Power grid power prediction method and device, electronic equipment and medium

Abstract

This application provides a method, apparatus, electronic device, and medium for predicting grid power. The method includes: acquiring grid power data for the current period; detecting the grid power data for the current period to obtain a detection result, wherein the detection result is a data mutation or no data mutation; determining whether to perform grid power prediction based on the detection result and a first counter, wherein the first counter is used to count the detection result; if so, generating a grid power prediction value based on the grid power data for the current period. This solution, by predicting future grid power based on grid power data, allows for advance energy scheduling, accurately suppressing grid fluctuations, and improving power supply stability.

Description

Technical Field

[0001] This application relates to the field of energy storage technology, and in particular to a method, apparatus, electronic device and medium for predicting grid power. Background Technology

[0002] Power is supplied to electrical equipment through power generation by generators, charging and discharging of energy storage systems, and grid interaction. Within the energy storage system, the energy storage inverter maintains the grid's power within a preset range through energy dispatch, ensuring a stable power supply.

[0003] In related technologies, the power of the power grid is measured, and the power is used as a basis for energy dispatching of the energy storage inverter to maintain the power of the power grid within a preset range.

[0004] However, due to the delay in signal and command transmission, this method suffers from lag, resulting in low power supply stability. Summary of the Invention

[0005] This application provides a method, apparatus, electronic device, and medium for predicting grid power, in order to improve power supply stability.

[0006] In a first aspect, embodiments of this application provide a method for predicting grid power, comprising: acquiring grid power data for the current period; detecting the grid power data for the current period to obtain a detection result, wherein the detection result is a data mutation or no data mutation; determining whether to perform grid power prediction based on the detection result and a first counter, wherein the first counter is used to count the detection result; if so, generating a grid power prediction value based on the grid power data for the current period.

[0007] In one possible implementation, the power grid data of the current period is detected to obtain a detection result, including: obtaining the power grid power latch value of the previous period and a first mutation threshold; calculating a first difference between the power grid power data of the current period and the power grid power latch value; determining whether the first difference is greater than or equal to the first mutation threshold; if yes, then determining that the detection result is a data mutation; if no, then determining that the detection result is no data mutation.

[0008] In one possible implementation, determining whether to perform grid power prediction based on the detection result and the first counter includes: acquiring the first counter; determining a first current count value of the first counter, wherein the first current count value is the count value of consecutive occurrences of detection results without data mutation; if the detection result is a data mutation, resetting the first current count value to a preset value; if the detection result is a data mutation, accumulating the first current count value to obtain a target count value; and if the target count value is greater than or equal to a first count value threshold, performing grid power prediction.

[0009] In one possible implementation, generating a grid power prediction value based on the grid power data of the current period includes: latching the grid power data of the current period as a grid power prediction reference point; determining the inverter power value corresponding to the grid power data of the current period, and latching the inverter power value as an inverter power prediction reference point; obtaining the real-time inverter power value of the next period of the current period; calculating a second difference between the real-time inverter power value and the inverter power prediction reference point; and generating the grid power prediction value based on the grid power prediction reference point and the second difference.

[0010] In one possible implementation, generating the power grid prediction value based on the power grid prediction benchmark and the second difference includes: acquiring historical power grid fluctuation data; determining a corresponding compensation coefficient based on the variance of the historical power grid fluctuation data; calculating the product of the compensation coefficient and the second difference; and determining the power grid prediction value as the sum of the power grid prediction benchmark and the product.

[0011] In one possible implementation, the method further includes: acquiring a second counter; determining a second current count value of the second counter, the second current count value being a count value of the number of grid power fluctuations; if the grid power data of the current period meets a preset fluctuation condition, then accumulating the second current count value to obtain a fluctuation count value; if the fluctuation count value is greater than or equal to a second count value threshold, then updating the grid power prediction reference point and the inverter power prediction reference point.

[0012] In one possible implementation, the preset fluctuation conditions are: the energy dispatch of the energy storage inverter is in a discharging state, and the real-time value of the grid power data is less than or equal to a preset lower limit; and / or, the energy dispatch of the energy storage inverter is in a charging state, and the real-time value of the grid power data is greater than or equal to a preset upper limit.

