Power failure risk early warning system and method based on real-time state of power grid

Abstract

The invention discloses a power failure risk early warning system and method based on the real-time state of a power grid, and relates to the technical field of power grid monitoring, and the system comprises a data collection module, a power grid analysis module, an interval evaluation module and an early warning evaluation module. The method comprises the following steps: analyzing the collected number of holidays, power consumption data and temperature data to obtain a sudden change load difference value, predicting the sudden change date of the week based on the predicted temperature, and finally performing early warning evaluation on the power consumption data of the week based on the sudden change load difference value and the sudden change date and sending out an early warning signal; the method is used for solving the problems that an existing power failure risk early warning technology does not carry out sudden change analysis on other sudden environment data, an obtained power failure risk early warning result is not accurate enough, and emergency situations cannot be coped with.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid monitoring, and in particular to a power outage risk early warning system and method based on the real-time status of a power grid. Background Art

[0002] Power outage risk warning refers to the release of early warning information through monitoring and analysis of various factors that may affect the operation of the power grid so that appropriate response measures can be taken to ensure the safe and stable operation of the power grid.

[0003] Existing power outage risk warning methods usually collect power grid data and environmental data and then analyze the real-time status of the power grid to obtain a power outage risk warning. For example, in a patent application with publication number CN119047846A, a household electricity metering data security risk warning method and system are disclosed. The solution is to collect load power time series data, temperature, and holiday data for the past seven days, generate a first calibration coefficient, calibrate the load power data and divide it into intervals by time; collect the average, maximum, and minimum power of each interval, set a weight coefficient, and generate reference power data; collect power, holiday, and temperature data in real time, generate a second calibration coefficient, calibrate the monitored power data, calculate the average power and power growth rate, comprehensively generate a power change index, and compare it with the safety risk threshold to determine whether the power metering data is abnormal, and issue a warning if it is abnormal; this method does not perform sudden change analysis on other sudden environmental data, so there is a problem that the warning result obtained is not accurate enough and cannot cope with emergencies. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the prior art to at least a certain extent, by analyzing the collected weekend holidays, electricity consumption data and temperature data to obtain a sudden load difference, predicting the sudden change date of this week based on the predicted temperature, and finally performing an early warning evaluation on this week's electricity consumption data based on the sudden load difference and the sudden change date and issuing an early warning signal, so as to solve the problem that the existing power outage risk early warning technology does not perform sudden change analysis on other sudden environmental data, and the resulting power outage risk early warning results are not accurate enough to cope with emergencies.

[0005] In a first aspect, the present invention provides a power outage risk warning system based on the real-time status of a power grid, including a data acquisition module, a power grid analysis module, an interval assessment module, and a warning assessment module;

[0006] The data collection module is used to collect and record the number of days of weekly holidays, electricity consumption data and temperature data from the big data;

[0007] The power grid analysis module analyzes the power consumption data based on the number of days of the week and holidays to obtain the power load parameter interval, and analyzes the temperature data to obtain the sudden load difference;

[0008] The interval evaluation module obtains this week's predicted temperature data from the Meteorological Bureau, predicts this week's sudden change date based on this week's predicted temperature data, and corrects the power load parameter interval based on this week's sudden change date and sudden change load difference to obtain a reference interval;

[0009] The early warning assessment module performs early warning assessment on the electricity consumption data of this week based on the reference interval and issues an early warning signal.

[0010] Furthermore, the data collection module includes an electricity consumption collection unit, and the electricity consumption collection unit is configured with an electricity consumption collection strategy. The electricity consumption collection strategy includes obtaining a target power plant and its corresponding electricity consumption area, recording the unit power generation of the target power plant and the unit power consumption of the electricity consumption area, and setting them as electricity consumption data.

[0011] Furthermore, the data acquisition module also includes other acquisition units, and the other acquisition units are configured with other acquisition strategies. The other acquisition strategies include obtaining the number of holidays and working days per week from big data; obtaining the real-time temperature in the power consumption area from the Meteorological Bureau and setting it as temperature data.

[0012] Further, the power grid analysis module includes a power consumption analysis unit, the power consumption analysis unit is configured with a power consumption analysis strategy, the power consumption analysis strategy includes acquiring power consumption data from the data acquisition module, setting the ratio of unit power consumption to unit power generation at the same time as the power load, and using a fitting correction method to screen and correct the power load;

[0013] The fitting correction method includes: establishing a plane rectangular coordinate system, recorded as a load screening coordinate system, obtaining the power load corresponding to each hour in the power consumption area, and marking points in the load screening coordinate system with the power load as the ordinate and time as the abscissa; fitting the power load corresponding to each hour in the power consumption area in the load screening coordinate system into a curve, recorded as a load relationship curve;

