Online evaluation system of power grid restoration status based on big data

Abstract

The present invention relates to the technical field of data analysis of distribution networks, and in particular to an online evaluation system for power grid restoration status based on big data, comprising a data acquisition module, a status evaluation module, a maintenance prediction module and a remote alarm module. The data acquisition module monitors power grid signals in real time when the power grid is running, and then automatically stores the data generated by the monitoring. In the online evaluation system for power grid restoration status based on big data, the status evaluation module is used to detect the damaged power grid, and when more losses are detected in the power grid, the damage degrees are sorted, and then the remote alarm module is used to remotely report to the staff to restore the power grid in time. In the process of power grid restoration, the restoration time is predicted, and the predicted restoration time is used to calculate whether the common damage situation will cause the problem escalation within the corresponding time, so that the maintenance personnel can be accurately allocated to avoid the waste of human resources.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution network data analysis, and in particular to an online evaluation system for power grid restoration status based on big data. Background Art

[0002] With the development of smart grids, the power supply reliability and power quality provided by traditional distribution networks can no longer meet the needs of users. According to statistics on power grid failures, about 80% of power grid failures come from distribution networks. Moreover, with the access of new energy nodes, voltage fluctuations in active distribution networks and other factors will increase the failure risk of distribution networks.

[0003] In the existing big data analysis, when a large amount of damage occurs to the power grid when used in different environments, staff are required to perform immediate restoration, and then conduct online evaluation based on the restoration time and recovery status. However, in the restoration process, due to a large amount of damage, a large number of staff are urgently needed to restore it. When the power grid is damaged, different damage situations will occur. Different damage situations require different staff to restore at different times. Some damage situations can be repaired within a certain period of time, but some damage situations still need urgent repair. At this time, the number of personnel will be allocated according to the actual situation. However, when allocating personnel, it should also be considered whether the lines with less serious damage will cause the problem to worsen due to untimely repair. Summary of the invention

[0004] The purpose of the present invention is to provide an online evaluation system for power grid restoration status based on big data to solve the problems raised in the above-mentioned background technology. The power grid damage detection unit can not only detect the damage occurring in the power grid operation, but also judge the degree of damage. At the same time, it can allocate the staff who need to restore the power grid according to the degree of damage, and update the historical data to facilitate the comparison of abnormal data next time.

[0005] Therefore, in order to achieve the above purpose, the online evaluation system of power grid restoration status based on big data includes data acquisition module, status evaluation module, maintenance prediction module and remote alarm module;

[0006] The data acquisition module is used to monitor the signals in the power grid in real time and store the signals in the power grid, and the remote alarm module is used for remote alarm, wherein:

[0007] The network monitoring unit is used to establish a power system model, and then estimate the state variables of the power grid, such as data of voltage, current, power and frequency, through the power system model and real-time measurement data. When the power grid is running, the parameters of voltage, current, frequency and power of the power grid are collected in real time by setting sensors to monitor the data of the power grid. The method for monitoring the state variables of the power grid is: the online state estimation method of the power flow equation, and its calculation formula is as follows:

[0008] YV=S+BI

[0009] Y is the Jacobian matrix of the network, which represents the relationship between the voltage and current of the nodes, V is the voltage vector, S is the injected power of the node, and B is the branch matrix of the network, which represents the power flow between the branches.

[0010] The sensor uses the photosensitivity effect to convert the parameters of the power grid into electrical signals.

[0011] The data storage unit is used to periodically perform storage tasks through a timer. In the storage tasks, the location of the stored data is historical data, so that the data detected in the power grid monitoring unit is automatically stored in the historical data, thereby updating the historical data;

[0012] The timer algorithm steps are as follows:

[0013] Step 1: Set the time constant of the timer;

[0014] Step 2: Start the timer;

[0015] Step 3: The timer counter starts to decrease;

[0016] Step 4: When the counter is decremented to , the power grid data collected by the power grid monitoring unit is stored in the historical data;

[0017] Calculation formula:

[0018] The relationship between the time constant TC and the time interval TI of the timer is usually determined by the clock frequency F of the timer:

[0019] TC=TI×F

[0020] Historical data: During the operation of power grid equipment, a large amount of operation data will be generated, such as voltage, current, power, temperature, and humidity. These data are collected and stored by staff for a long time to form historical operation data. The data analysis unit will store new data into it regularly through a timer;

