Power supply strategy adjustment method and device and storage medium

Abstract

The invention discloses a power supply strategy adjustment method and device and a storage medium. The method comprises the steps of obtaining a power distribution network graph model; acquiring real-time operation data of the target power distribution network, and determining an abnormal value in the real-time operation data; correcting an abnormal value in the real-time operation data to obtain standard operation data of the target power distribution network; and adjusting the current power supply strategy according to the power distribution network graph model and the standard operation data. After the abnormal value in the real-time operation data is detected, the standard operation data of the target power distribution network can be obtained by correcting the abnormal value and updating the real-time operation data, and the current power supply strategy is adjusted based on the standard operation data, so that useful information in the abnormal value can be reserved, and the accuracy of the power supply strategy is improved. The possibility of loss of useful information can be reduced, so that the accuracy and reliability of power distribution network power supply strategy adjustment can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of strategy adjustment, and in particular to a power supply strategy adjustment method, device and storage medium. Background Art

[0002] In the management and operation of power systems, in order to achieve efficient energy distribution and management, it is becoming increasingly important to dynamically adjust power supply strategies. With the development of smart grid technology, real-time data acquisition and analysis has become one of the key technologies to achieve this goal. In this context, graph computing-based methods are widely used in power system status monitoring, fault diagnosis, and dynamic adjustment of power supply strategies due to their powerful data processing and pattern recognition capabilities. In the graph computing-based power supply strategy dynamic adjustment method, real-time analysis and processing of data is one of the core links. However, due to various reasons (such as equipment failure, human error, external interference, etc.), the collected data often contains some outliers. The existence of these outliers will have a negative impact on subsequent data analysis, pattern recognition, and the final power supply strategy adjustment.

[0003] Existing power supply strategy adjustment methods usually remove outliers through preprocessing to provide data support for power supply strategy adjustment. However, directly removing outliers may lead to the loss of valuable information, resulting in low accuracy of power supply strategy adjustment. Summary of the invention

[0004] The present invention provides a power supply strategy adjustment method to solve the technical problem that the existing power supply strategy adjustment method directly removes abnormal values, which may cause valuable information loss and result in low accuracy of power supply strategy adjustment.

[0005] The present invention provides a power supply strategy adjustment method, comprising:

[0006] Obtain distribution network diagram model;

[0007] Acquire real-time operation data of the target distribution network, and determine abnormal values ​​in the real-time operation data;

[0008] Correcting abnormal values ​​in the real-time operation data to obtain standard operation data of the target distribution network;

[0009] The current power supply strategy is adjusted according to the distribution network diagram model and the standard operation data.

[0010] Further, the determining of abnormal values ​​in the real-time operation data includes:

[0011] Obtaining an average value of the real-time operation data in the preset sliding window within a preset time range, wherein the preset sliding window includes an initialization window and a moving window;

[0012] Calculate the standard deviation of the real-time operation data within the preset time range according to the average value;

[0013] An abnormality score of the real-time operation data at each moment is calculated according to the standard deviation, and an abnormal value of the real-time operation data is determined according to the abnormality score.

[0014] Furthermore, the obtaining of the average value of the real-time operation data in the preset sliding window within the preset time range includes:

[0015] Acquire the operation data of the initialization window within a preset time range;

[0016] Calculate a first average value according to the operation data of the initialization window;

[0017] Moving the initialization window forward or backward by one data point at a time to obtain a plurality of moving windows, and obtaining the operation data of each moving window within the preset time range;

[0018] Calculate a second average value according to the operating data of each moving window;

[0019] According to the first average value and the second average value, a sequence of average values ​​of the initialization window and the moving window is calculated, and the average value of the real-time operation data is determined by the sequence of average values.

[0020] Furthermore, the correcting of abnormal values ​​in the real-time operation data includes:

[0021] Obtain a first estimated value of the outlier based on the neighborhood at each moment, and obtain a second estimated value of the outlier based on polynomial regression at each moment;

[0022] Determining a final estimated value based on the first estimated value and the second estimated value;

[0023] The outliers are corrected with the final estimated values.