[0014] For any point A in the load screening coordinate system, draw a straight line parallel to the y-axis from point A, and record the intersection of the straight line and the load relationship curve as point B, and record the distance between point A and point B as the screening distance; obtain the screening distances of all points in the load screening coordinate system, and record the point corresponding to the longest screening distance as C;

[0015] Draw a straight line parallel to the y-axis from point C, and record the intersection of the straight line and the load relationship curve as point D, obtain the ordinate of point D, and replace the ordinate of point C with the ordinate of point D to obtain the correction relationship curve;

[0016] Obtain the correction relationship curves for working days and holidays respectively; obtain the workload peak value and workload valley value from the correction relationship curve for working days; obtain the holiday load peak value and holiday load valley value from the correction relationship curve for holidays;

[0017] Establishing a working power load parameter interval, setting the working load valley value as the minimum value of the working power load parameter interval, and setting the working load peak value as the maximum value of the working power load parameter interval;

[0018] Establish a holiday power load parameter interval, set the holiday load valley value as the minimum value of the holiday power load parameter interval, and set the holiday load peak value as the maximum value of the holiday power load parameter interval;

[0019] The working power load parameter range and the holiday power load parameter range are collectively referred to as the power load parameter range.

[0020] Further, the power grid analysis module also includes a temperature analysis unit, the temperature analysis unit is configured with a temperature analysis strategy, the temperature analysis strategy includes using a sudden change analysis method to analyze the temperature data to obtain a sudden change date;

[0021] The sudden change analysis method includes obtaining the daily average temperature in the power consumption area for a week, and for any day M in a week, using the elimination fluctuation formula to obtain the elimination fluctuation parameter of the Mth day, the elimination fluctuation formula is: Among them, S(M) is the fluctuation elimination parameter, Ti is the daily average temperature of the i-th day except the M-th day, and T0 is the average of all daily average temperatures except the M-th day;

[0022] Establish a line graph of daily average temperature changes, with time as the horizontal axis and daily average temperature as the vertical axis. Set the slope between any two adjacent points as the change rate, and set the day with the largest change rate as the pending day; when the elimination fluctuation parameter of the pending day is less than the average value of all the elimination fluctuation parameters, the pending day is recorded as the sudden change date;

[0023] The daily average power load before the sudden change date is set as the normal power load, and the power load corresponding to the sudden change date is set as the sudden change power load; the difference between the sudden change power load and the normal power load is obtained to obtain the sudden change load difference.

[0024] Further, the interval assessment module is configured with a state assessment strategy, which includes obtaining the number of holidays this week from big data when performing state assessment, obtaining the power load parameter interval and sudden load difference with the same number of holidays from historical data based on the number of holidays this week, and setting them as standard power load parameter interval and standard sudden load difference, wherein the standard power load parameter interval includes a standard working power load parameter interval and a standard holiday power load parameter interval;

[0025] Use the sudden change analysis method to analyze the predicted temperature data and obtain the sudden change date;

[0026] The standard power load parameter interval before the sudden change date is set as a first reference interval, wherein the first reference interval includes a first working reference interval and a first holiday reference interval;

[0027] The maximum value and the minimum value of the standard power load parameter interval on and after the sudden change date are both adjusted upward to obtain a second reference interval, wherein the second reference interval includes a second working reference interval and a second holiday reference interval; the amount of the upward adjustment is the sudden change load difference;

[0028] The reference interval includes a first reference interval and a second reference interval.

[0029] Further, the early warning evaluation module is configured with an early warning evaluation strategy, and the early warning evaluation strategy includes, when the electricity consumption data of this week is obtained, performing electricity consumption analysis on the electricity consumption data of this week to obtain a real-time electricity load parameter interval;

[0030] Use the early warning comparison method to compare the real-time power load parameter intervals and output a real-time risk-free signal or an early warning signal. The early warning comparison method includes: for any real-time power load parameter interval, if and only if the minimum value of the real-time power load parameter interval is greater than or equal to the minimum value of the reference interval and the maximum value of the power load parameter interval is less than or equal to the maximum value of the reference interval, output a real-time risk-free signal, otherwise output a early warning signal;

[0031] For the electricity consumption data before the sudden change date, when the real-time electricity consumption data of this week is obtained on a working day, the first working reference interval is used for comparison; when the real-time electricity consumption data of this week is obtained on a holiday, the first holiday reference interval is used for comparison;

[0032] For the electricity consumption data after the sudden change date, when the real-time electricity consumption data for this week is on a working day, the second working reference interval is used for comparison; when the real-time electricity consumption data for this week is on a holiday, the second holiday reference interval is used for comparison.