[0021] The state assessment module includes a power grid damage detection unit, a data analysis and comparison unit, and a priority calculation unit. The maintenance prediction module includes a calculation unit and a prediction unit. The power grid damage detection unit is used to detect the voltage and current change rate of the power grid in a short period of time and compare them with the data monitored in real time in the data acquisition module. When the power grid data is abnormal, the state assessment module is used to distinguish the degree of damage to the power grid. Then, the calculation unit is used to calculate the time required for restoration when the power grid is damaged and the number of restoration personnel required for restoration. When the time required for restoration when the power grid is damaged and the number of restoration personnel required for restoration are predicted, the prediction unit is used to compare the maintenance time required for severe damage with the maintenance time that can be waited for ordinary damage.

[0022] When the repair time required for ordinary damage is less than the recovery time for severe damage: the remote alarm module will be used to output to the staff again, and then the staff will promptly assign ordinary damage recovery personnel to restore it;

[0023] When the repair time required for ordinary damage is longer than the recovery time for severe damage, it means that the recovery time for ordinary damage can be restored after the severe damage is restored. After the severe damage is restored, the staff will again assign recovery personnel close to the ordinary damage node for recovery.

[0024] The power grid damage detection unit uses a transient detection method to detect whether the voltage and current change rates of the power grid in a short period of time are abnormal. The calculation formula of the transient detection method is as follows:

[0025] ΔU / Δt=(Upeak-Uavg) / Δt

[0026] ΔI / Δt=(Ipeak-Iavg) / Δt

[0027] ΔP / Δt=(Ppeak-Pavg) / Δt

[0028] Among them, Uavg, Iavg and Pavg represent the average voltage, current and power of the power grid in a short period of time respectively.

[0029] The data analysis and comparison unit is used to analyze the priority of the degree of damage to the power grid through the Z-Score algorithm when the power grid damage detection unit detects that the voltage and current change rates in the power grid have changed abnormally in a short period of time, and compare the abnormal data with the historical data stored in the data storage unit through a direct comparison method;

[0030] The priority calculation unit is used to analyze the priority of the damage degree of the power grid by using the Z-Score algorithm when the damage conditions of the power grid are different.

[0031] Z-Score is a statistic that measures the degree of deviation of a data point from the mean value. The calculation formula is:

[0032]

[0033] Among them, X is the power grid damage data point, μ is the average value of the power grid standard value, σ is the standard deviation, and if the absolute value of the Z value is greater than the power grid standard value, the data point is considered abnormal;

[0034] The direct comparison method is to compare the priorities from high to low with the standard values ​​in the historical data.

[0035] When the priority calculation unit evaluates the degree of damage to the power grid, and after calculating the degree of damage to the power grid, the degree of damage can be automatically saved to the historical data through the timer used by the data storage unit;

[0036] The state evaluation module also includes an evaluation unit, which, after sorting, divides the abnormal values ​​into common damage and severe damage, and at this time, evaluates the severe damage first, and then evaluates the common damage;

[0037] The damage conditions in the power grid are: short circuit, overload, undervoltage, overvoltage, overfrequency, and underfrequency;

[0038] Evaluation system: By calculating the total, average, peak and effective value of the power grid damage, the damage degree in the power grid is evaluated. The calculation formula of the evaluation system is as follows:

[0039]

[0040] The calculation unit predicts the time required to restore the severely damaged power grid and the restoration personnel by analyzing the time from the start to the end of restoring the power grid, and then reports to the staff through the remote alarm module;

[0041] The time from the beginning to the end of restoring the power grid will seriously damage the power grid. The time required to restore the power grid is calculated through the event history analysis model, and the calculation formula is as follows:

[0042] Estimate the survival function, i.e. the probability that the device has not failed before time t,

[0043] For the i-th event time ti, if there are n observations before ti, and d of them occur at ti, then the survival probability S(t) at ti is updated as:

[0044] S(t)=S(t-1)*(1-d / n)

[0045] The KM curve is usually drawn with time t as the horizontal axis and the survival probability S(t) as the vertical axis.

