Load section early warning method, equipment and medium

Abstract

The invention provides a load section early warning method and device and a medium, and relates to the technical field of data processing, and the method comprises the steps: obtaining the real-time load of a load section; according to the real-time load, whether early warning judgment for the load section is executed or not is determined; if it is determined that the early warning judgment for the load section is executed, a first time period and a second time period are determined respectively; acquiring first integral data of the active power of the load section in the first time period; acquiring second integral data of the active power of the load section in a second time period; determining a load rate prediction value of the load section according to the first integral data and the second integral data; if the load rate prediction value is larger than a preset load rate prediction threshold value, load section early warning is triggered; and the early warning efficiency and the early warning accuracy are improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, device and medium for early warning of load sections. Background Technology

[0002] For power grids, the N-1 principle must be followed. This means that in the event of a single fault, load changes are monitored in real time and warnings are issued for exceeding limits by setting cross-sectional limits that take into account the overload capacity of equipment. This ensures stable power supply and system operation under a single fault. For example, if each main transformer has a rated capacity of 240 MVA and a power factor of 0.95, and a substation has four main transformers with an overload capacity of 1.3 times the rated capacity, then the load supplied by the four main transformers must meet the N-1 principle control section power = 240 * 0.95 * 1.3 * (4-1) = 889 MW. If one of the four main transformers is out of service for maintenance, the remaining three transformers must meet the N-1 principle control section power = 240 * 0.95 * 1.3 * (3-1) = 593 MW. Therefore, to ensure stable system operation, developing a more accurate load section warning method is a promising direction.

[0003] In existing technologies, load section limits are calculated based on the N-1 principle, and real-time monitoring and early warning are implemented. Control personnel control the section within the limits by means of load transfer and adjustment of operation mode.

[0004] However, in existing technologies, load section early warning relies on real-time monitoring and is easily affected by factors such as power plant output and weather, resulting in delayed early warning when load changes suddenly occur. The control response is difficult to match the speed of load increase, causing the section to continuously exceed the limit and exacerbating the risk of power grid failure. Although lowering the early warning threshold can intervene in advance, it will trigger a large number of false alarms due to non-critical fluctuations, resulting in ineffective accounting and manpower consumption. It has technical problems of low early warning efficiency and poor early warning accuracy. Summary of the Invention

[0005] The load section early warning method, equipment and medium provided in this application are intended to improve the technical effects of early warning efficiency and accuracy.

[0006] Firstly, this application provides a method for early warning of load sections, including:

[0007] Obtain the real-time load of the load section;

[0008] Based on the real-time load, determine whether to execute an early warning judgment for the load section;

[0009] If it is determined that an early warning judgment will be executed for the load section, then the first time period and the second time period are determined respectively. The first time period is the time period that is traced back to the current real-time load acquisition time point of the day and is the same as the current real-time load acquisition time point of the previous day and is the same as the current real-time load acquisition time point.

[0010] Obtain the first integral data of the active power of the load section within the first time period;

[0011] Obtain the second integral data of the active power of the load section during the second time period;

[0012] Based on the first integral data and the second integral data, determine the predicted load rate of the load section;

[0013] If the predicted load rate is greater than the preset predicted load rate threshold, a load section warning will be triggered.

[0014] In one possible implementation, determining whether to perform an early warning judgment for a load section based on the real-time load includes:

[0015] Obtain the preset load section limit;

[0016] Calculate the real-time load rate of the load section based on the preset load section limit and the real-time load;

[0017] If the real-time load rate is greater than or equal to the first load rate threshold, then a warning judgment for the load section will be executed.

[0018] In one possible implementation, determining the predicted load rate of the load section based on the first integral data and the second integral data includes:

[0019] Determine the maximum load rate of the load section the day before;

[0020] Calculate the difference between the first integral data and the second integral data;

[0021] Calculate the product of the preset load section limit and the length of the first time period;

[0022] The predicted load factor difference is determined based on the ratio of the difference to the product.

[0023] The sum of the previous day's maximum load rate and the predicted difference between the load rates is used to determine the predicted load rate for the load section.

[0024] In one possible implementation, determining the maximum load rate of the load section the previous day includes:

[0025] Obtain the load rate data of the load section for the previous day;

[0026] Determine the time point of maximum power based on load rate data;

[0027] Perform data mutation detection at the maximum power time point;

[0028] If the time point of maximum power is not the time point of data mutation, then the first load rate corresponding to the time point of maximum power is determined to be the maximum load rate of the previous day.

[0029] In one possible implementation, determining data abrupt changes at the maximum power time point includes:

[0030] Obtain the first load rate at the time of maximum power;

[0031] Determine the first and second time points adjacent to the time point of maximum power;

[0032] Obtain the second load rate at the first time point and the third load rate at the second time point, respectively.

