Fault processing method and device and computer equipment

Abstract

The invention relates to a fault processing method and device and computer equipment. The method comprises the steps of determining a priority recovery sequence of each load according to the importance level of each load to a user in a fault area, obtaining a current scheduling strategy for power supply recovery of each load, and controlling power supply recovery of each load in the fault area according to the priority recovery sequence of each load and the current scheduling strategy of each load. By adopting the method, the priority recovery sequence of each load can be determined according to the importance level of each load to the user in the fault area, so that power utilization of the load with relatively high power supply sensitivity in the fault area can be preferentially recovered based on the priority recovery sequence of each load; and the load with relatively low sensitivity to power supply in the fault area recovers power utilization, so that the recovery effect can be improved when the power utilization of each load in the fault area is recovered.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a fault handling method, device and computer equipment. Background Art

[0002] As the operating scale of the distribution network system continues to expand, the operating failures of the distribution network system are also increasing.

[0003] In practical applications, in order to ensure that the distribution network system can meet the current power supply demand, the power supply to each load in the fault area can be restored accordingly.

[0004] However, in the related art, when restoring power to the loads in the fault area, there is a problem of poor restoration effect. Summary of the invention

[0005] Based on this, it is necessary to provide a fault handling method, device and computer equipment to address the above technical problems, which can improve the recovery effect when restoring power to each load in the fault area.

[0006] In a first aspect, an embodiment of the present application provides a fault handling method, the method comprising:

[0007] Determine the priority restoration sequence of each load based on the importance of each load to the user in the fault area;

[0008] Obtain the current scheduling strategy for restoring power to each load;

[0009] According to the priority restoration sequence of each load and the current dispatch strategy of each load, control is performed to restore power supply to each load in the fault area.

[0010] In one embodiment, according to the importance level of each load in the fault area to the user, determining the priority recovery sequence of each load includes:

[0011] Obtain the initial priority recovery sequence corresponding to each load in the fault area;

[0012] According to the importance level of each load, determine the measurement index value of each load for power supply;

[0013] According to the measurement index value of each load for power supply, the initial priority recovery sequence is adjusted to obtain the priority recovery sequence of each load.

[0014] In one embodiment, obtaining an initial priority recovery sequence corresponding to each load in a fault area includes:

[0015] According to the dependency relationship between the loads and / or the target load among the loads, a recovery sequence is assigned to each load to obtain an initial priority recovery sequence of each load; the target load includes at least one load with special recovery requirements.

[0016] In one embodiment, obtaining a current scheduling strategy for restoring power supply to each load includes:

[0017] Determine the initial dispatching strategy for each load based on the initial grid state and initial available resource information of each distribution network node and the power resource information required by each load;

[0018] If the initial grid state and initial available resource information of each distribution network node are changed, the initial dispatching strategy of each load is determined as the current dispatching strategy of each load.

[0019] In one embodiment, obtaining a current scheduling strategy for restoring power supply to each load includes:

[0020] If at least one of the initial grid state and the initial available resource information of each distribution network node changes, obtaining the current grid state and the current available resource information of each distribution network node;

[0021] The current dispatching strategy for each load is determined based on the current grid status and currently available resource information of each distribution network node, as well as the power resource information required by each load.

[0022] In one embodiment, the method further comprises:

[0023] Acquire auxiliary adjustment information; the auxiliary adjustment information includes at least one of renewable energy information and load balancing supply and demand information;

[0024] According to the auxiliary adjustment information, the current scheduling strategy of each load is adjusted to obtain the updated scheduling strategy of each load, and the updated scheduling strategy of each load is used as the current scheduling strategy of each load. The priority recovery sequence of each load and the current scheduling strategy of each load are executed to control the steps of restoring power supply to each load in the fault area.

[0025] In one embodiment, the current scheduling strategy includes an optimal restoration path and a restoration strategy; according to the priority restoration sequence of each load and the current scheduling strategy of each load, controlling the restoration of power supply to each load in the fault area includes:

[0026] Determine the target power source in the non-fault area that can supply power to each load according to the optimal recovery path of each load;

[0027] According to the priority recovery sequence of each load, the recovery strategy of each load is sent to different terminal devices in the distribution network system in turn, instructing different terminal devices to control and enable the corresponding target power supply to restore power supply to each load.

[0028] In one embodiment, the method further comprises:

[0029] If each target power source is insufficient to support normal operation of each load, determining at least one backup power source in a non-fault area;

[0030] According to the priority recovery sequence of each load, the recovery strategy of each load is sent to different terminal devices in the distribution network system in turn, instructing different terminal devices to control the activation of the corresponding backup power supply to restore power supply to each load.

[0031] In one embodiment, the method further comprises:

[0032] For any distribution network node, if the power usage data of the distribution network node is abnormal, the distribution network node is determined to be a faulty node;

[0033] Determine the fault area based on the fault node and fault location;

[0034] At least one power supply in the fault area is controlled to be shut down to achieve fault isolation.

[0035] In one embodiment, the method further comprises:

[0036] Obtain the root cause information of the fault in the fault area;

[0037] Develop a fault repair strategy based on the root cause information, and repair the fault according to the repair strategy.

[0038] In a second aspect, an embodiment of the present application provides a fault handling device, the device comprising:

[0039] A sequence determination module is used to determine the priority restoration sequence of each load in the fault area according to the importance level of each load to the user;

[0040] An acquisition module is used to obtain a current scheduling strategy for restoring power supply to each load;

[0041] The power supply restoration control module is used to control the restoration of power supply to each load in the fault area according to the priority restoration sequence of each load and the current scheduling strategy of each load.

[0042] In a third aspect, an embodiment of the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method of any one of the embodiments of the first aspect when executing the computer program.

[0043] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method of any embodiment in the above-mentioned first aspect are implemented.

[0044] In a fifth aspect, an embodiment of the present application further provides a computer program product, the computer program product comprising a computer program, which, when executed by a processor, implements the steps of the method of any embodiment of the first aspect above.

[0045] The fault handling method, apparatus and computer equipment provided in the embodiments of the present application include: determining a priority recovery sequence of each load in a fault area according to the importance level of each load to the user, obtaining a current scheduling strategy for restoring power to each load, and controlling the restoration of power to each load in the fault area according to the priority recovery sequence of each load and the current scheduling strategy of each load. By adopting the above method, the priority recovery sequence of each load can be determined according to the importance level of each load in the fault area to the user, and then based on the priority recovery sequence of each load, power can be restored to the loads with higher sensitivity to power supply in the fault area first (that is, power supply is obtained first), and power can be restored to the loads with lower sensitivity to power supply in the fault area later (that is, power supply is obtained later), so that when power is restored to each load in the fault area, the recovery effect can be improved; at the same time, the method can supply power to each load in turn according to the sensitivity of each load to the power supply in the fault area, which can improve the user experience of each load and improve the performance of the distribution network system; in addition, the above method can obtain the current scheduling strategy for restoring power to each load, that is, the scheduling path that bypasses the fault area, and can safely and effectively restore power to each load according to the current scheduling strategy of each load.

[0046] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 An application environment diagram of a fault handling method in an embodiment;

[0048] Figure 2 A schematic diagram of a flow chart of a fault handling method in an embodiment;

[0049] Figure 3 is a flowchart of a fault handling method in another embodiment;

[0050] Figure 4 is a flowchart of a fault handling method in another embodiment;

[0051] Figure 5 is a flowchart of a fault handling method in another embodiment;

[0052] Figure 6 is a flowchart of a fault handling method in another embodiment;

[0053] Figure 7 is a flowchart of a fault handling method in another embodiment;

[0054] Figure 8 is a flowchart of a fault handling method in another embodiment;

[0055] Fig. 9 is a flowchart of a fault handling method in another embodiment;

[0056] Fig.10 is a flowchart of a fault handling method in another embodiment;

[0057] Fig.11 is a structural block diagram of a fault handling device in another embodiment;

[0058] Fig.12 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] In the field of power distribution networks, the operating scale of the distribution network system continues to expand, and the operating failures of the distribution network system also increase accordingly. In practical applications, in order to ensure that the distribution network system can meet the current power supply needs, the corresponding power restoration to each load in the fault area can be adopted. However, when restoring power to each load in the fault area in the related technology, there is a problem of poor recovery effect. Based on this, an embodiment of the present application provides a fault handling method, which can improve the recovery effect when restoring power to each load in the fault area.