[0046] The prediction unit calculates the recovery time required for severe damage through the calculation unit and substitutes it into the calculation formula for the repair waiting time required for ordinary damage, and then predicts the waiting time for recovery of ordinary damage. At this time, the statistics of the deviation degree between the data points and the average value are used to analyze whether the damage situation in the ordinary situation will be upgraded due to the required recovery time in the severe damage situation;

[0047] When multiple common damages cannot be restored within the recovery time of severe damages, a secondary report will be sent to the staff through the remote alarm module to prompt the staff to restore the damage in time;

[0048] When multiple common damages can be restored after the recovery time of serious damages, the remote alarm module will be used to report to the staff for the second time, and the staff will arrange the restoration time by themselves;

[0049] The data screening unit screens the damaged values ​​in the power grid with the values ​​in the historical data by a unique identification method, and then automatically saves the new values ​​after screening into the historical data, and then provides a reference for the next damage;

[0050] The unique identification method identifies duplicates by checking the unique identifier in the historical data. If two records have the same unique identifier, they are considered duplicates.

[0051] The remote alarm module includes a signal receiving unit and an alarm priority management unit;

[0052] The signal receiving unit monitors the dynamic changes of abnormal data in real time to detect abnormalities in time, thereby receiving the damage situation and recovery time in the power grid, and then remotely reporting to the staff;

[0053] The detection change rate is calculated by the following formula:

[0054] Assume we have two consecutive data points x1 and x2, whose time interval is Δt, and the rate of change Δx is calculated by the following formula:

[0055]

[0056] After the alarm priority unit has identified the degree of damage to the power grid through the data analysis and comparison unit, it will give different degrees of alarms for common damage and severe damage to the power grid.

[0057] The remote alarm module also includes a power grid recovery assessment unit, which is used to compare the stability of the power grid after recovery with that of the power grid before recovery through a direct comparison method, and then manually evaluate the power grid status through staff, and then record the evaluation results in historical data.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] In this online assessment system of power grid recovery status based on big data, a status assessment module is used to detect damaged power grids. When multiple losses are detected in the power grid, the degree of damage is ranked, and then the remote alarm module is used to remotely report to the staff to restore the power grid in a timely manner. During the power grid restoration process, the recovery time is predicted, and the predicted recovery time is used to calculate whether the common damage situation will escalate within the corresponding time, so that maintenance personnel can be accurately allocated to avoid waste of human resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is the overall module principle diagram of the present invention;

[0061] Figure 2 It is the principle diagram of the data acquisition module of the present invention;

[0062] Figure 3 It is the principle diagram of the state assessment module of the present invention;

[0063] Figure 4 This is a schematic diagram of the maintenance prediction module of the present invention;

[0064] Figure 5 This is a schematic diagram of a remote alarm module of the present invention;

[0065] Figure 6 It is the operating principle diagram of the present invention.

[0066] The meaning of each number in the figure is:

[0067] 100, data acquisition module; 110, power grid monitoring unit; 120, data storage unit;

[0068] 200, state assessment module; 210, power grid damage detection unit; 220, data analysis and comparison unit; 230, priority calculation unit; 240, assessment unit;

[0069] 300, maintenance prediction module; 310, calculation unit; 320, prediction unit; 330, data screening unit;

[0070] 400, remote alarm module; 410, signal receiving unit; 420, alarm priority management unit; 430, power grid restoration assessment unit. DETAILED DESCRIPTION

[0071] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0072] The online evaluation system of power grid restoration status based on big data includes a data acquisition module 100, a status evaluation module 200, a maintenance prediction module 300 and a remote alarm module 400;

[0073] The data acquisition module 100 is used to monitor the signals in the power grid in real time and store the signals in the power grid. The remote alarm module 400 is used for remote alarm, wherein:

[0074] The network monitoring unit 110 is used to establish a power system model, and then estimate the state variables of the power grid, such as data of voltage, current, power and frequency, through the power system model and real-time measurement data. When the power grid is running, the parameters of voltage, current, frequency and power of the power grid are collected in real time by setting sensors to monitor the data of the power grid. The method for monitoring the state variables of the power grid is: the online state estimation method of the power flow equation, and its calculation formula is as follows:

[0075] YV=S+BI

[0076] Y is the Jacobian matrix of the network, which represents the relationship between the voltage and current of the nodes, V is the voltage vector, S is the injected power of the node, and B is the branch matrix of the network, which represents the power flow between the branches.

[0077] The sensor uses the photosensitivity effect to convert the parameters of the power grid into electrical signals.

