Power dynamic balance control method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses an electric power dynamic balance control method and device, equipment and a storage medium. Through the above method, the mode of predicting the future load rate according to the first prediction step length is more efficient; and whether the target power grid region is in the power balance state at the future target moment can be pre-judged by predicting the future load rate, so that when the target power grid region is not in the power balance state at the target moment, a prediction result that the target power grid region is in the power balance state at present can be obtained in time. According to the invention, the current operation mode of the target power grid area is adjusted to the target operation mode by ensuring the target moment to be in the power balance state, so that the condition that the target moment is not in the power balance state can be processed in time and in advance, and rapid, flexible and accurate power grid operation mode adjustment is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system dispatching, and particularly relates to a power dynamic balance control method and device, equipment and a storage medium. BACKGROUND

[0002] The dispatching operation of the existing power system largely relies on manual operation and experience. Generally, the relevant departments formulate the future power grid operation mode according to experience, and then the dispatch personnel controls the power system according to the planned operation mode in real time. If an emergency such as power imbalance, fault or natural disaster occurs, the dispatch personnel needs to temporarily adjust the system operation mode according to experience to realize the safe and stable operation of the power system.

[0003] With the access of a large number of new grid-connected subjects to the new power system and the randomness and uncertainty of the whole period brought by the power market transaction, the difficulty of power balance in the local area of the power system in a short time is getting higher and higher, and the situation of temporary adjustment of the operation mode is getting more and more frequent. The traditional manual dispatching has been unable to adapt to these new changes, so a fast, flexible and accurate power grid operation mode adjustment technical solution is needed to meet these new requirements. SUMMARY

[0004] The main purpose of the present application is to provide a power dynamic balance control method and device, equipment and a storage medium, which can solve the problem of lack of a fast, flexible and accurate power grid operation mode adjustment technical solution in the prior art.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides a power dynamic balance control method, which comprises:

[0006] acquiring a first prediction step and a last prediction time, the prediction step being used to reflect the prediction frequency of the future load rate of the target grid area;

[0007] when the time interval between the last prediction time and the current time reaches the first prediction step, acquiring the current power operation data of the target grid area, and using the current power operation data to predict the future load rate of the target grid area to determine the target load rate at the target time in the future;

[0008] determining whether the target grid area is in a power balance state at the target time according to the target load rate and a preset power balance judgment condition;

[0009] If the target power grid region is not in the power balance state at the target time, a running mode deduction process is performed according to a preset deduction rule to determine a target running mode; and the current running mode of the target power grid region is adjusted to the target running mode; the target running mode is a power grid running mode which ensures that the target power grid region is currently in the power balance state and ensures that the target time is in the power balance state.

[0010] If the target power grid region is in the power balance state at the target time, the step of obtaining the first prediction step and the last prediction time is continued.

[0011] In a feasible implementation manner, the method further includes:

[0012] obtaining a first computing power feature of the current prediction time and a second computing power feature of the last prediction time, the computing power feature being used to reflect computing power resources at each prediction time;

[0013] performing computing power change evaluation by using the first computing power feature and the second computing power feature to determine a target evaluation result, the target evaluation result being used to reflect a change of the current computing power resources;

[0014] If the target evaluation result includes a first evaluation result, it is determined that the first prediction step is not updated, the first evaluation result being that the computing power resources are unchanged.

[0015] If the target evaluation result includes a second evaluation result, it is determined that the first prediction step is updated, the second evaluation result being that the computing power resources are changed.

[0016] In a feasible implementation manner, the method of determining that the first prediction step is updated further includes:

[0017] determining a second prediction step by using the first computing power feature, the second computing power feature, the first prediction step and a preset step length updating algorithm;

[0018] the second prediction step is used as the updated first prediction step.

[0019] In a feasible implementation manner, the step length updating algorithm is as follows:

[0020]

[0021] In the formula, ΔT n is the first prediction step, ΔT n+1 is the updated first prediction step, is the first computing power feature, is the second computing power feature.

[0022] In a possible implementation, the preset power balance judgment condition comprises at least a preset load rate threshold, and the determining whether the target power grid region is in the power balance state at the target time according to the target load rate and the preset power balance judgment condition comprises:

[0023] If the target load rate is greater than or equal to the load rate threshold, it is determined that the target power grid region is not in the power balance state at the target time.

[0024] If the target load rate is less than the load rate threshold, it is determined that the target power grid region is in the power balance state at the target time.

[0025] In a possible implementation, the determining the target operation mode according to the preset deduction rule comprises the following steps.

[0026] The preset clearing period is obtained.

[0027] The time difference between the target time and the current time is determined.

[0028] If the time difference is greater than or equal to the clearing period, the step of obtaining the first prediction step and the last prediction time is executed.

[0029] If the time difference is less than the clearing period, the step of determining the target operation mode according to the preset deduction rule is executed.

[0030] In a possible implementation, the deduction rule comprises an exhaustive method, and the determining the target operation mode according to the preset deduction rule comprises the following steps.