[0013] Secondly, embodiments of this application provide a power grid prediction device, comprising: an acquisition module for acquiring power grid data for the current period; a detection module for detecting the power grid data for the current period and obtaining a detection result, wherein the detection result is a data mutation or no data mutation; a judgment module for determining whether to perform power grid prediction based on the detection result and a first counter, wherein the first counter is used to count the detection result; and a generation module for generating a power grid prediction value based on the power grid data for the current period if the result is positive.

[0014] In one possible implementation, the detection module is specifically configured to acquire the grid power latch value of the previous cycle and a first mutation threshold; the detection module is further configured to calculate a first difference between the grid power data of the current cycle and the grid power latch value; the detection module is further configured to determine whether the first difference is greater than or equal to the first mutation threshold; the detection module is further configured to determine that the detection result is a data mutation if the first difference is greater than or equal to the first mutation threshold; the detection module is further configured to determine that the detection result is no data mutation if the first difference is not greater than or equal to the first mutation threshold.

[0015] In one possible implementation, the judgment module is specifically configured to acquire a first counter; the judgment module is further configured to determine a first current count value of the first counter, wherein the first current count value is the count value of consecutive occurrences of detection results where the data has not changed; the judgment module is further configured to reset the first current count value to a preset value if the detection result is a data change; the judgment module is further configured to accumulate the first current count value to obtain a target count value if the detection result is a data change; and the judgment module is further configured to perform grid power prediction if the target count value is greater than or equal to a first count value threshold.

[0016] In one possible implementation, the apparatus further includes: an execution module, configured to latch the grid power data of the current period as a grid power prediction reference point; the execution module is further configured to determine the inverter power value corresponding to the grid power data of the current period, and latch the inverter power value as an inverter power prediction reference point; the execution module is further configured to obtain the real-time inverter power value of the next period of the current period; the execution module is further configured to calculate a second difference between the real-time inverter power value and the inverter power prediction reference point; the execution module is further configured to generate the grid power prediction value based on the grid power prediction reference point and the second difference.

[0017] In one possible implementation, the execution module is specifically configured to acquire historical power grid fluctuation data; the execution module is further configured to determine a corresponding compensation coefficient based on the variance of the historical power grid fluctuation data; the execution module is further configured to calculate the product of the compensation coefficient and the second difference; the execution module is further configured to determine the sum of the power grid prediction benchmark point and the product as the predicted power grid value.

[0018] In one possible implementation, the device further includes: an update module for acquiring a second counter; the update module is further configured to determine a second current count value of the second counter, the second current count value being a count value of the number of grid power fluctuations; the update module is further configured to accumulate the second current count value to obtain a fluctuation count value if the grid power data of the current period meets a preset fluctuation condition; the update module is further configured to update the grid power prediction reference point and the inverter power prediction reference point if the fluctuation count value is greater than or equal to a second count value threshold.

[0019] In one possible implementation, the preset fluctuation conditions are: the energy dispatch of the energy storage inverter is in a discharging state, and the real-time value of the grid power data is less than or equal to a preset lower limit; and / or, the energy dispatch of the energy storage inverter is in a charging state, and the real-time value of the grid power data is greater than or equal to a preset upper limit.

[0020] Thirdly, embodiments of this application provide a power grid prediction device, including: a memory and a processor;

[0021] The memory stores computer-executed instructions;

[0022] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0023] Fourthly, embodiments of this application provide a non-volatile 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 implementations of the first aspect.

[0024] Fifthly, embodiments of this application provide 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.

[0025] The power grid power prediction method, apparatus, electronic device, and medium provided in this application include: acquiring power grid power data for the current period; detecting the power grid power data for the current period to obtain a detection result, wherein the detection result is a data mutation or no data mutation; determining whether to perform power grid power prediction based on the detection result and a first counter, wherein the first counter is used to count the detection result; if so, generating a predicted power grid value based on the power grid power data for the current period. This scheme, by predicting future power grid power based on power grid power data, allows for advance energy scheduling, accurately suppressing power grid fluctuations, and improving power supply stability. Attached Figure Description

[0026] 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.

[0027] Figure 1 A schematic diagram illustrating an application scenario of a power grid power prediction method provided in this application embodiment;

[0028] Figure 2 A flowchart illustrating a power grid power prediction method provided in this application embodiment;

[0029] Figure 3 A flowchart illustrating another method for predicting grid power provided in an embodiment of this application;

[0030] Figure 4 A schematic diagram illustrating stability verification provided in an embodiment of this application;

[0031] Figure 5 This is a schematic diagram illustrating the generation of predicted grid power values ​​provided in an embodiment of this application;

[0032] Figure 6 A schematic diagram of the structure of a power grid prediction device provided in an embodiment of this application;

[0033] Figure 7 A schematic diagram of another power grid prediction device provided in an embodiment of this application;

[0034] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0035] The accompanying drawings have illustrated 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 specific embodiments. Detailed Implementation

[0036] 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.