[0033] The first mutation judgment ratio is determined based on the first load rate and the second load rate;

[0034] The second mutation judgment ratio is determined based on the first load rate and the third load rate;

[0035] The larger of the first mutation judgment ratio and the second mutation judgment ratio is determined as the target mutation judgment ratio;

[0036] If the target mutation judgment ratio is not greater than the preset mutation judgment threshold, then the maximum power time point is determined not to be the data mutation time point.

[0037] In one possible implementation, after triggering a load section warning if the predicted load rate is greater than a preset load rate prediction threshold, the method further includes:

[0038] Obtain load information for load sections;

[0039] The load information is sent to the preset early warning database.

[0040] In one possible implementation, after sending the load information to a preset early warning database, the method further includes:

[0041] Generate an early warning notification interface based on the early warning database;

[0042] The warning prompt interface will be displayed.

[0043] Secondly, this application provides a load section early warning device, comprising:

[0044] The first acquisition module is used to acquire the real-time load of the load section;

[0045] The first determining module is used to determine whether to execute an early warning judgment for the load section based on the real-time load.

[0046] The second determining module is used to determine the first time period and the second time period respectively if it is determined to perform an early warning judgment for the load section; wherein, the first time period is the time period that is traced back to the current real-time load acquisition time point of the day and the second time period is the time period that is traced back to the same time point corresponding to the current real-time load acquisition time point of the previous day and the same time period that is traced back to the same time point of the previous day.

[0047] The second acquisition module is used to acquire the first integral data of the active power of the load section within the first time period;

[0048] The third acquisition module is used to acquire the second integral data of the active power of the load section within the second time period;

[0049] The third determining module is used to determine the predicted load rate of the load section based on the first integral data and the second integral data.

[0050] The early warning module is used to trigger a load section early warning if the predicted load rate is greater than the preset predicted load rate threshold.

[0051] In one possible implementation, the first determining module is further configured to:

[0052] Obtain the preset load section limit;

[0053] Calculate the real-time load rate of the load section based on the preset load section limit and the real-time load;

[0054] If the real-time load rate is greater than or equal to the first load rate threshold, then a warning judgment for the load section will be executed.

[0055] In one possible implementation, the third determining module is further configured to:

[0056] Determine the maximum load rate of the load section the day before;

[0057] Calculate the difference between the first integral data and the second integral data;

[0058] Calculate the product of the preset load section limit and the length of the first time period;

[0059] The predicted load factor difference is determined based on the ratio of the difference to the product.

[0060] The sum of the previous day's maximum load rate and the predicted difference between the load rates is used to determine the predicted load rate for the load section.

[0061] In one possible implementation, the third determining module is further configured to:

[0062] Obtain the load rate data of the load section for the previous day;

[0063] Determine the time point of maximum power based on load rate data;

[0064] Perform data mutation detection at the maximum power time point;

[0065] If the time point of maximum power is not the time point of data mutation, then the first load rate corresponding to the time point of maximum power is determined to be the maximum load rate of the previous day.

[0066] In one possible implementation, the third determining module is further configured to:

[0067] Obtain the first load rate at the time of maximum power;

[0068] Determine the first and second time points adjacent to the time point of maximum power;

[0069] Obtain the second load rate at the first time point and the third load rate at the second time point, respectively.

[0070] The first mutation judgment ratio is determined based on the first load rate and the second load rate;

[0071] The second mutation judgment ratio is determined based on the first load rate and the third load rate;

[0072] The larger of the first mutation judgment ratio and the second mutation judgment ratio is determined as the target mutation judgment ratio;

[0073] If the target mutation judgment ratio is not greater than the preset mutation judgment threshold, then the maximum power time point is determined not to be the data mutation time point.

[0074] In one possible implementation, the early warning module is also used for:

[0075] Obtain load information for load sections;

[0076] The load information is sent to the preset early warning database.

[0077] In one possible implementation, the early warning module is also used for:

[0078] Generate an early warning notification interface based on the early warning database;

[0079] The warning prompt interface will be displayed.

[0080] Thirdly, this application provides a load section early warning device, including: a memory and a processor;

[0081] The memory stores the instructions that the computer executes;

[0082] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0083] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible embodiments of the first aspect.

