Power failure early warning method and device of power distribution network, processor and electronic equipment

Abstract

The invention discloses a power failure early warning method and device for a power distribution network, a processor and electronic equipment. The method comprises the following steps: acquiring attribute information of a power distribution network in a normal power supply state at the current moment; inputting the attribute information into the target prediction model for power failure prediction to obtain a prediction result; and in response to the possibility degree exceeding a preset possibility degree, sending a target early warning signal and a target power failure maintenance strategy to the client, the target power failure maintenance strategy being used for representing a rule for maintaining the power distribution network in response to power failure of the power distribution network at a future moment. The technical problem of low accuracy of power failure judgment of the power distribution network is solved.

Description

Technical Field

[0001] The present invention relates to the field of electric power, and in particular to a power outage early warning method, device, processor and electronic equipment for a distribution network. Background Art

[0002] At present, if there is a power outage or power outage in the distribution network, it will have a serious impact on the production of all walks of life. Therefore, how to predict the power outage in the distribution network in advance so as to take timely measures to reduce the impact of the power outage on users is crucial in the power field.

[0003] However, in the prior art, the prediction of power outages in distribution networks mainly relies on manual experience and simple data analysis methods, which results in limitations in the judgment results of power outages in distribution networks, leading to the technical problem of low accuracy in judging power outages in distribution networks.

[0004] Currently, no effective solution has been proposed to the technical problem of low accuracy in judging power outages in the above-mentioned distribution network. Summary of the invention

[0005] Embodiments of the present invention provide a power outage warning method, device, processor and electronic device for a distribution network, so as to at least solve the technical problem of low accuracy in power outage judgment of the distribution network.

[0006] According to one aspect of an embodiment of the present invention, a power outage warning method for a distribution network is provided, the method comprising: obtaining attribute information of the distribution network in a normal power supply state at a current moment, wherein the attribute information is used to represent electrical information of the distribution network in a normal power supply state at a current moment, and status information of equipment in the distribution network in a normal power supply state at a current moment; inputting the attribute information into a target prediction model to perform power outage prediction and obtain a prediction result, wherein the target prediction model is obtained by training an initial prediction model based at least on historical attribute information, the historical attribute information is used to represent historical electrical information of the distribution network in a normal power supply state at a historical moment, and historical status information of equipment in the distribution network in a normal power supply state at a historical moment, and the prediction result is used to represent the possibility of a power outage in the distribution network at a future moment; in response to the possibility exceeding a preset possibility, sending a target warning signal and a target power outage maintenance strategy to a client, wherein the target power outage maintenance strategy is used to represent a rule for performing maintenance on the distribution network in response to a power outage in the distribution network at a future moment.

[0007] Optionally, the attribute information is input into the target prediction model to perform power outage prediction and obtain a prediction result, including: obtaining meteorological information of the environment in which the distribution network is located at the current moment; inputting the meteorological information and attribute information into the target prediction model to perform power outage prediction and obtain a prediction result.

[0008] Optionally, in response to the possibility degree exceeding a preset possibility degree, a target warning signal and a target power outage maintenance strategy are sent to the client, including: in response to the possibility degree exceeding a preset possibility degree, determining the severity of a power outage event occurring in the distribution network at a future moment; based on the severity, sending a target warning signal and a target power outage maintenance strategy to the client.

[0009] Optionally, based on the severity, sending a target warning signal and a target power outage maintenance strategy to the client, including: determining a target warning signal and a target power outage maintenance strategy corresponding to the severity; sending a target warning signal and a target power outage maintenance strategy corresponding to the severity to the client.

[0010] Optionally, the method also includes: inputting the attribute information into a target prediction model for strategy prediction to obtain a target power outage maintenance strategy, wherein the target prediction model is obtained by training an initial prediction model based at least on historical attribute information and historical power outage maintenance strategies, and the historical power outage maintenance strategies are used to represent rules for maintaining the distribution network in response to a power outage in the distribution network at a historical moment.

[0011] Optionally, the method further includes: adjusting the target prediction model; inputting the attribute information into the adjusted target prediction model to perform power outage prediction and obtain a prediction result.

[0012] According to one aspect of an embodiment of the present invention, a power outage warning device for a distribution network is provided, and the device may include: an acquisition unit, used to acquire attribute information of the distribution network in a normal power supply state at a current moment, wherein the attribute information is used to represent electrical information of the distribution network in a normal power supply state at a current moment, and status information of equipment in the distribution network in a normal power supply state at a current moment; a prediction unit, used to input the attribute information into a target prediction model to perform power outage prediction and obtain a prediction result, wherein the target prediction model is obtained by training an initial prediction model based on at least historical attribute information, the historical attribute information is used to represent historical electrical information of the distribution network in a normal power supply state at a historical moment, and historical status information of equipment in the distribution network in a normal power supply state at a historical moment, and the prediction result is used to represent the possibility of a power outage in the distribution network at a future moment; a sending unit, used to send a target warning signal and a target power outage maintenance strategy to a client in response to the possibility degree exceeding a preset possibility degree, wherein the target power outage maintenance strategy is used to represent a rule for repairing the distribution network in response to a power outage in the distribution network at a future moment.

[0013] According to another aspect of an embodiment of the present invention, a processor is further provided, wherein the processor is used to run a program, wherein when the program is run by the processor, the power outage warning method for a distribution network in an embodiment of the present invention is executed.

[0014] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein when the program is running, the power outage warning method for the distribution network in each embodiment of the present invention is executed.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the power outage warning method for the distribution network in the present invention.

[0016] According to another aspect of an embodiment of the present invention, a computer program product is further provided. The computer program product includes a computer program. When the computer program is executed by a processor, the power outage warning method for a distribution network in the embodiment of the present invention is implemented.

[0017] According to another aspect of an embodiment of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the power outage warning method for the distribution network in the embodiment of the present invention is implemented.

[0018] According to another aspect of an embodiment of the present invention, an embodiment of the present application further provides a computer program, which, when executed by a processor, implements the power outage warning method for a distribution network in the above-mentioned embodiment of the present invention.

