, the duration corresponding to the power acquisition time can be one day. For example, the sequence of power data sets includes: power data set A, power data set B, and power data set C. The power acquisition time corresponding to power data set A can be January 1st. The power acquisition time corresponding to power data set B can be January 2nd. The power acquisition time corresponding to power data set C can be January 3rd. The power data is the power detection data of each power device in the power sub-area at the corresponding power acquisition time. The power detection data can include a set of power data attribute information corresponding to the power data attribute feature set. In practice, the power data attribute feature set can include: voltage feature, electricity consumption feature, transformer-related feature, line-related feature. The above target power area includes: each power sub-area. For example, for the target power area of Tianjin, the corresponding power sub-areas can include: Heping District, Hedong District, Hexi District, Nankai District, Hebei District, Hongqiao District, Dongli District, Xiqing District, Jinnan District, Beichen District, Wuqing District, Baodi District, Binhai New Area, Ninghe District, Jinghai District, and Jizhou District.

[0026] Step 102, performing data preprocessing on each power data in the above sequence of power data sets to generate a sequence of preprocessed power data sets.

[0027] In some embodiments, the execution subject can perform data preprocessing on each power data in the above sequence of power data sets to generate a sequence of preprocessed power data sets. Among them, the data preprocessing can include but is not limited to at least one of the following: error data deletion, data completion, data format unification, data fine-tuning.

[0028] Step 103: Extract the power attribute information corresponding to each preprocessed power data in the above preprocessed power data set sequence to obtain a sequence of power attribute information sets.

[0029] In some embodiments, the above execution subject may extract the power attribute information corresponding to each preprocessed power data in the above preprocessed power data set sequence to obtain a sequence of power attribute information sets. Among them, the power attribute information may be a set of power data attribute feature information corresponding to the power data attribute feature set.

[0030] As an example, the above execution subject may extract, from each preprocessed power data in the above preprocessed power data set sequence, the set of power data attribute feature information corresponding to the power data attribute feature set as the power attribute information to obtain a sequence of power attribute information sets.

[0031] Step 104: For each power attribute information set, perform the following first generation step:

[0032] Step 1041: Perform clustering processing on the above power attribute information set to generate a set of power attribute information clusters.

[0033] In some embodiments, the above execution subject may perform clustering processing on the above power attribute information set to generate a set of power attribute information clusters. Among them, the power data attribute feature information sets corresponding to the power attribute information in each power attribute information cluster are highly similar.

[0034] As an example, the above execution subject may use the K-means algorithm to perform clustering processing on the above power attribute information set to generate a set of power attribute information clusters.

[0035] In some optional implementation manners of some embodiments, the above performing clustering processing on the above power attribute information set to generate a set of power attribute information clusters may include the following steps:

[0036] The first step: Obtain the power data attribute feature set.

[0037] The second step: Determine the feature importance degree of each power data attribute feature in the above power data attribute feature set with respect to the power usage to generate feature importance degree information and obtain a set of feature importance degree information.

[0038] Step 3: Determine the importance degree of the feature set corresponding to the predetermined power data attribute feature subset in the above power data attribute feature set to generate feature set importance degree information, and obtain at least one piece of feature set importance degree information. Among them, the predetermined power data attribute feature can be part of the power data attribute features set by relevant experience (for example, key power data attribute features). The power data attribute feature set includes: at least one predetermined power data attribute feature subset. The importance degree of the feature set can characterize the importance degree of the feature combination corresponding to the predetermined power data attribute feature subset. The importance degree of the feature set can be a value between 0 and 1, and the higher the value, the higher the importance degree of the corresponding predetermined power data attribute feature subset. There is a one-to-one correspondence between the feature importance degree information in at least one piece of feature set importance degree information and the predetermined power data attribute feature subset in at least one predetermined power data attribute feature subset. At least one piece of feature set importance degree information can be set in advance.

