A power management method and management system for an intelligent distribution box

Abstract

The present application provides a power management method and management system for an intelligent distribution box, which can obtain the historical temperature data of each branch; linearly reconstruct the historical temperature data corresponding to each branch to obtain multiple linear trend sequences, and then extract the temperature matching anomaly corresponding to each branch; obtain the historical active power transmission data of each branch, determine the load distribution of the target distribution box at each sampling time, and determine the load structure entropy in the target distribution box at each sampling time through all load distribution conditions; perform load compensation on the temperature matching anomaly corresponding to each branch through all load structure entropies to obtain the abnormal measurement of each branch in the target distribution box at each sampling time; perform abnormal warning management based on all abnormal measurements. Using the solution of the present application, the temperature abnormal warning of the distribution box can be compensated based on the load balancing of the distribution box, thereby realizing power abnormal warning management under load imbalance.

Description

Technical Field

[0001] The present application relates to the field of power management technology, and more specifically, to a power management method and management system for an intelligent distribution box. Background Art

[0002] Power management is a key technology in modern electronic devices and systems. Its purpose is to ensure that devices and systems achieve maximum energy efficiency and reliable power supply while meeting functional requirements. Power management technology covers a variety of strategies and methods at the hardware and software levels to optimize the distribution, regulation and monitoring of electrical energy. With the widespread application of electronic devices and the continuous growth of energy demand, the importance of power management technology in various fields has become increasingly prominent.

[0003] The power management of intelligent distribution boxes is an important innovation in modern power systems, which aims to improve the efficiency, safety and reliability of distribution systems through intelligent means. With the development of smart grid and Internet of Things technologies, traditional distribution boxes are gradually replaced by intelligent distribution boxes. This transformation not only improves the efficiency of power management, but also brings richer data and stronger control capabilities. However, in the existing technology, the power supply is only managed by monitoring whether the temperature of the circuit breaker of each branch in the distribution box exceeds the set temperature abnormality threshold. This method often causes the temperature of the circuit breaker of some branches with excessive load to rise due to the unbalanced load of the distribution box, resulting in abnormal warning false alarms. Therefore, how to achieve power supply abnormal warning management under unbalanced load has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a power management method and management system for an intelligent distribution box, which can realize power abnormality early warning management under load imbalance.

[0005] In a first aspect, the present application provides a power management method for an intelligent distribution box, comprising the following steps:

[0006] Collect the temperature of the circuit breakers in each branch of the target distribution box, and then obtain the historical temperature data of each branch;

[0007] Based on the trend characteristics of the historical temperature data of each branch, the historical temperature data corresponding to each branch is linearly reconstructed to obtain the linear trend sequence of the circuit breaker temperature in each branch, and then the temperature matching anomaly corresponding to each branch is extracted through all linear trend sequences;

[0008] Obtain the historical active power transmission data of each branch in the target distribution box, determine the load distribution of the target distribution box at each sampling time based on the historical active power transmission data of each branch and the power transmission limit of the target distribution box, and then determine the load structure entropy in the target distribution box at each sampling time through all load distribution conditions;

[0009] The load compensation of the temperature matching anomaly corresponding to each branch is performed through all load structure entropies to obtain the anomaly measurement of each branch in the target distribution box at each sampling moment;

[0010] Perform abnormal warning management on the power supply of the target distribution box based on all abnormal measurements.

[0011] In some embodiments, based on the trend characteristics of the historical temperature data of each branch, the historical temperature data corresponding to each branch is linearly reconstructed to obtain the linear trend sequence of the circuit breaker temperature in each branch, specifically including:

[0012] Select a branch;

[0013] Determine the temperature potential component of the corresponding historical temperature data at each sampling time based on the trend characteristics of the historical temperature data corresponding to the branch;

[0014] All temperature potential components are linearly changed to obtain the linear trend sequence of the circuit breaker temperature in the branch;

[0015] Repeat the above steps to determine the linear trend series of the circuit breaker temperatures in the remaining branches.

[0016] In some embodiments, extracting the temperature matching anomaly corresponding to each branch through all linear trend sequences specifically includes:

[0017] Select a branch;

[0018] Obtain the historical temperature data and linear trend sequence corresponding to the branch;

[0019] Determine a temperature prediction parameter column according to the historical temperature data and the linear trend sequence;

[0020] Perform matching anomaly extraction on the historical temperature data through the temperature prediction parameter column to obtain the temperature matching anomaly amount corresponding to the branch;

[0021] Repeat the above steps to determine the temperature matching anomaly corresponding to the remaining branches.

[0022] In some embodiments, determining the temperature prediction parameter column according to the historical temperature data and the linear trend sequence specifically includes:

[0023] Determine a historical temperature vector according to the historical temperature data;

[0024] Determine a temperature trend matrix according to the linear trend sequence;

[0025] A temperature prediction parameter column is determined according to the historical temperature vector and the temperature trend matrix.

[0026] In some embodiments, determining the load distribution of the target distribution box at each sampling time based on the historical active power transmission data of each branch and the power transmission limit of the target distribution box specifically includes:

[0027] Determine the load rate corresponding to the historical active power transmission amount at each sampling moment in the historical active power transmission data of each branch according to the power transmission limit of the target distribution box;

[0028] Determine the load distribution of the target distribution box at each sampling time based on all load rates.

[0029] In some embodiments, load compensation is performed on the temperature matching anomaly corresponding to each branch through all load structure entropies to obtain the anomaly measurement of each branch in the target distribution box at each sampling time, specifically including:

[0030] Select a sampling time;

[0031] Obtain the temperature matching anomaly of each branch at the sampling moment;

[0032] Obtain the load structure entropy corresponding to the sampling moment;

[0033] All temperature matching anomalies are compensated according to the load structure entropy corresponding to the sampling moment, and the anomaly measurement of each branch at the sampling moment is obtained;

[0034] Repeat the above steps to determine the abnormality measure of each branch at the remaining sampling moments, thereby obtaining the abnormality measure of each branch in the target distribution box at each sampling moment.