[0061] The fault handling method provided in the embodiment of the present application can be applied to Figure 1The application environment diagram shown. The application environment includes a fault handling system, which can be a distribution network system and a computer device. The distribution network system includes multiple hardware facilities for supplying power to the load, multiple distribution network nodes and multiple control devices, and each distribution network node is electrically connected through multiple hardware facilities. Optionally, the distribution network system can supply power to multiple different loads. Optionally, the hardware facility can be an overhead line, a cable, a line support structure (such as a pole tower), a distribution transformer, a disconnector, a reactive power compensation device, a substation, a smart meter, a sensor, a circuit breaker, etc.; any sensor can be set on the corresponding distribution network node or the corresponding hardware facility, and can be a current sensor, a voltage sensor, a temperature sensor, a power sensor, etc., for real-time monitoring of the current, voltage, frequency, temperature, harmonic content and other electrical and environmental parameters of the corresponding distribution network node or the corresponding hardware facility. Optionally, the distribution network node can be a substation, a transformer location, a switch site, etc. in the distribution network system.

[0062] Among them, smart meters are not only used to measure user electricity consumption, but also serve as an important data collection point for the distribution network. They can transmit power consumption information in real time or on demand, as well as electrical parameter data such as voltage and current, and can also provide detailed power consumption data to grid operators through the communication network connection with the distribution network system. Circuit breakers can be used to quickly cut off circuits in the event of overcurrent, short circuit and other faults to isolate the fault area, prevent the fault from spreading, and protect the safety of grid equipment and users.

[0063] It should be noted here that the distribution network system can be divided into multiple distribution network areas, each of which includes a distribution network node and multiple hardware facilities; each distribution network area is equipped with a control device for controlling the operating status of each hardware facility in the distribution network area. Optionally, each control device can be a remote control terminal unit, a programmable logic controller or an automation control system, etc. Optionally, each distribution network node can include multiple hardware facilities and monitoring devices; in actual applications, the computer device and the monitoring device can be connected by communication, and the communication method can be Wi-Fi, mobile network or Bluetooth connection, etc. The following embodiment of the present application uses a computer device as the executor of the fault handling method to introduce the specific process of the fault handling method.

[0064] like Figure 2 FIG. 1 is a flow chart of a fault handling method provided in an embodiment of the present application, and the method can be implemented by the following steps:

[0065] S100: Determine a priority restoration sequence of each load according to the importance level of each load in the fault area to the user.

[0066] In actual applications, computer equipment can obtain the power usage data, power consumption patterns, degree of dependence on power supply stability, ability to respond to faults, impact of the fault on its own operation and economic losses caused by power outages corresponding to each load in the fault area, and determine the importance level of each load based on the power usage data, power consumption patterns, degree of dependence, response capabilities, impact on performance and economic losses corresponding to each load.

[0067] It should be noted here that the power usage data corresponding to each load in the fault area can be obtained through smart meters and sensors installed on each distribution network node in the fault area. In an embodiment of the present application, the computer device can obtain the power usage data corresponding to each load in the fault area stored in the energy management system and the distribution management system in the distribution network system.

[0068] Optionally, the power consumption mode of each load can be determined based on the load information of each load periodically obtained. Optionally, the load information can be the specific conditions of each load in the distribution network system, including but not limited to the type of load (such as lighting, motor, heater, etc.), rated power, operating status (working or standby), location, importance level to the user, etc. In the embodiment of the present application, the load information can be demand information such as continuity, volatility and peak value.

[0069] Alternatively, continuous demand can be understood as relatively stable and uninterrupted power consumption over a long period of time. This demand is usually related to basic loads, such as daily household electricity consumption and basic operating requirements of industrial equipment. Alternatively, fluctuating demand can be understood as the unstable characteristics of power demand changing over time. This change can be periodic (such as day and night changes, seasonal changes) or random (such as caused by weather or special events); among them, fluctuating demand requires the distribution network system to have certain flexibility and responsiveness in order to effectively manage and balance supply and demand and avoid overload or waste. Optionally, peak demand can be understood as the highest power consumption level that the distribution network system needs to meet within a specific time period, which usually occurs during some peak hours of the day (such as morning and evening peaks) or specific seasons of the year.

[0070] At the same time, the computer equipment can obtain the power usage data of each load, regularly analyze the time characteristics of the power usage data of each load, determine the peak period, trough period, seasonality and daily variation characteristics of the power usage of each load, and then use an evaluation algorithm to evaluate the degree of dependence of each load on the stability of the power supply based on the peak period, trough period, seasonality and daily variation characteristics of the power usage of each load; as well as based on the power usage data of each load, the degree of dependence between the loads and the historical power usage data of each load.

[0071] Optionally, a time series analysis method (such as moving average method, exponential smoothing method) can be used to analyze the power usage data of each load to identify the long-term trend and seasonal changes in the power usage data of each load. Among them, the power usage data of each load can be analyzed by Fourier transform or seasonal decomposition (such as STL) to identify the daily changes and seasonal characteristics in the power usage data of each load. In addition, in actual applications, the power consumption is the largest during peak hours and the smallest during trough hours.

[0072] Specifically, the power usage data can be compared with the historical power usage data, the load changes in similar time periods can be analyzed, and the load patterns in specific time windows can be identified. At the same time, the correlation coefficient or covariance analysis can be used to evaluate the correlation between specific loads (such as industrial, commercial, and residential) and total power consumption, and identify key loads. Based on the historical power usage data of each load, regression analysis and machine learning models (such as random forests and neural networks) can be used to quantify the impact of each load on the stability of power supply, analyze the sensitivity of each load to power supply in different time periods, and obtain the degree of dependence of each load on the stability of power supply.

[0073] In the embodiment of the present application, an evaluation algorithm can be used to test the capacity and response time of the power supply (such as a generator and / or an uninterruptible power supply UPS) in the non-fault area to evaluate the ability to cope with the fault. Further, a prediction algorithm can be used to predict the impact of the fault on the operation of each load based on the ability of the power supply in the non-fault area to cope with the fault, the historical fault data of the distribution network system, and the currently monitored power usage data.

[0074] Optionally, the above-mentioned evaluation algorithm can be an evaluation method based on a clustering model, a qualitative evaluation method, etc.; the above-mentioned prediction algorithm can be a time series prediction method, a regression prediction method, a qualitative prediction method, etc.

[0075] In addition, the historical electricity consumption data of each load and the contribution data of each load to the economy can be obtained, and an evaluation algorithm can be used to evaluate the economic losses caused by power outages (power outages caused by faults) to each load based on the historical electricity consumption data of each load and the contribution data of each load to the economy.

[0076] At the same time, economic models (such as cost-benefit analysis and multi-criteria decision analysis) can be used to comprehensively consider the above-mentioned losses, and combine the comprehensive indicator system of power outage impact on users and information such as direct economic losses of users, economic losses of power supply companies, and the impact of power supply reliability assessment indicators to determine the economic losses of each load caused by power outage (power outage caused by fault).

[0077] In one implementation, an algorithm model can be pre-trained, and then the power usage data, power consumption pattern, degree of dependence, coping capability, impact on performance and economic loss corresponding to each load are input into the algorithm model, and the algorithm model outputs the importance level of each load.

[0078] In another implementation, arithmetic operations can be performed based on the power usage data, power consumption mode, dependence, response capability, performance impact and economic loss corresponding to each load, and the importance level of each load can be determined based on the arithmetic operation results. Optionally, the arithmetic operation can be implemented by at least one of addition, subtraction, multiplication, division, logarithm, exponential operation, etc.

[0079] Based on the acquired importance level of each load in the fault area to the user, the computer device can search for the importance level that matches the importance level of each load in the fault area to the user in the mapping relationship between different importance levels and different recovery sequences, and then determine the recovery sequence corresponding to the matched importance level as the recovery sequence of each load, and then determine the priority recovery sequence of each load according to the recovery sequence of each load. Among them, the recovery sequence of different loads is different, and the recovery sequence of each load represents the order of restoring power supply to each load in the fault area.