[0084] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0085] This application provides a load section early warning method, device, and medium. By collecting load data in real time as the basis for early warning, it dynamically determines whether to initiate the early warning process to optimize computing resources. It combines the load trend analysis of the current day and the same period in history to improve the accuracy of prediction. It uses integral data to quantify the load change rate and cumulative effect, and predicts potential over-limit risks based on dual-time period comparison. Finally, it achieves early warning to reserve control time. While reducing the false alarm rate, it enhances the power grid's proactive defense capability against load surges, thereby achieving the technical effect of improving early warning efficiency and accuracy. Attached Figure Description

[0086] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0087] Figure 1 This application provides a schematic diagram of an application data processing system architecture.

[0088] Figure 2 Flowchart of the load section early warning method provided in the embodiments of this application Figure 1 ;

[0089] Figure 3 Flowchart of the load section early warning method provided in the embodiments of this application Figure 2 ;

[0090] Figure 4 Flowchart of the load section early warning method provided in the embodiments of this application Figure 3 ;

[0091] Figure 5 Flowchart of the load section early warning method provided in the embodiments of this application Figure 4 ;

[0092] Figure 6 Flowchart of the load section early warning method provided in the embodiments of this application Figure 5 ;

[0093] Figure 7 Flowchart of the load section early warning method provided in the embodiments of this application Figure 6 ;

[0094] Figure 8 This is a schematic diagram of the load section early warning device provided in the embodiments of this application;

[0095] Figure 9 This is a schematic diagram of the load section early warning device provided in the embodiments of this application.

[0096] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0097] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0098] In existing technologies, load section early warning relies on real-time monitoring and is easily affected by factors such as power plant output and weather, resulting in delayed early warning when load changes suddenly occur. The control response is difficult to match the speed of load increase, causing the section to continuously exceed the limit and exacerbating the risk of power grid failure. Although lowering the early warning threshold can intervene in advance, it will trigger a large number of false alarms due to non-critical fluctuations, resulting in ineffective accounting and manpower consumption. It has technical problems of low early warning efficiency and poor early warning accuracy.

[0099] To address the aforementioned issues, this application provides a load section early warning method, device, and medium. It uses real-time load data as the basis for early warning, dynamically determines whether to initiate the early warning process to optimize computational resources, combines daily and historical load trend analysis to improve prediction accuracy, quantifies the load change rate and cumulative effect using integral data, and predicts potential over-limit risks based on dual-time period comparison. Ultimately, it achieves early warning to reserve control time, reducing false alarm rates while enhancing the power grid's proactive defense capabilities against load surges, thereby improving both early warning efficiency and accuracy.

[0100] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0101] Figure 1 This is a schematic diagram of an application data processing system architecture provided in an embodiment of this application. The application data processing system is a computer device. Figure 1 As shown, the above architecture includes at least one of a data acquisition device 101, a processing device 102, and a display device 103.

[0102] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the architecture of the application data processing system. In other feasible embodiments of this application, the above architecture may include more or fewer components than illustrated, or combine some components, or split some components, or arrange different components, which can be determined according to the actual application scenario and is not limited here. Figure 1 The components shown can be implemented in hardware, software, or a combination of both.

[0103] In the specific implementation process, the data acquisition device 101 may include an input / output interface or a communication interface, and the data acquisition device 101 can be connected to the processing device through the input / output interface or the communication interface.

[0104] Processing device 102 can dynamically combine real-time load data with historical load change patterns to construct a predictive model based on the time integral effect, enabling early detection of load section risks. Its core lies in overcoming the limitations of traditional real-time monitoring due to its lag. By collecting the active power integral values ​​for the corresponding time periods of the current day and the previous day, it quantifies the cumulative trend and growth rate of load changes, rather than relying on instantaneous values ​​at a single point in time. By comparing the differences between the integral data from the two time periods, it can accurately capture early signals of load surges and predict future trends by combining historical patterns. When the predicted load rate exceeds a threshold, it triggers an early warning, gaining a valuable time window for control operations and effectively balancing warning sensitivity with the risk of false alarms.

[0105] The display device 103 can also be a touch screen or the screen of a terminal device, used to receive user commands while displaying the above-mentioned content, so as to realize interaction with the user.

[0106] It should be understood that the aforementioned processing device can be implemented by a processor reading instructions from memory and executing those instructions, or it can be implemented by a chip circuit.

[0107] Furthermore, the network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0108] Figure 2 Flowchart of the load section early warning method provided in the embodiments of this application Figure 1 ,like Figure 2 As shown, the load section early warning method provided in this embodiment includes:

[0109] S201. Obtain the real-time load of the load section.

[0110] By continuously monitoring real-time power data of power grid load sections, a dynamic monitoring foundation is established, providing the original basis for subsequent early warning judgments.

[0111] S202. Based on the real-time load, determine whether to execute an early warning judgment for the load section.

[0112] The system dynamically determines whether to initiate the early warning calculation process based on the current load level, avoiding ineffective calculations during low-load periods and optimizing system resource allocation.