[0031] The preset typical operation mode is deduced to determine a first operation mode by using the exhaustive method, and the first operation mode is a power grid operation mode ensuring that the target time is in the power balance state.

[0032] The first operation mode and the current power operation data are used for safety checking to determine a safety checking result.

[0033] If the safety checking result is a first checking result, the step of deducing the preset typical operation mode to determine the first operation mode is executed, and the first checking result is that the safety checking fails.

[0034] If the safety checking result is a second checking result, it is determined that the target operation mode is the first operation mode, and the second checking result is that the safety checking is passed.

[0035] To achieve the above object, the second aspect of the present application provides a power dynamic balance control device, which comprises:

[0036] a step length obtaining module, configured to obtain a first prediction step length and a last prediction time, wherein the prediction step length is used to reflect the prediction frequency of the future load rate of the target power grid area;

[0037] a load rate prediction module, configured to, when the time interval between the last prediction time and the current time reaches the first prediction step length, obtain the current power operation data of the target power grid area, and predict the future load rate of the target power grid area by using the current power operation data to determine the target load rate of the target time in the future;

[0038] a state determining module, configured to determine whether the target power grid area is in a power balance state at the target time according to the target load rate and a preset power balance judgment condition;

[0039] a running control module, configured to, if the target power grid area is not in the power balance state at the target time, perform running mode deduction processing according to a preset deduction rule to determine a target running mode, and adjust the current running mode of the target power grid area to the target running mode, wherein the target running mode is a power grid running mode which ensures that the target power grid area is in the power balance state at the current time and at the target time, and if the target power grid area is in the power balance state at the target time, the step of obtaining the first prediction step length and the last prediction time is continued.

[0040] To achieve the above object, the third aspect of the present application provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to make the processor execute the steps shown in the first aspect and any feasible implementation manner.

[0041] To achieve the above object, the fourth aspect of the present application provides a computer device, which comprises a memory and a processor, wherein the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the steps shown in the first aspect and any feasible implementation manner.

[0042] By adopting the embodiment of the present application, the following beneficial effects are achieved:

[0043] The application provides a power dynamic balance control method, which comprises the following steps: obtaining a first prediction step and a last prediction time, wherein the prediction step is used to reflect the prediction frequency of the future load rate of a target power grid area; when the time interval between the last prediction time and the current time reaches the first prediction step, obtaining the current power operation data of the target power grid area, and using the current power operation data to predict the future load rate of the target power grid area to determine the target load rate of a target time in the future; determining whether the target power grid area is in a power balance state at the target time according to the target load rate and a preset power balance judgment condition; if the target power grid area is not in the power balance state at the target time, performing operation mode deduction processing according to a preset deduction rule to determine a target operation mode; and adjusting the current operation mode of the target power grid area to the target operation mode; the target operation mode is a power grid operation mode which not only ensures that the target power grid area is in the power balance state at present, but also ensures that the target power grid area is in the power balance state at the target time; if the target power grid area is in the power balance state at the target time, the step of obtaining the first prediction step and the last prediction time is continuously performed.

[0044] Through the above method, the way of predicting the future load rate according to the first prediction step is more efficient, and the future target time target power grid area whether in the power balance state can be pre-judged by predicting the future load rate, and then when the target power grid area is not in the power balance state at the target time, the target power grid operation mode which not only ensures that the target power grid area is in the power balance state at present, but also ensures that the target power grid area is in the power balance state at the target time can be deduced in time, the current operation mode of the target power grid area is adjusted to the target operation mode, so that the situation that the target power grid area is not in the power balance state at the target time can be processed in time and in advance, and a fast, flexible and accurate power grid operation mode adjustment is realized. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0046] Among them:

[0047] Figure 1 It is a flow chart of the power dynamic balance control method in the embodiment of the present application;

[0048] Figure 2 It is another flow chart of the power dynamic balance control method in the embodiment of the present application;

[0049] Figure 3 This is a structural block diagram of a power dynamic balance control device according to an embodiment of the present invention;

[0050] Figure 4 This is a structural block diagram of a computer device in an embodiment of the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] Please see Figure 1 , Figure 1 This is a flowchart of a power dynamic balance control method according to an embodiment of the present invention, such as... Figure 1 The method shown can be applied to both terminals and servers. The terminal can be a desktop terminal or a mobile terminal, and a mobile terminal can be at least one of a mobile phone, tablet computer, or laptop computer. The server can be a standalone server or a server cluster composed of multiple servers. This embodiment uses a cloud server as an example, and the method includes the following steps:

[0053] 101. Obtain the first prediction step size and the last prediction time, wherein the prediction step size is used to reflect the prediction frequency of the future load rate of the target power grid area;