[0033] In a second aspect, the present invention also provides a power outage risk warning method based on the real-time status of the power grid, comprising the following steps:

[0034] Collect and record weekly holidays, electricity consumption data, and temperature data from big data;

[0035] The power consumption data is analyzed based on the number of days in the week and holidays to obtain the power load parameter range, and the temperature data is analyzed to obtain the sudden load difference;

[0036] Obtain this week's forecast temperature data from the Meteorological Bureau, predict this week's sudden change date based on this week's forecast temperature data, calibrate the power load parameter range based on this week's sudden change date and sudden change load difference to obtain a reference range;

[0037] Based on the reference range, a risk warning assessment is conducted on this week’s electricity consumption data and a warning signal is issued.

[0038] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the above method are performed.

[0039] In a fourth aspect, the present application provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the above method are performed.

[0040] Beneficial effects of the present invention: The present invention first collects and records the number of days of the week and holidays, electricity consumption data and temperature data from big data, and then analyzes the electricity consumption data based on the number of days of the week and holidays to obtain the power load parameter interval. The residential electricity consumption data will change periodically with the change of time and the rotation of working days. Therefore, after collecting the number of days of the week and holidays, the power load parameter interval obtained by analyzing the electricity consumption data in different periods is more accurate, thereby improving the accuracy of the early warning result;

[0041] The present invention also obtains the sudden load difference by analyzing the temperature data. The temperature has a greater impact on the electricity consumption of residents and then on the grid load. In particular, a sudden change in temperature will cause a sudden change in the electricity consumption of the grid. Therefore, the sudden change in temperature can be judged by analyzing the temperature data. The sudden load difference obtained by analysis can reflect the impact of the sudden temperature change, has a high data reference value, and provides accurate data support for subsequent risk prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a functional block diagram of the system of the present invention;

[0043] Figure 2 It is a schematic diagram of the load screening coordinate system of the present invention;

[0044] Figure 3It is a schematic diagram of a line graph of daily average temperature variation of the present invention;

[0045] Figure 4 is a flow chart of the steps of the method of the present invention;

[0046] Figure 5 It is a schematic structural diagram of the electronic device of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of 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.

[0048] Example 1, please refer to Figure 1 As shown, the present application provides a power outage risk warning system based on the real-time status of the power grid, including a data acquisition module, a power grid analysis module, an interval assessment module and a warning assessment module;

[0049] The data collection module is used to collect and record the number of days of weekly holidays, electricity consumption data and temperature data from big data; the data collection module includes an electricity consumption collection unit, and the electricity consumption collection unit is configured with an electricity consumption collection strategy. The electricity consumption collection strategy includes obtaining the target power plant and its corresponding power consumption area, recording the unit power generation of the target power plant and the unit power consumption of the power consumption area, and setting them as power consumption data; in the specific implementation process, the average power generation per hour is recorded as the real-time unit power generation, and some of the recorded power consumption data are shown in Table 1 below:

[0050] Recording time Unit power generation (MW) Unit power consumption (MW) 12:00 450 300 13:00 425 330 14:00 380 220 15:00 350 200

[0051] Table 1

[0052] The data collection module also includes other collection units, which are configured with other collection strategies. The other collection strategies include obtaining the number of holidays and working days per week from big data; obtaining the real-time temperature in the power consumption area from the Meteorological Bureau and setting it as temperature data;

[0053] The power grid analysis module analyzes the power consumption data based on the number of holidays to obtain the power load parameter range, and analyzes the temperature data to obtain the sudden load difference;

[0054] The power grid analysis module includes a power consumption analysis unit, which is configured with a power consumption analysis strategy. The power consumption analysis strategy includes obtaining power consumption data from the data acquisition module, setting the ratio of unit power consumption to unit power generation at the same time as the power load, and using the fitting correction method to screen and correct the power load. In the specific implementation process, when acquiring power grid data, circuit failures and other reasons may occur, resulting in a large fluctuation in the collected regional power consumption, so it is necessary to screen and correct the power load.

[0055] The fitting correction method includes: establishing a plane rectangular coordinate system, recorded as the load screening coordinate system, obtaining the corresponding power load in the power consumption area every hour, and marking points in the load screening coordinate system with the power load as the ordinate and time as the abscissa; fitting the corresponding power load in the power consumption area every hour in the load screening coordinate system into a curve, recorded as the load relationship curve;

[0056] For any point A in the load screening coordinate system, draw a straight line parallel to the y-axis from point A, and record the intersection of the straight line and the load relationship curve as point B, and record the distance between point A and point B as the screening distance; obtain the screening distances of all points in the load screening coordinate system, and record the point corresponding to the longest screening distance as C;

[0057] Draw a straight line parallel to the y-axis from point C, and record the intersection of the straight line and the load relationship curve as point D, obtain the ordinate of point D, and replace the ordinate of point C with the ordinate of point D to obtain the correction relationship curve;