[0113] S203. If it is determined that an early warning judgment will be executed for the load section, then the first time period and the second time period shall be determined respectively.

[0114] In this embodiment, the first time period is a time period that traces back a preset duration from the current real-time load acquisition time point of the day, and the second time period is a time period that traces back a preset duration from the same time point corresponding to the current real-time load acquisition time point of the previous day.

[0115] By setting up two comparison windows—one for the current day and one for the same period in history—we can capture the current load change trend and introduce historical patterns as a predictive reference, thus establishing a spatiotemporal dual-dimensional analysis framework.

[0116] S204. Obtain the first integral data of the active power of the load section within the first time period.

[0117] The first integral data of active power of the load section is calculated in the first time period, and the discrete power data is transformed into a cumulative energy index, which more accurately reflects the continuous growth trend of the load.

[0118] S205. Obtain the second integral data of the active power of the load section during the second time period.

[0119] Simultaneously, the second integral data of active power at the load section during the second time period is calculated, transforming discrete power data into cumulative energy indicators to more accurately reflect the continuous growth trend of load.

[0120] S206. Based on the first integral data and the second integral data, determine the predicted load rate of the load section.

[0121] By comparing the integral differences between two time periods, a load rate evolution prediction model is established to quantitatively assess the risk of sudden load increases rather than simply relying on instantaneous values.

[0122] S207. If the predicted load rate is greater than the preset predicted load rate threshold, a load section warning will be triggered.

[0123] Early warnings are triggered when the predicted value reaches the critical value, providing a window of time for regulators to take action and achieving a technological leap from passive over-limit handling to proactive risk prevention and control.

[0124] This application provides a load section early warning method that uses real-time load data as the basis for early warning, dynamically determines whether to initiate the early warning process to optimize computing resources, combines daily and historical load trend analysis to improve prediction accuracy, uses integral data to quantify the load change rate and cumulative effect, and predicts potential over-limit risks based on dual-time period comparison. Ultimately, it achieves early warning to reserve control time, reduces false alarm rate, and enhances the power grid's proactive defense capability against load surges, thereby achieving the technical effect of improving early warning efficiency and accuracy.

[0125] Figure 3 Flowchart of the load section early warning method provided in the embodiments of this application Figure 2 ,like Figure 3 As shown, this embodiment, based on the above embodiments, provides a detailed explanation of the process for determining the early warning judgment of the load section, including:

[0126] S301. Obtain the preset load section limit value.

[0127] By reading the system's preset load section limit P1, a benchmark parameter for early warning judgment is established. This limit is calculated and determined based on the overload capacity of power grid equipment and the N-1 principle, providing a standardized reference for subsequent load rate calculation.

[0128] S302. Calculate the real-time load rate of the load section based on the preset load section limit and the real-time load.

[0129] The load factor A0 is calculated by using the ratio of real-time load P0 to preset limit P1, converting the absolute power value into a relative index in percentage form, so that the risk levels of load sections of different magnitudes are comparable.

[0130] S303. If the real-time load rate is greater than or equal to the first load rate threshold, then determine to execute the early warning judgment for the load section.

[0131] By comparing the real-time load rate A0 with the first load rate threshold B, real-time monitoring is directly triggered when A0≥B. At this time, the section is already in a high-risk state and the early warning response mechanism needs to be activated immediately.

[0132] The load section early warning method provided in this application establishes a standardized early warning benchmark and combines it with a load rate conversion mechanism to transform equipment capacity constraints into quantifiable indicators. Finally, risk-level triggering is achieved through threshold comparison. This technical solution overcomes the limitations of traditional fixed-threshold early warning systems. By combining dynamic load rate calculation with multi-level thresholds, it can respond quickly during load surges while avoiding false triggering of the early warning process during low-load periods. This forms a complete early warning triggering mechanism from benchmark setting to risk quantification, effectively balancing early warning sensitivity and system computational load, thereby improving early warning efficiency and accuracy.

[0133] Figure 4 Flowchart of the load section early warning method provided in the embodiments of this application Figure 3 ,like Figure 4 As shown, this embodiment, based on the above embodiments, provides a detailed explanation of the process for determining the predicted load rate of the load section, including:

[0134] S401. Determine the maximum load rate of the load section on the previous day.

[0135] The maximum load factor A2 of yesterday was determined by analyzing historical data. This value is calculated based on the actual load peak after excluding data mutations, and provides a benchmark reference for the prediction model.

[0136] For example, when a sudden change in the power value P2 at time T2 is detected (such as (P2-P3) / P3 or (P2-P4) / P4 exceeding the threshold), the system will remove the abnormal point to ensure that A2 truly reflects the normal load peak.