[0080] For example, City A decided to upgrade the distribution network system to be intelligent, and therefore installed smart meters and multi-point sensors to collect power usage data of the distribution network system in real time. The smart meter was set up in an office building in the central business district of City A, and collected peak power consumption of 2 MW and minimum power consumption of 5 MW at night. The smart meter collected data every 15 minutes and stored it in the database of the distribution network system. During the week, the building's power consumption data showed that power consumption on weekdays was 30% higher than on weekends; in the summer, due to increased use of air conditioning, the peak power consumption of the office building increased to 5 MW, while power consumption during the trough period remained at 5 MW. Historical power usage data showed that when the power supply was interrupted, the IT company in the building would lose about $10,000 in revenue within 5 minutes. In addition, the sensor collected that the office building had three power outages in a month, due to fluctuations in the distribution network system, the voltage dropped to 215 volts, while the standard was 230 volts, and the frequency dropped from 50 Hz to 45 Hz. Tests show that the building's diesel generators can start and restore power within 30 seconds of a power outage, but the uninterruptible power supply UPS can only keep critical loads running for 10 minutes. Combined with historical power usage data, it is predicted that when extreme weather causes a failure, the building's power supply may be interrupted for up to 2 hours, affecting economic activities of approximately $200,000. Based on historical power usage data over the past year, power outages cost businesses in the building an average of $5,000 per hour. In order to reduce economic losses, the office building in the CBD area is given a "high" importance level because it has a high reliance on the stability of power supply and power outages can have a significant impact on economic activities. City A can optimize its distribution network system operations, prioritize the stable power supply of critical infrastructure, and take quick response measures when failures occur to reduce economic losses.

[0081] S200: Obtain a current scheduling strategy for restoring power supply to each load.

[0082] The current dispatching strategy of each load may include information such as a method for restoring power supply to each load, a dispatching path for restoring power supply to each load, etc. Optionally, the dispatching path for restoring power supply to the load may be a path that bypasses the fault area and can supply power to the load.

[0083] Specifically, the computer device can obtain the pre-stored scheduling strategy for restoring power supply to each load from a local location, cloud, disk, hard disk, etc. as the current scheduling strategy for each load. It should be noted here that the current scheduling strategy for each load can be formulated based on the load level, power generation capacity, network constraints and other data of the distribution network system, and can ensure the stable operation and power supply demand of the distribution network system during the power supply restoration process.

[0084] In addition, the computer equipment can determine in real time the current scheduling strategy for restoring power to each load based on the current power usage data of each distribution network node in the non-fault area of ​​the distribution network system and the power resource information required for restoring power to each load.

[0085] S300: Control the restoration of power supply to each load in the fault area according to the priority restoration sequence of each load and the current dispatching strategy of each load.

[0086] Specifically, the computer device can send the priority recovery sequence of each load and the current scheduling policy of each load to the corresponding control device in the non-fault area, instructing the control device to control the activation of multiple backup units in the non-fault area in sequence according to the priority recovery sequence of each load according to the current scheduling policy of each load, so as to restore power supply to each load in the fault area through multiple backup units.

[0087] In practical applications, the optimal scheduling strategy can be determined by considering renewable energy information and / or load balance supply and demand information. In one embodiment, before executing the steps in S300 above, Figure 3 As shown, the above method may further include the following steps:

[0088] S400, obtaining auxiliary adjustment information; the auxiliary adjustment information includes at least one of renewable energy information and load balancing supply and demand information.

[0089] In an embodiment of the present application, the above-mentioned renewable energy information can be understood as information corresponding to the renewable energy that can be generated by the corresponding hardware facilities on each distribution network node in the non-fault area; the load balance supply and demand information can be understood as the load corresponding to different distribution network nodes in the non-fault area after the load in the fault area is distributed to the non-fault area or other power supply systems outside the distribution network system due to an increase or decrease in the load in the distribution network system.

[0090] S500. According to the auxiliary adjustment information, the current scheduling strategy of each load is adjusted to obtain the updated scheduling strategy of each load, and the updated scheduling strategy of each load is used as the current scheduling strategy of each load, and the steps of controlling the restoration of power supply to each load in the fault area are executed according to the priority recovery sequence of each load and the current scheduling strategy of each load.

[0091] In practical applications, the current dispatching strategy of each load can be adjusted based on the auxiliary adjustment information according to the preset adjustment strategy to obtain the updated dispatching strategy of each load. Optionally, the current dispatching strategy can include the processing of the power plant, the access method of the backup power supply, the load distribution method, etc.

[0092] In addition, a scheduling strategy adjustment model can be pre-trained, and the auxiliary adjustment information and the current scheduling strategy of each load are input into the scheduling strategy adjustment model, and the scheduling strategy adjustment model outputs the updated scheduling strategy of each load. Optionally, the scheduling strategy adjustment model can be implemented by at least one of a convolutional neural network model, a fully connected neural network model, a long short-term memory neural network model, a recurrent neural network model, etc.

[0093] Furthermore, the updated scheduling strategy of each load may be used as the current scheduling strategy of each load, and the steps of controlling the restoration of power supply to each load in the fault area may be executed according to the priority recovery sequence of each load and the current scheduling strategy of each load.

[0094] This embodiment can adjust the current scheduling strategy of each load according to the auxiliary adjustment information, so that the obtained scheduling strategy of each load is more accurate, so as to provide a reference basis for further improving the power supply restoration effect of each load in the fault area.

[0095] The technical solution in the embodiment of the present application determines the priority recovery sequence of each load according to the importance level of each load in the fault area to the user, obtains the current scheduling strategy for restoring power supply to each load, and controls the restoration of power supply to each load in the fault area according to the priority recovery sequence of each load and the current scheduling strategy of each load; the above method can first determine the priority recovery sequence of each load according to the importance level of each load in the fault area to the user, and then based on the priority recovery sequence of each load, it can give priority to restoring power to the loads with higher sensitivity to power supply in the fault area (that is, give priority to obtaining power supply), and restore power to the loads with lower sensitivity to power supply in the fault area later (that is, obtain power supply later), so that when restoring power to each load in the fault area, the restoration effect can be improved; at the same time, the method can supply power to each load in turn according to the sensitivity of each load to the power supply in the fault area, which can improve the user experience of each load and can also improve the performance of the distribution network system; in addition, the above method can obtain the current scheduling strategy for restoring power supply to each load, that is, the scheduling path that bypasses the fault area, and can safely and effectively restore power to each load according to the current scheduling strategy of each load.

[0096] The following is a description of the process of determining the priority recovery sequence of each load based on the importance level of each load in the fault area to the user. Figure 4 As shown, the steps in S100 above can be implemented in the following manner:

[0097] S110. Obtain an initial priority recovery sequence corresponding to each load in the fault area.

[0098] Specifically, the computer equipment can assign an initial recovery sequence to each load in the fault area in turn according to reference information such as the setting order of each load in the fault area, the function of each load and / or the volume of each load, and then determine the initial priority recovery sequence corresponding to each load in the fault area based on the initial recovery sequence assigned to each load.

[0099] In one embodiment, the step of obtaining the initial priority recovery sequence corresponding to each load in the fault area in S110 may include: assigning a recovery sequence to each load according to the dependency relationship between the loads and / or the target load among the loads to obtain the initial priority recovery sequence of each load. The target load includes at least one load with special recovery requirements.

[0100] Specifically, the order of restoration of the loads in the fault area can be determined according to the dependency relationship between the loads, and the initial priority restoration sequence of the loads can be determined according to the order of restoration of the loads. At the same time, at least one load with special restoration requirements can be determined from the loads in the fault area, and the loads with special restoration requirements can be assigned a larger restoration sequence, and other loads without special restoration requirements can be assigned a smaller restoration sequence, and the initial priority restoration sequence of each load can be determined based on the restoration sequence of each load.

[0101] In addition, the order of recovery of the loads in the fault area can be determined based on the dependency relationship between the loads, and at least one load with special recovery requirements can be determined from the loads in the fault area. Each load with special recovery requirements can be assigned a larger recovery sequence, and the order of recovery of each load can be adjusted based on the recovery sequence of each load with special recovery requirements. The order of recovery of each load with special recovery requirements can be adjusted to the front to obtain the initial priority recovery sequence of each load.

[0102] S120. Determine a measurement index value of each load for power supply according to the importance level of each load.

[0103] In practical applications, the more important the load is to the user, the greater the load's measurement index value for power supply. At the same time, different loads have different importance levels, and correspondingly, the load's measurement index value for power supply is different. In the embodiment of the present application, the load's importance level can be low, medium, high, etc. Optionally, the load's measurement index value for power supply can be any value between 0 and 1.

[0104] Specifically, for any load, the computer device can search for the importance level of the load in the association relationship between different importance levels and different measurement index values ​​for power supply, and then determine the measurement index value corresponding to the found importance level as the measurement index value of the load for power supply.

[0105] In the embodiment of the present application, the above-mentioned measurement index values ​​can be the recovery time objective (RTO) of the load and the recovery point objective (RPO) of the load. Optionally, RTO can be understood as the length of interruption time that the load service can tolerate, reflecting the degree of demand for rapid power restoration; RPO can be understood as the time point to which the data must be restored after the load power is restored, reflecting the load's tolerance time for data loss due to power outages.

[0106] S130. Adjust the initial priority recovery sequence according to the measurement index value of each load for power supply to obtain the priority recovery sequence of each load.