[0037] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0038] It should be noted that the phrase "at...time" in the embodiments of this application can refer to the instant at which a certain situation occurs, or to a period of time after the occurrence of a certain situation; the embodiments of this application do not specifically limit this. Furthermore, the display interface provided in the embodiments of this application is merely an example, and the display interface may include more or less content.

[0039] It should be noted that the power grid prediction method, device, electronic equipment and medium of this application can be used in the field of energy storage technology, or in any field other than energy storage. The application field of the power grid prediction method, device, electronic equipment and medium of this application is not limited.

[0040] Figure 1 This is a schematic diagram illustrating an application scenario of a power grid prediction method provided in this application embodiment. The scenario illustrated is as follows: a power generation device generates electricity and transmits it to an energy storage system for storage. The energy storage system then stably inputs the electricity into the power grid according to the grid's needs.

[0041] For example, an energy storage system may include a battery and an energy storage inverter. The battery is used for energy storage. The energy storage inverter is connected to both the battery and the grid, and is used to control the storage and release of electrical energy according to energy dispatch commands, thereby achieving bidirectional energy conversion between the battery and the grid.

[0042] To illustrate with a scenario example, if the grid power is too high, the net grid load is too high. This can be mitigated by controlling the energy storage inverter to discharge power into the grid. Conversely, if the grid power is too low, it will affect the normal operation of connected electrical equipment. This can be resolved by controlling the energy storage inverter to increase charging of the grid.

[0043] For example, solar energy can be converted into electrical energy through photovoltaic power generation to provide power input for an energy storage inverter. Similarly, wind energy can be converted into electrical energy through wind power generation to provide power input for an energy storage inverter.

[0044] In related technologies, smart meters connected to the power grid measure the grid power. If the grid power is abnormal, the smart meter sends a signal to an energy storage inverter. The energy storage inverter then performs energy dispatching based on the signal generation instructions to restore the grid power to a preset range. However, the generation and transmission of signals and instructions require a fixed amount of time, causing the energy dispatching of the energy storage inverter to lag behind the moment of grid power abnormality. During the lag period, the abnormal state of the grid power will persist and may further deteriorate, resulting in low power supply stability.

[0045] The method for predicting grid power provided in this application aims to solve the above-mentioned technical problems in the prior art.

[0046] 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 be described below with reference to the accompanying drawings.

[0047] Figure 2 A flowchart illustrating a power grid prediction method provided in this application embodiment, the method comprising the following steps:

[0048] S201. Obtain the grid power data for the current period.

[0049] For example, real-time power data of the power grid can be read from smart meters or high-precision current transformers connected to the energy storage system according to a preset sampling period.

[0050] For example, smart meters or high-precision current transformers are connected to the power grid so that the power grid power data accurately reflects the working status of the power grid.

[0051] S202. Detect the power grid data for the current period and obtain the detection result, which is either a data mutation or no data mutation.

[0052] For example, a data mutation indicates a significant jump in grid power data between two adjacent sampling periods. Such a jump could be caused by events such as the sudden commissioning of high-power loads or large-area shading of photovoltaic arrays.

[0053] For example, mutation detection is used to identify these violent disturbance events because the grid state is extremely unstable and the grid power data is also unstable for a very short period of time after these events occur. Predicting the grid power at future moments based on unstable grid power data will result in a large error.

[0054] Optionally, the grid power data read in the current cycle is compared with the grid power data stored in the previous cycle, and the difference between the two is calculated. This difference is then compared with a preset threshold value for determining a data mutation. If the difference reaches or exceeds the threshold value, it is determined that a data mutation has occurred; otherwise, it is determined that no data mutation has occurred.

[0055] Optionally, the threshold value can be a fixed value or dynamically adjusted based on the fluctuation range of historical power data to adapt to different power grid operating environments.

[0056] S203. Determine whether to perform grid power prediction based on the detection results and the first counter. The first counter is used to count the detection results.

[0057] For example, the first counter is used to continuously observe the stability of the power grid, and the first counter counts based on each detection result.