[0035] In some embodiments, performing abnormal warning management on the power supply of the target distribution box according to all abnormal measurements specifically includes:

[0036] Get the abnormal alarm threshold;

[0037] Select a sampling time;

[0038] An abnormality judgment is performed on the abnormality measurement of each branch at the sampling moment by using the abnormal alarm threshold to obtain multiple abnormal branches corresponding to the sampling moment;

[0039] Repeat the above steps to determine multiple abnormal branches corresponding to the remaining sampling moments;

[0040] Perform abnormal warning management on the power supply of the target distribution box through all abnormal branches.

[0041] In a second aspect, the present application provides a power management system for an intelligent distribution box, which includes:

[0042] An acquisition module is used to collect the temperature of the circuit breakers in each branch of the target distribution box, and then obtain the historical temperature data of each branch;

[0043] A processing module is used to linearly reconstruct the historical temperature data corresponding to each branch based on the trend characteristics of the historical temperature data of each branch, obtain the linear trend sequence of the circuit breaker temperature in each branch, and then extract the temperature matching anomaly corresponding to each branch through all linear trend sequences;

[0044] The processing module is further used to obtain the historical active power transmission data of each branch in the target distribution box, determine the load distribution of the target distribution box at each sampling time based on the historical active power transmission data of each branch and the power transmission limit of the target distribution box, and then determine the load structure entropy in the target distribution box at each sampling time through all load distribution conditions;

[0045] The processing module is also used to perform load compensation on the temperature matching anomaly corresponding to each branch through all load structure entropies to obtain an anomaly measurement of each branch in the target distribution box at each sampling moment;

[0046] The execution module is used to perform abnormal warning management on the power supply of the target distribution box based on all abnormal measurements.

[0047] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned power management method for the intelligent distribution box.

[0048] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the power management method of the above-mentioned intelligent distribution box is implemented.

[0049] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0050] In the power management method and management system of the intelligent distribution box provided in the present application, the temperature of the circuit breakers in each branch of the target distribution box is collected to obtain the historical temperature data of each branch; the historical temperature data corresponding to each branch is linearly reconstructed based on the trend characteristics of the historical temperature data of each branch to obtain a linear trend sequence of the temperature of the circuit breaker in each branch, and then the temperature matching anomaly corresponding to each branch is extracted through all linear trend sequences; the historical active power transmission data of each branch in the target distribution box is obtained, and the load distribution of the target distribution box at each sampling time is determined based on the historical active power transmission data of each branch and the power transmission limit of the target distribution box, and then the load structure entropy in the target distribution box at each sampling time is determined through all load distribution conditions; the temperature matching anomaly corresponding to each branch is load compensated through all load structure entropies to obtain the abnormal measurement of each branch in the target distribution box at each sampling time; the power supply of the target distribution box is managed with abnormal warning based on all abnormal measurements.

[0051] It can be seen that in this application, first, each historical temperature data is predicted through the trend characteristics of the historical temperature data of the circuit breaker in each branch, and then the matching degree between all the predicted results (temperature matching values) and the corresponding historical temperature values ​​is determined, that is, the temperature matching anomaly. Secondly, the load distribution of the target distribution box at each sampling moment is determined based on the historical active power transmission data of each branch and the power transmission limit of the target distribution box. Then, the load balancing index in the target distribution box at each sampling moment is determined through all the load distribution conditions, that is, the load structure entropy. Finally, the load balancing index in the target distribution box at each sampling moment is used to load compensate the temperature matching anomaly corresponding to each branch. After obtaining the anomaly measurement of each branch in the target distribution box at each sampling moment, according to All abnormal measurements perform abnormal early warning management on the power supply of the target distribution box; the present application performs load compensation for the temperature matching abnormalities corresponding to each branch of the target distribution box through the load balance situation in the target distribution box at each sampling moment, that is: when the load of the target distribution box is unbalanced, the load structure entropy is larger, then the temperature matching abnormality corresponding to the corresponding branch is increased; when the load of the target distribution box is balanced, the load structure entropy is smaller, then the temperature matching abnormality corresponding to the corresponding branch is reduced, thereby distributing the abnormal risk under load imbalance according to the load situation of each branch, avoiding abnormal early warning false alarms caused by the increase in temperature at the circuit breakers of some branches with excessive load due to the load imbalance of the distribution box; in summary, the scheme of the present application realizes power supply abnormal early warning management under load imbalance. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flowchart of a power management method of an intelligent distribution box according to some embodiments of the present application;

[0053] Figure 2 is a schematic diagram of a process for determining a linear trend sequence according to some embodiments of the present application;

[0054] Figure 3 It is a schematic diagram of a process for abnormal warning management according to some embodiments of the present application;

[0055] Figure 4 It is a structural block diagram of a power management system of an intelligent distribution box according to some embodiments of the present application;

[0056] Figure 5 It is an internal structure diagram of a computer device that implements a power management method for an intelligent distribution box as shown in some embodiments of the present application. DETAILED DESCRIPTION

[0057] The core of this application is to collect the temperature of each branch circuit breaker of the target distribution box, and then obtain the historical temperature data of each branch; based on the trend characteristics of the historical temperature data of each branch, the historical temperature data corresponding to each branch is linearly reconstructed to obtain the linear trend sequence of the temperature of the circuit breaker in each branch, and then the temperature matching anomaly corresponding to each branch is extracted through all linear trend sequences; the historical active power transmission data of each branch in the target distribution box is obtained, and the load distribution of the target distribution box at each sampling time is determined based on the historical active power transmission data of each branch and the power transmission limit of the target distribution box, and then the load structure entropy in the target distribution box at each sampling time is determined through all load distribution conditions; the temperature matching anomaly corresponding to each branch is load compensated through all load structure entropies to obtain the abnormal measurement of each branch in the target distribution box at each sampling time; the power supply of the target distribution box is managed abnormally based on all abnormal measurements; abnormal power supply warning management under load imbalance can be realized.

[0058] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is a flow chart of a power management method for an intelligent distribution box according to some embodiments of the present application. The power management method 100 for the intelligent distribution box mainly includes the following steps:

[0059] In step 101, the temperature of each branch circuit breaker of the target distribution box is obtained, and then the historical temperature data of each branch is obtained.