[0058] In a specific implementation, for example, in a processing process, the load screening coordinate system obtained is as follows: Figure 2 As shown, curve L1 is the load relationship curve, point B is the intersection of the straight line parallel to the y-axis from point A and the load relationship curve, and line segment L2 is the longest screening distance;

[0059] Obtain the correction relationship curves for working days and holidays respectively; obtain the workload peak value and workload valley value from the correction relationship curve for working days; obtain the holiday load peak value and holiday load valley value from the correction relationship curve for holidays;

[0060] Establish a working power load parameter interval, set the working load valley value as the minimum value of the working power load parameter interval, and set the working load peak value as the maximum value of the working power load parameter interval; in the specific implementation process, for example, in a data analysis process, the obtained working load peak value is 80%, and the working load valley value is 50%, then the working power load parameter interval is [50%, 80%];

[0061] Establish a holiday power load parameter interval, set the holiday load valley value as the minimum value of the holiday power load parameter interval, and set the holiday load peak value as the maximum value of the holiday power load parameter interval; in the specific implementation process, for example, in a data analysis process, the holiday load peak value is 86%, and the holiday load valley value is 62%, then the holiday power load parameter interval is [62%, 86%];

[0062] The working power load parameter range and the holiday power load parameter range are collectively referred to as the power load parameter range.

[0063] The power grid analysis module also includes a temperature analysis unit, which is configured with a temperature analysis strategy. The temperature analysis strategy includes using a sudden change analysis method to analyze the temperature data to obtain a sudden change date.

[0064] The sudden change analysis method includes obtaining the daily average temperature in the power consumption area for a week. For any day M in a week, the elimination fluctuation formula is used to obtain the elimination fluctuation parameter of the Mth day. The elimination fluctuation formula is: Wherein, S(M) is the fluctuation elimination parameter, Ti is the daily average temperature of the i-th day except the M-th day, and T0 is the average of all daily average temperatures except the M-th day; in the specific implementation process, for example, in a data processing process, the daily average temperatures obtained are 22°C, 20°C, 19°C, 21°C, 11°C, 10°C and 12°C, respectively, and the fluctuation elimination parameters S(1) to S(7) obtained are 4.57, 4.95, 5.00, 4.79, 4.6, 4.35 and 4.81 respectively;

[0065] See also Figure 3 As shown, a line graph of daily average temperature change is established, with time as the horizontal axis and daily average temperature as the vertical axis. The slope between any two adjacent points is set as the change rate, and the day with the largest change rate is set as the pending day; when the elimination fluctuation parameter of the pending day is less than the average value of all the elimination fluctuation parameters, the pending day is recorded as the sudden change date; in the specific implementation process, for example, in a data processing process, the pending day is the fifth day, and the elimination fluctuation parameters S(1) to S(7) obtained are 4.57, 4.95, 5.00, 4.79, 4.6, 4.35, and 4.81, respectively. The average value of all the elimination fluctuation parameters is 4.72. At this time, the elimination fluctuation parameter S(5) of the fifth day is 4.6, and 4.6<4.72, so the fifth day is set as the sudden change date;

[0066] The daily average power load before the sudden change date is set as the normal power load, and the power load corresponding to the sudden change date is set as the sudden change power load; the difference between the sudden change power load and the normal power load is obtained to obtain the sudden change load difference; in the specific implementation process, for example, in a data processing process, the sudden change date obtained is the 5th day, the daily average power load from the 1st to the 4th day is obtained and set as the normal power load, which is 70% in this embodiment, and the power load corresponding to the sudden change date is set as the sudden change power load, which is 78% in this embodiment, and the sudden change load difference is 8%.

[0067] The interval evaluation module obtains this week's predicted temperature data from the Meteorological Bureau, predicts this week's sudden change date based on this week's predicted temperature data, and corrects the power load parameter interval based on this week's sudden change date and sudden change load difference to obtain a reference interval;

[0068] The interval assessment module is configured with a state assessment strategy. The state assessment strategy includes obtaining the number of holidays this week from big data when conducting state assessment, obtaining the power load parameter interval and sudden load difference with the same number of holidays from historical data based on the number of holidays this week, and setting them as standard power load parameter interval and standard sudden load difference. The standard power load parameter interval includes standard working power load parameter interval and standard holiday power load parameter interval; in the specific implementation process, when selecting the power load parameter interval and sudden load difference with the same number of holidays as this week, the data closest to this week is selected first;

[0069] Use the sudden change analysis method to analyze the predicted temperature data and obtain the sudden change date;

[0070] The standard power load parameter interval before the sudden change date is set as the first reference interval, and the first reference interval includes the first working reference interval and the first holiday reference interval;

[0071] The maximum value and the minimum value of the standard power load parameter interval on and after the sudden change date are both adjusted upward to obtain a second reference interval, which includes a second working reference interval and a second holiday reference interval; the amount of the upward adjustment is the sudden change load difference;

[0072] In the specific implementation process, for example, in a data processing process, the standard power load parameter intervals obtained are [50%, 80%] and [62%, 86%], the sudden change date obtained is the 4th day, and the sudden change load difference obtained is 8%. Then, the standard power load parameter intervals from the 1st to the 4th day are [50%, 80%] and [62%, 86%], and the standard power load parameter intervals from the 4th to the 7th day are [58%, 88%] and [70%, 94%].

