Intelligent power consumption management method and system

Abstract

The invention provides an intelligent power consumption management method and system. The system comprises one or more data acquisition devices configured to acquire power utilization parameters in a power grid in real time; the data processing server is configured to receive the electricity utilization parameters transmitted by the data acquisition device and analyze the electricity utilization parameters so as to identify electricity utilization abnormity types and obtain electricity utilization abnormity analysis reports of the electricity utilization abnormity types; wherein the data processing server comprises a first-order electricity consumption anomaly detection engine, and the data processing server identifies the electricity consumption anomaly type based on the first-order electricity consumption anomaly detection engine; the data processing server further comprises a second-order electricity consumption anomaly detection model, and the data processing server carries out deep analysis on the detected electricity consumption anomaly type based on the second-order electricity consumption anomaly detection model; the input of the second-order electricity consumption anomaly detection model comprises electricity consumption parameters and electricity consumption anomaly types, and the output of the second-order electricity consumption anomaly detection model comprises an electricity consumption anomaly analysis report.

Description

Technical Field

[0001] The present application relates to the field of electrical data processing, and more specifically, to a smart electricity management method and system. Background Art

[0002] With the development of smart grid technology, real-time monitoring of the grid operation status and timely detection of abnormal power consumption behavior have become particularly important. Traditional power management systems often rely on manual regular inspections or simple alarm systems based on fixed thresholds. These methods cannot effectively cope with the complex and changing power grid environment and changes in user power consumption behavior. For example, traditional systems usually only collect basic power consumption parameters, such as total power consumption, but lack the collection of detailed data, such as real-time changes in current, voltage, power, etc. Traditional data analysis methods are relatively simple and can only identify some obvious problems, such as power consumption exceeding the normal range, but it is difficult to accurately judge more complex and hidden abnormal situations (such as changes in power consumption patterns). In addition, due to the long data collection cycle and limited analysis methods, it takes a long time to discover and solve problems, affecting the power supply quality and user experience. In addition, traditional systems rarely consider the impact of external environmental factors (such as weather changes, social events, etc.) on power consumption behavior, which may cause the system to misreport or miss abnormal situations in some special cases.

[0003] Therefore, the present application provides a smart electricity management method and system to solve one of the above technical problems. Summary of the invention

[0004] The purpose of this application is to provide a smart electricity management method and system that can solve at least one of the technical problems mentioned above. The specific solution is as follows: According to the specific implementation of the present application, in the first aspect, the present application provides a smart electricity management method, which is applied to a smart electricity management system including a data acquisition device and a data processing server, including: Control the data acquisition device to collect power consumption parameters in the power grid in real time, wherein the power consumption parameters include current, voltage, power, and power consumption; control the data processing server to receive the power consumption parameters transmitted by the data acquisition device, and analyze the power consumption parameters to identify the power consumption anomaly type and obtain a power consumption anomaly analysis report of the power consumption anomaly type; wherein the data processing server includes a first-order power consumption anomaly detection engine, and the data processing server identifies the power consumption anomaly type based on the first-order power consumption anomaly detection engine; the data processing server also includes a second-order power consumption anomaly detection model, and the data processing server performs an in-depth analysis of the detected power consumption anomaly type based on the second-order power consumption anomaly detection model; the input of the second-order power consumption anomaly detection model includes the power consumption parameters and the power consumption anomaly type, and the output of the second-order power consumption anomaly detection model includes the power consumption anomaly analysis report.

[0005] In one embodiment, the types of power consumption anomalies include high-load power consumption at night, instantaneous power demand peak, continuous low voltage, unplanned power outages, power consumption pattern changes, and remote monitoring signal loss; different types of power consumption anomalies are detected in the following manner: controlling the first-order power consumption anomaly detection engine to detect high-load power consumption at night based on the power consumption; controlling the first-order power consumption anomaly detection engine to detect instantaneous power demand peak based on the power consumption; controlling the first-order power consumption anomaly detection engine to detect continuous low voltage based on the voltage value; controlling the first-order power consumption anomaly detection engine to detect unplanned power outages based on the voltage value; controlling the first-order power consumption anomaly detection engine to detect power consumption pattern changes based on the power consumption; and controlling the first-order power consumption anomaly detection engine to detect remote monitoring signal loss based on the transmission status of the power consumption parameters.

[0006] In one embodiment, the data acquisition device includes a data crawling engine, and the method further includes: controlling the data acquisition device to crawl data on the monitored power consumption area to obtain crawled data; wherein the crawled data includes meteorological data of the power consumption area, social media data of the power consumption area, news data of the power consumption area, pre-marked high power consumption areas in the power consumption area, wired communication data of the power consumption area, and historical power consumption data of the power management intranet; the input of the second-order power consumption anomaly detection model also includes the crawled data.

[0007] In one embodiment, the data processing server also includes a communication data processor, and the method also includes: controlling the communication data processor to divert the target communication data output by the wired port from the wired communication data based on the port type; controlling the communication data processor to simulate the number of terminals based on the data type of the target communication data; and in response to the difference between the number of terminals currently simulated and the number of terminals previously simulated being greater than a preset threshold, controlling the second-order power consumption anomaly detection model to use the currently simulated number of terminals as one of the inputs.