[0024] Further, the calculating, based on the average value, the standard deviation of the real-time operation data within the preset time range includes:

[0025] The standard deviation of the real-time operation data is calculated according to the following formula:

[0026]

[0027] Among them, σ(i) represents the standard deviation of the real-time running data at time i, is the average value, W is the moving window width, g(i) is the value of the real-time running data at time i, and t represents the tth moment.

[0028] Furthermore, the calculating, according to the standard deviation, of an abnormality score of the real-time operation data at each moment includes:

[0029] The standardized data value of the real-time running data at each moment is calculated according to the mean value and the standard deviation:

[0030] The abnormality score of the real-time operation data at each moment is calculated according to the standardized data value.

[0031] Furthermore, the calculation formula of the standardized data value is:

[0032]

[0033] Wherein, z(i) is the standardized data value of the real-time running data at time i.

[0034]

[0035] The present invention also provides a power supply strategy adjustment device, comprising:

[0036] A distribution network diagram model acquisition module, used to acquire a distribution network diagram model;

[0037] An abnormal value determination module, used to obtain real-time operation data of the target distribution network and determine abnormal values ​​in the real-time operation data;

[0038] An abnormal value correction module, used to correct abnormal values ​​in the real-time operation data to obtain standard operation data of the target distribution network;

[0039] The power supply strategy adjustment module is used to adjust the current power supply strategy according to the distribution network diagram model and the standard operation data.

[0040] The present invention also provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the power supply strategy adjustment method as described above.

[0041] After detecting an abnormal value, the embodiment of the present invention can obtain standard operating data of the target distribution network by correcting the abnormal value and updating the real-time operating data, and adjust the current power supply strategy based on the standard operating data. The useful information in the abnormal value can be retained, and the possibility of losing useful information can be reduced, thereby effectively improving the accuracy and reliability of the adjustment of the power supply strategy of the distribution network.

[0042] Furthermore, an embodiment of the invention determines a final estimated value based on the first estimated value and the second estimated value, that is, the final estimated value is determined by comprehensively considering factors of capturing local characteristics and global trends, thereby effectively improving the accuracy and reliability of correcting abnormal values ​​according to the final estimated value, and further effectively improving the accuracy and reliability of power supply strategy adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a flow chart of a power supply strategy adjustment method provided by an embodiment of the present invention;

[0044] Figure 2 It is a structural schematic diagram of a power supply strategy adjustment device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0047] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0048] See also Figure 1 The present invention provides a power supply strategy adjustment method, comprising:

[0049] S1. Obtain distribution network diagram model;

[0050] In an embodiment of the present invention, a distribution characteristic data set of a target distribution network may be collected, graph attribute information may be defined, entity abstraction and topological connection may be performed according to the graph attribute information and the distribution characteristic data set, and a distribution network graph model may be generated.

[0051] S2. Obtaining real-time operation data of the target distribution network and determining abnormal values ​​in the real-time operation data;

[0052] In the embodiment of the present invention, the real-time operation data of the target power distribution network can be monitored by a sensor monitoring system, and abnormal values ​​can be determined by detecting abnormal values ​​in the real-time operation data.

[0053] S3, correcting abnormal values ​​in the real-time operation data to obtain standard operation data of the target distribution network;

[0054] In the embodiment of the present invention, after the abnormal value is detected, the standard operation data of the target power distribution network can be obtained by correcting the abnormal value and updating the real-time operation data.

[0055] S4. Adjust the current power supply strategy according to the distribution network diagram model and standard operation data.

[0056] In an embodiment of the present invention, traversal topology analysis and distributed power flow calculation can be performed on the distribution network graph model and the standard operation data of the distribution network through graph calculation to obtain entity node topology information and distribution network power flow calculation results, and based on the entity node topology information and the distribution network power flow calculation results, the distribution network graph calculation and analysis information is determined, and the distribution network graph calculation and analysis information includes operation fault identification feature information.

[0057] Based on the power supply strategy of the distribution network, the distribution network power supply strategy parameter solution space is constructed through data mining technology. The parameter optimization analysis of the operating fault identification feature information is carried out through the distribution network power supply strategy parameter solution space, the power supply strategy control parameter set is determined, and the current power supply strategy of the target distribution network is dynamically feedback adjusted based on the power supply strategy control parameter set.