[0019] In an embodiment of the present invention, when a power outage warning is performed on the distribution network, the attribute information of the distribution network in a normal power supply state at the current moment can be obtained. The obtained attribute information is input into the target prediction model for power outage prediction, and a prediction result can be obtained, that is, the possibility of a power outage in the distribution network at a future moment can be obtained. In response to the obtained possibility exceeding the preset possibility, a target warning signal and a target power outage maintenance strategy are sent to the client, thereby achieving the purpose of reducing the limitations of the judgment results of the power outage of the distribution network, thereby solving the technical problem of low accuracy of the power outage judgment of the distribution network, and then achieving the technical effect of improving the accuracy of the power outage judgment of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0021] Figure 1 is a flow chart of a power outage warning method for a distribution network according to an embodiment of the present invention;

[0022] Figure 2 is a flow chart of a power outage warning method for a distribution network based on artificial intelligence according to an embodiment of the present invention;

[0023] Figure 3 2 is a schematic diagram of a power outage warning device for a distribution network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only embodiments of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] According to an embodiment of the present invention, a power outage warning method for a distribution network is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] Figure 1 is a flow chart of a power outage warning method for a distribution network according to an embodiment of the present invention. The method may include the following steps:

[0028] Step S101, obtaining attribute information of the power distribution network in a normal power supply state at the current moment.

[0029] In the technical solution provided in the above step S101 of the present invention, the above attribute information can be used to represent the electrical information of the distribution network in a normal power supply state at the current moment, and the status information of the equipment in the distribution network in a normal power supply state at the current moment. The electrical information may include at least one of the following data: voltage, current, power, etc., and the status information may include at least one of the following data: the temperature of the equipment, the noise of the equipment, and the display of the indicator light of the equipment, etc., which are only given as examples and are not specifically limited.

[0030] In this embodiment, the attribute information of the distribution network in a normal power supply state at the current moment is obtained. Optionally, this embodiment monitors the working state of the distribution network in real time, and can obtain the attribute information of the distribution network in the working state at the current moment. Among them, the working state can be used to indicate whether the power supply of the distribution network is normal. The working state can be that the distribution network is in a normal power supply state, or it can be that the distribution network is in an abnormal power supply state. This is only an example for illustration and is not specifically limited.

[0031] In this embodiment, if the working state of the distribution network is a normal power supply state, the attribute information of the distribution network being in a normal power supply state at the current moment can be obtained. If the working state of the distribution network is an abnormal power supply state, the attribute information of the distribution network being in an abnormal power supply state at the current moment can be obtained.

[0032] Step S102: input the attribute information into the target prediction model to perform power outage prediction and obtain a prediction result.

[0033] In the technical solution provided in the above step S102 of the present invention, the above target prediction model can be obtained by training the initial prediction model based on at least historical attribute information. The initial prediction model can be a power outage prediction model constructed based on a convolutional neural network (CNN) and a long short-term memory network (LSTM), which is only used as an example and is not specifically limited.

[0034] In this embodiment, the above historical attribute information can be used to represent the historical electrical information of the distribution network in a normal power supply state at a historical moment, and the historical status information of the equipment in the distribution network in a normal power supply state at a historical moment. The historical electrical information may include at least one of the following data: historical voltage, historical current, and historical power, etc. The historical status information may include at least one of the following data: historical temperature of the equipment, historical noise of the equipment, and historical display of the indicator light of the equipment, etc., which are only given as examples and are not specifically limited.

[0035] In this embodiment, the above prediction results can be used to indicate the possibility of a power outage in the distribution network at a future moment. The above possibility can be expressed as a percentage, and a percentage of 0% to 20% can indicate that the possibility of a power outage in the distribution network at a future moment is low, a percentage of 20% to 40% can indicate that the possibility of a power outage in the distribution network at a future moment is low, a percentage of 40% to 60% can indicate that the possibility of a power outage in the distribution network at a future moment is medium, a percentage of 60% to 80% can indicate that the possibility of a power outage in the distribution network at a future moment is high, and a percentage of 80% to 100% can indicate that the possibility of a power outage in the distribution network at a future moment is extremely high, which is only used as an example and is not specifically limited.

[0036] In this embodiment, after obtaining the attribute information that the distribution network is in a normal power supply state at the current moment, the attribute information is input into the target prediction model to perform power outage prediction and obtain a prediction result. Optionally, this embodiment, based on obtaining the attribute information that the distribution network is in a normal power supply state at the current moment, inputs the obtained attribute information into the target prediction model to perform power outage prediction, and then outputs the obtained prediction result through the output layer of the target prediction model.

[0037] Step S103, in response to the possibility degree exceeding the preset possibility degree, sending a target warning signal and a target power outage maintenance strategy to the client.

[0038] In the technical solution provided in the above step S103 of the present invention, the above target power outage maintenance strategy can be used to represent a rule for performing maintenance on the distribution network in response to a power outage occurring in the distribution network at a future moment.

[0039] In this embodiment, the above-mentioned preset possibility degree can be adjusted according to the power supply data of the distribution network. For example, if there is no abnormal data in the power supply data of the distribution network in the previous quarter, the preset possibility degree set in the previous quarter can be adjusted upward, and if there is abnormal data in the power supply data of the distribution network in the previous quarter, the preset possibility degree set in the previous quarter can be adjusted downward.

[0040] In this embodiment, the above-mentioned target warning signal can be presented in at least one of the following forms: voice, text message, email, system pop-up window and i State Grid push, etc., which are only used as examples here and are not specifically limited.

[0041] In this embodiment, after the attribute information is input into the target prediction model to perform power outage prediction and obtain the prediction result, in response to the possibility degree exceeding the preset possibility degree, a target warning signal and a target power outage maintenance strategy are sent to the client. Optionally, based on the prediction result, this embodiment compares the possibility degree of power outage of the distribution network represented by the prediction result at a future moment with the preset possibility degree to obtain a comparison result. Among them, the comparison result can be used to represent the relationship between the possibility degree and the preset possibility degree. If the comparison result obtained is that the possibility degree exceeds the preset possibility degree, a target warning signal and a target power outage maintenance strategy are sent to the client.

[0042] In the above steps S101 to S103 of the present application, when a power outage warning is performed on the distribution network, the attribute information of the distribution network in a normal power supply state at the current moment can be obtained. The obtained attribute information is input into the target prediction model for power outage prediction, and a prediction result can be obtained, that is, the possibility of a power outage in the distribution network at a future moment can be obtained. In response to the obtained possibility degree exceeding the preset possibility degree, a target warning signal and a target power outage maintenance strategy are sent to the client, thereby achieving the purpose of reducing the limitations of the judgment results of the power outage of the distribution network, thereby solving the technical problem of low accuracy of the power outage judgment of the distribution network, and then achieving the technical effect of improving the accuracy of the power outage judgment of the distribution network.

[0043] The above method of this embodiment is further introduced below.

[0044] As an optional implementation method, step S102, inputting the attribute information into the target prediction model to perform power outage prediction and obtain a prediction result, including: obtaining the meteorological information of the environment in which the distribution network is located at the current moment; inputting the meteorological information and attribute information into the target prediction model to perform power outage prediction and obtain a prediction result.