[0060] In specific implementation, the temperature of each branch circuit breaker of the target distribution box can be obtained through the operation database of the target distribution box, and then the historical temperature data of each branch can be obtained.

[0061] It should be noted that the operation database described in the present application contains the historical temperatures of each branch circuit breaker of the target distribution box. The present application uses a temperature acquisition device to collect the temperatures of each branch circuit breaker of the target distribution box at a predetermined sampling period, and stores them in the operation database, and uses the temperature values ​​stored in the operation database as historical temperature values ​​again; in addition, the temperature acquisition device is a thermistor temperature sensor, which detects the temperature value of the relay by monitoring the change in resistance value caused by the change in the temperature of the relay, and the predetermined sampling period is 5 minutes.

[0062] In step 102, based on the trend characteristics of the historical temperature data of each branch, the historical temperature data corresponding to each branch is linearly reconstructed to obtain a linear trend sequence of the circuit breaker temperature in each branch, and then the temperature matching anomaly corresponding to each branch is extracted through all linear trend sequences;

[0063] In some embodiments, based on the trend characteristics of the historical temperature data of each branch, the historical temperature data corresponding to each branch is linearly reconstructed to obtain the linear trend sequence of the circuit breaker temperature in each branch. The following steps can be used to achieve this:

[0064] Select a branch;

[0065] Determine the temperature potential component of the corresponding historical temperature data at each sampling time based on the trend characteristics of the historical temperature data corresponding to the branch;

[0066] All temperature potential components are linearly changed to obtain the linear trend sequence of the circuit breaker temperature in the branch;

[0067] Repeat the above steps to determine the linear trend series of the circuit breaker temperatures in the remaining branches.

[0068] In some embodiments, determining the temperature potential component of the corresponding historical temperature data at each sampling time based on the trend characteristics of the historical temperature data corresponding to the branch can be implemented by the following steps:

[0069] Determine the trend component of the historical temperature data corresponding to the branch at each sampling time, and all trend components are the trend characteristics of the corresponding historical temperature data;

[0070] Determine the temperature potential component of the corresponding historical temperature data at each sampling moment according to the trend characteristics.

[0071] In specific implementation, the trend component of the historical temperature data corresponding to the branch at each sampling moment can be determined in the following manner, namely: first, after obtaining the Haar wavelet as the wavelet function, the historical temperature data corresponding to the branch is decomposed into multiple wavelet coefficients of different frequencies through the wavelet transform in the prior art; secondly, the low-frequency wavelet coefficients among all the wavelet coefficients are retained as the trend component of the corresponding historical temperature data at each sampling moment; in other embodiments, other methods can also be used to determine, which are not limited here. It should be noted that the wavelet coefficients in the wavelet coefficients contain the trend characteristics of the corresponding historical temperature data; the trend characteristics of the corresponding historical temperature data at each sampling moment can be extracted by retaining the low-frequency coefficients and discarding the high-frequency coefficients, and all trend characteristics are used as the trend components of the corresponding historical temperature data at each sampling moment.

[0072] It should be noted that, the present application eliminates the random fluctuation of the trend component of the corresponding historical temperature data at each sampling moment by accumulating the trend component of the historical temperature data corresponding to the branch at each sampling moment to obtain the temperature potential component at the corresponding sampling moment, thereby highlighting the trend change law of the historical temperature data corresponding to the branch; as a preferred embodiment, determining the temperature potential component of the corresponding historical temperature data at each sampling moment according to the trend characteristics can be achieved in the following way, namely: first, selecting the trend component of the historical temperature data corresponding to the branch at a sampling moment in the trend characteristics, and secondly, taking the sum of the trend components corresponding to all sampling moments before the sampling moment as the temperature potential component at the sampling moment, repeating the above steps, determining the temperature potential components of the remaining sampling moments, and thus obtaining the temperature potential component of the corresponding historical temperature data at each sampling moment.

[0073] Wherein, in some embodiments, reference Figure 2 As shown, this figure is a schematic diagram of the process of determining a linear trend sequence shown in some embodiments of the present application. All temperature potential components are linearly changed to obtain a linear trend sequence of the temperature of the circuit breaker in the branch circuit, which can be achieved by the following steps:

[0074] First, in step 1021, the left adjacent temperature potential component of each temperature potential component is obtained;

[0075] Then, in step 1022, the linear trend value corresponding to each temperature potential component is determined according to each temperature potential component and the corresponding left adjacent temperature potential component;

[0076] Finally, in step 1023, all linear trend values ​​are further sorted according to the order of sampling moments of the corresponding temperature potential components to form a linear trend sequence of the circuit breaker temperature in the branch.

[0077] It should be noted that, as a preferred embodiment, the temperature potential component of the temperature potential component at the previous sampling moment can be used as the left adjacent temperature potential component of the corresponding temperature potential component. In other embodiments, it can also be determined in other ways, which will not be repeated here.

[0078] In specific implementation, the linear trend value corresponding to each temperature potential component is determined according to each temperature potential component and the corresponding left adjacent temperature potential component, which can be achieved in the following manner, namely: first, each temperature potential component is added to the corresponding left adjacent temperature potential component and then divided by 2; secondly, the obtained value is used as the linear trend value of the corresponding temperature potential component; in other embodiments, it can also be determined by other methods, which are not limited here. In addition, it should be noted that in the present application, the linear reconstruction refers to extracting the trend of the historical temperature data, linearizing the trend characteristics at each sampling moment to obtain a plurality of the linear trend values; the linear trend values ​​are used to linearize the trends of all temperature potential components, thereby improving the reliability of the prediction.

[0079] In some embodiments, the temperature matching anomaly corresponding to each branch can be obtained by extracting all linear trend sequences using the following steps:

[0080] Select a branch;

[0081] Obtain the historical temperature data and linear trend sequence corresponding to the branch;

[0082] Determine a temperature prediction parameter column according to the historical temperature data and the linear trend sequence;

[0083] Perform matching anomaly extraction on the historical temperature data through the temperature prediction parameter column to obtain the temperature matching anomaly amount corresponding to the branch;

[0084] Repeat the above steps to determine the temperature matching anomaly corresponding to the remaining branches.