[0137] S402. Calculate the difference between the first integral data and the second integral data.

[0138] Calculate the difference between today's T1 period integral (first integral data) D1 and yesterday's same period integral (second integral data) D2. This difference directly reflects the difference in the cumulative load growth between the two periods. For example, if D1-D2=50MWh, it means that today's load growth consumes 50MWh more energy than yesterday's same period.

[0139] It is important to note that when calculating the difference between today's points and yesterday's points for the same period, special attention should be paid to whether the points calculation period spans two days. If the current time is earlier than the preset time period boundary, it indicates that the points calculation includes not only parts of today's period but also parts of yesterday's period.

[0140] In the above situation, further judgment needs to be made based on the real-time load rate:

[0141] If the real-time load rate is high, reaching or exceeding the preset high threshold, the integral value from midnight today to the current time is calculated and compared with the integral value of the same time period yesterday.

[0142] If the real-time load rate is low and does not reach the high threshold, the early warning calculation will be suspended until the entire period for calculating the points falls within today's values. When the entire period for calculating the points falls within today's values, the early warning calculation can be initiated as long as the real-time load rate reaches or exceeds the preset regular threshold.

[0143] S403. Calculate the product of the preset load section limit and the length of the first time period.

[0144] Multiply the load section limit P1 by the duration T1 to obtain the standardized denominator P1T1, which physically represents the maximum allowable energy consumption of the section during the T1 time period. For example, when P1 = 100 MW and T1 = 2 h, P1T1 = 200 MWh is the theoretical maximum integral value.

[0145] S404. Determine the predicted load rate difference value based on the ratio of the difference to the product.

[0146] The integral difference is converted into the load rate change rate by calculating (D1-D2) / (P1*T1). For example, if the ratio is 0.05, it means that the load rate increases by 5% per hour.

[0147] S405. The sum of the previous day's maximum load rate and the predicted difference between the load rates is determined as the predicted load rate of the load section.

[0148] The historical peak value A2 is superimposed with the rate of change to obtain the predicted load factor A1 = A2 + ΔA. For example, when A2 = 90% and ΔA = 8%, A1 = 98%, which reflects the comprehensive prediction result after considering the historical peak value and the current growth rate.

[0149] The load section early warning method provided in this application establishes a reliable historical benchmark, quantifies the load growth trend by combining integral difference, eliminates dimensional differences through standardization, and transforms it into an interpretable load rate change rate, ultimately achieving a dynamic fusion of historical patterns and real-time trends. This technical solution overcomes the limitations of prediction based solely on historical or real-time data. It avoids missed warnings caused by historical peaks not reaching limits, and prevents false alarms caused by relying solely on real-time growth rates. Through a mathematical model, discrete load data is transformed into a continuous risk evolution trajectory, enabling the prediction results to be supported by historical patterns and calibrated by real-time trends. This significantly improves the accuracy and foresight of load section overload prediction, thereby achieving the technical effect of improving early warning efficiency and accuracy.

[0150] Figure 5 Flowchart of the load section early warning method provided in the embodiments of this application Figure 4 ,like Figure 5 As shown, this embodiment, based on the above embodiments, provides a detailed explanation of the process for determining the maximum load rate of the load section on the previous day, including:

[0151] S501. Obtain the load rate data of the load section on the previous day.

[0152] By retrieving the load data for the previous day's 24-hour period, a foundation for analyzing historical load curves is established.

[0153] For example, the system extracts power records from the database for each second from 00:00 to 24:00 on a given day, forming a time series containing 86,400 data points.

[0154] S502. Determine the time point of maximum power based on the load rate data.

[0155] By iterating through the data throughout the day and comparing the load rate A=P / P1 at each time point, the time T2 corresponding to the maximum value is determined.

[0156] For example, at 14:32, the load rate was found to be 92%, significantly higher than at other times.

[0157] S503, perform data mutation judgment at the maximum power time point.

[0158] After determining the time point of maximum power, it is necessary to determine whether this point is a data abrupt change point. Since data abrupt changes may be caused by sensor malfunctions or transient disturbances, this will affect the accuracy of the maximum load rate. Therefore, it is necessary to determine this by checking the rate of change of data over a period of time before and after this time point.

[0159] S504. If the maximum power time point is not the data mutation time point, then determine the first load rate corresponding to the maximum power time point as the maximum load rate of the previous day.

[0160] After confirming that T2 is the actual peak load, its load rate A2=92% is used as the historical baseline value. If a data mutation is detected, the data is backtracked to the second highest peak point for re-verification until valid historical peak data is obtained and determined as the maximum load rate of the previous day.