[0039] Step 4: Perform clustering processing on the above power attribute information set according to the above feature importance degree information set and the above at least one piece of feature set importance degree information to generate the above power attribute information cluster set.

[0040] Among them, in the process of determining the information distance between every two power attribute information, determine the feature distance set corresponding to the power data attribute feature set. Perform weighted summation processing on the feature distance set and the feature importance degree information set to generate a first weighted summation value. For each piece of feature set importance degree information in at least one piece of feature set importance degree information, first, determine the predetermined power data attribute feature subset corresponding to the feature set importance degree information. Then, determine the feature distance subset in the above feature distance set corresponding to the predetermined power data attribute feature subset. Next, perform weighted summation on the feature distance subset and the feature set importance degree information to generate a second weighted summation value. Add the obtained second weighted summation value set and the first weighted summation value to generate the information distance between every two power attribute information. Based on this method of determining the information distance, generate the above power attribute information cluster set through clustering.

[0041] The above technical solution and its related content, as an inventive point of an embodiment of the present disclosure, solve the technical problem: how to accurately perform clustering processing on the above power attribute information set. Based on this, the present disclosure can accurately determine the information distance between two power attribute information during the clustering process by setting at least one piece of feature set importance degree information and determining the feature importance degree information set, so as to achieve precise clustering processing.

[0042] Step 1042: Input each power attribute information in the above power attribute information set into the power usage classification model to generate initial power usage information.

[0043] In some embodiments, the above-mentioned execution entity may input each piece of power attribute information in the above-mentioned power attribute information set into a power usage classification model to generate initial power usage information. Among them, the power usage classification model may be a neural network model for processing classification tasks that generates power usage information. In practice, the power usage classification model may be a fully connected layer in series with multiple layers. The initial power usage information may be information characterizing the power usage corresponding to the power attribute information. In practice, the initial power usage information may be one of the following: information characterizing that the power usage corresponding to the power attribute information is commercial power usage, and information characterizing that the power usage corresponding to the power attribute information is residential power usage.

[0044] Step 1043: Generate predicted power usage information corresponding to each piece of power attribute information in the above-mentioned power attribute information set according to the obtained initial power usage information set and the above-mentioned power attribute information cluster set.

[0045] In some embodiments, the above-mentioned execution entity may generate predicted power usage information corresponding to each piece of power attribute information in the above-mentioned power attribute information set according to the obtained initial power usage information set and the above-mentioned power attribute information cluster set. Among them, the predicted power usage information corresponding to the power attribute information may be the predicted power usage under the power attribute information.

[0046] In some optional implementation manners of some embodiments, the generating predicted power usage information corresponding to each piece of power attribute information in the above-mentioned power attribute information set according to the obtained initial power usage information set and the above-mentioned power attribute information cluster set may include the following steps:

[0047] For each power attribute information cluster in the above-mentioned power attribute information cluster set, perform the following fourth generation step:

[0048] Sub-step 1: Determine the cluster center information corresponding to the above-mentioned power attribute information cluster as the target cluster center information.

[0049] Sub-step 2: Determine the power attribute information in the above-mentioned power attribute information cluster whose vector distance from the above-mentioned target cluster center information is less than the first vector distance as the first power attribute information, and obtain at least one piece of first power attribute information. Among them, the first vector distance may be a preset value. The first vector distance may be set based on experience.

[0050] Sub-step 3: Determine the power attribute information in the above-mentioned power attribute information cluster whose vector distance from the above-mentioned target cluster center information is less than the second vector distance and greater than the above-mentioned first vector distance as the second power attribute information, and obtain at least one piece of second power attribute information. The second vector distance may be set based on experience. The second vector distance is greater than the first vector distance.

[0051] Sub-step 4: Determine the power attribute information in the above power attribute information cluster whose vector distance from the above target cluster center information is greater than the second vector distance as the third power attribute information, and obtain at least one piece of third power attribute information.