[0058] After detecting an abnormal value, the embodiment of the present invention can obtain standard operating data of the target distribution network by correcting the abnormal value and updating the real-time operating data, and adjust the current power supply strategy based on the standard operating data. The useful information in the abnormal value can be retained, and the possibility of losing useful information can be reduced, thereby effectively improving the accuracy and reliability of the adjustment of the power supply strategy of the distribution network.

[0059] In one embodiment, S2, determining abnormal values ​​in real-time operation data, comprises:

[0060] S21, obtaining an average value of real-time running data in a preset sliding window within a preset time range, wherein the preset sliding window includes an initialization window and a moving window;

[0061] In the embodiment of the present invention, the preset time range can be set according to actual needs, for example, the preset time range is a preset time range from 10 o'clock to 16 o'clock. In the embodiment of the present invention, a set of time series operation data can be Q(t)=[10, 15, 13, 16, 12, 18, 14], and the average value of the operation data in the initial window and the moving window at all times is calculated.

[0062] S22. Calculate the standard deviation of the real-time running data within a preset time range based on the average value;

[0063] In the embodiment of the present invention, the standard deviation of the real-time operation data can be calculated according to the following formula:

[0064]

[0065] Among them, σ(i) represents the standard deviation of the real-time running data at time i, is the average value, W is the moving window width, g(i) is the value of the real-time running data at time i, and t represents the tth moment.

[0066] S23. Calculate anomaly scores of the real-time operation data at each moment according to the standard deviation, and determine anomaly values ​​of the real-time operation data according to the anomaly scores.

[0067] In an embodiment of the present invention, an anomaly score threshold can be defined according to actual needs. For example, the standardized data z(i) = [-1.03, 0.89, 0.13, 0.22, -0.79, 0.89, -0.5, 0.4, 0.2, -0.6, 0.,5, -0.3]. It can be observed that most of the above standardized data values ​​are between [-1, 1], and the anomaly score threshold can be set to 1.

[0068] In an embodiment of the present invention, the anomaly score of the operating data at the current moment can be compared with the anomaly score threshold. If the anomaly score of the operating data at the current moment is greater than the anomaly score threshold, the operating data at the current moment is determined to be an anomaly value; if the anomaly score of the operating data at the current moment is less than or equal to the anomaly score threshold, the operating data at the current moment is determined to be a standard value.

[0069] It should be noted that the real-time operation data of the time series contains multiple data points such as current, voltage, and load. The operation data in the initialization window and the moving window may represent different data points. By comparing the anomaly score of each data point with the anomaly threshold, it can be determined whether it is an outlier.

[0070] The embodiments of the present invention can continuously track and analyze real-time operation data by using an initialization window and a moving window within a preset time range; calculating the average value of the data in the sliding window can help identify the central trend of the data, thereby accurately determining the standard deviation of the real-time operation data; by calculating the standard deviation, the fluctuation range of the real-time operation data is comprehensively considered; by calculating the abnormal score at each moment through the standard deviation, the degree to which the data point deviates from the normal range can be quantified, thereby accurately determining the abnormal value.

[0071] In one embodiment, S21, obtaining an average value of real-time running data in a preset sliding window within a preset time range, includes:

[0072] S211, obtaining operation data of the initialization window within a preset time range;

[0073] In an embodiment of the present invention, the current window can be initialized to obtain an initialization window, the width of the initialization window is W=3, the data point at time t in the time series is selected as the initial data point of the initialization window, and the operating data range covered by the initialization window is from time t to the Wth data point, thereby obtaining the operating data of the initialization window within the time range.

[0074] S212, calculating a first average value according to the operation data of the initialization window;

[0075] S213, moving the initialization window forward or backward by one data point at a time to obtain a plurality of moving windows, and obtaining the operation data of each moving window within a preset time range;

[0076] S214, calculating a second average value according to the operating data of each moving window;

[0077] S215. Calculate a sequence of average values ​​of the initialization window and the moving window based on the first average value and the second average value, and determine the average value of the real-time running data with the sequence of average values.

[0078] In the embodiment of the present invention, the first average value and the second average value are integrated together to obtain an average value sequence, and the numerical value converted into the average value sequence can be used as the average value of the real-time operation data.