[0107] Specifically, the computer device can pre-train a sequence adjustment model, and then input the measurement index value of each load for power supply and the initial priority recovery sequence of each load into the sequence adjustment model, and the sequence adjustment model outputs the priority recovery sequence of each load.

[0108] In addition, the computer equipment can also readjust the recovery sequence of each load in the initial priority recovery sequence according to the size of the measurement index value of each load for power supply, adjust the recovery sequence of the load with a larger measurement index value to the front of the initial priority recovery sequence, and adjust the recovery sequence of the load with a smaller measurement index value to the back of the initial priority recovery sequence, and determine the adjusted initial priority recovery sequence as the priority recovery sequence of each load.

[0109] Optionally, the above-mentioned sequence adjustment model can be implemented by at least one of a convolutional neural network model, a fully connected neural network model, a long short-term memory neural network model, a recurrent neural network model, a residual neural network model, etc.

[0110] For example, the fault area includes three loads, namely the hospital emergency medical system (load A), the bank transaction processing system (i.e., load B), and the university education network system (load C). In practical applications, the recovery sequence of each load can be adjusted according to the importance level of each load. Among them, since the hospital emergency medical system involves people's life and health, the tolerance time for power outage is relatively short, so the importance level of the hospital emergency medical system is level 1; because the interruption of the bank transaction processing system will cause economic losses, the tolerance time for power outage is relatively short, so the importance level of the bank transaction processing system is level 2; because the educational activities of the university education network system can be temporarily carried out in a non-network form, the tolerance time for power outage is relatively long, so the importance level of the university education network system is level 3.

[0111] Among them, the hospital emergency medical system relies on a stable power supply to maintain the operation of the life support system and the emergency operating room, the bank transaction processing system relies on power to ensure the real-time processing of financial transactions, and the university education network system relies on power to maintain the availability of the online learning platform. The RTO of the hospital emergency medical system is 1 hour and the RPO is 0 hours, indicating that the hospital emergency medical system needs to be restored within 1 hour and the data loss tolerance time is zero; the RTO of the bank transaction processing system is 4 hours and the RPO is 30 minutes, indicating that the bank transaction processing system can accept a maximum of 4 hours of interruption and data loss within 30 minutes; the RTO of the university education network system is 24 hours and the RPO is 2 hours, indicating that the university education network system can tolerate a maximum of 24 hours of interruption and needs to restore the recorded data within 2 hours. The risks faced by the hospital emergency medical system include equipment failure caused by unstable power supply, and regular power supply system maintenance and backup generator preparation are required; the risks of the bank transaction processing system include cyber attacks or hardware failures, and multiple backups and network security protection measures need to be set up; the risks of the university education network system are mainly system overload, which can be alleviated by expanding server capacity and setting access restrictions during high traffic periods. Based on the above analysis, it can be concluded that the priority recovery sequence is that the recovery sequence of the hospital emergency medical system is higher than the recovery sequence of the bank transaction processing system, and the recovery sequence of the bank transaction processing system is higher than the recovery sequence of the university education network system. Such a priority recovery sequence can ensure that the most critical services can be restored as quickly as possible when a power supply interruption occurs, while also taking into account the effective allocation of resources and other relevant risk factors.

[0112] The technical solution in the embodiment of the present application obtains an initial priority recovery sequence corresponding to each load in the fault area, determines a measurement index value of each load for power supply according to the importance level of each load, and adjusts the initial priority recovery sequence according to the measurement index value of each load for power supply to obtain a priority recovery sequence for each load; the above method can assign an optimal priority recovery sequence to each load in the fault area according to the importance level of each load, so as to provide reference information for subsequently restoring power supply to loads that are more sensitive to power supply in the fault area in priority, and restoring power supply to loads that are less sensitive to power supply; at the same time, the method does not require user participation, thereby reducing manual participation errors and improving the accuracy of the obtained priority recovery sequence.

[0113] The following is an explanation of the process of obtaining the current scheduling strategy for restoring power to each load. Figure 5 As shown, the steps in S200 above can be implemented in the following manner:

[0114] S210: Determine an initial dispatching strategy for each load based on the initial grid state and initial available resource information of each distribution network node, and the power resource information required by each load.

[0115] Optionally, the initial grid state of the distribution network node may include whether the distribution network node is in a normal operating state or an abnormal state. Among them, the voltage, current, power, power and other information of each hardware facility in the distribution network area where the distribution network node is located can be obtained, and then the voltage, current and / or power and other information of each hardware facility is analyzed. If it is determined that the voltage, current and / or power and other information of each hardware facility exceeds the corresponding standard voltage, current and / or power, the distribution network node is determined to be in an abnormal state, otherwise, the distribution network node is determined to be in a normal operating state. In addition, the initial available resource information of the distribution network node may include information such as the total power and remaining power of each power source in the distribution network area where the distribution network node is located.

[0116] Meanwhile, the power resource information required by each load may include information such as the amount of power provided by the power supply required for normal operation of each load.

[0117] In practical applications, the computer device can determine at least one distribution network node in normal operating state among the distribution network nodes as a candidate node based on the initial grid state of each distribution network node, and then select a candidate node whose initial available resource information meets the power resource information required by each load from the candidate nodes as the target node based on the initial available resource information of each candidate node, and then determine the initial scheduling strategy for each load based on the target node.

[0118] In addition, the computer device can pre-train an algorithm model, and then input the initial grid status and initial available resource information of each distribution network node and the power resource information required by each load into the algorithm model, and the algorithm model outputs the initial scheduling strategy for each load.

[0119] Among them, before executing the step of determining the initial scheduling strategy for each load based on the initial grid state and initial available resource information of each distribution network node, and the power resource information required by each load, the initial grid state, initial available resource information and the power resource information required by each load can also be cleaned (i.e., outliers and noise are removed), and then the initial scheduling strategy for each load is determined based on the cleaned data.

[0120] S220: If the initial grid state and initial available resource information of each distribution network node are changed, the initial scheduling strategy of each load is determined as the current scheduling strategy of each load.

[0121] Among them, the grid status and available resource information collected by the sensors set on each distribution network node can be obtained. If the grid status of each distribution network node at the current moment is still the initial grid status and the available resource information of each distribution network node is still the initial available resource information, it is determined that the initial grid status and initial available resource information of each distribution network node are changed. At this time, the initial scheduling strategy of each load can be determined as the current scheduling strategy of each load.

[0122] In one embodiment, if Figure 6 As shown, the step of obtaining the current scheduling strategy for restoring power supply to each load in the above S200 may include:

[0123] S230: If at least one of the initial grid state and the initial available resource information of each distribution network node changes, the current grid state and the current available resource information of each distribution network node are obtained.

[0124] In actual applications, if the grid state of each distribution network node is still the initial grid state, and / or the available resource information of each distribution network node is still the initial available resource information, then the current grid state and current available resource information of each distribution network node can be obtained.

[0125] S240. Determine the current dispatching strategy for each load based on the current grid status and currently available resource information of each distribution network node, as well as the power resource information required by each load.

[0126] In the embodiment of the present application, the implementation method of the above step S240 is similar to the implementation method of the above step S210, which will not be described in detail in the embodiment of the present application.

[0127] It should be noted here that the initial recovery path of each load can be determined based on the current grid status and current available resource information of each distribution network node, as well as the power resource information required by each load, and the load amount of different power supply areas in the non-fault area and the load amount of each load in the fault area are obtained, and then the load amount of different power supply areas in the non-fault area is balanced and distributed according to the total load amount corresponding to the two (to ensure the stable operation of the distribution network system), and the initial recovery path of each load is adjusted according to the distribution result to obtain the optimal recovery path of each load in the fault area. In addition, the availability and allocation efficiency of the resources of each distribution network node, as well as the different risk types (such as natural disasters, human errors, hardware failures) and levels suffered by each load can be obtained, and the recovery strategy of each load can be determined according to the availability and allocation efficiency of the resources of each distribution network node, as well as the different risk types and levels suffered by each load.