[0058] For example, the larger the value of the first counter, the longer the power grid remains stable, thus quantifying the stability of the power grid.

[0059] The scenario example illustrates that predictions are only made when the power grid is relatively stable. When the power grid is stable, its fluctuations follow certain patterns, which allow for accurate predictions.

[0060] S204. If so, generate a predicted grid power value based on the grid power data of the current period.

[0061] For example, when the prediction execution conditions are met, a grid power prediction is generated. The grid power prediction is an optimal estimate of the actual grid power state generated locally in real time, given the inherent communication delays in the energy storage system architecture. It replaces outdated historical data due to delays, thereby supporting timely and accurate decisions in energy dispatch strategies.

[0062] With the help of scenario examples, the power grid prediction value is ahead of the actual changes in the power grid in the time dimension. This allows energy dispatch instructions based on this prediction value to be calculated and prepared in advance, effectively offsetting the time consumed in the communication process and improving the overall response speed of the energy storage system.

[0063] The grid power prediction method provided in this application involves acquiring grid power data for the current period; detecting the grid power data for the current period to obtain a detection result, which may be a data mutation or no data mutation; determining whether to perform grid power prediction based on the detection result and a first counter, where the first counter is used to count the detection result; and if so, generating a grid power prediction value based on the grid power data for the current period. This scheme, by predicting future grid power based on grid power data, allows for advance energy scheduling, accurately suppressing grid fluctuations, and improving power supply stability.

[0064] Based on any of the above embodiments, the following, in conjunction with Figure 3 The detailed process of predicting power grid output is explained.

[0065] Figure 3 This is a flowchart illustrating another method for predicting grid power provided in an embodiment of this application. Figure 3 As shown, the method includes:

[0066] S301. Obtain the grid power data for the current period.

[0067] It should be noted that the execution process of S301 is the same as that of S201, and will not be repeated here.

[0068] S302. Detect the power grid data for the current period and obtain the detection result, which is either a data mutation or no data mutation.

[0069] One feasible implementation method is to detect the data by: obtaining the grid power latch value of the previous cycle and the first mutation threshold; calculating the first difference between the grid power data of the current cycle and the grid power latch value; determining whether the first difference is greater than or equal to the first mutation threshold; if so, determining that the detection result is a data mutation; if not, determining that the detection result is no data mutation.

[0070] For example, the grid power latch value for the previous period is obtained by latching the grid power data collected in the previous sampling period. The grid power latch value is a historical reference benchmark. The latching operation ensures that the historical reference benchmark is fixed and clear, thereby improving the accuracy of the prediction.

[0071] For example, the first mutation threshold is a dividing line for determining whether a mutation has occurred, used to distinguish between normal fluctuations and mutations.

[0072] Optionally, the first mutation threshold can be dynamically determined based on historical change data of the power grid.

[0073] For example, a first difference is calculated to quantify the drastic change in grid power between the previous cycle and the current cycle. If the drastic change exceeds a first abrupt change threshold, a sudden change in grid power is determined; otherwise, no sudden change in grid power is determined.

[0074] In this feasible implementation, by comparing the first difference and the first mutation threshold, the degree of change in the power grid can be accurately quantified, improving the accuracy of power grid power prediction and thus enhancing power supply stability.

[0075] S303. Determine whether to perform grid power prediction based on the detection results and the first counter. The first counter is used to count the detection results.

[0076] One feasible implementation method is to determine whether to perform grid power prediction by: acquiring a first counter; determining a first current count value of the first counter, wherein the first current count value is the count value of consecutive occurrences of detection results where the data has not changed; if the detection result is a data change, resetting the first current count value to a preset value; if the detection result is no data change, accumulating the first current count value to obtain a target count value; if the target count value is greater than or equal to a first count value threshold, then performing grid power prediction.

[0077] For example, the first current count value is the current reading of the first counter.

[0078] For example, the first count value represents the consecutive counts of detection results where the data does not change abruptly. This means that the first counter is essentially a stability duration meter. The increase of the first count value directly and quantitatively reflects the duration during which the power state of the grid remains stable (without abrupt changes).

[0079] For example, when a data mutation is detected, the first current count value is immediately reset to a preset value (which can be 1 or 0). The technical implication of this operation is that any significant power mutation event signifies the end of the previous stable period, and the energy storage system enters a period requiring reassessment. The reset operation clears historical stability records, preventing the state before the mutation from being carried into the new assessment period, thereby improving the accuracy of stability determination.