[0052] Sub-step 5: Determine at least one first initial power usage information corresponding to the above at least one first power attribute information. Among them, there is a one-to-one correspondence between the first power attribute information in the at least one first power attribute information and the first initial power usage information in the at least one first initial power usage information. The first initial power usage information can be the initially determined power usage information.

[0053] Sub-step 6: Determine at least one second initial power usage information corresponding to the above at least one second power attribute information. Among them, there is a one-to-one correspondence between the second power attribute information in the at least one second power attribute information and the second initial power usage information in the at least one second initial power usage information.

[0054] Sub-step 7: Determine at least one third initial power usage information corresponding to the above at least one third power attribute information. Among them, there is a one-to-one correspondence between the third power attribute information in the at least one third power attribute information and the third initial power usage information in the at least one third initial power usage information.

[0055] Sub-step 8: Generate the predicted power usage information corresponding to each power attribute information in the above power attribute information cluster according to the above at least one first initial power usage information, the corresponding at least one first vector distance, the above at least one second initial power usage information, the corresponding at least one second vector distance, the above at least one third initial power usage information, and the corresponding at least one third vector distance.

[0056] In some optional implementation manners of some embodiments, the above first initial power usage information includes: power usage type and power usage type probability; the above second initial power usage information includes: power usage type and power usage type probability; the above third initial power usage information includes: power usage type and power usage type probability. The power usage type can be the type of power consumption purpose. In practice, the power usage type can be one of the following: commercial power consumption, residential power consumption. The power usage type probability can represent the accuracy of the determined power usage type. The higher the power usage type probability, the more accurately the determined power usage type is represented.

[0057] Optionally, generating the predicted power usage information corresponding to each power attribute information in the power attribute information cluster according to the above at least one first initial power usage information, the corresponding at least one first vector distance, the above at least one second initial power usage information, the corresponding at least one second vector distance, the above at least one third initial power usage information, and the corresponding at least one third vector distance may include the following steps:

[0058] First step, determine at least one power usage type probability corresponding to the above at least one first initial power usage information as at least one first power usage type probability. Among them, there is a one-to-one correspondence between the first initial power usage information in the at least one first initial power usage information and the first power usage type probability in the at least one first power usage type probability.

[0059] Second step, determine at least one power usage type probability corresponding to the above at least one second initial power usage information as at least one second power usage type probability. Among them, there is a one-to-one correspondence between the second initial power usage information in the at least one second initial power usage information and the second power usage type probability in the at least one second power usage type probability.

[0060] Third step, determine at least one power usage type probability corresponding to the above at least one third initial power usage information as at least one third power usage type probability. Among them, there is a one-to-one correspondence between the third initial power usage information in the at least one third initial power usage information and the third power usage type probability in the at least one third power usage type probability.

[0061] Fourth step, determine whether each first power usage type probability in the above at least one first power usage type probability is inversely proportional to the corresponding value of each first vector distance in the above at least one first vector distance. Among them, the inverse proportional relationship may be that the larger the power usage type probability, the smaller the corresponding first vector distance.

[0062] Fifth step, in response to determining an inverse proportional relationship with the corresponding value of each first vector distance in the above at least one first vector distance, determine whether each second power usage type probability in the above at least one second power usage type probability is inversely proportional to the corresponding value of each second vector distance in the above at least one second vector distance.

[0063] Step 6, in response to determining that the respective numerical values corresponding to each of the at least one second vector exhibit an inverse relationship, determine whether the average probability corresponding to the at least one first power usage type probability is greater than the average probability corresponding to the at least one second power usage type probability. The average probability corresponding to the at least one first power usage type probability may be a numerical value obtained by averaging each of the first power usage type probabilities. The average probability corresponding to the at least one second power usage type probability may be a numerical value obtained by averaging each of the second power usage type probabilities.

[0064] Step 7, in response to determining that it is greater, determine whether the respective third power usage type probabilities among the at least one third power usage type probabilities exhibit an inverse relationship with the respective numerical values corresponding to each of the at least one third vector.