[0085] In some embodiments, determining the temperature prediction parameter sequence according to the historical temperature data and the linear trend sequence may be implemented by the following steps:

[0086] Determine a historical temperature vector according to the historical temperature data;

[0087] Determine a temperature trend matrix according to the linear trend sequence;

[0088] A temperature prediction parameter column is determined according to the historical temperature vector and the temperature trend matrix.

[0089] It should be noted that the historical temperature vector is a vector containing the historical temperature values ​​of the historical temperature data corresponding to the branch at all sampling times, and the temperature trend matrix is ​​a matrix containing the linear trend values ​​of all historical temperature values ​​in the historical temperature data corresponding to the branch. The present application analyzes the historical temperature vector and the temperature trend matrix to achieve the prediction of the stationary taper sequence; as a preferred embodiment, the historical temperature vector can be determined according to the historical temperature data in the following manner, namely: each historical temperature value in the historical temperature data is used as a vector element in the order of sampling time to obtain the historical temperature vector. In addition, it should be noted that the historical temperature vector is expressed as A=(a1, a2, a3, ..., a l-1 , a I ), where A is the historical temperature vector, a1 is the historical temperature value corresponding to the historical temperature data at the first sampling time, and so on. I is the historical temperature value corresponding to the historical temperature data at the I-th sampling time, and I is the total number of historical temperature values ​​in the historical temperature data.

[0090] In specific implementation, the temperature trend matrix can be determined according to the linear trend sequence in the following manner, namely: first, a matrix with 1 row, 2 columns, and all elements of the second column being 1 is obtained; secondly, each linear trend value in the linear trend sequence is negated and then used as the matrix element of the first column of the matrix in the order of the corresponding sampling moments, thereby obtaining the temperature trend matrix.

[0091] In some embodiments, the temperature trend matrix can be represented in the following manner:

[0092]

[0093] Wherein, B is the temperature trend matrix, b1 represents the linear trend value corresponding to the first sampling moment in the linear trend sequence, b2 represents the linear trend value corresponding to the second sampling moment in the linear trend sequence, and so on. I Represents the linear trend value corresponding to the Ith sampling moment in the linear trend sequence.

[0094] In specific implementation, the temperature prediction parameter column can be determined according to the historical temperature vector and the temperature trend matrix in the following manner: first, the temperature trend matrix is ​​transposed to obtain the transposed matrix B of the temperature trend matrix: T , Secondly, calculate the product of the temperature trend matrix and the transposed matrix of the temperature trend matrix to obtain the matrix B T B, then, perform an inverse operation on it to obtain the inverse matrix (B TB) -1 , and then the product of the above inverse matrix, the transposed matrix of the temperature trend matrix and the historical temperature vector is used as the temperature prediction parameter column. It should be noted that the temperature prediction parameter column is expressed as C = (α, β), where α is the temperature prediction coefficient and β is the temperature reference parameter.

[0095] It should be noted that the temperature prediction parameter column is the result obtained after analyzing the historical temperature vector and the temperature trend matrix, wherein the temperature prediction coefficient is used to control the development trend of the historical temperature data corresponding to the branch, the larger the temperature prediction coefficient is, the faster the development speed of the historical temperature data corresponding to the branch is, and the smaller the temperature prediction coefficient is, the slower the development speed of the historical temperature data corresponding to the branch is; the temperature reference parameter is the reference degree of the predicted amount of the historical temperature data corresponding to the branch, the larger the temperature reference parameter is, the larger the predicted amount of the historical temperature data corresponding to the branch is, and the smaller the temperature reference parameter is, the smaller the predicted amount of the historical temperature data is.

[0096] Among them, in some embodiments, matching anomaly extraction is performed on the historical temperature data through the temperature prediction parameter column to obtain the temperature matching anomaly amount corresponding to the branch, which can be achieved by the following steps:

[0097] Determine the matching gain coefficient of each historical temperature value in the historical temperature data by using the temperature prediction parameter column;

[0098] Then, predicting the temperature matching value of each historical temperature value in the historical temperature data according to all matching gain coefficients and the temperature prediction parameter column;

[0099] The historical temperature data is extracted according to all temperature matching values ​​to obtain the temperature matching anomaly corresponding to the branch.

[0100] In some embodiments, determining the matching gain coefficient of each historical temperature value in the historical temperature data through the temperature prediction parameter column can be implemented by the following steps:

[0101] Obtaining a temperature potential component corresponding to each historical temperature value in the historical temperature data;

[0102] The matching gain coefficient of each historical temperature value in the historical temperature data is determined according to the temperature potential component corresponding to each historical temperature value and the temperature prediction parameter column.

[0103] In specific implementation, the matching gain coefficient of each historical temperature value in the historical temperature data is determined according to the temperature potential component corresponding to each historical temperature value and the temperature prediction parameter column, which can be achieved in the following manner, namely: first, the product of the number of sampling moments of the historical temperature value corresponding to the temperature potential component and the temperature prediction coefficient in the temperature prediction parameter column is used as the negative exponential function power of the natural constant e; secondly, the obtained result is used as the matching gain coefficient of the historical temperature value corresponding to the selected temperature potential component; in other embodiments, it can also be determined by other methods, which are not limited here.

[0104] It should be noted that the matching gain coefficient is used to control the growth rate of the temperature matching value. The larger the matching gain coefficient, the higher the growth rate of the corresponding temperature matching value, and the smaller the matching gain coefficient, the lower the growth rate of the corresponding temperature matching value. When the number of sampling moments corresponding to the temperature matching value is small, the value of the matching gain coefficient approaches 1, thereby increasing the growth rate of the temperature matching value. When the number of sampling moments corresponding to the temperature matching value is large, the value of the matching gain coefficient approaches 0, thereby decreasing the growth rate of the temperature matching value. The present application adjusts the growth rate of the temperature matching value through the matching gain coefficient, so that the change of the temperature matching value is more in line with the actual situation.