[0080] For example, when no sudden change in data is detected, the first current counter value is incremented. The technical implication of this operation is that with each passing stable cycle, the system's confidence in its current stable state increases by one point. The increment of the first current counter value is quantitative evidence that the energy storage system has gradually confirmed that the power grid has recovered from potential disturbances and maintained stability.

[0081] Below, in conjunction with Figure 4 The stability verification is explained.

[0082] Figure 4 This is a schematic diagram illustrating stability verification provided for an embodiment of this application. For example... Figure 4 As shown, the first current count value of the first counter is 3. If the detection result is a data mutation, the first current count value is reset to 0. If the detection result is no data mutation, the first current count value is updated to 4, and the stability of the power grid is confirmed based on the updated first current count value.

[0083] In this feasible implementation, a continuous and stable periodic confirmation mechanism enforces a mandatory entry threshold for the activation of the prediction function. This ensures that prediction calculations are only triggered after sufficient grid power has been generated, improving the accuracy of grid power prediction and thus enhancing power supply stability.

[0084] S304. Latch the grid power data for the current period as the grid power prediction reference point.

[0085] For example, when the grid is in a stable state, the current grid power data is locked and stored so that subsequent calculations are based on fixed values, thereby improving the accuracy of predictions.

[0086] S305. Determine the inverter power value corresponding to the grid power data of the current period, and lock the inverter power value as the inverter power prediction reference point.

[0087] For example, the inverter power value is the instantaneous value of the power of the energy storage inverter, representing the real-time power transmitted between the energy storage inverter and the grid.

[0088] For example, a positive inverter power value indicates that the energy storage inverter is charging the grid. A negative inverter power value indicates that the energy storage inverter is discharging into the grid.

[0089] For example, when the power grid is stable, the current inverter power value is acquired and stored simultaneously to establish a correlation between the power grid power data and the inverter power value at the same observation time, providing a time-consistent data foundation for subsequent calculations.

[0090] S306. Obtain the real-time value of the inverter power for the next cycle of the current cycle.

[0091] Optionally, the real-time inverter power value of the energy storage inverter can be directly obtained through the digital signal processor (DSP) of the energy storage device, without the need for communication and without communication delay.

[0092] For example, the real-time inverter power value is used as a variable to reflect the current instantaneous power interaction state.

[0093] S307. Calculate the second difference between the real-time value of inverter power and the inverter power prediction reference point.

[0094] For example, the second difference quantifies the net change in the output power of the energy storage system since the reference point was established. For instance, a positive difference indicates that the energy storage inverter has increased its discharge power or decreased its charging power compared to the reference time.

[0095] S308. Generate the power prediction value based on the power prediction benchmark point and the second difference.

[0096] Below, in conjunction with Figure 5 The generated power grid power prediction values ​​are explained.

[0097] Figure 5 This is a schematic diagram illustrating the generation of grid power prediction values ​​provided in an embodiment of this application. For example... Figure 5 As shown, abrupt changes are detected in the power grid data to eliminate interference from these changes in the prediction. When the data is stable, a first current count value is used to check the grid stability. If the target count value is greater than or equal to a count value threshold, the grid is considered relatively stable. The predicted power grid value is generated using the grid power prediction benchmark as a reference and combined with the second difference in the change.

[0098] Based on the above implementation method, since the real-time value of inverter power is acquired in real time, the generation of grid power prediction value is almost synchronized with the change of grid state, thereby improving the accuracy of grid power prediction value.

[0099] One feasible approach to generating power prediction values ​​involves: acquiring historical power grid fluctuation data; determining the corresponding compensation coefficient based on the variance of the historical power grid fluctuation data; calculating the product of the compensation coefficient and the second difference; and determining the sum of the power grid prediction benchmark point and the product as the power grid prediction value.

[0100] For example, an energy storage system continuously records and stores a sequence of power fluctuation data from the grid over a specific time window in the past. This data sequence is used to assess the current fluctuation patterns of the power grid.

[0101] For example, statistical analysis is performed on historical power grid fluctuation data to calculate the variance. Variance is a core indicator in probability and statistics representing the degree of dispersion of data fluctuations. A large variance value indicates that the power grid power fluctuates drastically and frequently during the historical period; a small variance value indicates that the power grid power is relatively stable during the historical period.