[0065] Step 8, in response to determining that it exhibits an inverse relationship with the respective numerical values corresponding to each of the at least one third vector, determine whether the average probability corresponding to the at least one second power usage type probability is greater than the average probability corresponding to the at least one third power usage type probability. The average probability corresponding to the at least one third power usage type probability may be a numerical value obtained by averaging each of the third power usage type probabilities.

[0066] Step 9, in response to determining that it is greater, determine the initial power usage information corresponding to each power attribute information in the power attribute information cluster as the corresponding predicted power usage information.

[0067] Step 105, according to the obtained sequence of predicted power usage information sets, conduct a power usage verification on the target power region to generate power usage verification information.

[0068] In some embodiments, the above-mentioned execution subject may conduct a power usage verification on the target power region according to the obtained sequence of predicted power usage information sets to generate power usage verification information. Among them, the power usage verification information may be information indicating whether there is an abnormal power usage in the target power region.

[0069] In some optional implementation manners of some embodiments, the above-mentioned conducting a power usage verification on the target power region according to the obtained sequence of predicted power usage information sets to generate power usage verification information may include the following steps:

[0070] Step 1, for each power sub-region among the above-mentioned respective power sub-regions, execute the following second generation step:

[0071] Sub-step 1: Determine the power equipment usage registration information corresponding to the above power sub-region at the current time. Among them, the power equipment usage registration information can characterize the registration situation of the electricity usage types of each power equipment in the power sub-region.

[0072] Sub-step 2: Determine the predicted power usage information sequence corresponding to the above power sub-region as the target predicted power usage information sequence.

[0073] Sub-step 3: Determine the power usage verification sub-information corresponding to the above power sub-region according to the above target predicted power usage information sequence and the above power equipment usage registration information.

[0074] As an example, the above execution entity can perform a difference comparison between the target predicted power usage information sequence and the above power equipment usage registration information to determine the power usage verification sub-information corresponding to the above power sub-region.

[0075] Second step: Generate the above power usage verification information according to the obtained power usage verification sub-information.

[0076] As an example, the above execution entity can directly determine each power usage verification sub-information as the power usage verification information.

[0077] Optionally, the determining the power usage verification sub-information corresponding to the above power sub-region according to the above target predicted power usage information sequence and the above power equipment usage registration information may include the following steps:

[0078] First step: Determine whether each target predicted power usage information in the above target predicted power usage information sequence is the same as the above power equipment usage registration information.

[0079] Second step: In response to determining the same, generate power usage verification sub-information indicating that there is no abnormal usage in the above power sub-region.

[0080] Third step: In response to determining that there is a difference, determine the target predicted power usage information in the above target predicted power usage information sequence that is different from the above power equipment usage registration information to obtain at least one target predicted power usage information.

[0081] Fourth step: Determine at least one power acquisition time corresponding to the above at least one target predicted power usage information.

[0082] Fifth step: For each power acquisition time in the above at least one power acquisition time, determine the power equipment usage registration information corresponding to the above power sub-region at the above power acquisition time as the target power equipment usage registration information.

[0083] Step 6: Determine whether at least one of the above target predicted power usage information is the same as at least one of the obtained target power device usage registration information.

[0084] Step 7: In response to determining that they are the same, generate power usage verification sub-information indicating that there is no abnormal usage within the above power sub-region.

[0085] Step 8: In response to determining that there are differences, generate power usage verification sub-information indicating that there is abnormal usage within the above power sub-region.

[0086] In some optional implementation manners of some embodiments, after step 105, the steps further include:

[0087] For each of the above power sub-regions, perform the following third generation steps:

[0088] Sub-step 1: Determine the power attribute information sequence corresponding to the above power sub-region.

[0089] Sub-step 2: According to the above power attribute information sequence, determine the power-related data set of the above power sub-region within a future time period. Wherein, the above power-related data set includes: power consumption data, power generation data, and power usage distribution.