[0008] In one embodiment, the second-order power consumption anomaly detection model includes a data filter, and the method further includes: controlling the data filter to perform data filtering on the crawled data, including: filtering the text data of the meteorological data, the social media data, the news data, the wired communication data, and the historical power consumption data to extract keywords or phrases related to power consumption anomalies; filtering the meteorological data, the social media data, the news data, and image data of pre-marked high power consumption areas in the power consumption area to extract image data related to power consumption anomalies; and annotating the text data and the image data with association; wherein the association annotation includes setting the same label for the associated text data and image data.

[0009] According to a specific implementation of the present application, in a second aspect, the present application provides a smart electricity management system, which is used as an implementation carrier of the method of the first aspect, including: One or more data acquisition devices are configured to acquire power consumption parameters in a power grid in real time, wherein the power consumption parameters include current, voltage, power, and power consumption; a data processing server is configured to receive the power consumption parameters transmitted by the data acquisition device and analyze the power consumption parameters to identify the power consumption anomaly type and obtain a power consumption anomaly analysis report of the power consumption anomaly type; wherein the data processing server includes a first-order power consumption anomaly detection engine, and the data processing server identifies the power consumption anomaly type based on the first-order power consumption anomaly detection engine; the data processing server also includes a second-order power consumption anomaly detection model, and the data processing server performs an in-depth analysis of the detected power consumption anomaly type based on the second-order power consumption anomaly detection model; the input of the second-order power consumption anomaly detection model includes the power consumption parameters and the power consumption anomaly type, and the output of the second-order power consumption anomaly detection model includes the power consumption anomaly analysis report.

[0010] In one embodiment, the types of power consumption anomalies include high-load power consumption at night, instantaneous power demand peak, continuous low voltage, unplanned power outages, changes in power consumption patterns, and loss of remote monitoring signals; the first-order power consumption anomaly detection engine is configured to: detect high-load power consumption at night based on the power consumption; detect instantaneous power demand peak based on the power consumption; detect continuous low voltage based on the voltage value; detect unplanned power outages based on the voltage value; detect changes in power consumption patterns based on the power consumption; and detect loss of remote monitoring signals based on the transmission status of the power consumption parameters.

[0011] In one embodiment, the data acquisition device includes a data crawling engine, which is configured to crawl data on the monitored power consumption area to obtain crawled data; wherein the crawled data includes meteorological data of the power consumption area, social media data of the power consumption area, news data of the power consumption area, pre-marked high power consumption areas in the power consumption area, wired communication data of the power consumption area, and historical power consumption data of the power management intranet; the input of the second-order power consumption anomaly detection model also includes the crawled data.

[0012] In one embodiment, the data processing server also includes a communication data processor, which is configured to: divert target communication data output by the wired port based on the port type in the wired communication data; simulate the number of terminals based on the data type of the target communication data; in response to the difference between the number of terminals currently simulated and the number of terminals previously simulated being greater than a preset threshold, the input of the second-order power consumption anomaly detection model also includes the number of terminals currently simulated.

[0013] In one embodiment, the second-order power consumption anomaly detection model includes a data filter, which is configured to: perform data filtering on the crawled data, including: filtering the text data of the meteorological data, the social media data, the news data, the wired communication data, and the historical power consumption data; filtering the image data of the meteorological data, the social media data, the news data, and the pre-marked high power consumption areas in the power consumption area; and annotating the association between the text data and the image data; wherein the association annotation includes setting the same label for the associated text data and image data.

[0014] Compared with the prior art, the above solution of the embodiment of the present application has at least the following beneficial effects: The present application provides a smart power management system, which can quickly detect abnormal situations by real-time collection of power parameters in the power grid, shorten the time interval from the occurrence of the problem to the solution of the problem, and improve the response speed of the entire system. Through the first-order power consumption anomaly detection engine and the second-order power consumption anomaly detection model, it is possible to identify various types of power consumption anomalies, including but not limited to high-load power consumption at night, instantaneous power demand peak, continuous low voltage, etc., so as to ensure that abnormal situations are fully covered. In addition, the present application uses the second-order power consumption anomaly detection model to conduct in-depth analysis of the detected anomaly types, improves the accuracy of problem diagnosis, and helps to quickly locate the cause of the problem and take targeted measures. Furthermore, the data crawling engine contained in the data acquisition device can obtain external data related to power consumption, such as meteorological data, social media data, etc., making anomaly detection more comprehensive and helping to more accurately evaluate the influencing factors of abnormal situations. In addition, the power consumption anomaly analysis report generated by the present application provides detailed information support for power grid managers, which is conducive to scientific and effective decision-making and improves overall operational efficiency. The system realizes the automation of the entire process from data collection to anomaly detection to analysis report generation, reduces the need for manual intervention, improves the stability and reliability of the system, and provides the possibility for regional intelligent management of power grids. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A flow chart of a smart electricity management method according to an embodiment of the present application is shown; Figure 2 A flow chart of a method for providing input data via a communication data processor is shown; Figure 3 A block diagram of a smart electricity management system according to an embodiment of the present application is shown; Figure 4 A block diagram of a data processing server according to an embodiment of the present application is shown; Figure 5 A block diagram of a data acquisition device according to an embodiment of the present application is shown; Figure 6 A block diagram of a data acquisition device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0017] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0018] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0019] It should be understood that although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0020] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0021] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the commodity or device including the elements.

[0022] It should be particularly noted that any symbols and / or numbers in the specification that are not marked in the accompanying drawings are not drawing marks.