[0045] In this embodiment, the above-mentioned meteorological information may include at least one of the following data: rainfall data, snowfall data, dust data, haze data, wind speed data, humidity data and temperature data, etc., which are only given as examples here and are not specifically limited.

[0046] In this embodiment, after obtaining the attribute information of the power distribution network being in a normal power supply state at the current moment, the meteorological information of the environment in which the power distribution network is located at the current moment is obtained. Optionally, this embodiment can obtain the meteorological information of the environment in which the power distribution network is located at the current moment from the meteorological center on the basis of obtaining the attribute information of the power distribution network being in a normal power supply state at the current moment. For example, rainfall data, snowfall data, dust data, haze data, wind speed data, humidity data, and temperature data can be obtained from the meteorological station, which are only used as examples and are not specifically limited.

[0047] In this embodiment, after obtaining the meteorological information of the environment where the distribution network is located at the current moment, the meteorological information and attribute information are input into the target prediction model to perform power outage prediction and obtain the prediction result. Optionally, this embodiment, based on obtaining the meteorological information of the environment where the distribution network is located at the current moment, inputs the obtained meteorological information and attribute information into the target prediction model to perform power outage prediction, and then outputs the obtained prediction result through the output layer of the target prediction model.

[0048] As an optional implementation method, in response to the possibility degree exceeding the preset possibility degree, a target warning signal and a target power outage maintenance strategy are sent to the client, including: in response to the possibility degree exceeding the preset possibility degree, determining the severity of the power outage event of the distribution network occurring at a future moment; based on the severity, sending a target warning signal and a target power outage maintenance strategy to the client.

[0049] In this embodiment, after the attribute information is input into the target prediction model to perform power outage prediction and obtain the prediction result, in response to the possibility degree exceeding the preset possibility degree, the severity of the power outage event of the distribution network at a future moment is determined. Optionally, based on the prediction result, this embodiment compares the possibility degree of the distribution network at a future moment represented by the prediction result to the preset possibility degree, and obtains a comparison result. If the comparison result obtained is that the possibility degree exceeds the preset possibility degree, the severity of the power outage event of the distribution network at a future moment can be determined.

[0050] In this embodiment, in response to the possibility degree exceeding the preset possibility degree, after determining the severity of the power outage event of the power distribution network at a future moment, a target warning signal and a target power outage maintenance strategy are sent to the client based on the severity. Optionally, this embodiment can send a target warning signal and a target power outage maintenance strategy to the client based on determining the severity of the power outage event of the power distribution network at a future moment.

[0051] As an optional implementation method, based on the severity, a target warning signal and a target power outage maintenance strategy are sent to the client, including: determining a target warning signal and a target power outage maintenance strategy corresponding to the severity; sending a target warning signal and a target power outage maintenance strategy corresponding to the severity to the client.

[0052] In this embodiment, in response to the possibility degree exceeding the preset possibility degree, after determining the severity of the power outage event of the power outage occurring in the distribution network at a future moment, a target warning signal and a target power outage maintenance strategy corresponding to the severity are determined. Optionally, this embodiment can determine the target warning signal and a target power outage maintenance strategy corresponding to the severity based on the determination of the severity of the power outage event of the power outage occurring in the distribution network at a future moment. For example, if the determined severity is level one, the target warning signal and the target power outage maintenance strategy corresponding to the level one severity are determined; if the determined severity is level two, the target warning signal and the target power outage maintenance strategy corresponding to the level two severity are determined. This is merely an example and is not specifically limited here.

[0053] In this embodiment, after determining the target warning signal and the target power outage maintenance strategy corresponding to the severity, the target warning signal and the target power outage maintenance strategy corresponding to the severity are sent to the client. Optionally, this embodiment sends the target warning signal and the target power outage maintenance strategy corresponding to the severity to the client on the basis of determining the target warning signal and the target power outage maintenance strategy corresponding to the severity, and displays the target warning signal and the target power outage maintenance strategy on the display interface of the client. The display interface may be a human-computer interaction interface displayed on a display screen.

[0054] As an optional implementation manner, the method further includes: inputting the attribute information into a target prediction model to perform strategy prediction to obtain a target power outage maintenance strategy.

[0055] In this embodiment, the target prediction model may be obtained by training an initial prediction model based at least on historical attribute information and historical power outage maintenance strategies.

[0056] In this embodiment, the above historical power outage maintenance strategy can be used to represent a rule for performing maintenance on the distribution network in response to a power outage occurring in the distribution network at a historical moment.

[0057] In this embodiment, the attribute information is input into the target prediction model for strategy prediction to obtain the target power outage maintenance strategy. Optionally, this embodiment inputs the acquired meteorological information and attribute information into the target prediction model for strategy prediction to obtain the target power outage maintenance strategy. The target power outage maintenance strategy can be output through the output layer of the target prediction model.

[0058] As an optional implementation manner, the method further includes: adjusting the target prediction model; inputting the attribute information into the adjusted target prediction model to perform power outage prediction and obtain a prediction result.

[0059] In this embodiment, the target prediction model is adjusted. Optionally, at least the loss parameter and convergence degree of the target prediction model are adjusted, thereby completing the adjustment of the target prediction model.

[0060] In this embodiment, after adjusting the target prediction model, the attribute information is input into the adjusted target prediction model to perform power outage prediction and obtain a prediction result. Optionally, based on the adjusted target prediction model, this embodiment inputs the acquired meteorological information and attribute information into the adjusted target prediction model to perform power outage prediction, and then outputs the obtained prediction result through the output layer of the adjusted target prediction model.

[0061] In an embodiment of the present invention, when a power outage warning is performed on the distribution network, the attribute information of the distribution network in a normal power supply state at the current moment can be obtained. The obtained attribute information is input into the target prediction model for power outage prediction, and a prediction result can be obtained, that is, the possibility of a power outage in the distribution network at a future moment can be obtained. In response to the obtained possibility exceeding the preset possibility, a target warning signal and a target power outage maintenance strategy are sent to the client, thereby achieving the purpose of reducing the limitations of the judgment results of the power outage of the distribution network, thereby solving the technical problem of low accuracy of the power outage judgment of the distribution network, and then achieving the technical effect of improving the accuracy of the power outage judgment of the distribution network.

[0062] The technical solution of the embodiment of the present invention is illustrated below in conjunction with preferred implementation modes.

[0063] At present, if there is a power outage or power outage in the distribution network, it will have a serious impact on the production of all walks of life. Therefore, how to predict the power outage in the distribution network in advance so as to take timely measures to reduce the impact of the power outage on users is crucial in the power field.