[0105] It should be noted that each historical temperature value in the historical temperature data corresponding to the branch has a unique corresponding sampling time, and each historical temperature value in the historical temperature data corresponding to the branch is sorted according to the order of the corresponding sampling time. Therefore, in some embodiments, the temperature matching value of each historical temperature value in the historical temperature data is predicted according to all matching gain coefficients and the temperature prediction parameter column. The following steps can be used to achieve:

[0106] Obtaining the temperature prediction coefficient and the temperature reference parameter in the temperature prediction parameter column;

[0107] Selecting a matching gain coefficient of a historical temperature value at a sampling time in the historical temperature data;

[0108] Obtaining the temperature potential component of the historical temperature value corresponding to the first sampling moment in the historical temperature data;

[0109] Predicting the temperature matching value of the historical temperature value at the next sampling moment according to the temperature prediction coefficient and the temperature reference parameter in the temperature prediction parameter column, the matching gain coefficient of the historical temperature value at the sampling moment, and the temperature potential component of the historical temperature value corresponding to the first sampling moment;

[0110] Repeat the above steps to obtain temperature matching values ​​of the remaining historical temperature values ​​in the historical temperature data.

[0111] It should be noted that the temperature matching value is a descriptive quantity of the predicted temperature value of the corresponding historical temperature value at different sampling moments; as a preferred embodiment, the temperature matching value of the historical temperature value at the next sampling moment of the current sampling moment is predicted according to the temperature prediction coefficient and temperature reference parameter in the temperature prediction parameter column, the matching gain coefficient of the historical temperature value at the current sampling moment and the temperature potential component of the historical temperature value corresponding to the first sampling moment, which can be achieved in the following manner, namely: taking the result of [temperature potential component of the historical temperature value at the first sampling moment - (temperature reference parameter / temperature prediction coefficient)] * response gain coefficient of the historical temperature value at the current sampling moment + (temperature reference parameter / temperature prediction coefficient) as the temperature matching value of the historical temperature value at the next sampling moment of the current sampling moment; in other embodiments, prediction can also be performed by other methods, which are not limited here.

[0112] In specific implementation, the historical temperature data is extracted according to all temperature matching values, and the temperature matching anomaly corresponding to the branch is obtained by the following method, namely: first, a historical temperature value in the historical temperature data is selected to obtain the temperature matching value of the historical temperature value; secondly, the difference between the historical temperature value and the corresponding temperature matching value is used as the temperature matching anomaly of the historical temperature value; the above steps are repeated to determine the temperature matching anomaly of the remaining historical temperature values ​​in the historical temperature data, thereby obtaining the temperature matching anomaly corresponding to the branch.

[0113] It should be noted that the matching anomaly extraction described in the present application refers to determining the degree of matching between each historical temperature value and the corresponding temperature matching value after predicting the temperature matching value of each historical temperature value in the corresponding historical temperature data, and taking the matching degree as the corresponding temperature matching anomaly amount. As a preferred embodiment, that is, the temperature matching anomaly amount characterizes the degree of matching between the historical temperature value and the corresponding temperature matching value. The larger the temperature matching anomaly amount, the lower the degree of matching between the historical temperature value and the corresponding temperature matching value. The smaller the temperature matching anomaly amount, the higher the degree of matching between the historical temperature value and the corresponding temperature matching value. The present application determines whether an abnormality occurs in the corresponding branch by determining the degree of matching between each historical temperature value and the corresponding temperature matching value.

[0114] In step 103, the historical active power transmission data of each branch in the target distribution box is obtained, and the load distribution of the target distribution box at each sampling moment is determined based on the historical active power transmission data of each branch and the power transmission limit of the target distribution box, and then the load structure entropy in the target distribution box at each sampling moment is determined through all load distribution conditions.

[0115] In specific implementation, the historical active power transmission data of each branch in the target distribution box can be obtained through the operation database of the target distribution box, wherein it should be noted that the operation database contains the historical active power transmission amounts of each branch of the target distribution box. The present application uses a power collection device to collect the active power transmission amounts of each branch of the target distribution box at a predetermined sampling period, and stores them in the operation database, and re-uses the active power transmission amounts stored in the operation database as the historical active power transmission amounts. The power collection device is a smart meter, and the predetermined sampling period is 5 minutes.

[0116] In some embodiments, the load distribution of the target distribution box at each sampling time can be determined based on the historical active power transmission data of each branch and the power transmission limit of the target distribution box by using the following steps:

[0117] Determine the load rate corresponding to the historical active power transmission amount at each sampling moment in the historical active power transmission data of each branch according to the power transmission limit of the target distribution box;

[0118] Determine the load distribution of the target distribution box at each sampling time based on all load rates.

[0119] In some embodiments, determining the load rate corresponding to each sampling moment in the historical active power transmission data of each branch according to the power transmission limit of the target distribution box can be implemented by the following steps:

[0120] Select a branch in the target distribution box as the selected branch;

[0121] Obtain historical active power transmission data of the selected branch;

[0122] Selecting a historical active power transmission amount corresponding to a sampling time in the historical active power transmission data;

[0123] Determine the load rate of the selected branch at the sampling moment according to the power transmission limit of the target distribution box and the historical active power transmission amount corresponding to the sampling moment;

[0124] Repeat the above steps to determine the load rate corresponding to the remaining sampling moments in the historical active power transmission data of the selected branch;

[0125] Repeat the above steps, and take the remaining branches in the target distribution box as selected branches in turn, and then obtain the load rate corresponding to each sampling moment in the historical active power transmission data of each branch.

[0126] It should be noted that the power transmission limit can be obtained through the technical manual of the target distribution box. In addition, the load rate represents the load degree of the selected branch at the corresponding sampling moment. The higher the load rate, the higher the load degree of the selected branch at the corresponding sampling moment, and the lower the load rate, the lower the load degree of the selected branch at the corresponding sampling moment. As a preferred embodiment, determining the load rate corresponding to the selected branch at the sampling moment according to the power transmission limit of the target distribution box and the historical active power transmission amount corresponding to the sampling moment can be achieved in the following way, namely: taking the ratio of the historical active power transmission amount corresponding to the sampling moment to the power transmission limit of the target distribution box as the load rate corresponding to the sampling moment. In other embodiments, it can also be determined by other methods, which are not limited here.