[0023] The optional embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0024] Figure 1 A flow chart of a smart power management method according to an embodiment of the present application is shown. Figure 1As shown, the method is applied to a smart electricity management system including a data acquisition device and a data processing server, including the following steps S101 and S102.

[0025] Step S101, controlling the data acquisition device to collect power consumption parameters in the power grid in real time.

[0026] Among them, the power consumption parameters include current, voltage, power, and power consumption.

[0027] Step S102, controlling the data processing server to receive the power usage parameters transmitted by the data acquisition device, and analyzing the power usage parameters to identify the power usage anomaly type and obtain a power usage anomaly analysis report of the power usage anomaly type.

[0028] In the present application, the data processing server includes a first-order power consumption anomaly detection engine, and the data processing server identifies the power consumption anomaly type based on the first-order power consumption anomaly detection engine.

[0029] In the present application, the data processing server also includes a second-order power consumption anomaly detection model, and the data processing server performs an in-depth analysis of the detected power consumption anomaly type based on the second-order power consumption anomaly detection model.

[0030] In the present application, the input of the second-order power consumption anomaly detection model includes power consumption parameters and power consumption anomaly types, and the output of the second-order power consumption anomaly detection model includes a power consumption anomaly analysis report.

[0031] The method provided by the present application can quickly discover abnormal situations by real-time collection of power consumption parameters in the power grid, shorten the time interval from the occurrence of the problem to the solution of the problem, and improve the response speed of the entire system. Through the first-order power consumption anomaly detection engine and the second-order power consumption anomaly detection model, it is possible to identify various types of power consumption anomalies, including but not limited to high-load power consumption at night, instantaneous power demand peak, continuous low voltage, etc., so as to ensure that abnormal situations are fully covered. In addition, the present application uses the second-order power consumption anomaly detection model to conduct in-depth analysis of the detected anomaly types, improves the accuracy of problem diagnosis, and helps to quickly locate the cause of the problem and take targeted measures. Further, the data crawling engine contained in the data acquisition device can obtain external data related to power consumption, such as meteorological data, social media data, etc., making anomaly detection more comprehensive and helping to more accurately evaluate the influencing factors of abnormal situations. In addition, the power consumption anomaly analysis report generated by the present application provides detailed information support for power grid managers, which is conducive to scientific and effective decision-making and improves overall operational efficiency. The system realizes the automation of the entire process from data collection to anomaly detection to analysis report generation, reduces the need for manual intervention, improves the stability and reliability of the system, and provides the possibility for regional intelligent management of power grids.

[0032] In this application, the types of abnormal power consumption include high load power consumption at night, instantaneous power demand peak, continuous low voltage, unplanned power outage, change in power consumption pattern, and loss of remote monitoring signal.

[0033] In one embodiment, different types of power consumption anomalies may be detected in the following manner. For example, a first-order power consumption anomaly detection engine is controlled to detect high-load power consumption at night based on power consumption. For another example, a first-order power consumption anomaly detection engine is controlled to detect instantaneous power demand peaks based on power consumption. For another example, a first-order power consumption anomaly detection engine is controlled to detect continuous low voltage based on voltage values. For another example, a first-order power consumption anomaly detection engine is controlled to detect unplanned power outages based on voltage values. For another example, a first-order power consumption anomaly detection engine is controlled to detect power consumption mode changes based on power consumption. For another example, a first-order power consumption anomaly detection engine is controlled to detect the loss of remote monitoring signals based on the transmission status of power consumption parameters.

[0034] In the present application, the data acquisition device includes a data crawling engine. In one embodiment, the data acquisition device can be controlled to crawl data on the monitored power consumption area to obtain crawled data.

[0035] Among them, the crawled data includes meteorological data of the power consumption area, social media data of the power consumption area, news data of the power consumption area, pre-marked high-power consumption areas in the power consumption area, wired communication data of the power consumption area, and historical power consumption data of the power management intranet.

[0036] On this basis, the input of the second-order power consumption anomaly detection model can also include crawled data.

[0037] In the present application, the data processing server also includes a communication data processor, which is used to analyze the communication data to provide the required input data for the second-order power consumption anomaly detection model. A feasible way of providing input data is shown below.

[0038] Figure 2 A flow chart of a method for providing input data via a communication data processor is shown, Figure 2 As shown, the process includes the following steps S201 to S203.

[0039] Step S201 : Control the communication data processor to separate target communication data outputted by a wired port from the wired communication data based on the port type.

[0040] Step S202: Control the communication data processor to perform terminal quantity simulation based on the data type of the target communication data.

[0041] Step S203, in response to the difference between the number of terminals currently simulated and the number of terminals previously simulated being greater than a preset threshold, controlling the second-order power consumption anomaly detection model to use the number of terminals currently simulated as one of the inputs.

[0042] In this application, port type generally refers to the type of physical interface on a network device, which is used to connect different communication devices. Port types may include, for example, RJ-45 ports, fiber optic ports, USB ports, and serial ports. In this application, in smart power management, the focus is on ports connected to power devices, especially those wired ports directly related to power supply.