[0073] The reference interval includes a first reference interval and a second reference interval.

[0074] The early warning assessment module conducts early warning assessment on the electricity consumption data of this week based on the reference interval and issues an early warning signal;

[0075] The early warning assessment module is configured with an early warning assessment strategy, which includes, when the electricity consumption data of this week is obtained, performing an electricity consumption analysis on the electricity consumption data of this week to obtain a real-time electricity load parameter range;

[0076] Use the early warning comparison method to compare the real-time power load parameter intervals and output a real-time risk-free signal or an early warning signal. The early warning comparison method includes: for any real-time power load parameter interval, if and only if the minimum value of the real-time power load parameter interval is greater than or equal to the minimum value of the reference interval and the maximum value of the power load parameter interval is less than or equal to the maximum value of the reference interval, output a real-time risk-free signal, otherwise output a early warning signal;

[0077] For the electricity consumption data before the sudden change date, when the real-time electricity consumption data of this week is obtained on a working day, the first working reference interval is used for comparison; when the real-time electricity consumption data of this week is obtained on a holiday, the first holiday reference interval is used for comparison;

[0078] For electricity consumption data after the sudden change date, when the real-time electricity consumption data for this week is on a working day, the second working reference interval is used for comparison; when the real-time electricity consumption data for this week is on holidays, the second holiday reference interval is used for comparison; in the specific implementation process, for example, in an early warning assessment process, the real-time electricity load parameter interval obtained is [55%, 70%], and the data time obtained is a working day before the sudden change date, and the first working reference interval [50%, 80%] is used for comparison.

[0079] Example 2, please refer to Figure 4 As shown, the present invention also provides a power outage risk warning method based on the real-time status of the power grid, comprising the following steps:

[0080] S1: Collect and record the number of holidays, electricity consumption data and temperature data from big data;

[0081] Step S1 includes the following sub-steps:

[0082] S101: Acquire a target power plant and its corresponding power consumption area, record the unit power generation of the target power plant and the unit power consumption of the power consumption area, and set them as power consumption data.

[0083] S102: Obtain the number of holidays and working days per week from big data; obtain the real-time temperature in the power consumption area from the Meteorological Bureau and set it as temperature data.

[0084] S2: Analyze the power consumption data based on the number of days in the week and holidays to obtain the power load parameter range, and analyze the temperature data to obtain the sudden load difference;

[0085] Step S2 includes the following sub-steps:

[0086] S201: Acquire electricity consumption data from a data acquisition module, set the ratio of unit electricity consumption to unit power generation at the same time as the electricity load, and use a fitting correction method to screen and correct the electricity load;

[0087] The fitting correction method includes: establishing a plane rectangular coordinate system, recorded as the load screening coordinate system, obtaining the corresponding power load in the power consumption area every hour, and marking points in the load screening coordinate system with the power load as the ordinate and time as the abscissa; fitting the corresponding power load in the power consumption area every hour in the load screening coordinate system into a curve, recorded as the load relationship curve;

[0088] For any point A in the load screening coordinate system, draw a straight line parallel to the y-axis from point A, and record the intersection of the straight line and the load relationship curve as point B, and record the distance between point A and point B as the screening distance; obtain the screening distances of all points in the load screening coordinate system, and record the point corresponding to the longest screening distance as C;

[0089] Draw a straight line parallel to the y-axis from point C, and record the intersection of the straight line and the load relationship curve as point D, obtain the ordinate of point D, and replace the ordinate of point C with the ordinate of point D to obtain the correction relationship curve;

[0090] S202: respectively obtaining correction relationship curves for working days and holidays; obtaining workload peak values ​​and workload valley values ​​from the correction relationship curves for working days; obtaining holiday workload peak values ​​and holiday workload valley values ​​from the correction relationship curves for holidays;

[0091] S203: Establishing a working power load parameter interval, setting the working load valley value as the minimum value of the working power load parameter interval, and setting the working load peak value as the maximum value of the working power load parameter interval; establishing a holiday power load parameter interval, setting the holiday load valley value as the minimum value of the holiday power load parameter interval, and setting the holiday load peak value as the maximum value of the holiday power load parameter interval;

[0092] The working power load parameter range and the holiday power load parameter range are collectively referred to as the power load parameter range.