[0064] However, in the prior art, the prediction of power outages in distribution networks mainly relies on manual experience and simple data analysis methods, which results in limitations in the judgment results of power outages in distribution networks, leading to the technical problem of low accuracy in judging power outages in distribution networks.

[0065] In order to solve the above technical problems, an embodiment of the present invention proposes a power outage warning method for a distribution network, which obtains attribute information that the distribution network has not experienced a power outage at the current moment, and uses a target prediction model to perform power outage prediction on the acquired attribute information to obtain a prediction result, as well as send a target warning signal and a target power outage maintenance strategy to the client, thereby achieving the purpose of reducing the limitations of the judgment results of the power outage in the distribution network, thereby solving the technical problem of low accuracy of the power outage judgment in the distribution network, and further achieving the technical effect of improving the accuracy of the power outage judgment in the distribution network.

[0066] In this embodiment, through the power outage warning method of the distribution network based on artificial intelligence, the target prediction model can be used to predict the power outage of the acquired attribute information, thereby obtaining the prediction result, and sending the target warning signal and the target power outage maintenance strategy to the client. For example, Figure 2 is a flow chart of a power outage warning method for a distribution network based on artificial intelligence according to an embodiment of the present invention, such as Figure 2 As shown, the method may include the following steps:

[0067] Step S201, collecting and integrating data.

[0068] In the technical solution provided in the above step S201 of the present invention, based on the existing data sources and combined with the demand for predicting abnormal power outages in the distribution network, the following system data are integrated:

[0069] Data 1: Data from the enterprise-level real-time measurement center. This data may include: operation data of equipment such as busbars, switches, circuit breakers, and transformers. The above operation data may include: real-time data of electrical parameters such as voltage, current, and power;

[0070] Data 2: Data center data. Data center data can include: all historical operation data under the operation status of the power grid;

[0071] Data 3: Data from the meteorological center. The data from the meteorological center may include: numerical weather, radar, precipitation, lightning, strong winds, etc.;

[0072] Data 4: Power grid resource business middle platform data. Among them, the power grid resource business middle platform data can include: maintenance plan, emergency repair information, equipment test records, power grid topology information and equipment ledger information, etc.;

[0073] Data 5: The data of the new generation equipment asset management system (PMS3.0) can include: all the tests, maintenance, defects and hidden dangers of the equipment from the time of its entry to its retirement;

[0074] Data 6: planned power outage information and business expansion registration information. The above information can be used to predict the impact of load changes on the power grid;

[0075] Data seven: The video measurement point information in a power grid map may include: video monitoring data of equipment inside and outside the substation, transmission towers, distribution station rooms, etc.

[0076] After collecting and integrating the data, the process proceeds to step S202 to monitor and analyze the following data: electrical parameters, equipment status, meteorological and environmental factors.

[0077] In the technical solution provided in the above step S202 of the present invention, monitoring and analyzing electrical parameters can be achieved in the following ways:

[0078] Method 1: Determine whether the voltage fluctuation has intensified: monitor voltage changes and record the frequency and amplitude of voltage increases and decreases. Compare with the normal fluctuation range (for example, ±5% of the rated voltage), combine the data of the enterprise-level real-time measurement center and the topological information of the power grid, and analyze the impact of voltage fluctuations on related equipment and areas. At the same time, compare with the measured data during normal operation, including the average and peak values ​​of historical operation data. For example, if the voltage fluctuation frequency exceeds 3 times per minute, and the fluctuation amplitude exceeds ±10% of the rated voltage, and there is a significant change compared with the voltage fluctuation during normal operation, and the comparison with the average and peak values ​​of historical operation data exceeds the normal range, it is considered that the voltage fluctuation has intensified. The values ​​here are only used as examples and are not specifically limited. At this time, the causes of the intensified voltage fluctuations can be further analyzed, such as faults in the system, sudden changes in load, or unstable power supply. By viewing the topological information of the power grid, the affected equipment and areas can be determined, and combined with the video measurement point information and the analysis results of the artificial intelligence platform, observe whether there are any abnormal phenomena in the operation of related equipment, such as discharge, sparks, etc.;

[0079] Method 2, determine whether the voltage is gradually decreasing: continuously monitor the voltage value and observe the trend and amplitude of the voltage drop. Combined with the data from the enterprise-level real-time measurement center, analyze the reasons for the voltage drop, such as excessive load, power failure, or increased line loss. At the same time, compare it with the voltage data during normal operation, including comparing it with the average value of historical operation data. If the voltage drop rate exceeds 1% per minute and lasts for more than 5 minutes, and there is a significant decrease compared to the voltage level during normal operation, and the comparison with the average value of historical operation data exceeds the normal range, it is considered that the voltage is gradually decreasing. The values ​​here are only used as examples and are not specifically limited. In this case, it is necessary to check the load situation in time to see if any large equipment is suddenly started or overloaded. At the same time, check the power supply equipment and lines to find possible fault points. Use the data from the power grid resource business middle-office operation management center to understand the operating status and maintenance records of related equipment in order to quickly locate the problem;

[0080] Method three, determine whether the three-phase voltage is unbalanced: measure the three-phase voltage and calculate the imbalance of the three-phase voltage. Compare with the imbalance allowed by the standard (for example, not more than 5%). In the three-phase discrimination of A, B, and C, specifically analyze the difference between the three-phase voltages of A, B, and C to determine the phase difference of the imbalance. Combined with the data of the enterprise-level real-time measurement center, the three-phase imbalance is judged. At the same time, it is compared with the three-phase voltage data during normal operation, including the average and peak values ​​of historical operation data. If the three-phase voltage imbalance exceeds 8%, and there is a significant change compared with the balance of the three-phase voltage during normal operation, the unbalanced phase is determined, and the comparison with the average and peak values ​​of the historical operation data exceeds the normal range, it is considered that the three-phase voltage is unbalanced. The values ​​here are only used as examples and are not specifically limited. Optionally, the three-phase voltage imbalance may be caused by uneven load distribution, line faults, or transformer problems. By analyzing the topological information of the power grid and the ledger information of the equipment, the equipment and area causing the three-phase imbalance can be determined. Combining the video measurement point information with the analysis results of the artificial intelligence platform, it is possible to observe whether the operation of related equipment has abnormal discharge, abnormal noise, etc.