[0054] It should be noted that, in order to achieve dynamic power balance, this embodiment predicts the future load rate of the power grid area in real time. For example, it estimates the future load rate according to a certain prediction frequency. Specifically, the cloud server can obtain the first prediction step size and the time of the last prediction. The prediction step size reflects the prediction frequency of the future load rate of the target power grid area. The first prediction step size can be understood as the current prediction step size. The current prediction step size may be the initial prediction step size or it may be the prediction step size that has been updated as the prediction progresses. It can be understood that, in the first prediction, the first prediction step size is the initial prediction step size, and the initial prediction step size ΔT nThe initial time length can be preset, and the time length can be in seconds, minutes, hours, etc. For example, the initial time length is 10s, 20s, or 30s, etc. The specific initial time length can be set according to actual needs. The target power grid area is a power grid area to be predicted. The target power grid area can be regarded as a power balance object area Zi. Further, each power balance object area Zi can be pre-divided according to a preset area division rule. For example, the preset area division can be to divide the power balance object area Zi according to substations with different voltage levels. Generally, the power balance areas can be divided according to voltage levels, such as 35kV, 110kV, 220kV, and 500kV substations. The electrical elements of each area include the main transformer, switch, and line of the substation. High-voltage level elements belong to the power balance area of a high-voltage level substation, such as the main transformer, 110kV line, and 110kV switch in a 110kV substation, which are electrical elements in the power balance object area of the 110kV substation. However, the 220kV line and switch in the substation belong to the power balance area of other 220kV substations. Further, each target power grid area with different voltage levels can be obtained. The cloud server can be independent or composed of a cluster of distributed servers. Each server can be responsible for data processing of a target power grid area. In this way, each server can synchronously execute the control method shown in the embodiment to simultaneously control the power dynamic balance of multiple target power grid areas. The embodiment is exemplarily described by taking one target power grid area for power dynamic balance control, which does not mean that the embodiment is limited.

[0055] The load rate of the target power grid area can be represented by the load rate of each electrical element in the area. The load rate of an electrical element = (actual power of the electrical element / rated power) * 100%. The load rate exceeding 100% is called overload. The overload of an electrical element indicates that the power supply and demand in the area are unbalanced, which has a negative impact on the safe and stable operation of the power grid.

[0056] 102. When the time interval between the last prediction time and the current time reaches the first prediction step, the current power operation data of the target power grid area is obtained, and the future load rate of the target power grid area is predicted by using the current power operation data to determine the target load rate at the future target time.

[0057] Further, the first prediction step is obtained, the prediction frequency of the future load rate of the target power grid area is known, and the future load rate can be predicted every first prediction step. Specifically, the time interval between the last prediction time and the current time is determined before each prediction to determine whether the prediction frequency is met. If the time interval reaches the first prediction step, the prediction frequency is met and the future load rate can be predicted. Otherwise, the time interval does not reach the first prediction step, which means that the prediction frequency has not been reached. Step 101 is continued until the time interval reaches the first prediction step, and step 102 is performed to predict the future load rate. In the prediction of the future load rate, the current power operation data of the target power grid area is obtained, the current power operation data is used to predict the future load rate of the target power grid area, and the target load rate at the target time in the future is determined. The current power operation data is used to reflect the power operation of the current target power grid area. The current power operation data at least includes power operation data at the current time and each historical time. For example, the power operation data at least includes historical data, weather data, metering data, communication signal hotspot data, and power market data. The multi-dimensional and multi-element data is used for prediction. An example of a feasible prediction method can be based on all historical power operation data of the current target power grid area to fit the data and determine the historical data trend. The target power operation data at the target time is determined according to the historical data trend and the target time in the future to be predicted. Since the data variation law can be known based on the historical data trend, the target power operation data at the target time can be determined by referring to the law. The target power operation data at least includes the actual power of each electrical element at the target time. Thus, the load rate of each electrical element at the target time can be obtained by the above electrical element load rate calculation formula. The target load rate at least includes the load rate of each electrical element at the target time. The target time is a time in the future, which can be set according to the desired prediction time, such as seconds, minutes, or hours, which is not limited here.

[0058] Another possible prediction method can be to pre-train a deep learning model, and the deep learning model outputs the target load rate at the target time. The specific process is as follows: training sample data is collected in advance, the training sample data is composed of historical power operation data and historical load rates at each historical time in the target power grid region, and then the historical power operation data at each historical time is input into a preset deep learning model for training to obtain a prediction result output by the deep learning model. The prediction result includes the predicted load rate at each historical time. Further, the predicted load rate at each historical time and the historical load rate are used to determine whether the deep learning model converges. If the deep learning model does not converge, a loss value is determined, and the deep learning model is continuously trained based on the loss value. If the deep learning model converges, the deep learning model at this time is obtained, and the deep learning model is used as a load rate prediction model. In this way, all historical power operation data of the current target power grid region can be input into the load rate prediction model to obtain the target load rate at the target time output by the load rate prediction model.

[0059] For example, the real-time T0 is taken as an initial time, and the future T i time period Z i load rate R of each electrical element N in the time period Z Ni , where T i ≥ T0, and ΔT > 0. ΔT is a prediction step, which can be flexibly adjusted according to the computing resource. At present, it is recommended to be set to a minute level. After the computing resource is improved, the step can be gradually increased to a second level, so as to be closer to the real-time state of the power grid operation. The load rate at the future T i time is predicted by combining historical data, meteorological data, metering data, communication signal hotspot data, and power market data.