[0093] S204: Analyze the temperature data using a sudden change analysis method to obtain a sudden change date;

[0094] The sudden change analysis method includes obtaining the daily average temperature in the power consumption area for a week. For any day M in a week, the elimination fluctuation formula is used to obtain the elimination fluctuation parameter of the Mth day. The elimination fluctuation formula is: Among them, S(M) is the fluctuation elimination parameter, Ti is the daily average temperature of the i-th day except the M-th day, and T0 is the average of all daily average temperatures except the M-th day;

[0095] Establish a line graph of daily average temperature changes, with time as the horizontal axis and daily average temperature as the vertical axis. Set the slope between any two adjacent points as the change rate, and set the day with the largest change rate as the pending day; when the elimination fluctuation parameter of the pending day is less than the average value of all the elimination fluctuation parameters, the pending day is recorded as the sudden change date;

[0096] S205: The daily average power load before the sudden change date is set as the normal power load, and the power load corresponding to the sudden change date is set as the sudden change power load; the difference between the sudden change power load and the normal power load is obtained to obtain the sudden change load difference.

[0097] S3: Obtain this week's predicted temperature data from the Meteorological Bureau, predict this week's sudden change date based on this week's predicted temperature data, and calibrate the power load parameter range based on this week's sudden change date and sudden change load difference to obtain a reference range;

[0098] Step S3 includes the following sub-steps:

[0099] S301: When performing status assessment, obtain the number of holidays this week from big data, obtain the power load parameter range and sudden load difference with the same number of holidays from historical data based on the number of holidays this week, and set them as standard power load parameter range and standard sudden load difference. The standard power load parameter range includes a standard working power load parameter range and a standard holiday power load parameter range;

[0100] S302: Analyze the predicted temperature data using a sudden change analysis method to obtain a sudden change date;

[0101] S303: setting the standard power load parameter interval before the sudden change date to a first reference interval, where the first reference interval includes a first working reference interval and a first holiday reference interval;

[0102] The maximum value and the minimum value of the standard power load parameter interval on and after the sudden change date are both adjusted upward to obtain a second reference interval, which includes a second working reference interval and a second holiday reference interval; the amount of the upward adjustment is the sudden change load difference;

[0103] The reference interval includes a first reference interval and a second reference interval.

[0104] S4: Conduct risk warning assessment on this week’s electricity consumption data based on the reference interval and issue a warning signal;

[0105] Step S4 includes the following sub-steps:

[0106] S401: When the electricity consumption data of this week is obtained, the electricity consumption data of this week is analyzed to obtain a real-time electricity load parameter range;

[0107] S402: using the early warning comparison method to compare the real-time power load parameter intervals, and outputting a real-time risk-free signal or an early warning signal. The early warning comparison method includes: for any real-time power load parameter interval, if and only if the minimum value of the real-time power load parameter interval is greater than or equal to the minimum value of the reference interval and the maximum value of the power load parameter interval is less than or equal to the maximum value of the reference interval, outputting a real-time risk-free signal, otherwise outputting an early warning signal;

[0108] For the electricity consumption data before the sudden change date, when the real-time electricity consumption data of this week is obtained on a working day, the first working reference interval is used for comparison; when the real-time electricity consumption data of this week is obtained on a holiday, the first holiday reference interval is used for comparison;

[0109] For the electricity consumption data after the sudden change date, when the real-time electricity consumption data for this week is on a working day, the second working reference interval is used for comparison; when the real-time electricity consumption data for this week is on a holiday, the second holiday reference interval is used for comparison.

[0110] Example 3, please refer to Figure 5 As shown, Figure 5 The structural schematic diagram of an electronic device is illustrated, and the electronic device may include: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps in the power outage risk warning method based on the real-time state of the power grid are executed to achieve the following functions: first, the number of days of the week and holidays, power consumption data and temperature data are collected and recorded from the big data, and then the power consumption data is analyzed based on the number of days of the week and holidays to obtain the power load parameter interval, and the temperature data is analyzed to obtain the sudden load difference; the predicted temperature data of this week is obtained from the meteorological bureau, and the sudden change date of this week is predicted based on the predicted temperature data of this week, and the power load parameter interval is corrected based on the sudden change date and the sudden load difference of this week to obtain the reference interval; finally, the risk warning assessment of this week's power consumption data is performed based on the reference interval and a warning signal is issued.