[0161] The load section early warning method provided in this application establishes a complete historical data baseline, combines a peak location mechanism to ensure the capture of true load extremes, and uses abrupt change detection to filter data noise, ultimately outputting a reliable maximum load rate. This technical solution overcomes the limitations of solely relying on raw data peaks. Through a multi-dimensional verification mechanism, it integrates data quality control into the peak identification process, avoiding misjudgments caused by instantaneous sensor fluctuations and preventing missed judgments due to missing historical data, ensuring that the previous day's maximum load rate is both authentic and representative. This processing method significantly improves the baseline reliability of the prediction model, laying a solid data foundation for subsequent load rate evolution prediction, effectively enhancing the overall early warning system's anti-interference capability and prediction stability, thereby achieving the technical effect of improving early warning efficiency and accuracy.

[0162] Figure 6 Flowchart of the load section early warning method provided in the embodiments of this application Figure 5 ,like Figure 6 As shown, this embodiment, based on the above embodiments, provides a detailed explanation of the process for determining data mutations at the maximum power time point, including:

[0163] S601, Obtain the first load rate at the time of maximum power.

[0164] By reading the load rate data at the maximum power time point T2, the first load rate A2 at that moment is obtained as a basic reference value for judging data mutations.

[0165] S602. Determine the first time point and the second time point adjacent to the time point of maximum power.

[0166] Using time T2 as a baseline, we backtrack by E seconds to determine the first time point T2-E, and then move forward by E seconds to determine the second time point T2+E, thus forming an analysis interval covering the short-term window.

[0167] S603, respectively obtain the second load rate at the first time point and the third load rate at the second time point.

[0168] The second loading rate A3 at time T2-E and the third loading rate A4 at time T2+E are extracted respectively to provide before-and-after comparison data for mutation judgment.

[0169] S604. Determine the first mutation judgment ratio based on the first load rate and the second load rate.

[0170] Calculate the ratio of the first load factor A2 to the second load factor A3, F1=(A2-A3) / A3, to quantify the load factor change between the peak time and the preceding time.

[0171] S605. Determine the second mutation judgment ratio based on the first load rate and the third load rate.

[0172] Calculate the ratio F2=(A2-A4) / A4 between the first load rate A2 and the third load rate A4 to quantify the load rate change between the peak time and subsequent time.

[0173] S606. The larger of the first mutation judgment ratio and the second mutation judgment ratio is determined as the target mutation judgment ratio.

[0174] The larger value between F1 and F2 is selected as the target mutation judgment ratio F to ensure that the most significant unilateral change features are captured.

[0175] S607. If the target mutation judgment ratio is not greater than the preset mutation judgment threshold, then the maximum power time point is determined not to be the data mutation time point.

[0176] Compare F with the preset mutation threshold G. When F≤G, it is determined that the data mutation point at time T2 is not a data mutation point, and its load rate is retained as an effective historical benchmark.

[0177] The load profile early warning method provided in this application establishes a quantitative benchmark for peak times and combines it with a nearby sampling mechanism to construct a short-term data window to capture load abrupt changes. Simultaneously, it employs a two-sided ratio calculation and optimization strategy to avoid misjudgments caused by unilateral data fluctuations while ensuring the sensitivity of abrupt change detection. Finally, a threshold comparison mechanism effectively distinguishes between the actual load peak and data acquisition anomalies, ensuring that the determination of the previous day's maximum load rate combines data integrity and anti-interference capabilities. This technical solution breaks through the traditional direct dependence on raw data for peak identification. Through embedded data quality verification, noise filtering is completed during the historical benchmark parameter generation stage, significantly improving the reliability of the prediction model's input parameters and building a more robust data foundation for subsequent load rate evolution prediction. This achieves the technical effect of improving early warning efficiency and accuracy.

[0178] Figure 7 Flowchart of the load section early warning method provided in the embodiments of this application Figure 6 ,like Figure 7 As shown, this embodiment, based on the above embodiment, provides supplementary explanations of the subsequent process for triggering the load section early warning, including:

[0179] S701. Obtain load information of the load section.

[0180] The current operating parameters of the load section that triggers the early warning are obtained through the real-time data interface, including key indicators such as real-time power, load rate and predicted load rate, and a structured early warning information package is formed.

[0181] S702. Send the load information to the preset early warning database.

[0182] The information packet is sent to a dedicated early warning database via an encrypted transmission protocol. The database adopts a time-series data storage structure and is indexed by dimensions such as section identifier (ID), early warning time, and predicted overload time, enabling rapid access to massive amounts of early warning data.

[0183] S703. Generate an early warning prompt interface based on the early warning database.

[0184] Based on the early warning records in the database, an interactive interface is dynamically generated by calling the visualization component library.