[0078] The data storage unit 120 is used to periodically perform storage tasks through a timer. In the storage tasks, the location of the stored data is historical data, so that the data detected in the power grid monitoring unit 110 is automatically stored in the historical data, thereby updating the historical data;

[0079] The timer algorithm steps are as follows:

[0080] Step 1: Set the time constant of the timer;

[0081] Step 2: Start the timer;

[0082] Step 3: The timer counter starts to decrease;

[0083] Step 4: When the counter is decremented to 0, the power grid data collected by the power grid monitoring unit 110 is stored in the historical data;

[0084] Calculation formula:

[0085] The relationship between the time constant TC and the time interval TI of the timer is usually determined by the clock frequency F of the timer:

[0086] TC=TI×F

[0087] Historical data: During the operation of the power grid equipment, a large amount of operation data will be generated, such as voltage, current, power, temperature, and humidity. These data are collected and stored by the staff for a long time to form historical operation data. The data analysis unit 120 can store new data into it regularly through the timer;

[0088] The state assessment module 200 includes a power grid damage detection unit 210, a data analysis and comparison unit 220, and a priority calculation unit 230. The maintenance prediction module 300 includes a calculation unit 310 and a prediction unit 320. The power grid damage detection unit 210 is used to detect the voltage and current change rate of the power grid in a short period of time and compare it with the data monitored in real time in the data acquisition module 100. When the power grid data is abnormal, the state assessment module 200 is used to distinguish the degree of damage to the power grid. Then, the calculation unit 310 is used to calculate the time required for restoration when the power grid is damaged and the number of restoration personnel required for restoration. When the time required for restoration when the power grid is damaged and the number of restoration personnel required for restoration are predicted, the prediction unit 320 is used to compare the maintenance time required for severe damage with the maintenance time that can be waited for ordinary damage.

[0089] When the repair time required for ordinary damage is less than the recovery time for severe damage: the remote alarm module 400 will output the information to the staff again, and then the staff will promptly assign ordinary damage recovery personnel to restore the equipment;

[0090] When the repair time required for ordinary damage is longer than the recovery time for severe damage, it means that the recovery time for ordinary damage can be restored after the severe damage is restored. After the severe damage is restored, the staff will again assign recovery personnel close to the ordinary damage node for recovery.

[0091] The power grid damage detection unit 210 uses a transient detection method to detect whether there is an abnormality in the voltage and current change rate of the power grid in a short period of time. The calculation formula of the transient detection method is as follows:

[0092] ΔU / Δt=(Upeak-Uavg) / Δt

[0093] ΔI / Δt=(Ipeak-Iavg) / Δt

[0094] ΔP / Δt=(Ppeak-Pavg) / Δt

[0095] Among them, Uavg, Iavg and Pavg represent the average voltage, current and power of the power grid in a short period of time respectively.

[0096] The data analysis and comparison unit 220 is used to analyze the priority of the degree of damage to the power grid by using the Z-Score algorithm when the power grid damage detection unit 210 detects that the voltage and current change rates in the power grid have changed abnormally in a short period of time, and compare the abnormal data with the historical data stored in the data storage unit 120 by a direct comparison method;

[0097] The priority calculation unit 230 is used to analyze the priority of the damage degree of the power grid by using the Z-Score algorithm when the damage conditions of the power grid are different.

[0098] Z-Score is a statistic that measures the degree of deviation of a data point from the mean value. The calculation formula is:

[0099]

[0100] Among them, X is the power grid damage data point, μ is the average value of the power grid standard value, σ is the standard deviation, and if the absolute value of the Z value is greater than the power grid standard value, the data point is considered abnormal;

[0101] The direct comparison method is to compare the priorities from high to low with the standard values ​​in the historical data.

[0102] The priority calculation unit 230 evaluates the degree of damage to the power grid, and after calculating the degree of damage to the power grid, the degree of damage can be automatically saved to the historical data through the timer used by the data storage unit 120;

[0103] The state evaluation module 200 further includes an evaluation unit 240. After the sorting, the evaluation unit 240 classifies the abnormal values ​​into common damage and severe damage. At this time, the severe damage is evaluated first, and then the common damage is evaluated.