[0081] Method 4: Determine whether the current increases abnormally: monitor the current value, compare it with the rated current of the line, and observe whether the current increases suddenly. Combined with the data of the enterprise-level real-time measurement center, analyze the reasons for the abnormal increase in current, such as short circuit, ground fault or load overload. At the same time, compare it with the current data during normal operation, including the average and peak values ​​of historical operation data. If the current increases instantly by more than 20% of the rated current of the line, and is significantly increased compared with the current level during normal operation, and the average and peak values ​​of historical operation data are compared beyond the normal range, it is considered that the current increases abnormally. The values ​​here are only used as examples and are not specifically limited. Optionally, the abnormal increase in current may cause serious consequences such as overheating and damage of the equipment, or even fire. When an abnormal increase in current is found, the cause should be immediately found, and the operating status of the relevant equipment should be checked for short circuit, grounding and other faults. At the same time, pay attention to whether the load situation is overloaded. Using the data of the power grid resource business middle-end operation management center, the rated capacity and actual load of the equipment can be determined so that timely measures can be taken to avoid accidents;

[0082] Method five, determine current fluctuations: monitor the changes in current and record the frequency and amplitude of current fluctuations. Combined with the data from the enterprise-level real-time measurement center, determine the cause of current fluctuations, such as faults in the system or load changes. At the same time, compare with the current fluctuations during normal operation, including comparison with the average and peak values ​​of historical operating data. If the frequency of current fluctuations exceeds 5 times per minute, and the fluctuation amplitude exceeds ±15% of the rated current, and there is a significant change compared with the current fluctuations during normal operation, and the comparison with the average and peak values ​​of historical operating data exceeds the normal range, then the current is considered to be fluctuating. The values ​​here are only examples and are not specifically limited. Optionally, current fluctuations may affect the normal operation of the equipment, resulting in shortened equipment life or failures. By analyzing the work plan and maintenance information, it can be determined whether there are any operations or maintenance activities of related equipment that may cause current fluctuations. At the same time, combined with the video measurement point information and the analysis results of the artificial intelligence platform, it can be observed whether the operation of the related equipment has abnormal vibration, noise and other phenomena;

[0083] Method 6: Determine whether zero-sequence current occurs: Measure the zero-sequence current. When the zero-sequence current exceeds the set threshold (usually 10% of the rated current), it is determined that there is a ground fault. Combined with the data of the enterprise-level real-time measurement center, the location of the ground fault can be determined. At the same time, it is compared with the zero-sequence current data during normal operation, including the average and peak values ​​of the historical operation data. If the zero-sequence current exceeds 15% of the rated current, and is significantly increased compared with the zero-sequence current level during normal operation, and the comparison with the average and peak values ​​of the historical operation data exceeds the normal range, it is considered that the zero-sequence current occurs. The values ​​here are only used as examples and are not specifically limited. Optionally, the ground fault can cause the leakage protection device to operate and affect the power supply reliability. When the zero-sequence current is found, the ground fault point should be quickly found and the fault should be eliminated in time. Using the topological information of the power grid and the ledger information of the equipment, the possible ground fault path and related equipment can be determined. Combined with the video measurement point information and the analysis results of the artificial intelligence platform, it can be observed whether the appearance of the relevant equipment is abnormal, such as discharge, smoking, etc.

[0084] In the technical solution provided in the above step S202 of the present invention, monitoring and analyzing the status of the device can be achieved by the following methods: determining whether the device is hot, determining whether the noise of the device is abnormal, and determining whether the indicator light of the device is abnormal.

[0085] Among them, judging whether the equipment is hot can be achieved by performing the following steps: use an infrared thermometer or other equipment to measure the temperature of the equipment and compare it with the normal operating temperature range (for example, 80% of the rated temperature of the equipment). Combined with the data of the power grid resource business middle-office operation management center, understand the operating status of the equipment, such as equipment overload, internal fault or poor contact. At the same time, compare with the equipment temperature data during normal operation, including comparison with the average and peak values ​​of historical operating data. If the equipment temperature exceeds 20% of the normal operating temperature range, and is significantly higher than the equipment temperature during normal operation, and is compared with the average and peak values ​​of historical operating data and exceeds the normal range, it is considered that the equipment is hot. The values ​​here are only for example and are not specifically limited.

[0086] It should be noted that the heating of the equipment may be caused by overload, internal fault or poor heat dissipation. When the equipment is found to be heating, the load of the equipment should be checked in time to see if there is any overload. At the same time, check the internal structure of the equipment to find possible fault points. Using the test records and maintenance information of the equipment, the historical operation of the equipment can be determined to better determine the cause of the heating of the equipment.

[0087] Determining whether the noise of the equipment is abnormal can be achieved by performing the following steps: Detect the noise of the equipment through auditory or acoustic monitoring equipment, and compare it with the normal operating noise (for example, 60 decibels). Combined with the data from the power grid resource business middle-office operation management center, determine the cause of the abnormal equipment noise, such as internal equipment failure, looseness or overload. At the same time, compare it with the equipment noise data during normal operation, including comparing it with the average and peak values ​​of historical operating data. If the equipment noise exceeds the normal operating noise by 10 decibels, and there is a significant change compared with the equipment noise during normal operation, and the comparison with the average and peak values ​​of historical operating data exceeds the normal range, the equipment noise is considered abnormal. The values ​​here are only for example and are not specifically limited.

[0088] It should be noted that abnormal equipment noise may be a precursor to equipment failure and requires timely inspection and maintenance. By analyzing the equipment's test records and maintenance information, we can understand the equipment's historical operation and find out the possible causes of abnormal noise. At the same time, combined with the video measurement point information and the analysis results of the artificial intelligence platform, we can observe whether the operation of related equipment has abnormal vibration, discharge and other phenomena.

[0089] Determining whether the indicator light of the equipment is abnormal can be achieved by performing the following steps: Observe the indication status of the equipment indicator light and compare it with the normal indication status. Combined with the data of the power grid resource business middle-office operation management center, determine the cause of the abnormal equipment indicator light, such as equipment failure, power supply problem or communication failure. At the same time, compare it with the normal indication status of the indicator light of the equipment, including comparing it with the average value and peak value of historical operation data. If the indication status of the indicator light of the equipment does not match the normal indication status, for example, the flashing frequency is abnormal, the color changes are abnormal, etc., and there is a significant change compared with the normal indication status of the indicator light of the equipment, and it is compared with the average value and peak value of the historical operation data and exceeds the normal range, then the equipment indicator light is considered abnormal.

[0090] It should be noted that the abnormal indication state of the indicator light of the equipment may indicate that the equipment is faulty or in an abnormal working state. When the indicator light of the equipment is found to be abnormal, the operating state of the equipment should be checked in time to find the cause of the fault. Using the topological information of the power grid and the equipment ledger information, the impact of the abnormal indicator light of the equipment on related equipment and areas can be determined.

[0091] In the technical solution provided in the above step S202 of the present invention, the monitoring and analysis of meteorological and environmental factors can be achieved in the following ways: determining whether it is severe weather and determining whether there is external force damage.