[0185] S704, Display warning prompt interface.

[0186] By utilizing multi-terminal adaptation technologies such as scheduling large screens and mobile terminals, the early warning interface is pushed to the operator's work interface to ensure that critical information is delivered.

[0187] The load section early warning method provided in this application establishes a real-time data acquisition link to ensure strong consistency between early warning decisions and equipment status. Combined with a standardized data entry process, it constructs a data foundation for a power grid risk knowledge graph. Simultaneously, dynamic visualization technology transforms abstract early warning information into perceptible graphical language, overcoming the cognitive load bottleneck of traditional text-based alarms. Furthermore, a multi-terminal reach mechanism breaks down the spatial limitations of monitoring centers, enabling early warning response to shift from passive handling to proactive defense. This technical solution forms a complete closed loop from data acquisition, storage, presentation to response, avoiding response delays caused by manual inspections and solving the problem of fragmented presentation of multi-source early warning information. By digitally transforming early warning signals into executable scheduling instructions, it significantly improves the timeliness and accuracy of power grid risk prevention and control, thereby achieving the technical effect of improving early warning efficiency and accuracy.

[0188] Figure 8 This is a schematic diagram of the load section early warning device provided in an embodiment of this application. The device in this embodiment can be in the form of software and / or hardware. Figure 8 As shown in the embodiment of this application, the load section early warning device 800 includes: a first acquisition module 801, a first determination module 802, a second determination module 803, a second acquisition module 804, a third acquisition module 805, a third determination module 806, and an early warning module 807.

[0189] The first acquisition module 801 is used to acquire the real-time load of the load section;

[0190] The first determining module 802 is used to determine whether to perform an early warning judgment for the load section based on the real-time load.

[0191] The second determining module 803 is used to determine a first time period and a second time period respectively if it is determined to perform an early warning judgment for the load section; wherein, the first time period is a time period that traces back a preset duration from the current real-time load acquisition time point of the day, and the second time period is a time period that traces back a preset duration from the same time point corresponding to the current real-time load acquisition time point of the previous day.

[0192] The second acquisition module 804 is used to acquire the first integral data of the active power of the load section within the first time period;

[0193] The third acquisition module 805 is used to acquire the second integral data of the active power of the load section within the second time period;

[0194] The third determining module 806 is used to determine the predicted load rate of the load section based on the first integral data and the second integral data.

[0195] The early warning module 807 is used to trigger a load section early warning if the predicted load rate is greater than the preset predicted load rate threshold.

[0196] In one possible implementation, the first determining module 802 is further configured to:

[0197] Obtain the preset load section limit;

[0198] Calculate the real-time load rate of the load section based on the preset load section limit and the real-time load;

[0199] If the real-time load rate is greater than or equal to the first load rate threshold, then a warning judgment for the load section will be executed.

[0200] In one possible implementation, the third determining module 806 is further configured to:

[0201] Determine the maximum load rate of the load section the day before;

[0202] Calculate the difference between the first integral data and the second integral data;

[0203] Calculate the product of the preset load section limit and the length of the first time period;

[0204] The predicted load factor difference is determined based on the ratio of the difference to the product.

[0205] The sum of the previous day's maximum load rate and the predicted difference between the load rates is used to determine the predicted load rate for the load section.

[0206] In one possible implementation, the third determining module 806 is further configured to:

[0207] Obtain the load rate data of the load section for the previous day;

[0208] Determine the time point of maximum power based on load rate data;

[0209] Perform data mutation detection at the maximum power time point;

[0210] If the time point of maximum power is not the time point of data mutation, then the first load rate corresponding to the time point of maximum power is determined to be the maximum load rate of the previous day.

[0211] In one possible implementation, the third determining module 806 is further configured to:

[0212] Obtain the first load rate at the time of maximum power;

[0213] Determine the first and second time points adjacent to the time point of maximum power;

[0214] Obtain the second load rate at the first time point and the third load rate at the second time point, respectively.

[0215] The first mutation judgment ratio is determined based on the first load rate and the second load rate;

[0216] The second mutation judgment ratio is determined based on the first load rate and the third load rate;

[0217] The larger of the first mutation judgment ratio and the second mutation judgment ratio is determined as the target mutation judgment ratio;

[0218] If the target mutation judgment ratio is not greater than the preset mutation judgment threshold, then the maximum power time point is determined not to be the data mutation time point.

[0219] In one possible implementation, the early warning module 807 is also used for:

[0220] Obtain load information for load sections;

[0221] The load information is sent to the preset early warning database.

[0222] In one possible implementation, the early warning module 807 is also used for:

[0223] Generate an early warning notification interface based on the early warning database;

[0224] The warning prompt interface will be displayed.