[0111] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0112] Embodiment 4, the present application also provides a computer program product, the computer program product includes a computer program stored on a computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by the computer, the computer can execute the power outage risk warning method based on the real-time status of the power grid provided by the above methods, the method includes: first, collecting and recording the number of days of the week and holidays, electricity consumption data and temperature data from big data, and then performing electricity consumption analysis on the electricity consumption data based on the number of days of the week and holidays to obtain the electricity load parameter range, analyzing the temperature data to obtain the sudden load difference; obtaining the predicted temperature data of this week from the Meteorological Bureau, predicting the sudden change date of this week based on the predicted temperature data of this week, correcting the electricity load parameter range based on the sudden change date of this week and the sudden load difference to obtain a reference range; finally, performing a risk warning assessment on this week's electricity consumption data based on the reference range and issuing a warning signal.

[0113] Embodiment 5, the present application also provides a computer-readable storage medium, the present application provides a storage medium, on which a computer program is stored. When the computer program is executed by the processor, the steps in the power outage risk warning method based on the real-time status of the power grid are executed to achieve the following functions: first, the number of days of the week and holidays, electricity consumption data and temperature data are collected and recorded from the big data, and then the electricity consumption data is analyzed based on the number of days of the week and holidays to obtain the electricity load parameter range, and the temperature data is analyzed to obtain the sudden load difference; the predicted temperature data of this week is obtained from the Meteorological Bureau, and the sudden change date of this week is predicted based on the predicted temperature data of this week. The electricity load parameter range is corrected based on the sudden change date and the sudden load difference of this week to obtain a reference range; finally, a risk warning assessment is performed on this week's electricity consumption data based on the reference range and a warning signal is issued.

[0114] Through the description of the above implementation methods, the embodiments of the present invention can be provided as methods, systems or computer program products. Based on such an understanding, the above technical solutions can be essentially or partly contributed to the prior art in the form of software products, which can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and include several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0115] In the embodiments provided in the present application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A power outage risk warning system based on the real-time status of the power grid, characterized by: It includes data acquisition module, power grid analysis module, interval assessment module and early warning assessment module; The data collection module is used to collect and record the number of days of weekly holidays, electricity consumption data and temperature data from the big data; The power grid analysis module analyzes the power consumption data based on the number of days of the week and holidays to obtain the power load parameter interval, and analyzes the temperature data to obtain the sudden load difference; The interval evaluation module obtains this week's predicted temperature data from the Meteorological Bureau, predicts this week's sudden change date based on this week's predicted temperature data, and corrects the power load parameter interval based on this week's sudden change date and sudden change load difference to obtain a reference interval; The early warning assessment module performs early warning assessment on the electricity consumption data of this week based on the reference interval and issues an early warning signal.

2. The power outage risk warning system based on the real-time status of the power grid according to claim 1 is characterized in that: The data collection module includes an electricity consumption collection unit, which is configured with an electricity consumption collection strategy. The electricity consumption collection strategy includes obtaining a target power plant and its corresponding electricity consumption area, recording the unit power generation of the target power plant and the unit power consumption of the electricity consumption area, and setting them as electricity consumption data.

3. The power outage risk warning system based on real-time power grid status according to claim 2 is characterized in that: The data acquisition module also includes other acquisition units, and the other acquisition units are configured with other acquisition strategies. The other acquisition strategies include obtaining the number of holidays and working days per week from big data; obtaining the real-time temperature in the power consumption area from the Meteorological Bureau and setting it as temperature data.

4. The power outage risk warning system based on real-time power grid status according to claim 3 is characterized in that: The power grid analysis module includes a power consumption analysis unit, the power consumption analysis unit is configured with a power consumption analysis strategy, the power consumption analysis strategy includes obtaining power consumption data from the data acquisition module, setting the ratio of unit power consumption to unit power generation at the same time as the power load, and using a fitting correction method to screen and correct the power load; The fitting correction method includes: establishing a plane rectangular coordinate system, recorded as a load screening coordinate system, obtaining the power load corresponding to each hour in the power consumption area, and marking points in the load screening coordinate system with the power load as the ordinate and time as the abscissa; fitting the power load corresponding to each hour in the power consumption area in the load screening coordinate system into a curve, recorded as a load relationship curve; For any point A in the load screening coordinate system, draw a straight line parallel to the y-axis from point A, and record the intersection of the straight line and the load relationship curve as point B, and record the distance between point A and point B as the screening distance; obtain the screening distances of all points in the load screening coordinate system, and record the point corresponding to the longest screening distance as C; Draw a straight line parallel to the y-axis from point C, and record the intersection of the straight line and the load relationship curve as point D, obtain the ordinate of point D, and replace the ordinate of point C with the ordinate of point D to obtain the correction relationship curve; Obtain the correction relationship curves for working days and holidays respectively; obtain the workload peak value and workload valley value from the correction relationship curve for working days; obtain the holiday load peak value and holiday load valley value from the correction relationship curve for holidays; Establishing a working power load parameter interval, setting the working load valley value as the minimum value of the working power load parameter interval, and setting the working load peak value as the maximum value of the working power load parameter interval; Establish a holiday power load parameter interval, set the holiday load valley value as the minimum value of the holiday power load parameter interval, and set the holiday load peak value as the maximum value of the holiday power load parameter interval; The working power load parameter range and the holiday power load parameter range are collectively referred to as the power load parameter range.