[0043] In this application, the relationship between the data type and the simulation of the number of terminals is reflected in the in-depth analysis of power consumption anomalies in the smart power consumption management system. Specifically, the communication data processor estimates the number of terminals by analyzing the wired communication data, and uses this information in the second-order power consumption anomaly detection model to enhance the accuracy of anomaly detection. For example, the communication data processor analyzes the data type of the target communication data, where the data type may include but is not limited to different types of data transmission such as video streaming, audio streaming, file transfer, web browsing, etc. On this basis, the communication data processor simulates the number of terminals based on the data type, and the simulation process is based on the behavior pattern of the terminal using the data type. Further, the number of terminals currently simulated is compared with the number of terminals previously simulated. If the difference in number exceeds a preset threshold, it is considered that the number of terminals has changed significantly. Furthermore, if the change in the number of terminals is significant, then this change will be provided as an additional input to the second-order power consumption anomaly detection model, and the second-order power consumption anomaly detection model will analyze whether these changes are related to power consumption anomalies in combination with power consumption parameters and other data.

[0044] In this application, the second-order power consumption anomaly detection model supports input methods including power consumption parameters and power consumption anomaly types, and supports data analysis including the number of terminals. When the input includes the number of terminals, the model reduces the number of network layers and uses the number of terminals as a gold finger for auxiliary analysis. In this case, the number of network layers that the data passes through is reduced, and the model has higher processing efficiency and higher processing accuracy.

[0045] In the present application, the second-order power consumption anomaly detection model includes a data filter. In one embodiment, the data filter can be controlled to filter the crawled data so that the second-order power consumption anomaly detection model uses the filtered data to perform power consumption anomaly analysis. One example is shown below.

[0046] In this application, the number of terminals is conducive to the identification of abnormal power consumption in some specific scenarios. For example, in some indoor scenarios, it is possible to distinguish which are wireless traffic generated by mobile phones, laptops, etc. through wifi, and which are wired traffic generated by computers, TVs, girlfriends' machines, electronic display boards, multimedia blackboards, etc., and then through the simulation of wired traffic, determine whether the number of wired terminals has increased or decreased significantly, and then assist in judging whether the abnormal power consumption is related to it. Among them, the reason for screening wired terminals and eliminating wireless terminals is that for conventional power consumption scenarios, wired terminals usually need to be connected to a power supply while connecting to a wired port, so wired terminals are the main participants in power consumption, while wireless terminals participate in less power consumption on the one hand, and on the other hand, it is impossible to evaluate power consumption through the communication data of wireless terminals, so it is eliminated as small impurity data in the power consumption calculation to ensure the robustness of the second-order power consumption anomaly detection model 102b, and then ensure that the second-order power consumption anomaly detection model 102b can reach convergence during the training phase. In this way, while providing additional reference data for the second-order power consumption anomaly detection model 102b, it also ensures that the second-order power consumption anomaly detection model 102b can correctly output the power consumption anomaly analysis report, so that the analysis accuracy of the second-order power consumption anomaly detection model 102b is further improved.

[0047] As a simple implementation method, the number of wired ports identified during traffic diversion can be directly used as the number of terminals. This method is equivalent to assuming that the wired terminals and wired ports are connected in a one-to-one relationship.

[0048] However, in actual scenarios, the connection relationship between wired terminals and wired ports is not completely one-to-one. For example, different interfaces extended using a splitter actually only correspond to one wired port. In this case, the relationship between wired terminals and wired ports is many-to-one.

[0049] Among them, the communication data processor in the data processing server will divert the target communication data output by the wired port according to the port type. The communication data processor first needs to identify which ports are wired ports based on the physical characteristics or protocol type of the port. When the wired port type is identified, the system will start to monitor the data streams passing through these ports, filter out the data streams associated with the power-consuming devices, and exclude other irrelevant data streams. Furthermore, the number of terminals can be simulated based on the filtered data streams. For example, if multiple video streams are detected passing through the same port, it may indicate that multiple devices are using this port.

[0050] Therefore, as an advanced implementation method, the data stream of the same wired port can be classified and analyzed, and the specific quantity correspondence between the wired terminal and the wired port can be further determined according to different data types, so as to accurately determine the number of wired terminals. For example, at the same time, the data stream includes two channels of image media stream data. At this time, it can be determined that the wired port is connected to two wired terminals. Of course, the actual judgment method is not limited to this. The communication data processor is actually a classification model, which is obtained by pre-labeling a large number of classification scenarios and can meet the detection of the number of wired terminals in most scenarios.

[0051] Among them, data screening includes two methods: Method 1: Screening text data of meteorological data, social media data, news data, wired communication data, and historical electricity consumption data to extract keywords or phrases related to abnormal electricity consumption.

[0052] Among them, text data screening is used to screen the text content in meteorological data, social media data, news data, wired communication data and historical electricity consumption data, with the aim of extracting keywords or phrases related to abnormal electricity consumption, such as words mentioning power failures, power outages, severe weather, etc.

[0053] Method 2: Screen meteorological data, social media data, news data, and image data of pre-labeled high-power consumption areas within power consumption areas to extract image data related to abnormal power consumption.

[0054] In addition, the data filter can also perform association annotation on the text data and the image data, wherein the association annotation can be, for example, setting the same label on the associated text data and the image data.

[0055] In this application, to establish the association between text data and image data, it is necessary to find the common points or contextual connections between the two, which can be achieved in the following ways: Method 1: Considering time consistency, if the timestamps recorded in text data and image data are similar, then they are likely to describe events in the same time period.

[0056] Method 2: Consider geographic location matching. If the geographic location mentioned in the text data is consistent with the location where the image data was taken, this can be used to establish an association.