[0060] 103. Determine whether the target power grid region is in a power balance state at the target time according to the target load rate and a preset power balance judgment condition.

[0061] Further, after obtaining the target load rate, it can be determined whether the power will be unbalanced in the future by the load rate. Specifically, whether the target power grid region is in a power balance state at the target time is determined according to the target load rate and a preset power balance judgment condition.

[0062] Since the load rate exceeding 100% is called overload, and an electrical element is overloaded, it indicates that the power supply and demand in the region are unbalanced, which has a negative impact on the safe and stable operation of the power grid. Therefore, the preset power balance judgment condition at least includes a preset load rate threshold, which can be 100%. Step 103 can include the following steps A001 to A02:

[0063] A01, if the target load rate is greater than or equal to the load rate threshold, it is determined that the target power grid region is not in a power balance state at the target time;

[0064] A02, if the target load rate is less than the load rate threshold, it is determined that the target power grid region is in a power balance state at the target time.

[0065] It should be noted that the target load rate can include the load rate of all electrical elements in the target power grid region, and further, if the load rate of any electrical element in the region is greater than or equal to the load rate threshold, it is considered that the target load rate is greater than or equal to the load rate threshold, indicating that the target power grid region is not in a power balance state at the target time; on the contrary, if the load rate of all electrical elements in the region is less than the load rate threshold, it is considered that the target load rate is less than the load rate threshold, indicating that the target power grid region is in a power balance state at the target time.

[0066] Further, if the target power grid region is in a power balance state at the target time, step 105 is executed to continue step 101, otherwise, if the target power grid region is not in a power balance state at the target time, step 104 needs to be executed to perform a power dynamic balance control process to make the target power grid region be in a power balance state at the target time.

[0067] 104, if the target power grid region is not in a power balance state at the target time, a running mode deduction process is performed according to a preset deduction rule to determine a target running mode; and the current running mode of the target power grid region is adjusted to the target running mode; the target running mode is a power grid running mode which ensures that the target power grid region is in a power balance state at the target time;

[0068] The emerging grid-connected subjects include but are not limited to charging piles, energy storage, distributed new energy, virtual power plants, load aggregators and other devices or systems different from traditional power grid power sources and loads. The addition of these new grid-connected subjects may break the balance. Then if the target power grid region is not in a power balance state at the target time, the power balance can be restored by adjusting the power grid operation mode, wherein the power grid operation mode refers to the combination of the running states of all generator groups, transformers, transmission lines, circuit breakers and other electrical elements in the power system, so that each electrical element operates within the safety boundary to achieve the power balance between the active power output and the load power of the power system. Further, according to the preset deduction rule, the operation mode deduction processing is performed to determine the target operation mode, that is, the target operation mode can be obtained by deduction, which can make the target time in a power balance state, and the target operation mode is the power grid operation mode which ensures that the target power grid region is currently in a power balance state and ensures that the target time is in a power balance state. Finally, the current power grid operation mode can be switched to the target operation mode, so that the future target time can be in a balanced state on the basis of not destroying the current balance.

[0069] 105、If the target power grid region is in a power balance state at the target time, continue to perform the steps of obtaining the first prediction step and the last prediction time.

[0070] The application provides a power dynamic balance control method, which comprises the following steps: acquiring a first prediction step and a last prediction time, wherein the prediction step is used to reflect the prediction frequency of the future load rate of a target power grid area; acquiring current power operation data of the target power grid area and predicting the future load rate of the target power grid area by using the current power operation data when the time interval between the last prediction time and the current time reaches the first prediction step, so as to determine the target load rate at a target time in the future; determining whether the target power grid area is in a power balance state at the target time according to the target load rate and a preset power balance judgment condition; if the target power grid area is not in the power balance state at the target time, performing operation mode deduction processing according to a preset deduction rule to determine a target operation mode; and adjusting the current operation mode of the target power grid area to the target operation mode; the target operation mode is a power grid operation mode which ensures that the target power grid area is in the power balance state at present and ensures that the target power grid area is in the power balance state at the target time; if the target power grid area is in the power balance state at the target time, the step of acquiring the first prediction step and the last prediction time is continuously performed. By the above method, the prediction of the future load rate according to the first prediction step is more efficient, the future target time of the target power grid area can be predicted according to the future load rate, and the target power grid operation mode which ensures that the target power grid area is in the power balance state at present and ensures that the target power grid area is in the power balance state at the target time can be deduced in time when the target power grid area is not in the power balance state at the target time, so that the current operation mode of the target power grid area is adjusted to the target operation mode, the situation that the target power grid area is not in the power balance state at the target time can be processed in time and in advance, and a fast, flexible and accurate power grid operation mode adjustment is realized.