[0079] In the embodiment of the present invention, the first average value and the second average value can be calculated by the following formula:

[0080]

[0081] In the formula, represents the average value of the running data of the initial window or moving window at time i, W represents the moving window width, g(i) represents the value of the running data at time i, and t represents the tth time.

[0082] In the embodiment of the present invention, represent the first average value and the second average value respectively.

[0083] In an embodiment of the present invention, by calculating the average values ​​of the initialization window and the moving window, the trends and patterns of the data can be captured more accurately, thereby providing more reliable data support for the adjustment of the power supply strategy; the successive movement of the moving window can realize continuous monitoring of data changes and timely detection of anomalies or trend changes, thereby further providing more reliable data support for the adjustment of the power supply strategy.

[0084] In one embodiment, S3, correcting abnormal values ​​in real-time operation data, includes:

[0085] S31, obtaining a first estimated value of the outlier based on the neighborhood at each moment, and obtaining a second estimated value of the outlier based on polynomial regression at each moment;

[0086] In the embodiment of the present invention, for each time t, data points within a certain range before and after the time t are taken as a neighborhood, and the average value of the data points in the neighborhood is calculated as the first estimated value. Specifically:

[0087]

[0088] in, represents the first estimate based on the neighborhood at time t, N(t) represents the set of neighboring data points, K represents the maximum number of neighboring data points in the set of neighboring data points, and x(m) represents the value of the mth data point in the set of neighboring data points.

[0089] In the embodiment of the present invention, the expression of the second estimated value is:

[0090]

[0091] in, Represents the estimated value based on polynomial regression at time t, and a, b, c, d, ..., h are the coefficients of the polynomial.

[0092] The coefficients of the polynomial can be obtained by the least square method. The embodiment of the present invention provides a set of observation data (ti, pi), where ti represents a time point and pi represents a data point. First, a design matrix X and a vector y are constructed, where each row of the design matrix corresponds to one data point and a power term:

[0093]

[0094] The vector y contains all the data points:

[0095]

[0096] The goal of the least squares method is to minimize the sum of squared errors e:

[0097] e=||y-Xβ|| 2 ;

[0098] Among them, β represents the coefficient vector to be determined.

[0099] To find the coefficient vector that minimizes the sum of squared errors, solve the following equation:

[0100]

[0101] Here, T represents the transpose operation.

[0102] X T The X matrix is ​​a (n+1)×(n+1) matrix, where n is the order of the polynomial;

[0103]

[0104] Here, m represents the maximum moment.

[0105] X T y is an n+1 dimensional vector:

[0106]

[0107] β=(X T X) -1 X T y

[0108] Among them, the value in the β vector is the ah value.

[0109] S32, determining a final estimated value according to the first estimated value and the second estimated value;

[0110] In the embodiment of the present invention, the calculation formula of the final estimated value is as follows:

[0111]

[0112] in, represents the final estimated value at time t, represents the fusion weight. In a specific implementation,

[0113] S33. Correct the outliers with the final estimated values.

[0114] In the embodiment of the present invention, the outliers are corrected according to the following formula:

[0115]

[0116] x(t) * Represents the corrected value.

[0117] In an embodiment of the present invention, the neighborhood estimation value can capture local features, while the polynomial regression estimation value can capture global trends. The embodiment of the present invention determines a final estimation value based on the first estimation value and the second estimation value, that is, the factors of capturing local features and global trends are comprehensively considered to determine the final estimation value, thereby effectively improving the accuracy and reliability of correcting abnormal values ​​according to the final estimation value, and further effectively improving the accuracy and reliability of power supply strategy adjustment.

[0118] In one embodiment, step S23, calculating the abnormal score of the real-time operation data at each time point according to the standard deviation, includes:

[0119] The standardized data value of the real-time running data at each moment is calculated based on the mean value and standard deviation:

[0120] In the embodiment of the present invention, the calculation formula of the standardized data value is:

[0121]

[0122] Wherein, z(i) is the standardized data value of the real-time running data at time i.

[0123] The anomaly score of the real-time running data at each moment is calculated based on the standardized data value.

[0124] In this embodiment of the present invention, the calculation formula of the abnormality score is:

[0125]

[0126] Among them, s(i) is the anomaly score of the real-time running data at time i.