[0057] Method 3: Consider content consistency. If the content mentioned in the text data is consistent with the situation shown in the image data, for example, the text describes a storm, and the image captures the scene under the influence of the storm, then it can be considered that the data are related. If a power outage occurs in the area, it can be further considered that the power outage is caused by the damage caused by the storm to the power supply facilities.

[0058] Method 4: Consider the matching of keywords and image features. If the features identified in the image data correspond to the keywords extracted from the text data, it can also be considered that there is a correlation between them.

[0059] In the present application, in actual operation, the above-mentioned methods 1 to 4 can be implemented separately or in association, and a machine learning model will be used to automatically complete the task of such association annotation during execution. For example, a model can be trained to accept text and image inputs at the same time and predict whether they are related. Among them, the training data of the model can be positive examples and negative examples extracted from known related data sets. On this basis, keywords or phrases related to abnormal power consumption are extracted, image data related to abnormal power consumption is extracted, and the associated information will be further analyzed for abnormal power consumption identification to provide data support for the identification step.

[0060] The present application also provides a system embodiment that is consistent with the above-mentioned embodiment, which is used as an implementation carrier of the above-mentioned method embodiment. The explanation based on the same name meaning is the same as the above embodiment, and has the same technical effect as the above embodiment, which will not be repeated here.

[0061] Figure 3 A block diagram of a smart power management system according to an embodiment of the present application is shown. Figure 3 As shown, the smart electricity management system 100 includes a data acquisition device 101 and a data processing server 102 .

[0062] In the present application, the smart power management system 100 includes one or more data acquisition devices 101, which are configured to collect power parameters in the power grid in real time, including current, voltage, power, and power consumption. The data acquisition device 101 is usually composed of sensors (such as current transformers, voltage transformers), signal conditioning circuits, analog-to-digital converters (ADCs), and microcontroller units (MCUs). These components work together to monitor and collect key parameters in the power grid in real time.

[0063] For example, the data collection device 101 may send the collected data to the data processing server 102 via a wired or wireless method (eg, Wi-Fi, Bluetooth, cellular network, etc.).

[0064] In the present application, the smart electricity management system 100 includes a data processing server 102, which is configured to receive electricity usage parameters transmitted by the data acquisition device 101, and analyze the electricity usage parameters to identify the abnormal electricity usage type and obtain an abnormal electricity usage analysis report of the abnormal electricity usage type.

[0065] Figure 4 A block diagram of a data processing server according to an embodiment of the present application is shown. Figure 4As shown, the data processing server 102 includes a first-order power consumption anomaly detection engine 102a and a second-order power consumption anomaly detection model 102b.

[0066] For example, the data processing server 102 includes a first-order power usage anomaly detection engine 102 a , and the data processing server 102 identifies the power usage anomaly type based on the first-order power usage anomaly detection engine 102 a .

[0067] In the present application, the first-order power consumption anomaly detection engine 102a is used to monitor the data received from the data acquisition device 101 in real time. Once a parameter value exceeding a preset range is detected, it is considered that power consumption anomaly has occurred and further analysis is triggered.

[0068] For example, the first-order power usage anomaly detection engine 102a uses statistical methods or machine learning algorithms (such as threshold comparison, cluster analysis, etc.) to establish a benchmark for normal power usage patterns based on historical data.

[0069] For example, the data processing server 102 further includes a second-order power consumption anomaly detection model 102 b , and the data processing server 102 performs an in-depth analysis on the detected power consumption anomaly type based on the second-order power consumption anomaly detection model 102 b .

[0070] In the present application, the input of the second-order power consumption anomaly detection model 102b includes power consumption parameters and power consumption anomaly types. Of course, as the input of the second-order power consumption anomaly detection model 102b, it includes not only the power consumption parameters themselves, but also other relevant data such as anomaly types, timestamps, geographic location information, weather conditions, etc.

[0071] In the present application, the output of the second-order power consumption anomaly detection model 102b includes a power consumption anomaly analysis report, wherein the power consumption anomaly analysis report is used to analyze the power consumption anomaly type detected by the first-order power consumption anomaly detection engine 102a, for example, it may include a specific description of the anomaly type, possible causes, and recommended countermeasures.

[0072] As a feasible implementation scenario, it is assumed that in a typical industrial area, the data acquisition device 101 can be installed at various important nodes, such as substations, power distribution rooms of large factories, etc. These devices collect data once a minute and send it to the data processing server 102. Then as a scenario where power consumption anomaly may occur, for example, a factory suddenly adds an additional production line one night, causing the power consumption in its area to rise sharply. When the system provided by the present application analyzes this scenario, for example, the data acquisition device 101 detects an abnormal increase in current and power, and sends these data to the data processing server 102. The first-order power consumption anomaly detection engine 102a compares historical data and finds that the current power consumption mode deviates from the normal range, and preliminarily determines that it is a power consumption anomaly. The second-order power consumption anomaly detection model 102b conducts an in-depth analysis of this anomaly, combines the factory's location information and the weather forecast of the day (for example, there is no abnormal weather), and determines that this is a power consumption anomaly caused by the newly added production line, and then generates a power consumption anomaly analysis report. Among them, the report points out the specific location, start time, type of anomaly, and recommended measures of the anomaly, such as checking whether it meets safety standards, or considering temporary capacity increase.