[0128] Exemplarily, the power usage data of the distribution network node can be realized by deploying smart sensors and IoT devices on the substation, distribution line and user side. If the power usage data is collected every 5 minutes and uploaded to a storage location (such as cloud, local, disk, hard disk, etc.), the power usage data of a distribution network node can be cleaned (such as Kalman filter algorithm to remove outliers and noise), and the key features such as voltage, current, power, etc. in the cleaned data can be extracted by principal component analysis to form a 30-dimensional feature vector of the distribution network node, that is, the initial grid state. When the initial grid state is monitored to change, the random forest algorithm can be used to classify the 30-dimensional feature vector, identify the fault type and fault location, and calculate the corresponding initial scheduling strategy for each load in the fault area according to the fault type and fault location. When formulating the initial scheduling strategy for each load, the particle swarm optimization algorithm can be used, with the minimum power generation cost and the minimum grid loss as the optimization goal, while considering the constraints such as the ramp rate of the generator set and the capacity of the transmission line, and simulating 1000 possible scheduling strategies through Monte Carlo simulation, and selecting the scheme with the lowest risk and the best economy as the best recovery path. At the same time, through the short-term forecast of renewable energy such as wind power and photovoltaic power generation, the long short-term memory neural network model is used to make a rolling forecast of the power generation in the next 4 hours, and the forecast results are used as the input of the dispatching strategy to improve the grid's ability to absorb renewable energy. When the demand of the distribution network system fluctuates violently, the demand response mechanism can be used to use price incentives to guide users to actively participate in the peak load regulation of the grid, and the grid operation mode can be dynamically adjusted according to the size of the response. For example, when the demand response reaches 5%, part of the load can be transferred to the distributed energy storage system to reduce the pressure on the distribution network system.

[0129] The technical solution in the embodiment of the present application determines the initial scheduling strategy of each load according to the initial grid state and initial available resource information of each distribution network node, and the power resource information required by each load. If the initial grid state and initial available resource information of each distribution network node are changed, the initial scheduling strategy of each load is determined as the current scheduling strategy of each load; the above method can obtain the current scheduling strategy of each load in the fault area according to the actual operation request of the distribution network system, so as to provide an accurate reference basis for further restoring power supply to each load; at the same time, the above method does not require complex algorithms, thereby reducing the complexity of obtaining the current scheduling strategy of each load in the fault area, and improving the speed and efficiency of obtaining the current scheduling strategy of each load in the fault area.

[0130] In one embodiment, the current scheduling strategy includes an optimal recovery path and a recovery strategy; Figure 7 As shown, in the above S300, the step of controlling the restoration of power supply to each load in the fault area according to the priority restoration sequence of each load and the current scheduling strategy of each load can be implemented in the following manner:

[0131] S310: Determine a target power source in a non-fault area that can supply power to each load according to an optimal recovery path of each load.

[0132] Optionally, the target power supply may be one or more, and one target power supply can supply power to one load. The non-fault area may include multiple power supply areas, and each power supply area includes a power supply.

[0133] The above-mentioned optimal recovery path may include the identification of the power supply area in the non-fault area; and may also include the identification of the power supply in the non-fault area.

[0134] Specifically, the computer device can determine the corresponding target power supply area in the non-fault area according to the identification of the power supply area in the optimal recovery path of each load, and then select a target power supply that can meet the power required for the normal operation of each load from the power supplies in the target power supply area according to the total power and remaining power of each power supply in the target power supply area and the power required for the normal operation of each load. Optionally, the above-mentioned target power supply area can be at least one of multiple power supply areas.

[0135] In addition, the computer device can determine multiple power supplies corresponding to the non-fault area based on the identification of the power supply in the optimal recovery path of each load, and determine the multiple power supplies corresponding to the non-fault area as the target power supplies in the non-fault area that can supply power to each load.

[0136] S320. According to the priority recovery sequence of each load, the recovery strategy of each load is sent to different terminal devices in the distribution network system in turn, instructing different terminal devices to control and enable the corresponding target power supply to restore power supply to each load.

[0137] In actual applications, the recovery strategy of the load may include information such as the enable time, enable duration, disable time, power supply amount, etc. of the target power source corresponding to the load.

[0138] Specifically, for any load, the computer device can send the recovery strategy of each load to different terminal devices in the distribution network system in sequence based on the priority recovery sequence of each load, in a recovery sequence from large to small, and instruct different terminal devices to control and enable the corresponding target power supply to restore power to each load.

[0139] It should be noted here that, for any load, the computer device can send the recovery strategy of the load to the corresponding terminal device in the distribution network system, instructing the terminal device to enable the corresponding target power supply to restore power supply to the load.

[0140] In actual applications, information such as the load's power supply restoration strategy, restoration progress, and load power usage data can be displayed on the load's display interface for users to view.

[0141] In practical applications, the distribution network system may also be provided with a redundancy mechanism. When the target power sources in the distribution network system are insufficient to support the normal operation of the loads, a backup power source may be used to restore power supply. In one embodiment, before executing the steps in S320 above, Figure 8 As shown, the above method may also include:

[0142] S330: If each target power source is insufficient to support normal operation of each load, determine at least one backup power source in the non-fault area.

[0143] Among them, the above-mentioned target power supply is insufficient to support the normal operation of the corresponding load, which can be understood as the remaining power of the target power supply does not meet the power required for the normal operation of the corresponding load, and can also be understood as the target power supply suddenly fails or is abnormal (such as natural aging, wear, overheating, physical damage, electromagnetic interference, natural disasters (such as earthquakes, floods), man-made damage, man-made configuration errors, improper operation, etc.).

[0144] In practical applications, at least one backup power supply unit is provided in each power supply area, and the power supply unit may be a generator set or a UPS, etc. Specifically, for any load, when the computer device determines that the corresponding target power supply is insufficient to support the normal operation of the load, at least one power supply unit may be selected from at least one backup power supply unit in the power supply area where the target power supply is located as at least one backup power supply for the load.

[0145] It should be noted here that the above-mentioned terminal device can be a front-end execution unit for monitoring and controlling the distribution network system, and is connected to the distribution network system through a communication network (such as optical fiber, wireless network, etc.) to achieve two-way data transmission.

[0146] S340. According to the priority recovery sequence of each load, the recovery strategy of each load is sent to different terminal devices in the distribution network system in turn, instructing different terminal devices to control and enable the corresponding backup power supply to restore power supply to each load.

[0147] Specifically, for any load, the computer device can send the recovery strategy of each load to different terminal devices in the distribution network system in sequence based on the priority recovery sequence of each load, in a recovery sequence from large to small, and instruct different terminal devices to control the activation of the corresponding backup power supply to restore power to each load.

[0148] It should be noted here that, for any load, the computer device can send the recovery strategy of the load to the corresponding terminal device in the distribution network system, instructing the terminal device to enable at least one corresponding backup power supply to restore power supply to the load.

[0149] For example, in a distribution network system, there is the following load priority recovery sequence: hospital emergency room is the highest priority, residential area is high priority, commercial shopping center is medium priority, and industrial manufacturing workshop is low priority. The power usage data of different loads are obtained through real-time monitoring. The voltage of the hospital emergency room is 220V, the current is 50A, and the frequency is 50Hz; the voltage of the residential area is 218V, the current is 300A, and the frequency is 49Hz; the voltage of the commercial shopping center is 217V, the current is 200A, and the frequency is 48Hz; the voltage of the industrial manufacturing workshop is 215V, the current is 150A, and the frequency is 47Hz; based on these loads, the total load demand of the distribution network system is determined to be 700A, but due to a certain fault, the power supply capacity of the distribution network system is temporarily reduced to 600A. In addition, according to the priority recovery sequence of each load and the current power grid status, the power supply of the industrial manufacturing workshop with the lowest recovery sequence can be controlled to be disconnected. If the power supply capacity is further reduced to only 400A due to the fault, the backup power supply can be started and a generator set with a rated power of 200kW can be started to supplement the insufficient power supply capacity and give priority to ensuring the power supply to the hospital emergency room and residential areas.

[0150] In this embodiment, when the target power supplies are insufficient to support the normal operation of each load, power supply to each load can be restored by enabling multiple backup power supplies in the non-fault area, thereby ensuring that power supply to each load is restored normally and avoiding the occurrence of abnormal power supply restoration problems.

[0151] It should be noted here that in the process of restoring power supply to each load, the power usage data in the fault area can be monitored. If the power usage data changes significantly (that is, there is an anomaly in the power usage data), indicating that a new fault has occurred in the fault area or the impact scope of the original fault has changed, then continue to execute the steps in S100-S300 above to restore power supply to each load.

[0152] Optionally, the power usage data may include load, equipment status, weather conditions, voltage, current, frequency and other electrical parameters; wherein, if at least one of the voltage, current, frequency and other electrical parameters exceeds the corresponding normal operating range, it can be determined that there is an abnormality in the power usage data, which indicates that a new fault has occurred in the fault area.