[0071] Please refer to Figure 2 , Figure 2 Another flowchart of the power dynamic balance control method in the embodiment of the application is shown in Figure 2 The method comprises the following steps:

[0072] 201, acquiring a first prediction step and a last prediction time, wherein the prediction step is used to reflect the prediction frequency of the future load rate of a target power grid area;

[0073] 202, acquiring current power operation data of the target power grid area and predicting the future load rate of the target power grid area by using the current power operation data when the time interval between the last prediction time and the current time reaches the first prediction step, so as to determine the target load rate at a target time in the future;

[0074] 203、determining whether the target power grid region is in a power balance state at the target time according to the target load rate and a preset power balance judgment condition;

[0075] 204、if the target power grid region is not in a power balance state at the target time, performing operation mode deduction processing according to a preset deduction rule to determine a target operation mode, and adjusting the current operation mode of the target power grid region to the target operation mode; the target operation mode is a power grid operation mode that ensures that the target power grid region is in a power balance state at the target time;

[0076] It should be noted that the contents of steps 201, 202, 203 and 204 are similar to the contents of steps 101, 102, 103 and 104 in the method shown in Figure 1 For the sake of brevity, the contents of steps 101, 102, 103 and 104 in the method shown in Figure 1 For the sake of brevity, the contents of steps 101, 102, 103 and 104 in the method shown in

[0077] It should be noted that determining whether the load rate R i of any element at the future T Ni time is greater than or equal to 100%. If the load rate R i of each element at the future T Ni time is less than 100%, it means that there is no power imbalance problem in the region, and step 205 is executed to continuously predict the load rate after the next △T. If the load rate of the power grid electrical element exceeds 100%, on the one hand, it means that the electrical element is already overloaded and has the risk of failure and damage; on the other hand, it means that there is a local power imbalance in the region, and step 206 is entered. It should be noted that if there is a clearing cycle between the target time and the current time, the current operation mode does not need to be adjusted temporarily, that is, before step 206 is executed, it is determined whether there is a clearing cycle between the target time and the current time, and then the target operation mode is determined according to the preset deduction rule, and the steps B01 to B04 are further included:

[0078] B01, obtaining a preset clearing cycle;

[0079] B02, determining the time difference between the target time and the current time;

[0080] B03, if the time difference is greater than or equal to the clearing cycle, returning to execute the step of obtaining the first prediction step and the last prediction time;

[0081] B04, if the time difference is less than the clearing cycle, continuing to execute the step of determining the target operation mode according to the preset deduction rule.

[0082] Further, in order to determine whether there is a clearing cycle between the target time T i and the current time T0, first, the preset clearing cycle T m needs to be obtained, and then the time difference (T i -T0) between the target time T i and the current time T0 is determined. If the time difference is greater than or equal to the clearing cycle, it means that there is a clearing cycle between the target time T i and the current time T0, so step 206 does not need to be executed, and step 201 is returned to be executed. Conversely, if the time difference is less than the clearing cycle, it means that there is no clearing cycle between the target time T i and the current time T0, and the subsequent step, i.e., step 206, is continued to be executed.

[0083] It is determined whether the time interval between the future time T i and the real time T0 is less than the clearing cycle T m of the power spot market. The settlement cycle of the power spot market is 15 minutes at present, and if the future computing power improves the clearing frequency of the power spot market, this time T m may be adjusted according to the market transaction time cycle. If (T i -T0) is greater than T m , the power congestion problem caused by the power imbalance occurring at the future time T i is solved by market resources such as the spot market, auxiliary service market or demand response mechanism, and the regional power shortage or power abundance is considered as market transaction increment. At the time T i , the power grid operation mode adjustment is executed according to the market clearing result. If (T i -T0) is less than T m , it means that the power imbalance in the region is relatively urgent and cannot be solved by market mechanism, so the power grid operation mode needs to be adjusted immediately to balance the power supply and demand in the region, and step 206 is executed.

[0084] In one possible implementation manner, the deduction rule includes an exhaustive method, and the target operation mode is determined by exhaustively deducing typical operation modes. According to the preset deduction rule, the operation mode deduction processing is performed to determine the target operation mode, including steps C01 to C04.

[0085] C01, an exhaustive method is used to perform deduction processing on the preset typical operation mode to determine a first operation mode, and the first operation mode is a power grid operation mode ensuring that the target time is in a power balance state.

[0086] C02, performing safety check using the first operation mode and current power operation data to determine a safety check result;

[0087] C03, if the safety check result is a first check result, return to execute the step of deducing the preset typical operation mode to determine the first operation mode, and the first check result is failed in safety check;

[0088] C04, if the safety check result is a second check result, determine that the target operation mode is the first operation mode, and the second check result is passed in safety check.

[0089] Through the above steps, the first operation mode which makes the future in balance can be deduced first, and then the first operation mode is checked for safety under the current operation environment, so as to determine whether the first operation mode will destroy the balance at the moment. If the safety check result is passed, it is considered that the current operation environment will not be destroyed, and can be used as the target operation mode. Otherwise, the deduction needs to be performed again until the safety check result is passed, and the target operation mode is obtained. The typical operation mode includes but is not limited to switching action and various operations which can change the load. The specific deduction mode can be tried one by one for each electrical element.