[0225] The load section early warning device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0226] Figure 9 This is a structural schematic diagram of the load section early warning device provided in an embodiment of this application. Figure 9 As shown, the load section early warning device 900 provided in this embodiment includes at least one processor 901 and a memory 902. Optionally, the device 900 also includes a communication component 903. The processor 901, memory 902, and communication component 903 are connected via a bus.

[0227] In a specific implementation, at least one processor 901 executes computer execution instructions stored in memory 902, causing at least one processor 901 to perform the above-described method.

[0228] The specific implementation process of processor 901 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0229] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0230] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0231] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0232] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0233] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0234] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0235] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0236] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0237] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0238] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0239] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0240] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0241] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for early warning of load sections, characterized in that, include: Obtain the real-time load of the load section; Based on the real-time load, determine whether to execute an early warning judgment for the load section; If it is determined that an early warning judgment will be executed for the load section, then a first time period and a second time period are determined respectively; wherein, the first time period is a time period that traces back a preset duration from the current real-time load acquisition time point as the end point of the day, and the second time period is a time period that traces back the same preset duration from the previous day with the same time point corresponding to the current real-time load acquisition time point as the end point. Obtain the first integral data of the active power of the load section within the first time period; Obtain the second integral data of the active power of the load section during the second time period; Based on the first integral data and the second integral data, the predicted load rate of the load section is determined; If the predicted load rate is greater than the preset predicted load rate threshold, a load section warning will be triggered.

2. The method according to claim 1, characterized in that, The step of determining whether to execute an early warning judgment for the load section based on the real-time load includes: Obtain the preset load section limit; Calculate the real-time load rate of the load section based on the preset load section limit and the real-time load; If the real-time load rate is greater than or equal to the first load rate threshold, then a warning judgment is determined for the load section.

3. The method according to claim 2, characterized in that, Determining the predicted load rate of the load section based on the first integral data and the second integral data includes: Determine the maximum load rate of the load section on the previous day; Calculate the difference between the first integral data and the second integral data; Calculate the product of the preset load section limit and the length of the first time period; The predicted load rate difference is determined based on the ratio of the difference to the product. The sum of the previous day's maximum load rate and the predicted difference between the load rates is determined as the predicted load rate of the load section.

4. The method according to claim 3, characterized in that, Determining the maximum load rate of the load section on the previous day includes: Obtain the load rate data of the load section on the previous day; Based on the load rate data, determine the time point of maximum power; Perform data mutation judgment on the time point of maximum power; If the maximum power time point is not a data mutation time point, then the first load rate corresponding to the maximum power time point is determined to be the maximum load rate of the previous day.

5. The method according to claim 4, characterized in that, The step of determining data mutations at the maximum power time point includes: Obtain the first load rate at the time point of maximum power; Determine the first and second time points adjacent to the time point of maximum power; The second load rate at the first time point and the third load rate at the second time point are obtained respectively; The first mutation judgment ratio is determined based on the first load rate and the second load rate; The second mutation judgment ratio is determined based on the first load rate and the third load rate; The larger of the first mutation judgment ratio and the second mutation judgment ratio is determined as the target mutation judgment ratio; If the target mutation judgment ratio is not greater than the preset mutation judgment threshold, then the maximum power time point is determined not to be a data mutation time point.

6. The method according to any one of claims 1 to 5, characterized in that, After triggering a load section warning if the predicted load rate is greater than a preset load rate prediction threshold, the method further includes: Obtain the load information of the load section; The load information is sent to a preset early warning database.

7. The method according to claim 6, characterized in that, After sending the load information to the preset early warning database, the method further includes: Based on the aforementioned warning database, a warning notification interface is generated; The warning message interface is displayed.

8. A load section early warning device, characterized in that, include: The first acquisition module is used to acquire the real-time load of the load section; The first determining module is used to determine whether to execute an early warning judgment for the load section based on the real-time load. The second determining module is used to determine a first time period and a second time period respectively if it is determined that an early warning judgment for the load section is to be executed; wherein, the first time period is a time period that traces back a preset duration from the current real-time load acquisition time point of the day, and the second time period is a time period that traces back the same preset duration from the same moment corresponding to the current real-time load acquisition time point of the previous day. The second acquisition module is used to acquire the first integral data of the active power of the load section within the first time period; The third acquisition module is used to acquire the second integral data of the active power of the load section during the second time period; The third determining module is used to determine the predicted load rate of the load section based on the first integral data and the second integral data. The early warning module is used to trigger a load section early warning if the predicted load rate value is greater than a preset predicted load rate threshold.

9. A load section early warning device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

Images