[0153] The technical solution in the embodiment of the present application determines the target power supply in the non-fault area that can supply power to each load according to the optimal recovery path of each load, and sends the recovery strategy of each load to different terminal devices in the distribution network system in turn according to the priority recovery sequence of each load, instructing different terminal devices to control and enable the corresponding target power supply to restore power to each load; the above method can restore power to each load according to the priority recovery sequence of each load, so that power supply to loads with higher sensitivity to power supply in the fault area can be restored first, and power supply to loads with lower sensitivity to power supply in the fault area can be restored later, so that when power supply to each load in the fault area is restored, the recovery effect can be improved, the continuity of power supply to each load can be guaranteed, and the user experience of each load can be improved.

[0154] In one embodiment, before executing the step in S100 above, Fig. 9 As shown, the above method may further include the following steps:

[0155] S600: For any distribution network node, if there is an abnormality in the power usage data of the distribution network node, the distribution network node is determined to be a faulty node.

[0156] In practical applications, for any distribution network node, the computer device can obtain the power usage data of the distribution network node within a historical period of time, and determine whether there is any abnormality in the power usage data of the distribution network node. If there is an abnormality, the distribution network node is determined to be a faulty node.

[0157] Optionally, the power usage data may include various electrical and environmental data such as current, voltage, frequency, temperature, harmonic content, etc. In the embodiment of the present application, for any distribution network node, if at least one parameter in the power usage data of the distribution network node fluctuates continuously or significantly within a specific time period, it can be determined that the power usage data of the distribution network node is abnormal.

[0158] At the same time, for any distribution network node, the computer device can also compare the power usage data of the distribution network node with the power usage data corresponding to different known faults. If the two are consistent, it is determined that there is an abnormality in the power usage data of the distribution network node.

[0159] Optionally, for any distribution network node, the computer device may also obtain the power in the power usage data of the distribution network node. If the power is relatively stable within a certain period of time, it is determined that there is no abnormality in the power usage data of the distribution network node. Otherwise, there is an abnormality in the power usage data of the distribution network node. At the same time, when it is determined that there is an abnormality in the power usage data of the distribution network node, it can be further determined whether the abnormality is caused by a fault. For example, the power consumption and voltage levels of distribution network nodes corresponding to different load amounts are different, and an overload fault will cause the voltage of the corresponding distribution network node to decrease.

[0160] In addition, the computer device can also obtain the frequency or phase angle in the power usage data of the distribution network node. If the frequency or phase angle changes within a certain period of time and these changes are consistent with the changes in the frequency or phase angle of the corresponding known fault within a certain period of time, it can be determined that the power usage data of the distribution network node is abnormal. At the same time, the fault type of the distribution network node can also be determined based on the fault type of the corresponding known fault.

[0161] Optionally, the computer device can also determine whether the temperature rise in the power usage data of the distribution network node exceeds a preset temperature threshold. If so, it can be determined that the power usage data of the distribution network node is abnormal. Further, it can also analyze whether the distribution network node has an overload or poor contact fault, and determine the fault type of the distribution network system based on the analysis results.

[0162] For example, if the current value collected by the smart meter installed at a distribution network node is 500A, the current of the distribution network node should not exceed 400A under normal circumstances. Since the current value collected by the smart meter is not equal to 400A, the distribution network node can be determined to be a faulty node. Alternatively, based on the current values ​​collected by the smart meter in the past 5 minutes, it is determined that the current value of the distribution network node suddenly rises from the normal 380A to 500A, and continues to fluctuate between 480A and 520A. It can be determined that the current rises abnormally, and at this time, the distribution network node is determined to be a faulty node.

[0163] In addition, if the power usage data of the distribution network node is consistent with the power usage data corresponding to the known fault, the fault type in the fault area can be determined based on the known fault corresponding to the power usage data that matches the power usage data of the distribution network node. The fault type can be a short-term fault or a continuous fault, etc.

[0164] In an embodiment of the present application, for any distribution network node, the computer device can also perform harmonic analysis on the voltage and current waveforms in the power usage data of the distribution network node to obtain a harmonic waveform, and obtain multiple harmonic levels in the harmonic waveform. If any harmonic level exceeds a preset threshold, the distorted waveform in the harmonic waveform can be further obtained, and then the distorted waveform can be compared with the distorted waveforms of different known faults, and the fault type of the distribution network node can be determined according to the fault type of the matching known fault.

[0165] If the level of a harmonic in the harmonic waveform exceeds the preset threshold, it indicates that there is harmonic pollution in the harmonic waveform, which may be caused by nonlinear loads (such as inverters, UPS, etc.). At the same time, since the distorted waveform comes from the superposition of non-sinusoidal components in current or voltage, by comparing the distorted waveform in the harmonic waveform with the distorted waveforms of different known faults, it can help locate the fault type, such as arc fault, ground fault, line fault, transformer load imbalance, harmonic pollution or equipment aging.

[0166] For example, the harmonic waveform is obtained by performing harmonic analysis on the voltage and current waveforms in the power usage data of a distribution network node. If the current of the harmonic waveform reaches 25% of the total current, exceeding the normal safety threshold of 5%, it indicates that there is harmonic distortion in the harmonic waveform. If at a certain moment, the frequency of the distribution network node suddenly drops from 50Hz to 48Hz, and the phase angle changes by 30 degrees, this situation may be related to the disconnection of a large power source or the sudden access of a large load. After analysis, it is determined that the fault type of the distribution network node is a frequency drop fault according to the characteristics of the frequency drop fault. In addition, according to the optical signal output by the fault indicator of each distribution network node, if the fault indicator of the corresponding distribution network node lights up red, it indicates that the distribution network node is a faulty node.

[0167] If the normal operating range of the current of any distribution network node is set to 0-400A, and the normal operating range of the voltage is set to 220kV-250kV, if it is monitored that the current of a distribution network node suddenly rises to 500A and the corresponding voltage drops to 210kV, then the distribution network node can be determined as a faulty node.

[0168] In another implementation, the computer device can obtain the communication status of the smart meter and sensor on the distribution network node. If the communication status is a communication terminal, the network connectivity of the distribution network node can be checked, and the fault type of the distribution network node can be determined based on the inspection results.

[0169] For example, a high-precision current sensor and a high-precision voltage sensor may be set up in the distribution network system to obtain power usage data at a sampling frequency of 100ms. The computer equipment can perform intelligent analysis on the power usage data based on the preset operation thresholds and rules. When it is detected that the voltage deviation in the power usage data exceeds ±5% and the current in the power usage data exceeds 120% of the rated value, an alarm is immediately triggered to notify the operation and maintenance personnel through SMS, email, etc. The distribution network system automatically obtains the operation logs and power usage data before and after the fault occurs, and uses the fault diagnosis algorithm based on the decision tree to match the operation logs and power usage data corresponding to different known faults, and determines the fault type of the successfully matched known fault as the fault type of the current fault.

[0170] S700: Determine a fault area according to a fault node and a fault location.

[0171] Among them, the computer device can obtain the fault location sent by the fault indicator in the distribution network system, and then determine the fault area where the fault is located according to the fault node and the fault location, that is, the specific fault location corresponding to the fault node where the fault is located.

[0172] In an embodiment of the present application, the power usage data collected by data collectors such as smart meters and sensors can carry a timestamp, and then the exact time point when the fault occurred, that is, the time when the fault occurred, can be traced back based on the timestamp in the power usage data.

[0173] S800. Control at least one power supply in the fault area to shut down to achieve fault isolation.

[0174] Furthermore, the computer device may send a power off instruction to the terminal device corresponding to the fault area, instructing the terminal device to send a shutdown signal to a circuit breaker or switch connected to at least one power source in the fault area, so that the circuit breaker or switch is turned off and the corresponding power source is disconnected to achieve fault isolation, thereby preventing the fault in the fault area from affecting the non-fault area. Optionally, the shutdown signal may also carry the execution duration of the shutdown.

[0175] It should be noted here that the communication between the terminal device and the circuit breaker or switch may be, but is not limited to, power line communication (PLC) or radio frequency (RF).

[0176] In addition, after the fault is isolated, the computer equipment can control and adjust the network routing of the distribution network system to bypass the fault area and restore normal power supply to the non-fault area.

[0177] The technical solution in the embodiments of the present application can obtain the fault area where the fault is located in the distribution network system, and then control at least one power supply in the fault area to shut down, thereby isolating the fault area, preventing the fault from spreading, and improving the safety of the distribution network system. At the same time, it can avoid the impact of faults in the fault area on non-fault areas, thereby ensuring the normal operation of various hardware facilities in the non-fault area.

[0178] In one embodiment, Fig.10 As shown, the above method may further include the following steps:

[0179] S900: Obtain root cause information of a fault occurring in a fault area.