[0090] For example, in order to achieve the power supply and demand balance at future T i , several typical operation modes commonly used in the regional power grid are used as the basis, and the exhaustive method is used to deduce the power grid operation mode which can make the load rate R i <100% in the region Z Ni at future T i , and the order of exhaustion is arranged in descending order according to the load rate of the electrical element.

[0091] Step six: put the power grid operation mode at future T i obtained in the above steps into the current T0 power grid operation state to perform safety check, such as whether the first operation mode will exceed the limit. If the safety check is not passed, it means that the power grid operation mode at future T i will have a negative impact on the current T0 power grid operation, and the operation mode needs to be re-deduced in step five. If the safety check is passed, it means that the deduced power grid operation mode can meet the regional power balance demand at future T i , and can also ensure the safe and stable operation of the current T0 power grid. It is an effective power grid operation scheme, and can be determined as the target operation mode, then enters the last step, adjusts the current T0 power grid operation mode of the region Z i to the power grid operation mode which can realize power balance at T i .

[0092] 205、if the target power grid area is in a power balance state at the target time, continue to perform the steps of obtaining the first prediction step and the last prediction time;

[0093] It should be noted that the content of step 205 is similar to that of step 105 in the method shown in Figure 1 to avoid repetition, details are not described here, and the specific content can be referred to the foregoing Figure 1 content of step 105 in the method shown in

[0094] 206, obtain the first computing power feature of the current prediction time and the second computing power feature of the last prediction time, the computing power feature is used to reflect the computing power resource at each prediction;

[0095] 207, using the first computing power feature and the second computing power feature to evaluate the computing power change, determine the target evaluation result, the target evaluation result is used to reflect the change of the current computing power resource;

[0096] 208, if the target evaluation result includes the first evaluation result, it is determined that the first prediction step is not updated, and the first evaluation result is that the computing power resource is unchanged;

[0097] 209, if the target evaluation result includes the second evaluation result, it is determined that the first prediction step is updated, and the second evaluation result is that the computing power resource is changed.

[0098] It should be noted that the first prediction step can be dynamically updated according to the current computing power resource of the cloud server. After each prediction, the change of the computing power of the cloud server can be evaluated according to the current computing power resource and the last computing power resource to determine whether to update the first prediction step. First, the computing power resource data of the cloud server can be obtained after each prediction, and the computing power resource data at least includes the first computing power feature of the current prediction time and the second computing power feature of the last prediction time, wherein the computing power feature is used to reflect the computing power resource at each prediction, and the computing power feature includes but is not limited to the loading time of the load rate prediction process of the cloud server at each prediction, such as the loading time of the prediction program. The change of the loading time is used to evaluate the computing power change, so that the value of the first prediction step can be adaptively changed with the computing power change, and dynamic prediction is realized.

[0099] For example, after obtaining the computing power features of the current prediction moment and the previous prediction moment, the evaluation of the computing power change can be realized by comparing the two computing power features, and the target evaluation result can include a first evaluation result of unchanged computing power resources or a second evaluation result of changed computing power resources, such as the first computing power feature being equal to the second computing power feature. For example, taking the loading duration as the computing power feature, it is explained that the loading durations of the adjacent two predictions are equal, that is, the computing power resources have no change during this period, at this time, it is considered that the target evaluation result includes the first evaluation result, and step 208 is executed, and the first prediction step does not need to be updated. The next prediction continues to predict the future load rate according to the original first prediction step. On the contrary, the first computing power feature is not equal to the second computing power feature, which indicates that the loading durations of the adjacent two predictions are not equal, that is, the computing power resources change during this period, at this time, it is considered that the target evaluation result includes the second evaluation result, and step 209 is executed, and the first prediction step needs to be updated, and the next prediction needs to be performed according to the updated first prediction step to predict the future load rate.

[0100] In a feasible implementation manner, the determining to update the first prediction step further includes:

[0101] D01, determining a second prediction step by using the first computing power feature, the second computing power feature, the first prediction step, and a preset step length updating algorithm;

[0102] D02, taking the second prediction step as the updated first prediction step.

[0103] Taking the loading duration of the prediction program as the computing power feature as an example, the first computing power feature can be the first loading duration at the current moment, and the second computing power feature can be the second loading duration at the previous prediction moment. The first prediction duration, the second prediction duration, and the first prediction step are input into the step length updating algorithm to obtain the second prediction step, so as to obtain the updated first prediction step. When the next prediction starts, the future load rate is predicted according to the value of the second prediction step.

[0104] For example, the mathematical expression of the step length updating algorithm can refer to the following formula:

[0105]

[0106] In the formula, ΔT n is the first prediction step, ΔT n+1 is the updated first prediction step, which can also represent the second prediction step, is the first computing power feature, is the second computing power feature.

[0107] It can be understood that steps 206 to 209 can be executed after steps 203, 204 or 205, which are only exemplified and not specifically limited.