[0127] In specific implementation, the load distribution of the target distribution box at each sampling moment can be determined according to all load rates. The following method can be used, namely: first, a sampling moment is selected to obtain the load rate of each branch of the target distribution box at the sampling moment; second, a branch in the target distribution box is selected as the selected branch to obtain the load rate of the selected branch at the sampling moment; then, the load rate of the selected branch at the sampling moment is divided by the sum of the load rates of the branches of the target distribution box at the sampling moment as the load distribution amount of the selected branch at the sampling moment; the above steps are repeated to obtain the load rate of the selected branch at the sampling moment; The remaining branches of the target distribution box are taken as selected branches in turn to obtain the load distribution amounts of all branches corresponding to the sampling moment. Finally, the load distribution amounts of all branches corresponding to the sampling moment are sorted according to the branch order as the load distribution situation at the sampling moment. The above steps are repeated to determine the load distribution situation at the remaining sampling moments. It should be noted that the load distribution situation described in the present application represents the load distribution on each branch of the target distribution box at the corresponding sampling moment. In addition, in some preferred embodiments, the branch order can be set according to the size order of the factory branch setting number of the target distribution box.

[0128] In some embodiments, determining the load structure entropy in the target distribution box at each sampling time through all load distribution conditions can be achieved by using the following steps:

[0129] Select the load distribution corresponding to a sampling time;

[0130] Determine the load structure entropy in the target distribution box at the sampling time according to the load distribution amount corresponding to each branch in the load distribution situation;

[0131] Repeat the above steps to determine the load structure entropy corresponding to the remaining sampling moments.

[0132] In specific implementation, the load structure entropy in the target distribution box at the sampling moment is determined according to the load distribution amounts corresponding to each branch in the load distribution situation, which can be achieved in the following manner, namely: first, the load distribution amount corresponding to a branch in the load distribution situation corresponding to the sampling moment is selected as the selected load distribution amount, and the result of multiplying the selected load distribution amount by the natural logarithm of the selected load distribution amount is determined, and the above steps are repeated, and the load distribution amounts corresponding to the remaining branches in the load distribution situation corresponding to the sampling moment are successively used as the selected load distribution amounts, and then the results corresponding to the remaining load distribution amounts are obtained, and finally, the results corresponding to all the load distribution amounts at the sampling moment are summed and the negative result is taken as the load structure entropy in the target distribution box at the sampling moment. In other embodiments, it can also be determined by other methods, which are not limited here.

[0133] It should be noted that the load structure entropy described in this application characterizes the degree of balance of the loads of each branch in the target distribution box. The larger the load structure entropy, the higher the degree of balance of the loads of each branch in the target distribution box; the smaller the load structure entropy, the lower the degree of balance of the loads of each branch in the target distribution box. The value range of the load structure entropy is Where N is the total number of branches in the target distribution box. Obviously, when the load structure entropy is equal to When , the load balance of each branch in the target distribution box is the lowest, that is, half of the branches are fully loaded, and half are infinitely close to no-load. When the load structure entropy is equal to ln(N), the load balance of each branch in the target distribution box is the highest, that is, the load rate of each branch in the target distribution box is completely equal.

[0134] In step 104, load compensation is performed on the temperature matching anomaly corresponding to each branch through all load structure entropies to obtain the anomaly measurement of each branch in the target distribution box at each sampling moment.

[0135] It should be noted that one sampling moment corresponds to multiple branches, and one branch has one temperature matching anomaly at one sampling moment, that is, one sampling moment corresponds to multiple temperature matching anomalies. Therefore, in some embodiments, the temperature matching anomaly corresponding to each branch is load compensated by all load structure entropies, and the anomaly measurement of each branch in the target distribution box at each sampling moment can be obtained by the following steps:

[0136] Select a sampling time;

[0137] Obtain the temperature matching anomaly of each branch at the sampling moment;

[0138] Obtain the load structure entropy corresponding to the sampling moment;

[0139] All temperature matching anomalies are compensated according to the load structure entropy corresponding to the sampling moment, and the anomaly measurement of each branch at the sampling moment is obtained;

[0140] Repeat the above steps to determine the abnormality measure of each branch at the remaining sampling moments, thereby obtaining the abnormality measure of each branch in the target distribution box at each sampling moment.

[0141] In specific implementation, all temperature matching anomalies are compensated according to the load structure entropy corresponding to the sampling moment, and the anomaly measure of each branch at the sampling moment can be obtained in the following manner, namely: first, the standard deviation of all temperature matching anomalies is determined; secondly, the temperature matching anomaly corresponding to a branch is selected at the sampling moment as the selected temperature matching anomaly; then, the quotient of the selected temperature matching anomaly and the above standard deviation is determined; finally, the above result is compensated by the load structure entropy corresponding to the sampling moment, and the compensation is: multiplying the load structure entropy corresponding to the sampling moment with the above result. The present application uses the multiplication result as the load structure entropy to compensate the selected temperature matching anomaly and obtains the value obtained after compensating the selected temperature matching anomaly, namely: the anomaly measure of the branch; repeating the above steps, the temperature matching anomalies corresponding to the remaining branches at the sampling moment are successively used as the selected temperature matching anomaly, thereby determining the anomaly measure of the remaining branches, and obtaining the anomaly measure of each branch at the sampling moment.

[0142] It should be noted that when the load of the target distribution box is unbalanced, the degree of abnormality of each branch in the target distribution box will increase linearly. Therefore, the load compensation described in this application refers to compensating for all temperature matching abnormalities at the corresponding sampling moment through the load structure entropy. When the load of the target distribution box is unbalanced, the load structure entropy is larger, then all temperature matching abnormalities at the corresponding sampling moment are increased; when the load of the target distribution box is balanced, the load structure entropy is smaller, then all temperature matching abnormalities at the corresponding sampling moment are reduced, thereby achieving compensation for all temperature matching abnormalities and obtaining all abnormal measurements at the corresponding sampling moment.

[0143] In step 105, abnormal warning management is performed on the power supply of the target distribution box according to all abnormal measurements.