[0180] Specifically, in the case of the acquired fault area, the computer device can perform a fault depth analysis based on the power usage data of each load to obtain the root cause information of the fault occurring in the fault area. Optionally, the root cause information of the fault can be understood as the cause of the fault.

[0181] S910. Formulate a fault repair strategy based on the root cause information, and repair the fault according to the repair strategy.

[0182] In actual applications, computer equipment can search for the root source information of the fault occurring in the fault area among different root source information and fault repair strategies, and determine the fault repair strategy corresponding to the found root source information as the repair strategy for repairing the fault occurring in the fault area, and then output the repair strategy to instruct the operation and maintenance personnel to repair the fault according to the repair strategy.

[0183] In addition, computer equipment can also automatically repair faults that occur in the fault area according to the fault repair strategy.

[0184] At the same time, the computer device can pre-train a repair strategy formulation model, and then input the root cause information of the fault into the repair strategy formulation model, and the repair strategy formulation model outputs the repair strategy for the fault. Optionally, the above-mentioned repair strategy for the fault can include at least one fault repair method, repair patch, configuration parameters, fault repair time and other information.

[0185] Furthermore, after the fault is repaired, the power usage data of the distribution network system can be obtained to verify whether the distribution network system has returned to normal operation based on the power usage data to ensure that no additional faults are introduced after the repair. In addition, the computer device can build a fault log and store information such as the fault area where the fault is located, the fault type, the time point when the fault occurred, the fault repair strategy, and the current scheduling strategy for restoring power to each load in the fault log for subsequent optimization of fault response and preventive measures.

[0186] It should be noted here that during the power restoration process, the distribution network system collects key parameters at a frequency of 1 second, and evaluates the effectiveness of the power restoration operation through trend analysis and threshold comparison. If the service restart of each load fails after the power supply is restored, the distribution network system starts a deep diagnostic program, and through time series data mining and correlation analysis, the root cause of the fault can be located. After the fault is repaired, the distribution network system conducts a continuous 72-hour stability verification to monitor whether the power operation indicators of the distribution network system have returned to normal. Finally, the distribution network system automatically generates a fault handling report, updates the known fault database, optimizes the fault response process, and improves the intelligent operation and maintenance level of the distribution network.

[0187] The technical solution in the embodiment of the present application obtains the root cause information of the fault occurring in the fault area, formulates the fault repair strategy according to the root cause information, and repairs the fault according to the repair strategy; the above method can quickly repair the fault according to the formulated repair strategy for the fault occurring in the fault area, and on the basis of the fault repair, can improve the power supply quality of the distribution network system to a certain extent.

[0188] In one embodiment, the present application also provides a fault handling method, which is applied to a computer device, and the method includes the following process:

[0189] (1) For any distribution network node, if the power usage data of the distribution network node is abnormal, the distribution network node is determined to be a faulty node;

[0190] (2) Determine the fault area based on the fault node and fault location;

[0191] (3) Control at least one power supply in the fault area to shut down to achieve fault isolation.

[0192] (4) assigning a recovery sequence to each load according to the dependency relationship between the loads in the fault area and / or the target load among the loads to obtain an initial priority recovery sequence of each load; the target load includes at least one load with special recovery requirements;

[0193] (5) Determine the measurement index value of each load for power supply according to the importance level of each load;

[0194] (6) adjusting the initial priority recovery sequence according to the measurement index value of each load for power supply to obtain the priority recovery sequence of each load;

[0195] (7) Obtaining the current scheduling strategy for restoring power to each load;

[0196] The steps in (7) above can be implemented in any of the following ways:

[0197] The first method includes:

[0198] (71) determining an initial dispatching strategy for each load based on the initial grid state and initial available resource information of each distribution network node and the power resource information required by each load;

[0199] (72) If the initial grid state and initial available resource information of each distribution network node are changed, the initial dispatching strategy of each load is determined as the current dispatching strategy of each load;

[0200] The second method includes:

[0201] (73) if at least one of the initial grid state and the initial available resource information of each distribution network node changes, obtaining the current grid state and the current available resource information of each distribution network node;

[0202] (74) determining a current dispatching strategy for each load based on the current grid status and currently available resource information of each distribution network node and the power resource information required by each load;

[0203] (8) obtaining auxiliary adjustment information; the auxiliary adjustment information includes at least one of renewable energy information and load balancing supply and demand information;

[0204] (9) adjusting the current scheduling strategy of each load according to the auxiliary adjustment information to obtain an updated scheduling strategy of each load, and using the updated scheduling strategy of each load as the current scheduling strategy of each load;

[0205] (9) Control the restoration of power supply to each load in the fault area according to the priority restoration sequence of each load and the current dispatching strategy of each load;

[0206] The steps in (9) above can be implemented in any of the following ways:

[0207] The first method includes:

[0208] (91) determining a target power source in a non-fault area that can supply power to each load according to an optimal recovery path for each load;

[0209] (92) according to the priority recovery sequence of each load, the recovery strategy of each load is sent to different terminal devices in the distribution network system in turn, instructing different terminal devices to control and enable the corresponding target power supply to restore power supply to each load;

[0210] The second method includes:

[0211] (93) if each target power source is insufficient to support normal operation of each load, determine at least one backup power source in the non-fault area;

[0212] (94) according to the priority recovery sequence of each load, the recovery strategy of each load is sent to different terminal devices in the distribution network system in turn, instructing different terminal devices to control and enable the corresponding backup power supply to restore power supply to each load;

[0213] (10) When the fault area is determined, obtain the root cause information of the fault occurring in the fault area;

[0214] (11) Develop a fault repair strategy based on the root cause information and repair the fault according to the repair strategy.

[0215] The execution process of the above (1) to (11) can be specifically referred to the description of the above embodiment. The implementation principle and technical effect are similar and will not be repeated here.

[0216] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0217] Based on the same inventive concept, the embodiment of the present application also provides a fault handling device for implementing the fault handling method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more fault handling device embodiments provided below can refer to the limitations on the fault handling method above, and will not be repeated here.

[0218] In one embodiment, Fig.11 This is a schematic diagram of the structure of a fault handling device in one embodiment of the present application. The fault handling device provided in the embodiment of the present application can be applied to computer equipment. Fig.11 As shown, the fault handling device of the embodiment of the present application may include: a sequence determination module 11, an acquisition module 12 and a power supply recovery control module 13, wherein:

[0219] A sequence determination module 11, used to determine the priority restoration sequence of each load according to the importance level of each load in the fault area to the user;

[0220] An acquisition module 12 is used to acquire a current scheduling strategy for restoring power supply to each load;

[0221] The power supply restoration control module 13 is used to control the power supply restoration of each load in the fault area according to the priority restoration sequence of each load and the current scheduling strategy of each load.

[0222] The fault handling device provided in the embodiment of the present application can be used to execute the technical solution in the above-mentioned fault handling method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0223] In one embodiment, the sequence determination module 11 includes: a first acquisition unit, a first determination unit and a first adjustment unit, wherein:

[0224] A first acquisition unit is used to acquire an initial priority recovery sequence corresponding to each load in the fault area;

[0225] A first determining unit, configured to determine a measurement index value of each load for power supply according to the importance level of each load;

[0226] The first adjustment unit is used to adjust the initial priority recovery sequence according to the measurement index value of each load for power supply, so as to obtain the priority recovery sequence of each load.

[0227] The fault handling device provided in the embodiment of the present application can be used to execute the technical solution in the above-mentioned fault handling method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0228] In one embodiment, the acquisition unit is specifically used for:

[0229] According to the dependency relationship between the loads and / or the target load among the loads, a recovery sequence is assigned to each load to obtain an initial priority recovery sequence of each load; the target load includes at least one load with special recovery requirements.

[0230] The fault handling device provided in the embodiment of the present application can be used to execute the technical solution in the above-mentioned fault handling method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0231] In one embodiment, the acquisition module 12 includes: a second determination unit and a third determination unit, wherein:

[0232] A second determining unit is used to determine an initial dispatching strategy for each load according to an initial grid state and initial available resource information of each distribution network node and power resource information required by each load;

[0233] The third determining unit is used to determine the initial dispatching strategy of each load as the current dispatching strategy of each load when the initial grid state and the initial available resource information of each distribution network node are changed.

[0234] The fault handling device provided in the embodiment of the present application can be used to execute the technical solution in the above-mentioned fault handling method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0235] In one embodiment, the acquisition module 12 includes: a second acquisition unit and a fourth determination unit, wherein:

[0236] A second acquisition unit, configured to acquire the current grid state and current available resource information of each distribution network node when at least one of the initial grid state and the initial available resource information of each distribution network node changes;

[0237] The fourth determining unit is used to determine the current dispatching strategy of each load according to the current grid state and currently available resource information of each distribution network node, and the power resource information required by each load.