[0073] In this application, the types of abnormal power consumption include high load power consumption at night, instantaneous power demand peak, continuous low voltage, unplanned power outage, change in power consumption pattern, and loss of remote monitoring signal.

[0074] Further, the first-order power consumption anomaly detection engine 102a is configured to detect these types of power consumption anomalies when they occur, for example, detecting high-load power consumption at night based on power consumption, detecting instantaneous power demand peak based on power consumption, detecting continuous low voltage based on voltage value, detecting unplanned power outage based on voltage value, detecting power consumption mode change based on power consumption, and detecting remote monitoring signal loss based on the transmission status of power consumption parameters.

[0075] In one example, a sharp increase in electricity consumption in a short period of time (e.g., 15 minutes) can be used to detect sudden peaks in electricity demand, i.e., sudden increases in electricity demand beyond normal levels within a specific period of time, which may be caused by the startup or failure of large equipment, or the temporary increase of power-consuming equipment.

[0076] In one example, the first-order power consumption anomaly detection engine 102a can be used to detect sustained low voltage, that is, a voltage level below the standard appears in a certain area for a long time. The possible reasons are line aging, excessive load, uneven power distribution, etc.

[0077] In one example, the first-order power consumption anomaly detection engine 102a can be used to detect abnormal power consumption readings, that is, the power consumption recorded by the smart meter is inconsistent with expectations, which may be caused by meter failure, line short circuit or power theft.

[0078] In one example, the first-order power consumption anomaly detection engine 102a can be used to detect unplanned power outages, that is, sudden power outages without prior notice, which may be caused by line failures, equipment damage or other unforeseen factors.

[0079] In one example, the first-order power consumption anomaly detection engine 102a can be used to detect power quality degradation, that is, voltage fluctuations, harmonic distortion and other problems affect the power quality, which may be caused by unstable power supply, aging equipment or incompatible power equipment.

[0080] In one example, the first-order power consumption anomaly detection engine 102a can be used to detect seasonal power consumption changes, that is, abnormal power consumption changes in a specific season, which may be caused by changes in heating or cooling demand due to climate change, or increased power demand caused by special events.

[0081] In one example, the first-order power consumption anomaly detection engine 102a can be used to detect changes in power consumption patterns in a specific area, that is, the power consumption pattern in a specific area has changed significantly compared with historical data, which may be due to the introduction of new commercial activities, residential developments or industrial projects.

[0082] In one example, the first-order power consumption anomaly detection engine 102a can be used to detect abnormal electricity bills, that is, the electricity bill of a household or a region is significantly increased or decreased compared with the past, which may be caused by metering errors, equipment failure or energy waste.

[0083] In one example, the first-order power consumption anomaly detection engine 102a can be used to detect the loss of remote monitoring signals, that is, the smart meter or monitoring device cannot transmit data normally, which may be caused by network connection problems, equipment failure or human damage.

[0084] In the present application, when the first-order power consumption anomaly detection engine 102a detects power consumption anomaly and determines the type of power consumption anomaly, the second-order power consumption anomaly detection model 102b further takes over and performs anomaly analysis. The second-order power consumption anomaly detection model 102b can be an analysis model pre-trained based on the above-mentioned anomaly type and possible causes. When the second-order power consumption anomaly detection model 102b is given the input data required by the second-order power consumption anomaly detection model 102b, the second-order power consumption anomaly detection model 102b can analyze and output a power consumption anomaly analysis report.

[0085] Figure 5 A block diagram of a data acquisition device according to an embodiment of the present application is shown.

[0086] In this application, if Figure 5 As shown, the data collection device 101 may include a data crawling engine 101a, which is configured to crawl data on the monitored power consumption area to obtain crawled data.

[0087] Among them, the crawled data includes meteorological data of the power consumption area, social media data of the power consumption area, news data of the power consumption area, pre-marked high-power consumption areas in the power consumption area, wired communication data of the power consumption area, and historical power consumption data of the power management intranet.

[0088] As a feasible embodiment, the input of the second-order power consumption anomaly detection model 102b may include crawled data in addition to power consumption parameters and power consumption anomaly types.

[0089] In this application, the data acquisition device 101 collects power consumption parameters in the power grid in real time, including but not limited to power consumption parameters and crawled data. It should be noted that in the process of data acquisition and processing, this application complies with applicable data protection laws and regulations to ensure that all operations are carried out within a legal and compliant framework. In particular, for data involving personal privacy, this application adopts necessary de-identification processing measures to ensure the anonymization of data, thereby protecting user privacy from infringement.

[0090] Figure 6 A block diagram of a data acquisition device according to an embodiment of the present application is shown.

[0091] In this application, if Figure 6 As shown, the data processing server 102 also includes a communication data processor 102c, which is configured to divert target communication data output by the wired port in the wired communication data based on the port type, and to simulate the number of terminals based on the data type of the target communication data, and then in response to the difference between the number of terminals currently simulated and the number of terminals previously simulated being greater than a preset threshold, the input of the second-order power consumption anomaly detection model 102b also includes the number of terminals currently simulated.