[0092] Determining whether it is severe weather can be achieved by executing the following steps: Based on the data from the meteorological center, determine whether there is severe weather such as heavy rain, strong winds, lightning, etc. Combined with the data from the power grid resource business middle-office operation management center, determine the impact of severe weather on power grid equipment, such as line grounding faults, tower collapse, or substation flooding. If you encounter severe weather such as heavy rain (for example, rainfall exceeds 50 mm / hour), strong winds (for example, wind speed exceeds level 10), lightning, etc., and the enterprise-level meteorological data service center issues relevant warning information, and the power grid resource business middle-office operation management center shows that the power grid equipment is affected by severe weather, then it is considered that there is severe weather. The values ​​here are only for example and are not specifically limited.

[0093] It should be noted that in severe weather conditions, inspections and monitoring of power grid equipment should be strengthened to promptly detect and handle possible faults. Using the video measurement point information in the power grid map and the analysis results of the artificial intelligence platform, it is possible to observe in real time the operation of related equipment such as substations, transmission towers, and distribution stations in severe weather, and whether there are signs of damage, such as tilted towers and broken wires.

[0094] Determining whether there is external force damage can be achieved by performing the following steps: timely discover situations that may cause external force damage, such as construction activities, traffic accidents, or fallen trees, through inspections and monitoring. Combined with the data from the power grid resource business middle-office operation management center, determine the impact of external force damage on power grid equipment. If construction activities, traffic accidents, or fallen trees are found to have damaged power facilities, and the power grid resource business middle-office operation management center shows that the power grid equipment is affected by external force damage, it is considered that there is external force damage.

[0095] It should be noted that when external force damage is discovered, measures should be taken immediately to repair the damaged power facilities to ensure the reliability of power supply. The topological information of the power grid and the equipment ledger information are used to determine the specific impact of external force damage on the operation of the power grid and formulate corresponding emergency repair plans. Combined with the video measurement point information and the analysis results of the artificial intelligence platform, the location and situation of external force damage can be discovered and recorded in a timely manner to provide a basis for emergency repair work.

[0096] After monitoring and analyzing the following data: electrical parameters, equipment status, meteorological and environmental factors, proceed to step S203 to analyze historical data and load trends.

[0097] In the technical solution provided in the above step S203 of the present invention, analyzing historical data may be analyzing historical power outage records. Among them, analyzing historical power outage records can be achieved by executing the following steps: By analyzing historical power outage data, the law and related factors of power outages can be determined. Combined with the data of the PMS3.0 technical supervision module, the operating status of the power grid equipment can be evaluated, wherein the data of the PMS3.0 technical supervision module may include: all tests, maintenance, defects, hidden dangers and other information of the equipment from its entry to retirement. If the historical power outage data shows that the power outage frequency exceeds once a month under specific conditions (for example, a specific season, weather, etc.), and the PMS3.0 technical supervision module shows that the power grid equipment has potential faults or aging problems, it is considered that there is a historical power outage hidden danger. The numerical values ​​here are only for example and are not specifically limited.

[0098] It should be noted that by analyzing historical power outage records, the weak links of power grid equipment can be identified and preventive and maintenance measures can be taken in advance. At the same time, combined with the equipment's test, maintenance and defect information, a comprehensive assessment of the equipment's operating status can be conducted to identify the equipment and areas that need to be focused on.

[0099] In this embodiment, analyzing the load trend can be achieved by performing the following steps: monitoring load data, drawing a load trend graph, and comparing with the rated capacity of the equipment. Combined with the planned power outage information and the business expansion registration information, the impact of load changes on the power grid is predicted. If the load continues to grow and exceeds 80% of the rated capacity of the equipment, and the planned power outage information shows that there is no power outage plan in the near future, and the business expansion registration information shows that new power loads are connected, it is considered that there is a risk of load overload. The values ​​here are only for example and are not specifically limited.

[0100] It should be noted that in load trend analysis, the operation mode of the power grid and the configuration of equipment should be adjusted in a timely manner according to the growth rate and trend of the load. At the same time, the topological information of the power grid and the equipment ledger information should be combined to evaluate the specific impact of load growth on power grid equipment and determine the equipment and areas that need to be upgraded.

[0101] After analyzing the historical data and load trends, the process proceeds to step S204 to pre-process the collected and integrated data.

[0102] In the technical solution provided in the above step S204 of the present invention, the obtained distribution network operation, meteorological, environmental and other data are preprocessed to remove abnormal data and noise. Among them, the above preprocessing may include: data cleaning, by setting a scientific and reasonable data range and strict screening rules, to remove obvious errors, data points beyond the normal range and unreasonable data points. At the same time, statistical methods, such as mean, median, standard deviation, etc., are used to conduct in-depth analysis of the data and remove outliers to ensure the reliability of the data. Then the data is normalized to convert data of different dimensions into a unified scale. For example, data such as voltage, current, and power can be normalized so that their value range is between [0, 1], thereby effectively avoiding the adverse effects of data of different dimensions on model training, and improving the convergence speed and accuracy of the model. Then the normalized data is reduced in dimension, for example, by using methods such as principal component analysis to reduce the dimension of the data and the complexity of calculation, while retaining key information.

[0103] For example, for voltage data, if it is detected that the voltage value of a certain node exceeds a preset normal voltage range, or a sudden change occurs, the data point can be determined to be abnormal data and removed.

[0104] After preprocessing the collected and integrated data, the process proceeds to step S205 to perform power outage prediction and early warning using the established target prediction model.

[0105] In the technical solution provided in the above step S205 of the present invention, the CNN+LSTM algorithm is used to analyze and train the preprocessed distribution network operation data, thereby constructing an initial prediction model. The initial prediction model constructed by training the multi-dimensional historical data combination is combined with the judgment rules in the above step S202 to assist in learning the initial prediction model, and the target prediction model can be obtained. By constructing a multi-layer neural network, the high-level features of the data are gradually extracted to achieve accurate prediction of power outages for distribution network users. During the training process, the back propagation algorithm is used to adjust the network parameters and continuously optimize the performance of the model.

[0106] In this embodiment, based on the analysis results of multi-source data, the target prediction model can be used to determine the possibility of power outages in the distribution network. If it is found that the electrical parameters are abnormal, the equipment status is abnormal, the meteorological and environmental factors are unfavorable, or the historical data and trends show that there is a hidden danger of power outages, and these factors are interrelated and may lead to the occurrence of power outages, a target warning signal will be issued in time. Among them, the target warning signal can be sent to relevant personnel through SMS, email, system pop-up window, i State Grid push, etc., to remind relevant personnel and automatically provide optional measures, such as strengthening equipment inspections, adjusting load distribution, and repairing faulty equipment. At the same time, according to the results of power outage prediction, corresponding emergency plans can be formulated to ensure rapid response when a power outage occurs, reducing power outage time and losses.