[0090] As an example, the above execution entity can input the above power attribute information sequence into a power-related data generation model (for example, a neural network model based on a recurrent neural network) to generate the power-related data set of the above power sub-region within a future time period.

[0091] Step 106: Perform data alarm processing on the power usage verification information.

[0092] In some embodiments, the above execution entity can perform data alarm processing on the power usage verification information.

[0093] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the abnormal power grid data warning method of some embodiments of the present disclosure, the electricity usage in the target power area can be verified accurately and efficiently. Specifically, the reason for the inefficient verification of relevant electricity usage is that the workload of manually verifying electricity usage is large and the determination of abnormalities is relatively cumbersome, resulting in low verification efficiency. Based on this, the abnormal power grid data warning method of some embodiments of the present disclosure first obtains the power data set sequence corresponding to the target power area. Among them, there is a corresponding power acquisition time for the power data set in the above power data set sequence, and the power data is the power detection data of each power device in the power sub-area at the corresponding power acquisition time. The above target power area includes: each power sub-area. Here, by obtaining the power data at each power acquisition time in the target power area, sufficient data support can be provided for the subsequent verification of the electricity usage in the target power area. Then, data preprocessing is performed on each power data in the above power data set sequence to generate a preprocessed power data set sequence to remove the data noise existing in each power data and ensure the data accuracy of the subsequent electricity usage. Next, the power attribute information corresponding to each preprocessed power data in the above preprocessed power data set sequence is extracted to obtain a power attribute information set sequence to extract the feature information under each power attribute feature, which is convenient for accurately determining the electricity usage information from the attribute features later. Then, for each power attribute information set, the following first generation step is executed: The first step is to perform clustering processing on the above power attribute information set to generate a power attribute information cluster set. Here, through clustering processing, the power attribute information belonging to the same type of electricity usage can be accurately classified into one category, which is convenient for subsequent determination of the corresponding electricity usage. The second step is to input each power attribute information in the above power attribute information set into the electricity usage classification model to accurately and efficiently generate the initial electricity usage information. The third step is to accurately generate the predicted electricity usage information corresponding to each power attribute information in the above power attribute information set according to the obtained initial electricity usage information set and the above power attribute information cluster set. Here, through the power attribute information cluster set after clustering processing and the initial electricity usage information output by the electricity usage classification model, the accuracy of the predicted electricity usage information can be ensured under the mutual verification of the two. Finally, according to the obtained predicted electricity usage information set sequence, the electricity usage in the above target power area can be quickly verified to generate electricity usage verification information for data warning processing. In summary, through clustering processing and the electricity usage classification model, the electricity usage in the target power area can be accurately and efficiently verified under mutual verification.

[0094] Further reference Figure 2, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an abnormal power grid data warning device, and these device embodiments correspond to Figure 1 the method embodiments shown. The abnormal power grid data warning device can be specifically applied to various electronic devices.

[0095] As Figure 2 shown, an abnormal power grid data warning device 200 includes: an acquisition unit 201, a preprocessing unit 202, an extraction unit 203, an execution unit 204, a verification unit 205, and an alarm unit 206. Among them, the acquisition unit 201 is configured to acquire a sequence of power data sets corresponding to a target power region. Among them, there is a corresponding power acquisition time for the power data sets in the above sequence of power data sets, and the power data is the power detection data of each power device in the corresponding power sub-region at the corresponding power acquisition time. The above target power region includes: each power sub-region; the preprocessing unit 202 is configured to perform data preprocessing on each power data in the above sequence of power data sets to generate a sequence of preprocessed power data sets; the extraction unit 203 is configured to extract the power attribute information corresponding to each preprocessed power data in the above sequence of preprocessed power data sets to obtain a sequence of power attribute information sets; the execution unit 204 is configured to perform the following first generation step for each power attribute information set: perform clustering processing on the above power attribute information set to generate a set of power attribute information clusters; input each power attribute information in the above power attribute information set into a power usage classification model to generate initial power usage information; generate predicted power usage information corresponding to each power attribute information in the above power attribute information set according to the obtained initial power usage information set and the above power attribute information cluster set; the verification unit 205 is configured to perform a power usage verification on the above target power region according to the obtained sequence of predicted power usage information sets to generate power usage verification information. The alarm unit 206 is configured to perform data alarm processing on the above power usage verification information.