[0102] For example, a matching compensation coefficient is dynamically determined based on the variance, where historical fluctuation characteristics predict possible change patterns in the near future. The second difference is compensated by the compensation coefficient to ensure that the power grid prediction maintains optimal tracking speed and accuracy under different power grid scenarios with varying fluctuation characteristics, ultimately minimizing the prediction error.

[0103] In this feasible implementation, flexible compensation calculations are performed using dynamically determined compensation coefficients to match the predicted power grid values ​​with the actual fluctuations in the power grid, thereby improving the accuracy of power grid prediction and thus enhancing power supply stability.

[0104] One feasible implementation method for predicting grid power may further include: acquiring a second counter; determining a second current count value of the second counter, wherein the second current count value is the count value of the number of grid power fluctuations; if the grid power data of the current period meets the preset fluctuation conditions, then accumulating the second current count value to obtain a fluctuation count value; if the fluctuation count value is greater than or equal to the second count value threshold, then updating the grid power prediction benchmark point and the inverter power prediction benchmark point.

[0105] For example, the second counter is used to count the number of power fluctuations in the power grid. The second counter quantifies the cumulative trend of power grid deviations from the ideal steady state.

[0106] For example, preset fluctuation conditions are used to capture small, persistent deviations in grid power with relatively low trends.

[0107] For example, when the fluctuation count reaches or exceeds the second count threshold, it indicates that the grid power has been continuously deviating for a certain period of time, and the original prediction reference point can no longer accurately reflect the current steady-state operating point. At this time, the energy storage system triggers an update process: updating the grid power prediction reference point and the inverter power prediction reference point to adapt to the actual grid conditions.

[0108] Optionally, after the update is complete, reset the second counter to begin a new round of fluctuation monitoring.

[0109] In this feasible implementation, dynamic tracking of the prediction benchmark point is achieved, overcoming long-term drift and improving the accuracy of power grid power prediction, thereby enhancing power supply stability.

[0110] One feasible implementation method is to preset the fluctuation conditions as follows: the energy dispatch of the energy storage inverter is in the discharge state, and the real-time value of the grid power data is less than or equal to the preset lower limit value; and / or, the energy dispatch of the energy storage inverter is in the charging state, and the real-time value of the grid power data is greater than or equal to the preset upper limit value.

[0111] For example, the energy dispatching state of an energy storage inverter indicates that the inverter converts the DC power stored in the battery into AC power and inputs it into the grid. The charging state indicates that the inverter draws AC power from the grid, converts it into DC power, and stores energy in the battery.

[0112] For example, during discharge, grid power should be supported at a relatively high level. If the measured power consistently falls below the lower limit, it indicates that grid power is still too low even though the energy storage inverter is discharging. This may be because the grid's current operating point has deviated from the steady state at the prediction reference point, meaning the prediction reference point has failed.

[0113] For example, during charging, grid power should be absorbed to a relatively low level. If the measured power consistently exceeds the upper limit, it indicates that grid power is still too high even though the energy storage inverter is charging. This may be because the grid's current operating point has deviated from the steady state at the prediction reference point, meaning the prediction reference point has failed.

[0114] In this feasible implementation, accurate steady-state offset sensing can be achieved by setting a lower limit and a higher limit, which can improve the accuracy of power grid power prediction and thus improve power supply stability.

[0115] Figure 6 This is a schematic diagram of the structure of a power grid prediction device provided in an embodiment of this application. Figure 6 As shown, the power prediction device 60 for the power grid may include: an acquisition module 61, a detection module 62, a judgment module 63, and a generation module 64.

[0116] The acquisition module 61 is used to acquire the power grid data for the current period.

[0117] The detection module 62 is used to detect the power grid data of the current period and obtain the detection result, which is either a data mutation or no data mutation.

[0118] The judgment module 63 is used to determine whether to perform grid power prediction based on the detection results and the first counter. The first counter is used to count the detection results.

[0119] The generation module 64 is used to generate a grid power prediction value based on the grid power data of the current period if the condition is met.

[0120] Optionally, module 61 can be executed. Figure 2 S201 in the embodiment.

[0121] Optionally, the detection module 62 can perform... Figure 2 S202 in the embodiment.

[0122] Optionally, the judgment module 63 can execute... Figure 2 S203 in the embodiment.

[0123] Optionally, the generation module 64 can be executed. Figure 2 S204 in the embodiment.