[0108] The application provides a power dynamic balance control device, which has at least the following advantages: 1) relying on high computing power to predict and deduce the real-time and future power balance state of the power grid, quickly finding the electrical element that appears overload, and giving the operation mode to solve the power imbalance at the future time, avoiding the power imbalance of the power grid in advance, preventing the problem that the artificial dispatching cannot quickly and accurately realize the regional power balance under the condition that the operation mode of the regional power grid needs to be frequently adjusted in a short time; 2) the application sets the power balance region according to the voltage level and the electrical element of the substation, compared with taking the power flow section of the power grid as the object to judge the power imbalance, the application carries out the debugging of the operation mode of the power grid in layers and regions, and can more accurately solve the power imbalance problem of a certain region; 3) the application does not have a fixed requirement for the adjustment time of the operation mode of the power grid, and completely decides whether the operation mode of the power grid needs to be adjusted according to the situation of the regional power balance, dynamically calculates the time when the operation of the power grid needs to be adjusted, and generates the operation mode adjustment strategy of the power grid only after predicting that the electrical element is overloaded at a certain future time, which can greatly save system resources; 4) if the time interval between the time when the power imbalance is predicted to appear and the current time is within the clearing cycle of the power spot market, the power market resources are called to process the power imbalance problem, the power market resources are fully utilized to solve the power imbalance problem of a part of regions, and the efficiency of the operation resource configuration of the entire power system is improved.

[0109] Please refer to Figure 3 , Figure 3 The structure block diagram of the power dynamic balance control device in the embodiment of the application is shown in Figure 3 The device comprises the following steps:

[0110] The step length acquisition module 301 is used for acquiring a first prediction step length and a last prediction time, and the prediction step length is used for reflecting the prediction frequency of the future load rate of the target power grid region.

[0111] The load rate prediction module 302 is used for acquiring the current power operation data of the target power grid region when the time interval between the last prediction time and the current time reaches the first prediction step length, and predicting the future load rate of the target power grid region by using the current power operation data, to determine the target load rate at a target time in the future.

[0112] The state determination module 303 is used for determining whether the target power grid region is in the power balance state at the target time according to the target load rate and a preset power balance judgment condition.

[0113] The operation control module 304 is configured to, if the target power grid area is not in the power balance state at the target time, perform operation mode deduction processing according to preset deduction rules to determine a target operation mode, and adjust the current operation mode of the target power grid area to the target operation mode; the target operation mode is a power grid operation mode that ensures that the target power grid area is currently in the power balance state and ensures that the target time is in the power balance state; if the target power grid area is in the power balance state at the target time, the step of obtaining the first prediction step and the last prediction time is continued.

[0114] It should be noted that, Figure 3 The content of each module in the device is similar to that of the Figure 1 The content of each step in the method is similar to that of the Figure 1 The content of each step in the method is similar to that of the

[0115] This invention provides a power dynamic balancing control device, comprising: a step size acquisition module for acquiring a first prediction step size and the last prediction time, wherein the prediction step size reflects the prediction frequency of the future load rate of the target power grid area; a load rate prediction module for acquiring the current power operation data of the target power grid area when the time interval between the last prediction time and the current time reaches the first prediction step size, and using the current power operation data to predict the future load rate of the target power grid area to determine the target load rate at the future target time; a state determination module for determining whether the target power grid area is in a power balance state at the target time based on the target load rate and preset power balance judgment conditions; and an operation control module for performing operation mode deduction processing according to preset deduction rules to determine the target operation mode if the target power grid area is not in a power balance state at the target time, and adjusting the current operation mode of the target power grid area to the target operation mode; the target operation mode is a power grid operation mode that ensures both the current power balance state and the power balance state at the target time; if the target power grid area is in a power balance state at the target time, the step of acquiring the first prediction step size and the last prediction time continues. The aforementioned device not only makes the prediction of future load rates more efficient according to the first prediction step size, but also allows for the prediction of whether the target power grid region is in a state of power balance at the target time by forecasting the future load rate. Furthermore, if the target power grid region is not in a state of power balance at the target time, the device can promptly deduce the target power grid operation mode that ensures both the current power balance and the power balance at the target time. This allows the current operation mode of the target power grid region to be adjusted to the target operation mode, enabling timely and proactive handling of situations where the target power grid region is not in a state of power balance at the target time. This achieves a fast, flexible, and accurate adjustment of the power grid operation mode.

[0116] Figure 4 An internal structural diagram of a computer device in one embodiment is shown. This computer device can specifically be a terminal or a server. Figure 4 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program, which, when executed by the processor, causes the processor to perform the aforementioned methods. The internal memory may also store a computer program, which, when executed by the processor, causes the processor to perform the aforementioned methods. Those skilled in the art will understand that… Figure 4The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0117] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, the computer program being executed by the processor to cause the processor to perform the steps of Figure 1 or Figure 2 as shown.

[0118] In one embodiment, a computer readable storage medium is provided, storing a computer program, the computer program being executed by a processor to cause the processor to perform the steps of Figure 1 or Figure 2 as shown.