[0104] The damage conditions in the power grid are: short circuit, overload, undervoltage, overvoltage, overfrequency, and underfrequency;

[0105] Evaluation system: By calculating the total, average, peak and effective value of the power grid damage, the damage degree in the power grid is evaluated. The calculation formula of the evaluation system is as follows:

[0106]

[0107] The calculation unit 310 predicts the time and personnel required to restore the severely damaged power grid by analyzing the time from the start to the end of restoring the power grid, and then reports to the staff through the remote alarm module 400;

[0108] The time from the beginning to the end of restoring the power grid will seriously damage the power grid. The time required to restore the power grid is calculated through the event history analysis model, and the calculation formula is as follows:

[0109] Estimate the survival function, i.e. the probability that the device has not failed before time t

[0110] For the i-th event time ti, if there are n observations before ti, and d of them occur at ti, then the survival probability S(t) at ti is updated as:

[0111] S(t)=S(t-1)*(1-d / n)

[0112] The KM curve is usually drawn with time t as the horizontal axis and the survival probability S(t) as the vertical axis.

[0113] The prediction unit 320 calculates the recovery time required for severe damage through the calculation unit 310 and substitutes it into the calculation formula for the waiting time for ordinary damage, and then predicts the waiting time for ordinary damage to recover. At this time, the statistics of the deviation degree between the data point and the average value are used to analyze whether the damage situation in the ordinary situation will be upgraded due to the required recovery time in the severe damage situation.

[0114] When the calculation unit (310) calculates that the common damages cannot be restored within the restoration time of the serious damages, a second report will be sent to the staff through the remote alarm module (400) to prompt the staff to restore the damages in time;

[0115] When the calculation unit (310) calculates that the multiple common damages can be restored after the recovery time of the serious damages, the remote alarm module (400) will report it to the staff for the second time, and the staff will arrange the restoration time by themselves;

[0116] The data screening unit 330 screens the damaged values ​​in the power grid with the values ​​in the historical data by a unique identification method, and then automatically saves the new values ​​after screening into the historical data, and then provides a reference for the next damage;

[0117] The unique identification method identifies duplicates by checking the unique identifier in the historical data. If two records have the same unique identifier, they are considered duplicates.

[0118] The remote alarm module 400 includes a signal receiving unit 410 and an alarm priority management unit 420;

[0119] The signal receiving unit 410 monitors the dynamic changes of abnormal data in real time to detect abnormalities in time, thereby receiving the damage situation and recovery time in the power grid, and then remotely reporting to the staff;

[0120] The detection change rate is calculated by the following formula:

[0121] Assume we have two consecutive data points x1 and x2, whose time interval is Δt, and the rate of change Δx is calculated by the following formula:

[0122]

[0123] After the alarm priority unit 420 has identified the degree of damage to the power grid through the data analysis and comparison unit 220, it will give different degrees of alarms for common damage and severe damage to the power grid.

[0124] The remote alarm module 400 also includes a power grid recovery assessment unit 430, which is used to compare the stability of the power grid after recovery with that of the power grid before recovery through a direct comparison method, and then manually evaluate the power grid status through staff, and then record the evaluation results in historical data.

[0125] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. The online evaluation system of power grid restoration status based on big data is characterized by: It comprises a data acquisition module (100), a status assessment module (200), a maintenance prediction module (300) and a remote alarm module (400); The data acquisition module (100) is used to monitor the signals in the power grid in real time and store the signals in the power grid, and the remote alarm module (400) is used for remote alarm, wherein: The state assessment module (200) comprises a power grid damage detection unit (210), a data analysis and comparison unit (220), and a priority calculation unit (230); the maintenance prediction module (300) comprises a calculation unit (310) and a prediction unit (320); after the state assessment module (200) detects the voltage and current change rates of the power grid in a short period of time, it compares them with the data monitored in real time in the data acquisition module (100); and when the power grid data is abnormal, the data analysis and comparison unit (220) is used to distinguish the degree of damage to the power grid, and then the calculation unit (310) is used to calculate the time required for restoration when the power grid is damaged and the number of restoration personnel required for restoration, and when the time required for restoration when the power grid is damaged and the number of restoration personnel required for restoration are predicted, the prediction unit (320) is used to compare the maintenance time required for severe damage with the maintenance time that can be waited for ordinary damage; When the time required for repairing ordinary damage is less than the time required for restoring severe damage, the alarm will be output to the staff again through the remote alarm module (400), and then the staff will promptly assign ordinary damage restoration personnel to restore the damage; When the repair time required for ordinary damage is longer than the recovery time for severe damage, it means that the recovery time for ordinary damage can be restored after the severe damage is restored. After the severe damage is restored, the staff will again assign the recovery personnel who are close to the ordinary damage node for recovery; The calculation unit (310) predicts the time required for restoration of the severely damaged power grid and the restoration personnel by analyzing the time from the start to the end of restoring the power grid, and then reports to the staff through the remote alarm module (400); The prediction unit (320) calculates the recovery time required for severe damage through the calculation unit (310) and substitutes it into the calculation formula for the repair waiting time required for ordinary damage, and then predicts the waiting time for recovery of ordinary damage. At this time, the statistical quantity that measures the degree of deviation between the data point and the average value is used to analyze whether the damage situation in the ordinary situation will cause the damage situation to escalate due to the required recovery time in the severe damage situation; When the calculation unit (310) calculates that the multiple common damages cannot be restored after the recovery time of the serious damages, a second report will be sent to the staff through the remote alarm module (400) to prompt the staff to restore in time; When the calculation unit (310) calculates that the multiple common damages can be restored after the restoration time of the serious damages, the remote alarm module (400) will report the restoration to the staff for the second time, and the staff will arrange the restoration time by themselves; The remote alarm module (400) comprises a signal receiving unit (410) and an alarm priority management unit (420); The signal receiving unit (410) monitors the dynamic changes of abnormal data in real time so as to timely discover abnormalities, thereby receiving damage conditions and recovery time in the power grid, and then remotely reporting to staff; After the alarm priority unit (420) has identified the degree of damage to the power grid through the data analysis and comparison unit (220), it issues alarms of different degrees for common damage and severe damage to the power grid.