[0124] It should be noted that the power grid prediction device shown in the embodiments of this application can execute the technical solution shown in the above method embodiments, and its implementation principle and beneficial effects are similar, so they will not be described again here.

[0125] In one possible implementation, the detection module 62 is specifically used for:

[0126] Obtain the grid power latch value of the previous cycle and the first mutation threshold for the current cycle;

[0127] Calculate the first difference between the grid power data for the current period and the grid power latch value;

[0128] Determine whether the first difference is greater than or equal to the first mutation threshold;

[0129] If so, then the test result is determined to be a data mutation;

[0130] If not, then the test result indicates that the data has not mutated.

[0131] In one possible implementation, the determination module 63 is specifically used for:

[0132] Get the first counter;

[0133] Determine the first current count value of the first counter. The first current count value is the count value of consecutive occurrences of detection results where the data has not changed abruptly.

[0134] If the detection result is a data mutation, the first current count value will be reset to the preset value;

[0135] If the detection result shows that the data has not changed abruptly, then the target count value is obtained by accumulating the first current count value;

[0136] If the target count value is greater than or equal to the first count value threshold, then power grid prediction is performed.

[0137] Figure 7 This is a schematic diagram of another power grid prediction device provided in an embodiment of this application. Figure 6Based on the illustrated embodiments, as Figure 7 As shown, the power grid prediction device 60 also includes an execution module 65 and an update module 66.

[0138] Execution module 65 is used for:

[0139] The current period's grid power data is latched as the grid power prediction benchmark point;

[0140] Determine the inverter power value corresponding to the grid power data of the current period, and latch the inverter power value as the inverter power prediction reference point;

[0141] Obtain the real-time inverter power value for the next cycle of the current cycle;

[0142] Calculate the second difference between the real-time inverter power value and the inverter power prediction reference point;

[0143] The power grid prediction value is generated based on the power grid prediction benchmark and the second difference.

[0144] In one possible implementation, execution module 65 is specifically used for:

[0145] Obtain historical power grid fluctuation data;

[0146] The corresponding compensation coefficient is determined based on the variance of historical power grid fluctuation data;

[0147] Calculate the product of the compensation coefficient and the second difference;

[0148] The sum of the product of the power grid prediction benchmark point and the power grid power prediction value is determined as the power grid power prediction value.

[0149] Update module 66, used for:

[0150] Obtain the second counter;

[0151] Determine the second current count value of the second counter, where the second current count value is the count value of the number of power fluctuations in the grid;

[0152] If the power grid data for the current period meets the preset fluctuation conditions, then the second current count value is accumulated to obtain the fluctuation count value;

[0153] If the fluctuation count value is greater than or equal to the second count value threshold, the grid power prediction benchmark and the inverter power prediction benchmark will be updated.

[0154] The preset fluctuation conditions are:

[0155] The energy storage inverter is in a discharge state, and the real-time value of the grid power data is less than or equal to a preset lower limit; and / or,

[0156] The energy storage inverter is in a charging state, and the real-time value of the grid power data is greater than or equal to the preset upper limit value.

[0157] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 8 As shown, the electronic device includes:

[0158] The electronic device includes a processor 291 and a memory 292; it may also include a communication interface 293 and a bus 294. The processor 291, memory 292, and communication interface 293 can communicate with each other via the bus 294. The communication interface 293 can be used for information transmission. The processor 291 can invoke logical instructions stored in the memory 292 to execute the methods of the above embodiments.

[0159] Furthermore, the logic instructions in the aforementioned memory 292 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0160] The memory 292, as a non-volatile computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this application. The processor 291 executes functional applications and data processing by running the software programs, instructions, and modules stored in the memory 292, that is, it implements the methods in the above-described method embodiments.

[0161] The memory 292 may include a program storage area and a data storage area. The program storage area may store the operating system and application programs required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 292 may include high-speed random access memory and may also include non-volatile memory.

[0162] This application provides a non-volatile computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method as described in the foregoing embodiments.

[0163] This application provides a computer program product, including a computer program that, when executed by a processor, implements the method as described in the foregoing embodiments.

[0164] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0165] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps; they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages, which do not necessarily complete at the same time but can be executed at different times. The execution order of these sub-steps or stages is also not necessarily sequential but can be alternated or carried out in turn with other steps or at least some of the sub-steps or stages of other steps.