[0107] After preprocessing the collected and integrated data, proceed to step S206 to regularly update and optimize the target prediction model.

[0108] In the technical solution provided in the above step S206 of the present invention, the target prediction model is regularly updated and optimized to improve the accuracy of power outage prediction. With the changes in the distribution network operation, the commissioning of new equipment and the changes in environmental factors, the performance of the model may decline. Therefore, the abnormal data is collected regularly, and the model is retrained and optimized so that it can adapt to new situations and maintain good prediction performance. The online learning method is used to continuously update the model parameters so that it can adapt to changes in the distribution network operation status in real time. At the same time, regular evaluation and verification of the model can ensure its accuracy and reliability. If problems are found in the model, adjustments and optimizations can be made in a timely manner to improve the performance of the model.

[0109] In summary, an artificial intelligence-based power outage warning method for distribution networks can be implemented by establishing a data acquisition and integration system, developing data analysis and processing algorithms, and establishing a power outage prediction and warning system.

[0110] In this embodiment, the establishment of the data acquisition and integration system can be achieved by executing the following steps: developing interfaces and data transmission channels, thereby achieving the purpose of real-time acquisition and transmission of multi-source data such as enterprise-level real-time measurement centers, meteorological centers, power grid resource business centers, PMS3.0, and a power grid map. On the basis of developing interfaces and data transmission channels, a data storage and management system is established to store and manage the collected data, thereby achieving the purpose of ensuring the security and reliability of the data. Among them, the above storage can adopt distributed storage and cloud computing technology. After developing the data cleaning and preprocessing module, the collected data is cleaned and preprocessed to remove noise data and abnormal data, thereby achieving the purpose of ensuring the quality and accuracy of the data.

[0111] In this embodiment, the above-mentioned development of data analysis and processing algorithms can be achieved by executing the following steps: Based on multi-source data, develop electrical parameter monitoring and analysis algorithms, equipment status monitoring and analysis algorithms, meteorological and environmental factors monitoring and analysis algorithms, historical data and trend analysis algorithms, etc. Use machine learning, deep learning, and data mining technologies to improve the accuracy and efficiency of data analysis. Use an artificial intelligence platform to identify and analyze abnormalities in video measurement point information to improve the accuracy and efficiency of monitoring. Develop an image recognition algorithm based on deep learning to achieve real-time monitoring and abnormality identification of equipment inside and outside substations, transmission towers, distribution substations, etc.

[0112] In this embodiment, the above-mentioned establishment of a power outage prediction and warning system can be achieved by executing the following steps: According to the results of the data analysis and processing algorithm, a target prediction model is established to achieve accurate prediction of power outages in the distribution network. The possibility and time of power outages can be predicted by using a target prediction model based on a neural network and combining the analysis results of multi-source data. When it is predicted that a power outage may occur, a target warning signal is issued in a timely manner, and relevant personnel are notified by SMS, email, system pop-up window, i State Grid push, etc. At the same time, the target warning information corresponding to the target warning signal is sent to the mobile terminal of the power grid dispatching center and the operation and maintenance personnel to ensure that the operation and maintenance personnel take timely measures to repair the power distribution network that has been out of power. After the emergency plan management system is established, a corresponding emergency plan can be formulated according to the prediction results. The emergency plan may include: fault handling process, personnel division of labor and material allocation, etc., to ensure that a rapid response can be made when a power outage occurs, reducing power outage time and losses.

[0113] In this embodiment, attribute information that the distribution network has not experienced a power outage at the current moment is obtained, and a target prediction model is used to predict a power outage for the obtained attribute information to obtain a prediction result, and a target warning signal and a target power outage maintenance strategy are sent to the client, thereby achieving the purpose of reducing the limitations of the judgment results of the power outage in the distribution network, thereby solving the technical problem of low accuracy of the power outage judgment in the distribution network, and further achieving the technical effect of improving the accuracy of the power outage judgment in the distribution network.

[0114] According to an embodiment of the present invention, a power outage warning device for a distribution network is also provided. It should be noted that the power outage warning device for a distribution network can be used to execute a power outage warning method for a distribution network in an embodiment.

[0115] Figure 3 Schematic diagram of a power outage warning device for a distribution network according to an embodiment of the present invention. Figure 3 As shown, the power outage warning device 300 of the distribution network may include: an acquisition unit 301 , a prediction unit 302 and a sending unit 303 .

[0116] The acquisition unit 301 is used to obtain attribute information of the distribution network in a normal power supply state at the current moment, wherein the attribute information is used to represent the electrical information of the distribution network in a normal power supply state at the current moment, and the status information of the equipment in the distribution network in a normal power supply state at the current moment.

[0117] The prediction unit 302 is used to input the attribute information into the target prediction model to perform power outage prediction and obtain a prediction result, wherein the target prediction model is obtained by training an initial prediction model based on at least historical attribute information, and the historical attribute information is used to represent the historical electrical information of the distribution network in a normal power supply state at a historical moment, and the historical status information of the equipment in the distribution network that was in a normal power supply state at a historical moment, and the prediction result is used to represent the possibility of a power outage in the distribution network at a future moment.

[0118] The sending unit 303 is used to send a target warning signal and a target power outage maintenance strategy to the client in response to the possibility degree exceeding a preset possibility degree, wherein the target power outage maintenance strategy is used to represent the rules for maintaining the distribution network in response to a power outage in the distribution network at a future moment.

[0119] Optionally, the prediction unit 302 may include: an acquisition module for acquiring meteorological information of the environment in which the distribution network is located at the current moment; a prediction module for inputting meteorological information and attribute information into a target prediction model to perform power outage prediction and obtain a prediction result.

[0120] Optionally, the sending unit 303 may include: a determination module, used to determine the severity of a power outage event occurring in the distribution network at a future moment in response to the possibility degree exceeding a preset possibility degree; and a sending module, used to send a target warning signal and a target power outage maintenance strategy to the client based on the severity.

[0121] Optionally, the sending module may include: a determination submodule for determining a target warning signal and a target power outage maintenance strategy corresponding to the severity; and a sending submodule for sending a target warning signal and a target power outage maintenance strategy corresponding to the severity to the client.