[0096] It can be understood that the units described in the abnormal power grid data warning device 200 correspond to each step in the method described with reference to Figure 1 Therefore, the operations, features, and beneficial effects described above for the method also apply to the abnormal power grid data warning device 200 and the units included therein, and will not be repeated here.

[0097] Next, refer to Figure 3 , which shows a schematic structural diagram of an electronic device (for example, an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not impose any limitations on the functions and usage scopes of the embodiments of the present disclosure.

[0098] As shown Figure 3 in FIG. 1, the electronic device 300 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 301, which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0099] Generally, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 3 FIG. 1 shows an electronic device 300 having various devices, it should be understood that it is not required to implement or include all the shown devices. More or fewer devices may be implemented or included alternatively. Figure 3 Each block shown in FIG. 1 may represent one device or, as required, multiple devices.

[0100] Specifically, according to some embodiments of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for performing the method shown in the flowchart. In such some embodiments, the computer program may be downloaded and installed from a network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above functions defined in the method of some embodiments of the present disclosure are performed.

[0101] It should be noted that, in some embodiments of the present disclosure, the above-mentioned computer-readable medium may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0102] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0103] The above computer-readable medium may be included in the above electronic device; or it may exist independently and not be assembled into the electronic device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by the electronic device, the electronic device is caused to: obtain a sequence of power data sets corresponding to a target power region, wherein there is a corresponding power acquisition time for the power data sets in the sequence of power data sets, and the power data is the power detection data of each power device in each power sub-region at the corresponding power acquisition time. The above target power region includes: each power sub-region; perform data preprocessing on each power data in the sequence of power data sets to generate a sequence of preprocessed power data sets; extract the power attribute information corresponding to each preprocessed power data in the sequence of preprocessed power data sets to obtain a sequence of power attribute information sets; for each power attribute information set, perform the following first generation step: perform clustering processing on the power attribute information set to generate a set of power attribute information clusters; input each power attribute information in the power attribute information set into a power usage classification model to generate initial power usage information; generate predicted power usage information corresponding to each power attribute information in the power attribute information set according to the obtained initial power usage information set and the set of power attribute information clusters; perform a power usage verification on the above target power region according to the obtained sequence of predicted power usage information sets to generate power usage verification information.

[0104] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages - such as Java, Smalltalk, C++; and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or may be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0105] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0106] The units described in some embodiments of the present disclosure can be implemented in software or in hardware. The described units can also be provided in a processor. For example, it can be described as: a processor includes an acquisition unit, a preprocessing unit, an extraction unit, an execution unit, a verification unit, and an alarm unit. Among them, the names of these units do not constitute a limitation on the unit itself in some cases. For example, the acquisition unit can also be described as "the unit for acquiring the power dataset sequence corresponding to the target power region".

[0107] The functions described above can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Arrays (FPGA), Application Specific Integrated Circuits (ASIC), Application Specific Standard Products (ASSP), System on Chip (SOC), Complex Programmable Logic Devices (CPLD), and so on.