[0144] In some embodiments, reference Figure 3 As shown, this figure is a schematic diagram of the process of abnormal warning management shown in some embodiments of the present application. The abnormal warning management of the power supply of the target distribution box according to all abnormal measurements can be implemented by the following steps:

[0145] First, in step 1051, an abnormal alarm threshold is obtained;

[0146] Next, in step 1052, a sampling time is selected;

[0147] Then, in step 1053, the abnormal measurement of each branch at the sampling moment is judged by the abnormal alarm threshold, and multiple abnormal branches corresponding to the sampling moment are obtained;

[0148] Again, in step 1054, the above steps are repeated to determine multiple abnormal branches corresponding to the remaining sampling moments;

[0149] Finally, in step 1055, abnormal warning management is performed on the power supply of the target distribution box through all abnormal branches.

[0150] In specific implementation, after setting all abnormal measures to satisfy the standard normal distribution, the abnormal alarm threshold can be determined by the normal distribution model in the prior art. As a preferred embodiment, a reasonable confidence interval is determined by the normal distribution model, such as a 95% distribution interval, and the abnormal measure corresponding to the right endpoint of the confidence interval is used as the abnormal alarm threshold. In other embodiments, it can also be determined by other methods, which are not limited here.

[0151] In specific implementation, the abnormal measurement of each branch at the sampling moment is judged as abnormal through the abnormal alarm threshold, and multiple abnormal branches corresponding to the sampling moment are obtained, which can be implemented in the following way, namely: first, the abnormal measurement corresponding to one branch among the abnormal measurements of each branch at the sampling moment is selected; secondly, when the abnormal measurement is less than the abnormal alarm threshold, the corresponding branch is regarded as a non-abnormal branch; when the abnormal measurement is greater than or equal to the abnormal alarm threshold, the corresponding branch is regarded as an abnormal branch, and the above steps are repeated to judge the branches corresponding to the remaining abnormal measurements in all the abnormal measurements corresponding to the sampling moment, so as to obtain multiple abnormal branches corresponding to the sampling moment.

[0152] In specific implementation, the abnormal early warning management of the power supply of the target distribution box through all abnormal branches can be achieved in the following way, namely: first, a sampling moment is selected, and when there is an abnormal branch at the sampling moment, an alarm is issued to the power management center, and the corresponding abnormal branch is recorded; when there is no abnormal branch at the sampling moment, no processing is performed, and the above steps are repeated to achieve abnormal early warning management of the power supply of the target distribution box.

[0153] In addition, in another aspect of the present application, in some embodiments, the present application provides a power management system for an intelligent distribution box, referring to Figure 4 , which is a structural block diagram of a power management system of an intelligent distribution box according to some embodiments of the present application, and the power management system 200 of the intelligent distribution box includes: an acquisition module 201, a processing module 202 and an execution module 203, which are respectively described as follows:

[0154] Acquisition module 201, in this application, acquisition module 201 is mainly used to collect the temperature of each branch circuit breaker of the target distribution box, and then obtain the historical temperature data of each branch;

[0155] Processing module 202, in the present application, the processing module 202 is mainly used to linearly reconstruct the historical temperature data corresponding to each branch based on the trend characteristics of the historical temperature data of each branch, obtain the linear trend sequence of the circuit breaker temperature in each branch, and then extract the temperature matching anomaly corresponding to each branch through all linear trend sequences;

[0156] In addition, the processing module 202 in the present application is also used to obtain the historical active power transmission data of each branch in the target distribution box, determine the load distribution of the target distribution box at each sampling time based on the historical active power transmission data of each branch and the power transmission limit of the target distribution box, and then determine the load structure entropy in the target distribution box at each sampling time through all load distribution conditions;

[0157] In addition, the processing module 202 in the present application is also used to perform load compensation on the temperature matching anomaly corresponding to each branch through all load structure entropies, and obtain the anomaly measurement of each branch in the target distribution box at each sampling moment;

[0158] Execution module 203, in the present application, execution module 203 is mainly used to perform abnormal warning management on the power supply of the target distribution box based on all abnormal measurements.

[0159] In addition, the present application also provides a computer device, which includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned power management method for the intelligent distribution box.

[0160] In some embodiments, reference Figure 5 , which is an internal structure diagram of a computer device using a power management method of an intelligent distribution box according to some embodiments of the present application. The power management method of the intelligent distribution box in the above embodiment can be Figure 5 The computer device 300 shown in the figure is implemented, and the computer device 300 includes at least one processor 301, a communication bus 302, a memory 303 and at least one communication interface 304.

[0161] The processor 301 may be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC) or one or more processors for controlling the execution of the power management method of the intelligent distribution box in the present application.

[0162] The communication bus 302 is used to transmit information between the above components.

[0163] The memory 303 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 303 may exist independently and be connected to the processor 301 via the communication bus 302. The memory 303 may also be integrated with the processor 301.

[0164] The memory 303 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the program code stored in the memory 303. The program code may include one or more software modules. The power management method of the intelligent distribution box in the above embodiment can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0165] The communication interface 304 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0166] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0167] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0168] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the power management method of the above-mentioned intelligent distribution box is implemented.

[0169] In summary, in the power management method and management system of the intelligent distribution box disclosed in the embodiment of the present application, the temperature of the circuit breakers in each branch of the target distribution box is collected to obtain the historical temperature data of each branch; the historical temperature data corresponding to each branch is linearly reconstructed based on the trend characteristics of the historical temperature data of each branch to obtain a linear trend sequence of the temperature of the circuit breaker in each branch, and then the temperature matching anomaly corresponding to each branch is extracted through all linear trend sequences; the historical active power transmission data of each branch in the target distribution box is obtained, and the load distribution of the target distribution box at each sampling time is determined based on the historical active power transmission data of each branch and the power transmission limit of the target distribution box, and then the load structure entropy in the target distribution box at each sampling time is determined through all load distribution conditions; the temperature matching anomaly corresponding to each branch is load compensated through all load structure entropies to obtain the abnormal measurement of each branch in the target distribution box at each sampling time; the power supply of the target distribution box is managed abnormally based on all abnormal measurements; power supply abnormality warning management under load imbalance can be realized.