[0122] Optionally, the power outage warning device 300 of the distribution network may also include: a first prediction unit, used to input attribute information into a target prediction model for strategy prediction to obtain a target power outage maintenance strategy, wherein the target prediction model is obtained by training an initial prediction model based at least on historical attribute information and historical power outage maintenance strategies, and the historical power outage maintenance strategies are used to represent rules for maintaining the distribution network in response to a power outage in the distribution network at a historical moment.

[0123] Optionally, the power outage warning device 300 for the distribution network may further include: an adjustment unit, used to adjust the target prediction model; and a second prediction unit, used to input attribute information into the adjusted target prediction model to perform power outage prediction and obtain a prediction result.

[0124] In this embodiment, an acquisition unit is used to acquire attribute information of the distribution network in a normal power supply state at the current moment, wherein the attribute information is used to represent electrical information of the distribution network in a normal power supply state at the current moment, and status information of equipment in the distribution network in a normal power supply state at the current moment; a prediction unit is used to input the attribute information into a target prediction model to perform power outage prediction and obtain a prediction result, wherein the target prediction model is obtained by training an initial prediction model based on at least historical attribute information, and the historical attribute information is used to represent historical electrical information of the distribution network in a normal power supply state at historical moments, and status information of equipment in the distribution network in a normal power supply state at historical moments. The historical status information of the equipment in the distribution network under the normal power supply state, and the prediction result is used to indicate the possibility degree of power outage of the distribution network at a future moment; the sending unit is used to send the target warning signal and the target power outage maintenance strategy to the client in response to the possibility degree exceeding the preset possibility degree, wherein the target power outage maintenance strategy is used to indicate the rule for maintenance of the distribution network in response to power outage of the distribution network at a future moment, thereby achieving the purpose of reducing the limitation of the judgment result of the power outage of the distribution network, thereby solving the technical problem of low accuracy of the power outage judgment of the distribution network, and further achieving the technical effect of improving the accuracy of the power outage judgment of the distribution network.

[0125] According to an embodiment of the present invention, a processor is further provided, the processor being used to run a program, wherein when the program is run by the processor, the power outage warning method for the distribution network in the embodiment is executed.

[0126] According to an embodiment of the present invention, there is also provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the power outage warning method for the distribution network in the embodiment is executed when the program is running.

[0127] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the power outage warning method for the distribution network in the embodiment.

[0128] According to an embodiment of the present invention, a computer program product is further provided. The computer program product includes a computer program. When the computer program is executed by a processor, the power outage warning method for a distribution network in the embodiment is implemented.

[0129] According to an embodiment of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the power outage warning method for the distribution network in the embodiment is implemented.

[0130] According to an embodiment of the present invention, a computer program is further provided. When the computer program is executed by a processor, the power outage warning method for a distribution network in the embodiment is implemented.

[0131] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0132] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0133] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0135] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0136] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the relevant technology or the whole or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, referred to as Read-Only Memory), random access memory (RAM, referred to as Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0137] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A power outage warning method for a distribution network, characterized in that: include: Acquire attribute information of the distribution network in a normal power supply state at the current moment, wherein the attribute information is used to represent electrical information of the distribution network in the normal power supply state at the current moment, and status information of equipment in the distribution network in the normal power supply state at the current moment; Inputting the attribute information into a target prediction model to perform power outage prediction and obtain a prediction result, wherein the target prediction model is obtained by training an initial prediction model based at least on historical attribute information, the historical attribute information is used to represent historical electrical information of the distribution network in the normal power supply state at a historical moment, and historical status information of equipment in the distribution network in the normal power supply state at the historical moment, and the prediction result is used to represent the possibility of a power outage in the distribution network at a future moment; In response to the possibility degree exceeding a preset possibility degree, a target warning signal and a target power outage maintenance strategy are sent to the client, wherein the target power outage maintenance strategy is used to represent a rule for maintaining the distribution network in response to a power outage occurring in the distribution network at the future moment.

2. The method according to claim 1, characterized in that The attribute information is input into the target prediction model to perform power outage prediction, and a prediction result is obtained, including: Obtaining meteorological information of the environment in which the distribution network is located at the current moment; The meteorological information and the attribute information are input into the target prediction model to perform power outage prediction and obtain the prediction result.

3. The method according to claim 1, characterized in that In response to the possibility degree exceeding the preset possibility degree, sending a target early warning signal and a target power outage maintenance strategy to the client, including: In response to the possibility level exceeding the preset possibility level, determining the severity of a power outage event in which the power distribution network will experience a power outage at the future time; Based on the severity, the target warning signal and the target power outage maintenance strategy are sent to the client.

4. The method according to claim 3, characterized in that Based on the severity, sending the target warning signal and the target power outage maintenance strategy to the client includes: Determining the target warning signal and the target power outage maintenance strategy corresponding to the severity; The target warning signal and the target power outage maintenance strategy corresponding to the severity are sent to the client.

5. The method according to claim 1, characterized in that The method further comprises: The attribute information is input into the target prediction model for strategy prediction to obtain the target power outage maintenance strategy, wherein the target prediction model is obtained by training the initial prediction model based at least on the historical attribute information and the historical power outage maintenance strategy, and the historical power outage maintenance strategy is used to represent the rules for maintaining the distribution network in response to a power outage occurring in the distribution network at the historical moment.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Adjusting the target prediction model; The attribute information is input into the adjusted target prediction model to perform power outage prediction to obtain the prediction result.

7. A power outage warning device for a distribution network, characterized in that: include: An acquisition unit, used to acquire attribute information of the distribution network in a normal power supply state at the current moment, wherein the attribute information is used to represent electrical information of the distribution network in the normal power supply state at the current moment, and status information of equipment in the distribution network in the normal power supply state at the current moment; A prediction unit, used for inputting the attribute information into a target prediction model to perform power outage prediction and obtain a prediction result, wherein the target prediction model is obtained by training an initial prediction model based on at least historical attribute information, the historical attribute information is used to represent historical electrical information of the distribution network in the normal power supply state at a historical moment, and historical status information of equipment in the distribution network in the normal power supply state at the historical moment, and the prediction result is used to represent the possibility of a power outage in the distribution network at a future moment; A sending unit is used to send a target warning signal and a target power outage maintenance strategy to a client in response to the possibility degree exceeding a preset possibility degree, wherein the target power outage maintenance strategy is used to represent the rules for maintaining the distribution network in response to a power outage in the distribution network at a future moment.

8. A processor, characterized in that: The processor is used to run a program, wherein the program, when run by the processor, executes the power outage warning method for the distribution network as described in any one of claims 1 to 6.

9. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein when the program is run, the power outage warning method for the distribution network described in any one of claims 1 to 6 is executed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the storage medium is located is controlled to execute the power outage warning method for the distribution network as described in any one of claims 1 to 6.

Images