[0108] The above description is only some preferred embodiments of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. An abnormal power grid data alarm method, comprising: Obtaining a sequence of power data sets corresponding to a target power region, wherein there is a corresponding power acquisition time for the power data sets in the sequence of power data sets, and the power data is the power detection data of each power device in the corresponding power sub-region at the corresponding power acquisition time, and the target power region includes: each power sub-region; Performing data preprocessing on each power data in the sequence of power data sets to generate a sequence of preprocessed power data sets; Extracting the power attribute information corresponding to each preprocessed power data in the sequence of preprocessed power data sets to obtain a sequence of power attribute information sets; For each power attribute information set, performing the following first generation step: Performing clustering processing on the power attribute information set to generate a set of power attribute information clusters; Inputting each power attribute information in the power attribute information set into a power usage classification model to generate initial power usage information; Generating predicted power usage information corresponding to each power attribute information in the power attribute information set according to the obtained initial power usage information set and the set of power attribute information clusters; Performing a power usage verification on the target power region according to the obtained sequence of predicted power usage information sets to generate power usage verification information, wherein performing a power usage verification on the target power region according to the obtained sequence of predicted power usage information sets to generate power usage verification information includes: for each power sub-region in the respective power sub-regions, performing the following second generation step: determining the power device usage registration information corresponding to the power sub-region at the current time; determining the sequence of predicted power usage information corresponding to the power sub-region as the target sequence of predicted power usage information; determining the power usage verification sub-information corresponding to the power sub-region according to the target sequence of predicted power usage information and the power device usage registration information; generating the power usage verification information according to the obtained respective power usage verification sub-information; Performing a data alarm process on the power usage verification information.

2. The method according to claim 1, wherein The method further includes: For each power sub-region in the respective power sub-regions, performing the following third generation step: Determining the sequence of power attribute information corresponding to the power sub-region; Determining the power-related data sets of the power sub-region in a future time period according to the sequence of power attribute information, wherein the power-related data sets include: power consumption data, power generation data, and power usage distribution.

3. The method according to claim 1, wherein, The generating the predicted power usage information corresponding to each power attribute information in the power attribute information set according to the obtained initial power usage information set and the set of power attribute information clusters includes: For each power attribute information cluster in the set of power attribute information clusters, performing the following fourth generation step: Determining the cluster center information corresponding to the power attribute information cluster as the target cluster center information; Determine the power attribute information in the power attribute information cluster whose vector distance from the target cluster center information is less than the first vector distance as the first power attribute information, and obtain at least one piece of first power attribute information; Determine the power attribute information in the power attribute information cluster whose vector distance from the target cluster center information is less than the second vector distance and greater than the first vector distance as the second power attribute information, and obtain at least one piece of second power attribute information; Determine the power attribute information in the power attribute information cluster whose vector distance from the target cluster center information is greater than the second vector distance as the third power attribute information, and obtain at least one piece of third power attribute information; Determine at least one first initial power usage information corresponding to the at least one first power attribute information; Determine at least one second initial power usage information corresponding to the at least one second power attribute information; Determine at least one third initial power usage information corresponding to the at least one third power attribute information; Generate predicted power usage information corresponding to each power attribute information in the power attribute information cluster according to the at least one first initial power usage information, the corresponding at least one first vector distance, the at least one second initial power usage information, the corresponding at least one second vector distance, the at least one third initial power usage information, and the corresponding at least one third vector distance.

4. The method according to claim 3, wherein, The first initial power usage information includes: power usage type and power usage type probability, the second initial power usage information includes: power usage type and power usage type probability, and the third initial power usage information includes: power usage type and power usage type probability; and The generating the predicted power usage information corresponding to each power attribute information in the power attribute information cluster according to the at least one first initial power usage information, the corresponding at least one first vector distance, the at least one second initial power usage information, the corresponding at least one second vector distance, the at least one third initial power usage information, and the corresponding at least one third vector distance includes: Determine at least one power usage type probability corresponding to the at least one first initial power usage information as at least one first power usage type probability; Determine at least one power usage type probability corresponding to the at least one second initial power usage information as at least one second power usage type probability; Determine at least one power usage type probability corresponding to the at least one third initial power usage information as at least one third power usage type probability; Determine whether each first power usage type probability in the at least one first power usage type probability is inversely proportional to the corresponding value of each first vector distance in the at least one first vector distance; In response to determining that the respective numerical values corresponding to the at least one first vector distance exhibit an inverse relationship, determine whether the respective probabilities of the at least one second power usage type probability exhibit an inverse relationship with the respective numerical values corresponding to the at least one second vector distance; In response to determining that the respective numerical values corresponding to the at least one second vector distance exhibit an inverse relationship, determine whether the average probability corresponding to the at least one first power usage type probability is greater than the average probability corresponding to the at least one second power usage type probability; In response to determining that it is greater, determine whether the respective probabilities of the at least one third power usage type probability exhibit an inverse relationship with the respective numerical values corresponding to the at least one third vector distance; In response to determining that the respective numerical values corresponding to the at least one third vector distance exhibit an inverse relationship, determine whether the average probability corresponding to the at least one second power usage type probability is greater than the average probability corresponding to the at least one third power usage type probability; In response to determining that it is greater, determine the initial power usage information corresponding to each power attribute information in the power attribute information cluster as the corresponding predicted power usage information.