[0170] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0171] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A power management method for an intelligent distribution box, characterized in that: The steps include: Collect the temperature of the circuit breakers in each branch of the target distribution box, and then obtain the historical temperature data of each branch; Based on the trend characteristics of the historical temperature data of each branch, the historical temperature data corresponding to each branch is linearly reconstructed to obtain the linear trend sequence of the circuit breaker temperature in each branch, and then the temperature matching anomaly corresponding to each branch is extracted through all linear trend sequences; Obtain the historical active power transmission data of each branch in the target distribution box, determine the load distribution of the target distribution box at each sampling time based on the historical active power transmission data of each branch and the power transmission limit of the target distribution box, and then determine the load structure entropy in the target distribution box at each sampling time through all load distribution conditions, where the load structure entropy characterizes the balance degree of the load of each branch in the target distribution box; The load compensation of the temperature matching anomaly corresponding to each branch is performed through all load structure entropies to obtain the anomaly measurement of each branch in the target distribution box at each sampling moment; Perform abnormal warning management on the power supply of the target distribution box based on all abnormal measurements; Among them, based on the trend characteristics of the historical temperature data of each branch, the historical temperature data corresponding to each branch is linearly reconstructed to obtain the linear trend sequence of the circuit breaker temperature in each branch, which specifically includes: Select a branch; Determine the temperature potential component of the corresponding historical temperature data at each sampling time based on the trend characteristics of the historical temperature data corresponding to the branch; All temperature potential components are linearly changed to obtain the linear trend sequence of the circuit breaker temperature in the branch; Repeat the above steps to determine the linear trend sequence of the circuit breaker temperatures in the remaining branches; Among them, the temperature matching anomaly corresponding to each branch obtained by extracting all linear trend sequences specifically includes: Select a branch; Obtain the historical temperature data and linear trend sequence corresponding to the branch; Determine a temperature prediction parameter column according to the historical temperature data and the linear trend sequence; Perform matching anomaly extraction on the historical temperature data through the temperature prediction parameter column to obtain the temperature matching anomaly amount corresponding to the branch; Repeat the above steps to determine the temperature matching anomaly corresponding to the remaining branches; The load distribution of the target distribution box at each sampling time is determined based on the historical active power transmission data of each branch and the power transmission limit of the target distribution box, and specifically includes: Determine the load rate corresponding to the historical active power transmission amount at each sampling moment in the historical active power transmission data of each branch according to the power transmission limit of the target distribution box; Determine the load distribution of the target distribution box at each sampling time according to all load rates; Among them, the temperature matching anomaly corresponding to each branch is load compensated through all load structure entropies, and the anomaly measurement of each branch in the target distribution box at each sampling time is obtained, which specifically includes: Select a sampling time; Obtain the temperature matching anomaly of each branch at the sampling moment; Obtain the load structure entropy corresponding to the sampling moment; All temperature matching anomalies are compensated according to the load structure entropy corresponding to the sampling moment, and the anomaly measurement of each branch at the sampling moment is obtained; Repeat the above steps to determine the abnormality measure of each branch at the remaining sampling moments, thereby obtaining the abnormality measure of each branch in the target distribution box at each sampling moment; Among them, all temperature matching anomalies are compensated according to the load structure entropy corresponding to the sampling moment, and the anomaly measure of each branch at the sampling moment is obtained in the following manner, namely: first, the standard deviation of all temperature matching anomalies is determined; secondly, the temperature matching anomaly corresponding to a branch is selected at the sampling moment as the selected temperature matching anomaly; then, the quotient of the selected temperature matching anomaly and the above standard deviation is determined; finally, the above result is compensated by the load structure entropy corresponding to the sampling moment, and the compensation is: multiplying the load structure entropy corresponding to the sampling moment with the above result, and taking the multiplication result as the value obtained after compensating the selected temperature matching anomaly by the load structure entropy, namely: the anomaly measure of the branch; repeating the above steps, the temperature matching anomalies corresponding to the remaining branches at the sampling moment are successively taken as the selected temperature matching anomaly, thereby determining the anomaly measure of the remaining branches, and obtaining the anomaly measure of each branch at the sampling moment.

2. The method according to claim 1, characterized in that Determining the temperature prediction parameter column according to the historical temperature data and the linear trend sequence specifically includes: Determine a historical temperature vector according to the historical temperature data; Determine a temperature trend matrix according to the linear trend sequence; A temperature prediction parameter column is determined according to the historical temperature vector and the temperature trend matrix.

3. The method according to claim 1, characterized in that The abnormal warning management of the power supply of the target distribution box based on all abnormal measurements specifically includes: Get the abnormal alarm threshold; Select a sampling time; An abnormality judgment is performed on the abnormality measurement of each branch at the sampling moment by using the abnormal alarm threshold to obtain multiple abnormal branches corresponding to the sampling moment; Repeat the above steps to determine multiple abnormal branches corresponding to the remaining sampling moments; Perform abnormal warning management on the power supply of the target distribution box through all abnormal branches.

4. A power management system for an intelligent distribution box, which adopts the method according to any one of claims 1 to 3 to perform power management, characterized in that: The power management system of the intelligent distribution box includes: An acquisition module is used to collect the temperature of the circuit breakers in each branch of the target distribution box, and then obtain the historical temperature data of each branch; A processing module is used to linearly reconstruct the historical temperature data corresponding to each branch based on the trend characteristics of the historical temperature data of each branch, obtain the linear trend sequence of the circuit breaker temperature in each branch, and then extract the temperature matching anomaly corresponding to each branch through all linear trend sequences; The processing module is further used to obtain the historical active power transmission data of each branch in the target distribution box, determine the load distribution of the target distribution box at each sampling time based on the historical active power transmission data of each branch and the power transmission limit of the target distribution box, and then determine the load structure entropy in the target distribution box at each sampling time through all load distribution conditions; The processing module is also used to perform load compensation on the temperature matching anomaly corresponding to each branch through all load structure entropies to obtain an anomaly measurement of each branch in the target distribution box at each sampling moment; The execution module is used to perform abnormal warning management on the power supply of the target distribution box based on all abnormal measurements.

5. A computer device, comprising a memory and a processor, wherein the memory stores a code, characterized in that: The processor is configured to obtain the code and execute the power management method for the intelligent distribution box according to any one of claims 1 to 3.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the power management method for the intelligent distribution box according to any one of claims 1 to 3 is implemented.

Images