[0238] The fault handling device provided in the embodiment of the present application can be used to execute the technical solution in the above-mentioned fault handling method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0239] In one embodiment, the acquisition module 12 further includes: a third acquisition unit and a second adjustment unit, wherein:

[0240] A third acquisition unit is used to acquire auxiliary adjustment information; the auxiliary adjustment information includes at least one of renewable energy information and load balancing supply and demand information;

[0241] The second adjustment unit is used to adjust the current scheduling strategy of each load according to the auxiliary adjustment information, obtain the updated scheduling strategy of each load, and use the updated scheduling strategy of each load as the current scheduling strategy of each load, and execute the steps of controlling the power supply restoration to each load in the fault area according to the priority recovery sequence of each load and the current scheduling strategy of each load.

[0242] The fault handling device provided in the embodiment of the present application can be used to execute the technical solution in the above-mentioned fault handling method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0243] In one embodiment, the current scheduling strategy includes an optimal restoration path and a restoration strategy; the power restoration control module 13 includes: a fifth determination unit and a first sending unit, wherein:

[0244] A fifth determining unit, configured to determine a target power source in a non-fault area that can supply power to each load according to an optimal recovery path of each load;

[0245] The first sending unit is used to send the recovery strategy of each load to different terminal devices in the distribution network system in turn according to the priority recovery sequence of each load, and instruct different terminal devices to control and enable the corresponding target power supply to restore power supply to each load.

[0246] The fault handling device provided in the embodiment of the present application can be used to execute the technical solution in the above-mentioned fault handling method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0247] In one embodiment, the power supply recovery control module 13 further includes: a sixth determining unit and a second sending unit, wherein:

[0248] A sixth determining unit, configured to determine at least one backup power source in a non-fault area when each target power source is insufficient to support normal operation of each load;

[0249] The second sending unit is used to send the recovery strategy of each load to different terminal devices in the distribution network system in turn according to the priority recovery sequence of each load, and instruct different terminal devices to control the activation of the corresponding backup power supply to restore power supply to each load.

[0250] The fault handling device provided in the embodiment of the present application can be used to execute the technical solution in the above-mentioned fault handling method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0251] In one embodiment, the fault handling device further includes: a fault node determination module, a fault area determination module and a power supply control module, wherein:

[0252] A fault node determination module is used to determine, for any distribution network node, if there is an abnormality in the power usage data of the distribution network node, the distribution network node is determined to be a fault node;

[0253] A fault area determination module is used to determine the fault area according to the fault node and the fault location;

[0254] The fault area determination module is used to control at least one power supply in the fault area to shut down to achieve fault isolation.

[0255] The fault handling device provided in the embodiment of the present application can be used to execute the technical solution in the above-mentioned fault handling method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0256] In one embodiment, the fault handling device further includes: a root information acquisition module and a repair strategy formulation module, wherein:

[0257] A root cause information acquisition module is used to obtain the root cause information of the fault occurring in the fault area;

[0258] The repair strategy formulation module is used to formulate a repair strategy for the fault according to the root cause information and repair the fault according to the repair strategy.

[0259] The fault handling device provided in the embodiment of the present application can be used to execute the technical solution in the above-mentioned fault handling method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0260] For the specific definition of the fault handling device, please refer to the definition of the fault handling method above, which will not be repeated here. Each module in the above-mentioned fault handling device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0261] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.12 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide processing power. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the priority recovery sequence of each load and the current scheduling strategy of each load. The network interface of the computer device is used to communicate with an external endpoint through a network connection. When the computer program is executed by the processor, a fault handling method is implemented.

[0262] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0263] In one embodiment, a computer device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the technical solution in the above-mentioned fault handling method embodiment of the present application is implemented. The implementation principle and technical effect are similar and will not be repeated here.

[0264] In one embodiment, a computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, the technical solution of the above-mentioned fault handling method of the present application is implemented. The implementation principle and technical effect are similar and will not be repeated here.

[0265] In one embodiment, a computer program product is also provided, including a computer program. When the computer program is executed by a processor, the technical solution of the above-mentioned fault handling method of the present application is implemented. The implementation principle and technical effect are similar and will not be repeated here.

[0266] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0267] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0268] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A fault handling method, characterized in that: The method comprises: Determine the priority restoration sequence of each load in the fault area according to the importance level of each load to the user; Obtaining a current scheduling strategy for restoring power supply to each of the loads; According to the priority restoration sequence of each of the loads and the current scheduling strategy of each of the loads, control is performed to restore power supply to each of the loads in the fault area.

2. The method according to claim 1, characterized in that Determining the priority restoration sequence of each load in the fault area according to the importance level of each load to the user includes: Obtaining an initial priority recovery sequence corresponding to each of the loads in the fault area; Determining a measurement index value of each load for power supply according to the importance level of each load; The initial priority recovery sequence is adjusted according to the measurement index value of each load for power supply to obtain the priority recovery sequence of each load.

3. The method according to claim 2, characterized in that The obtaining of the initial priority recovery sequence corresponding to each of the loads in the fault area includes: According to the dependency relationship between the loads and / or the target load among the loads, a recovery sequence is assigned to each load to obtain an initial priority recovery sequence of each load; the target load includes at least one load with special recovery requirements.

4. The method according to any one of claims 1 to 3, characterized in that The obtaining of the current scheduling strategy for restoring power supply to each of the loads includes: Determine an initial dispatching strategy for each of the loads according to the initial grid state and initial available resource information of each distribution network node in the distribution network system, and the power resource information required by each of the loads; If the initial grid state and the initial available resource information of each of the distribution network nodes are changed, the initial scheduling strategy of each of the loads is determined as the current scheduling strategy of each of the loads.

5. The method according to any one of claims 1 to 3, characterized in that: The obtaining of the current scheduling strategy for restoring power supply to each of the loads includes: If at least one of the initial grid state and the initial available resource information of each distribution network node in the distribution network system changes, obtaining the current grid state and the current available resource information of each of the distribution network nodes; The current dispatching strategy of each of the loads is determined based on the current grid status and currently available resource information of each of the distribution network nodes, and the power resource information required by each of the loads.

6. The method according to claim 5, characterized in that The method further comprises: Acquire auxiliary adjustment information; the auxiliary adjustment information includes at least one of renewable energy information and load balancing supply and demand information; According to the auxiliary adjustment information, the current scheduling strategy of each of the loads is adjusted to obtain an updated scheduling strategy for each of the loads, and the updated scheduling strategy for each of the loads is used as the current scheduling strategy for each of the loads. The step of controlling the restoration of power supply to each of the loads in the fault area is executed according to the priority recovery sequence of each of the loads and the current scheduling strategy of each of the loads.

7. The method according to any one of claims 1 to 3, characterized in that The current scheduling strategy includes an optimal restoration path and a restoration strategy; the control of restoring power supply to each of the loads in the fault area according to the priority restoration sequence of each of the loads and the current scheduling strategy of each of the loads includes: Determining a target power source in a non-fault area that can supply power to each of the loads according to an optimal recovery path for each of the loads; According to the priority recovery sequence of each load, the recovery strategy of each load is sent to different terminal devices in the distribution network system in turn, instructing the different terminal devices to control and enable the corresponding target power supply to restore power supply to each load.

8. The method according to claim 7, characterized in that The method further comprises: If each of the target power sources is insufficient to support normal operation of each of the loads, determining at least one backup power source in the non-fault area; According to the priority recovery sequence of each load, the recovery strategy of each load is sent to different terminal devices in the distribution network system in turn, instructing the different terminal devices to control the activation of the corresponding backup power supply to restore power supply to each load.

9. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: For any distribution network node, if there is an abnormality in the power usage data of the distribution network node, the distribution network node is determined to be a faulty node; Determine the fault area according to the fault node and the fault location; At least one power supply in the fault area is controlled to be turned off to achieve fault isolation.

10. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Obtaining root cause information of the fault occurring in the fault area; A repair strategy for the fault is formulated according to the root cause information, and the fault is repaired according to the repair strategy.

11. A fault handling device, characterized in that: The device comprises: A sequence determination module, used to determine the priority restoration sequence of each load in the fault area according to the importance level of each load to the user; An acquisition module, used to acquire a current scheduling strategy for restoring power supply to each of the loads; The power supply restoration control module is used to control the power supply restoration of each load in the fault area according to the priority restoration sequence of each load and the current scheduling strategy of each load.

12. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 10 are implemented.

Images