5. The power outage risk warning system based on real-time power grid status according to claim 4 is characterized in that: The power grid analysis module further includes a temperature analysis unit, wherein the temperature analysis unit is configured with a temperature analysis strategy, wherein the temperature analysis strategy includes analyzing the temperature data using a sudden change analysis method to obtain a sudden change date; The sudden change analysis method includes obtaining the daily average temperature in the power consumption area for a week, and for any day M in a week, using the elimination fluctuation formula to obtain the elimination fluctuation parameter of the Mth day, the elimination fluctuation formula is: Among them, S(M) is the fluctuation elimination parameter, Ti is the daily average temperature of the i-th day except the M-th day, and T0 is the average of all daily average temperatures except the M-th day; Establish a line graph of daily average temperature changes, with time as the horizontal axis and daily average temperature as the vertical axis. Set the slope between any two adjacent points as the change rate, and set the day with the largest change rate as the pending day; when the elimination fluctuation parameter of the pending day is less than the average value of all the elimination fluctuation parameters, the pending day is recorded as the sudden change date; The daily average power load before the sudden change date is set as the normal power load, and the power load corresponding to the sudden change date is set as the sudden change power load; the difference between the sudden change power load and the normal power load is obtained to obtain the sudden change load difference.

6. The power outage risk warning system based on real-time power grid status according to claim 5 is characterized in that: The interval assessment module is configured with a state assessment strategy, which includes obtaining the number of holidays this week from big data when performing state assessment, obtaining the power load parameter interval and sudden load difference with the same number of holidays from historical data based on the number of holidays this week, and setting them as the standard power load parameter interval and the standard sudden load difference, wherein the standard power load parameter interval includes the standard working power load parameter interval and the standard holiday power load parameter interval; Use the sudden change analysis method to analyze the predicted temperature data and obtain the sudden change date; The standard power load parameter interval before the sudden change date is set as a first reference interval, wherein the first reference interval includes a first working reference interval and a first holiday reference interval; The maximum value and the minimum value of the standard power load parameter interval on and after the sudden change date are both adjusted upward to obtain a second reference interval, wherein the second reference interval includes a second working reference interval and a second holiday reference interval; the amount of the upward adjustment is the sudden change load difference; The reference interval includes a first reference interval and a second reference interval.

7. The power outage risk warning system based on real-time power grid status according to claim 6 is characterized in that: The early warning assessment module is configured with an early warning assessment strategy, which includes, when the electricity consumption data of this week is obtained, performing an electricity consumption analysis on the electricity consumption data of this week to obtain a real-time electricity load parameter interval; Use the early warning comparison method to compare the real-time power load parameter intervals and output a real-time risk-free signal or an early warning signal. The early warning comparison method includes: for any real-time power load parameter interval, if and only if the minimum value of the real-time power load parameter interval is greater than or equal to the minimum value of the reference interval and the maximum value of the power load parameter interval is less than or equal to the maximum value of the reference interval, output a real-time risk-free signal, otherwise output a early warning signal; For the electricity consumption data before the sudden change date, when the real-time electricity consumption data of this week is obtained on a working day, the first working reference interval is used for comparison; when the real-time electricity consumption data of this week is obtained on a holiday, the first holiday reference interval is used for comparison; For the electricity consumption data after the sudden change date, when the real-time electricity consumption data for this week is on a working day, the second working reference interval is used for comparison; when the real-time electricity consumption data for this week is on a holiday, the second holiday reference interval is used for comparison.

8. A power outage risk warning method based on the real-time status of a power grid, used to implement the power outage risk warning system based on the real-time status of a power grid as described in any one of claims 1 to 7, characterized in that: The steps include: Collect and record weekly holidays, electricity consumption data, and temperature data from big data; The power consumption data is analyzed based on the number of days in the week and holidays to obtain the power load parameter range, and the temperature data is analyzed to obtain the sudden load difference; Obtain this week's forecast temperature data from the Meteorological Bureau, predict this week's sudden change date based on this week's forecast temperature data, calibrate the power load parameter range based on this week's sudden change date and sudden change load difference to obtain a reference range; Based on the reference range, a risk warning assessment is conducted on this week’s electricity consumption data and a warning signal is issued.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method as claimed in claim 8 are executed.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method as claimed in claim 8 are executed.

Images