[0166] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0167] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0168] When the integrated unit / module is implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. The processor can be any suitable hardware processor, such as CPU, GPU, FPGA, DSP, and ASIC. The storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0169] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 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 application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0170] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0171] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the claims.

[0172] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for predicting power grid output, characterized in that, include: Obtain the grid power data for the current period; The power grid data for the current period is detected to obtain a detection result, which is either a sudden data change or no data change. Whether to perform grid power prediction is determined based on the detection results and the first counter, wherein the first counter is used to count the detection results; If so, then generate a predicted grid power value based on the grid power data of the current period; The process of generating a power grid prediction value includes: latching the power grid data of the current period as a power grid prediction reference point; determining the inverter power value corresponding to the power grid data of the current period and latching the inverter power value as an inverter power prediction reference point; obtaining the real-time inverter power value of the next period; calculating a second difference between the real-time inverter power value and the inverter power prediction reference point; and generating the power grid prediction value based on the power grid prediction reference point and the second difference. The process of generating the predicted power grid value includes: acquiring historical power grid fluctuation data; determining a corresponding compensation coefficient based on the variance of the historical power grid fluctuation data; calculating the product of the compensation coefficient and the second difference; and determining the predicted power grid value as the sum of the power grid prediction benchmark point and the product.

2. The method according to claim 1, characterized in that, The power grid data for the current period is detected to obtain the detection results, including: Obtain the grid power latch value of the previous cycle and the first mutation threshold for the current cycle; Calculate the first difference between the grid power data for the current period and the grid power latch value; Determine whether the first difference is greater than or equal to the first mutation threshold; If so, then the detection result is determined to be a data mutation; If not, then the test result is determined to be that the data has not mutated.

3. The method according to claim 1, characterized in that, Determining whether to perform grid power prediction based on the detection results and the first counter includes: Get the first counter; Determine the first current count value of the first counter, where the first current count value is the count value of consecutive occurrences of detection results where the data has not changed abruptly; If the detection result is a data mutation, then the first current count value is reset to a preset value; If the detection result is that the data has not changed abruptly, then the first current count value is accumulated to obtain the target count value; If the target count value is greater than or equal to the first count value threshold, then power grid prediction is performed.

4. The method according to claim 1, characterized in that, The method further includes: Obtain the second counter; Determine the second current count value of the second counter, where the second current count value is the count value of the number of power fluctuations in the grid; If the power grid data of the current period meets the preset fluctuation conditions, then the second current count value is accumulated to obtain the fluctuation count value; If the fluctuation count value is greater than or equal to the second count value threshold, then the power grid power prediction benchmark and the inverter power prediction benchmark are updated.

5. The method according to claim 4, characterized in that, The preset fluctuation conditions are: The energy storage inverter is in a discharge state, and the real-time value of the grid power data is less than or equal to a preset lower limit; and / or, The energy storage inverter is in a charging state, and the real-time value of the grid power data is greater than or equal to the preset upper limit value.

6. A power grid prediction device, characterized in that, include: The acquisition module is used to acquire the grid power data for the current period; The detection module is used to detect the power grid data of the current period and obtain the detection result, which is either a sudden change in data or no sudden change in data. The judgment module is used to determine whether to perform grid power prediction based on the detection result and the first counter, wherein the first counter is used to count the detection result; The generation module is used to generate a predicted grid power value based on the grid power data of the current period if the condition is met. The generation module is specifically configured to latch the grid power data of the current period as a grid power prediction reference point; the generation module is also specifically configured to determine the inverter power value corresponding to the grid power data of the current period, and latch the inverter power value as an inverter power prediction reference point; the generation module is also specifically configured to obtain the real-time inverter power value of the next period of the current period; the generation module is also specifically configured to calculate a second difference between the real-time inverter power value and the inverter power prediction reference point; the generation module is also specifically configured to generate the grid power prediction value based on the grid power prediction reference point and the second difference. The generation module is specifically used to acquire historical power grid fluctuation data; the generation module is also specifically used to determine the corresponding compensation coefficient based on the variance of the historical power grid fluctuation data; the generation module is also specifically used to calculate the product of the compensation coefficient and the second difference; the generation module is also specifically used to determine the sum of the power grid power prediction benchmark point and the product as the power grid power prediction value.

7. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-5.

8. A non-volatile computer-readable storage medium, characterized in that, The non-volatile 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 1-5.

Images