5. The method according to claim 1, wherein The determining of the power usage verification sub-information corresponding to the power sub-region according to the target predicted power usage information sequence and the power device usage registration information includes: Determine whether each target predicted power usage information in the target predicted power usage information sequence is the same as the power device usage registration information; In response to determining that they are the same, generate power usage verification sub-information indicating that there is no usage anomaly in the power sub-region; In response to determining that there are differences, determine the target predicted power usage information in the target predicted power usage information sequence that is different from the power device usage registration information, to obtain at least one target predicted power usage information; Determine the at least one power acquisition time corresponding to the at least one target predicted power usage information; For each power acquisition time in the at least one power acquisition time, determine the power device usage registration information corresponding to the power sub-region at the power acquisition time as the target power device usage registration information; Determine whether the at least one target predicted power usage information is the same as the at least one target power device usage registration information obtained; In response to determining that they are the same, generate power usage verification sub-information indicating that there is no usage anomaly in the power sub-region; In response to determining that there are differences, generate power usage verification sub-information indicating that there is a usage anomaly in the power sub-region.

6. An abnormal power grid data warning device, comprising: An acquisition unit, configured to acquire a sequence of power data sets corresponding to a target power region, wherein there is a corresponding power acquisition time for the power data sets in the sequence of power data sets, and the power data is power detection data of each power device in a power sub-region at the corresponding power acquisition time, and the target power region includes: each power sub-region; A preprocessing unit, configured to perform data preprocessing on each power data in the sequence of power data sets to generate a sequence of preprocessed power data sets; An extraction unit, configured to extract power attribute information corresponding to each preprocessed power data in the sequence of preprocessed power data sets to obtain a sequence of power attribute information sets; An execution unit, configured to, for each power attribute information set, perform the following first generation steps: perform clustering processing on the power attribute information set to generate a set of power attribute information clusters; input each power attribute information in the power attribute information set into a power usage classification model to generate initial power usage information; generate predicted power usage information corresponding to each power attribute information in the power attribute information set according to the obtained initial power usage information set and the set of power attribute information clusters; A verification unit, configured to perform power usage verification on the target power region according to the obtained sequence of predicted power usage information sets to generate power usage verification information, wherein performing power usage verification on the target power region according to the obtained sequence of predicted power usage information sets to generate power usage verification information includes: for each power sub-region among the power sub-regions, perform the following second generation steps: determine the power device usage registration information corresponding to the power sub-region at the current time; determine the sequence of predicted power usage information corresponding to the power sub-region as the target sequence of predicted power usage information; determine the power usage verification sub-information corresponding to the power sub-region according to the target sequence of predicted power usage information and the power device usage registration information; generate the power usage verification information according to the obtained power usage verification sub-information; An alarm unit, configured to perform data alarm processing on the power usage verification information.

7. An electronic device, comprising: One or more processors; A storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-5.

8. A computer-readable medium having a computer program stored thereon, wherein, The program, when executed by the processor, implements the method according to any one of claims 1-5.

Images