[0119] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The program can be stored in a non-volatile computer readable storage medium, and when the program is executed, the processes of the above-mentioned embodiments can be included. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0120] The technical features of the above embodiments can be combined in any way. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0121] The above-described embodiments are merely illustrative of several embodiments of the present application, which are described in more detail and in a specific manner, but should not be construed as limiting the scope of the patent of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A power dynamic balance control method, characterized in that, The method includes: Obtain the first prediction step size and the last prediction time. The prediction step size is used to reflect the prediction frequency of the future load rate of the target power grid area. When the time interval between the last prediction time and the current time reaches the first prediction step size, the current power operation data of the target power grid area is obtained, and the future load rate of the target power grid area is predicted using the current power operation data to determine the target load rate at the future target time. Based on the target load rate and the preset power balance judgment conditions, determine whether the target power grid area is in a power balance state at the target time; If the target power grid area is not in a state of power balance at the target time, then the operation mode is deduced according to the preset deduction rules to determine the target operation mode; and the current operation mode of the target power grid area is adjusted to the target operation mode; the target operation mode is a power grid operation mode that ensures that the target power grid area is in a state of power balance at the current time and also ensures that it is in a state of power balance at the target time. If the target power grid area is in a state of power balance at the target time, then continue to execute the steps of obtaining the first prediction step size and the previous prediction time.

2. The method according to claim 1, characterized in that, The method further includes: Obtain the first computing power characteristic at the current prediction time and the second computing power characteristic at the previous prediction time. The computing power characteristics are used to reflect the computing power resources at each prediction time. The computing power change is assessed using the first computing power characteristic and the second computing power characteristic to determine the target assessment result, which is used to reflect the current change in computing power resources. If the target evaluation result includes the first evaluation result, then it is determined that the first prediction step size will not be updated, and the first evaluation result is that the computing resources remain unchanged; If the target evaluation result includes the second evaluation result, then the first prediction step size is determined to be updated, and the second evaluation result is a change in computing resources.

3. The method according to claim 2, characterized in that, The step of determining and updating the first prediction step size further includes: The second prediction step size is determined using the first computing power feature, the second computing power feature, the first prediction step size, and a preset step size update algorithm. Use the second prediction step size as the updated first prediction step size.

4. The method according to claim 3, characterized in that, The step size update algorithm is as follows: In the formula, ΔT n Let ΔT be the first prediction step size. n+1 The updated first prediction step size, The primary characteristic of computing power, This is the second characteristic of computing power.

5. The method according to claim 1, characterized in that, The preset power balance judgment conditions include at least a preset load rate threshold. Therefore, determining whether the target power grid region is in a power balance state at the target time based on the target load rate and the preset power balance judgment conditions includes: If the target load rate is greater than or equal to the load rate threshold, then the target power grid area is determined to be in a state of power balance at the target time. If the target load rate is less than the load rate threshold, then the target power grid area is determined to be in a power balance state at the target time.

6. The method according to claim 1, characterized in that, The step of performing operational mode deduction processing according to preset deduction rules to determine the target operational mode also includes: Obtain the preset clearing cycle; Determine the time difference between the target time and the current time; If the time difference is greater than or equal to the clearing period, then return to the step of obtaining the first prediction step size and the last prediction time; If the time difference is less than the clearing period, then continue to execute the step of performing operation mode deduction processing according to preset deduction rules to determine the target operation mode.

7. The method according to claim 1, characterized in that, The deduction rules include exhaustive methods. Therefore, the step of performing operational mode deduction processing according to the preset deduction rules to determine the target operational mode includes: An exhaustive method is used to deduce and process the preset typical operating modes to determine the first operating mode, which is the power grid operating mode that ensures that the target is in a state of power balance at all times. The first operating mode and current power operation data are used to perform a safety check and determine the safety verification result. If the security verification result is the first verification result, then return to the step of performing the deduction process on the preset typical operating mode to determine the first operating mode, where the first verification result is that the security verification has failed. If the security verification result is the second verification result, then the target operating mode is determined to be the first operating mode, and the second verification result is that the security verification has been passed.

8. A power dynamic balance control device, characterized in that, The device includes: Step size acquisition module: used to acquire the first prediction step size and the last prediction time. The prediction step size is used to reflect the prediction frequency of the future load rate of the target power grid area. Load rate prediction module: When the time interval between the last prediction time and the current time reaches the first prediction step size, it acquires the current power operation data of the target power grid area, and uses the current power operation data to predict the future load rate of the target power grid area, and determines the target load rate at the future target time. Status determination module: used to determine whether the target power grid area is in a power balance state at the target time based on the target load rate and preset power balance judgment conditions; The operation control module is used to determine the target operation mode by performing operation mode deduction processing according to preset deduction rules if the target power grid area is not in a power balance state at the target time; and to adjust the current operation mode of the target power grid area to the target operation mode; the target operation mode is a power grid operation mode that ensures both the current power balance state and the power balance state at the target time; if the target power grid area is in a power balance state at the target time, the module continues to execute the steps of obtaining the first prediction step size and the previous prediction time.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it causes the processor to perform the steps of the method as described in any one of claims 1 to 7.

10. A computer device, comprising a memory and a processor, characterized in that, The memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method as described in any one of claims 1 to 7.

Images