[0092] In this application, the number of terminals is conducive to the identification of abnormal power consumption in some specific scenarios. For example, in some indoor scenarios, it is possible to distinguish which are wireless traffic generated by mobile phones, laptops, etc. through wifi, and which are wired traffic generated by computers, TVs, girlfriends' machines, electronic display boards, multimedia blackboards, etc., and then through the simulation of wired traffic, determine whether the number of wired terminals has increased or decreased significantly, and then assist in judging whether the abnormal power consumption is related to it. Among them, the reason for screening wired terminals and eliminating wireless terminals is that for conventional power consumption scenarios, wired terminals usually need to be connected to a power supply while connecting to a wired port, so wired terminals are the main participants in power consumption, while wireless terminals participate in less power consumption on the one hand, and on the other hand, it is impossible to evaluate power consumption through the communication data of wireless terminals, so it is eliminated as small impurity data in the power consumption calculation to ensure the robustness of the second-order power consumption anomaly detection model 102b, and then ensure that the second-order power consumption anomaly detection model 102b can reach convergence during the training phase. In this way, while providing additional reference data for the second-order power consumption anomaly detection model 102b, it also ensures that the second-order power consumption anomaly detection model 102b can correctly output the power consumption anomaly analysis report, so that the analysis accuracy of the second-order power consumption anomaly detection model 102b is further improved.

[0093] As a simple implementation method, the number of wired ports identified during traffic diversion can be directly used as the number of terminals. This method is equivalent to assuming that the wired terminals and wired ports are connected in a one-to-one relationship.

[0094] However, in actual scenarios, the connection relationship between wired terminals and wired ports is not completely one-to-one. For example, different interfaces extended using a splitter actually only correspond to one wired port. In this case, the relationship between wired terminals and wired ports is many-to-one.

[0095] Therefore, as an advanced implementation method, the specific quantitative correspondence between the wired terminal and the wired port can be further determined by classifying and analyzing the data stream of the same wired port, so as to accurately determine the number of wired terminals. For example, at the same time, the data stream includes two channels of image media stream data. At this time, it can be determined that the wired port is connected to two wired terminals. Of course, the actual judgment method is not limited to this. The communication data processor is actually a classification model, which is trained by pre-labeling a large number of classification scenarios and can meet the detection of the number of wired terminals in most scenarios.

[0096] In the present application, the second-order power consumption anomaly detection model 102b includes a data filter, and the data filter is configured to perform data filtering on the crawled data.

[0097] Among them, data screening includes two methods: Method 1: Screening text data of meteorological data, social media data, news data, wired communication data, and historical electricity consumption data.

[0098] Method 2: Screening of meteorological data, social media data, news data, and image data of pre-labeled high-power consumption areas within power consumption areas.

[0099] In addition, the data filter can also mark the association between the text data and the image data, wherein the association marking can be, for example, setting the same label for the associated text data and the image data.

[0100] Although operations are described in a particular order in the drawings, this should not be understood as requiring that the operations be performed in the particular order shown or in serial order, or that all shown operations be performed to achieve desired results. In certain circumstances, multitasking and parallel processing may be advantageous.

[0101] The methods and devices of the present application can be implemented using standard programming techniques, using rule-based logic or other logic to implement various method steps. It should also be noted that the words "device" and "module" used herein and in the claims are intended to include implementations using one or more lines of software code and / or hardware implementations and / or devices for receiving input.

[0102] Any steps, operations or procedures described herein may be performed or implemented using one or more hardware or software modules, either alone or in combination with other devices. In one embodiment, the software module is implemented using a computer program product including a computer-readable medium containing computer program code, which can be executed by a computer processor to perform any or all of the described steps, operations or procedures.

[0103] The foregoing description of the implementation of the present application has been given for the purpose of illustration and description. The foregoing description is not exhaustive nor is it intended to limit the present application to the exact form disclosed, and various variations and modifications may exist according to the above teachings or may be obtained from the practice of the present application. These embodiments are selected and described in order to illustrate the principles of the present application and its practical application, so that those skilled in the art can utilize the present application in various embodiments and various modifications suitable for the specific purpose contemplated.

[0104] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0105] It can be further understood that, unless otherwise specified, “connection” includes a direct connection without other components between the two, and also includes an indirect connection with other components between the two.

[0106] It is further understood that, although the operations are described in a specific order in the drawings in the embodiments of the present application, it should not be understood as requiring the operations to be performed in the specific order or serial order shown, or requiring the execution of all the operations shown to obtain the desired results. In certain environments, multitasking and parallel processing may be advantageous.

[0107] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to encompass any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the field of the present application that are not disclosed in the present application. The specification and embodiments are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following scope of rights.

[0108] It should be understood that the present application is not limited to the precise structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the scope of the appended claims.

[0109] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A smart electricity management method, characterized in that: Applied to smart power management systems including data acquisition devices and data processing servers, including: Controlling the data acquisition device to collect power parameters in the power grid in real time, wherein the power parameters include current, voltage, power, and power consumption; Controlling the data processing server to receive the power usage parameters transmitted by the data acquisition device, and analyzing the power usage parameters to identify the power usage anomaly type and obtain a power usage anomaly analysis report of the power usage anomaly type; The data processing server includes a first-order power usage anomaly detection engine, and the data processing server identifies the power usage anomaly type based on the first-order power usage anomaly detection engine; The data processing server further includes a second-order power consumption anomaly detection model, and the data processing server performs an in-depth analysis of the detected power consumption anomaly type based on the second-order power consumption anomaly detection model; The input of the second-order power consumption anomaly detection model includes the power consumption parameter and the power consumption anomaly type, and the output of the second-order power consumption anomaly detection model includes the power consumption anomaly analysis report.