2. The online evaluation system for power grid restoration status based on big data according to claim 1 is characterized in that: The data acquisition module (100) comprises: a power grid monitoring unit (110) and a data storage unit (120); The grid monitoring unit (110) is used to estimate the state variables of the grid, such as data of voltage, current, power and frequency, by combining the power system model and real-time measurement data. When the grid is running, the grid data is monitored by setting sensors to collect the parameters of voltage, current, frequency and power of the grid in real time; The data storage unit (120) is used to periodically execute a storage task through a timer. In the storage task, the location of the stored data is historical data, so that the data detected in the power grid monitoring unit (110) is automatically stored in the historical data, thereby updating the historical data.

3. The online evaluation system for power grid restoration status based on big data according to claim 1 is characterized in that: The power grid damage detection unit (210) is used to detect whether the voltage and current change rates of the power grid in a short period of time are different from the values ​​in historical data, and to obtain abnormal data; The data analysis and comparison unit (220) is used to analyze the priority of the degree of damage to the power grid by using a Z-Score algorithm when the power grid damage detection unit (210) detects that the rate of change of voltage and current in the power grid has changed abnormally in a short period of time, and to compare the abnormal data with the historical data stored in the data storage unit (120) by using a direct comparison method; The priority calculation unit (230) evaluates the degree of damage to the power grid and after calculating the degree of damage to the power grid, the degree of damage can be automatically saved into historical data through a timer used by the data storage unit (120); The direct comparison method is to compare the priorities from large to small with the standard values ​​in historical data.

4. The online evaluation system for power grid restoration status based on big data according to claim 1 is characterized in that: The state assessment module (200) further comprises an assessment unit (240), wherein the assessment unit (240) classifies abnormal values ​​into common damage and severe damage after sorting, and at this time, the severe damage is assessed first, and then the common damage is assessed, and the damage conditions in the power grid include short circuit, overload, undervoltage, overvoltage, overfrequency, and underfrequency; By calculating the total, average, peak and effective value of the power grid damage, the damage degree in the power grid is evaluated, and the evaluation calculation formula is as follows: 。 5. The online evaluation system for power grid restoration status based on big data according to claim 1 is characterized in that: The maintenance prediction module (300) further includes a data screening unit (330); The data screening unit (330) identifies duplicates by checking unique data in the historical data. If two records have the same unique identifier, they are considered to be duplicates, thereby screening the damage value in the power grid with the value in the historical data, and then automatically saving the new value after screening to the historical data, which then provides a reference for the next damage.

6. The online evaluation system for power grid restoration status based on big data according to claim 1 is characterized in that: The remote alarm module (400) further comprises a power grid recovery assessment unit (430), which is used to compare the stability of the power grid after recovery with that of the power grid before recovery by a direct comparison method, and then manually assess the power grid status by staff and record it in historical data.

Images