2. The smart electricity management method according to claim 1, characterized in that: The types of power consumption anomalies include high load power consumption at night, instantaneous power demand peak, sustained low voltage, unplanned power outage, change in power consumption pattern, and loss of remote monitoring signal; Different types of power usage anomalies are detected in the following ways: Controlling the first-order power consumption anomaly detection engine to detect high-load power consumption at night based on the power consumption; controlling the first-order power consumption anomaly detection engine to detect an instantaneous power demand peak based on the power consumption; controlling the first-order power consumption anomaly detection engine to detect a continuous low voltage based on the voltage value; controlling the first-order power consumption anomaly detection engine to detect an unplanned power outage based on the voltage value; Controlling the first-order power consumption anomaly detection engine to detect a change in power consumption mode based on the power consumption; as well as The first-order power usage anomaly detection engine is controlled to detect a loss of a remote monitoring signal based on a transmission status of the power usage parameter.

3. The smart electricity management method according to claim 1, characterized in that: The data acquisition device includes a data crawling engine, and the method further includes: Controlling the data acquisition device to crawl data from the monitored power consumption area to obtain crawled data; The crawled data includes meteorological data of the power consumption area, social media data of the power consumption area, news data of the power consumption area, pre-marked high-power consumption areas in the power consumption area, wired communication data of the power consumption area, and historical power consumption data of the power management intranet; The input of the second-order power consumption anomaly detection model also includes the crawled data.

4. The smart electricity management method according to claim 3, characterized in that: The data processing server further includes a communication data processor, and the method further includes: controlling the communication data processor to separate target communication data outputted by the wired port from the wired communication data based on the port type; controlling the communication data processor to perform terminal quantity simulation based on the data type of the target communication data; In response to a difference between the number of terminals currently simulated and the number of terminals previously simulated being greater than a preset threshold, the second-order power consumption anomaly detection model is controlled to use the number of terminals currently simulated as one of its inputs.

5. The smart electricity management method according to claim 3, characterized in that: The second-order power consumption anomaly detection model includes a data filter, and the method further includes: Controlling the data filter to filter the crawled data includes: screening the text data of the meteorological data, the social media data, the news data, the wired communication data, and the historical electricity usage data to extract keywords or phrases related to abnormal electricity usage; screening the meteorological data, the social media data, the news data, and the image data of pre-marked high-power-consumption areas within the power-consumption area to extract image data related to abnormal power consumption; and The text data and the image data are associated with each other. The associated annotation includes setting the same label for the associated text data and the image data.

6. A smart electricity management system, characterized in that: include: One or more data acquisition devices configured to acquire power parameters in the power grid in real time, wherein the power parameters include current, voltage, power, and power consumption; a data processing server configured to receive the power usage parameters transmitted by the data acquisition device, analyze the power usage parameters to identify the power usage anomaly type and obtain a power usage anomaly analysis report of the power usage anomaly type; The data processing server includes a first-order power usage anomaly detection engine, and the data processing server identifies the power usage anomaly type based on the first-order power usage anomaly detection engine; The data processing server further includes a second-order power consumption anomaly detection model, and the data processing server performs an in-depth analysis of the detected power consumption anomaly type based on the second-order power consumption anomaly detection model; The input of the second-order power consumption anomaly detection model includes the power consumption parameter and the power consumption anomaly type, and the output of the second-order power consumption anomaly detection model includes the power consumption anomaly analysis report.

7. The smart electricity management system according to claim 6, characterized in that: The types of power consumption anomalies include high load power consumption at night, instantaneous power demand peak, sustained low voltage, unplanned power outage, change in power consumption pattern, and loss of remote monitoring signal; The first-order power consumption anomaly detection engine is configured to: detecting high-load electricity consumption at night based on the electricity consumption; detecting an instantaneous power demand peak based on the power consumption; detecting a sustained low voltage based on the voltage value; detecting an unplanned power outage based on the voltage value; detecting a change in a power usage pattern based on the power usage; as well as A remote monitoring signal loss is detected based on the transmission status of the power usage parameter.

8. The smart electricity management system according to claim 6, characterized in that: The data acquisition device includes a data crawling engine configured to crawl data of the monitored power consumption area to obtain crawled data; The crawled data includes meteorological data of the power consumption area, social media data of the power consumption area, news data of the power consumption area, pre-marked high-power consumption areas in the power consumption area, wired communication data of the power consumption area, and historical power consumption data of the power management intranet; The input of the second-order power consumption anomaly detection model also includes the crawled data.

9. The smart electricity management system according to claim 8, characterized in that: The data processing server further includes a communication data processor, which is configured to: In the wired communication data, target communication data outputted by the wired port is separated based on the port type; Performing terminal quantity simulation based on the data type of the target communication data; In response to a difference between the number of terminals currently simulated and the number of terminals previously simulated being greater than a preset threshold, the input of the second-order power consumption anomaly detection model further includes the number of terminals currently simulated.

10. The smart electricity management system according to claim 8, characterized in that: The second-order power consumption anomaly detection model includes a data filter, which is configured to: The crawled data is screened, including: screening text data of the meteorological data, the social media data, the news data, the wired communication data, and the historical electricity usage data; screening the meteorological data, the social media data, the news data, and image data of pre-marked high-power-consumption areas within the power-consumption area; and The association between the text data and the image data is marked; wherein the association marking includes setting the same label for the associated text data and image data.

Images