[0127] The implementation of the embodiments of the present invention has the following beneficial effects:

[0128] After detecting an abnormal value, the embodiment of the present invention can obtain standard operating data of the target distribution network by correcting the abnormal value and updating the real-time operating data, and adjust the current power supply strategy based on the standard operating data. The useful information in the abnormal value can be retained, and the possibility of losing useful information can be reduced, thereby effectively improving the accuracy and reliability of the adjustment of the power supply strategy of the distribution network.

[0129] Furthermore, the embodiment of the present invention determines a final estimated value based on the first estimated value and the second estimated value, that is, the final estimated value is determined by comprehensively considering factors of capturing local characteristics and global trends, thereby effectively improving the accuracy and reliability of correcting abnormal values ​​according to the final estimated value, and further effectively improving the accuracy and reliability of power supply strategy adjustment.

[0130] See also Figure 2 Based on the same inventive concept as the above embodiment, the present invention also provides a power supply strategy adjustment device, comprising

[0131] A distribution network diagram model acquisition module 10, used to acquire a distribution network diagram model;

[0132] An abnormal value determination module 20 is used to obtain real-time operation data of the target distribution network and determine abnormal values ​​in the real-time operation data;

[0133] An abnormal value correction module 30 is used to correct abnormal values ​​in real-time operation data to obtain standard operation data of the target distribution network;

[0134] The power supply strategy adjustment module 40 is used to adjust the current power supply strategy according to the power distribution network diagram model and standard operation data.

[0135] In one embodiment, the outlier determination module 20 is further configured to:

[0136] Obtaining an average value of real-time running data in a preset sliding window within a preset time range, wherein the preset sliding window includes an initialization window and a moving window;

[0137] Based on the average value, the standard deviation of the real-time running data within the preset time range is calculated;

[0138] The abnormal score of the real-time operation data at each moment is calculated based on the standard deviation, and the abnormal value of the real-time operation data is determined based on the abnormal score.

[0139] In one embodiment, obtaining the average value of real-time running data in a preset sliding window within a preset time range includes:

[0140] Obtaining the operation data of the initialization window within the preset time range;

[0141] Calculate a first average value according to the operation data of the initialization window;

[0142] The initialization window is moved forward or backward by one data point at a time to obtain a plurality of moving windows, and the operation data of each moving window within a preset time range is obtained;

[0143] A second average value is calculated based on the running data of each moving window;

[0144] According to the first average value and the second average value, a sequence of average values ​​of the initialization window and the moving window is calculated, and the average value of the real-time running data is determined by the sequence of average values.

[0145] In one embodiment, the outlier correction module 30 is further configured to:

[0146] Obtain a first estimated value of the outlier based on the neighborhood at each moment, and obtain a second estimated value of the outlier based on polynomial regression at each moment;

[0147] Determining a final estimated value based on the first estimated value and the second estimated value;

[0148] The final estimates are corrected for outliers.

[0149] In one embodiment, the standard deviation of the real-time running data within a preset time range is calculated based on the average value, including:

[0150] The standard deviation of real-time running data is calculated according to the following formula:

[0151]

[0152] Among them, σ(i) represents the standard deviation of the real-time running data at time i, is the average value, W is the moving window width, g(i) is the value of the real-time running data at time i, and t represents the tth moment.

[0153] In one embodiment, the abnormal score of the real-time operation data at each time is calculated according to the standard deviation, including:

[0154] The standardized data value of the real-time running data at each moment is calculated based on the mean value and standard deviation:

[0155] The anomaly score of the real-time running data at each moment is calculated based on the standardized data value.

[0156] In one embodiment, the calculation formula of the normalized data value is:

[0157]

[0158] Wherein, z(i) is the standardized data value of the real-time running data at time i.

[0159]

[0160] Correspondingly, an embodiment of the present invention also provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the power supply strategy adjustment method of any one of the above embodiments is implemented.

[0161] The terminal device of this embodiment includes: a processor, a memory, and a computer program and computer instructions stored in the memory and executable on the processor. When the processor executes the computer program, each step in the above embodiment 1 is implemented, for example Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above device embodiment, such as the abnormal value correction module 30, are implemented.

[0162] Exemplarily, the computer program can be divided into one or more modules / units, one or more modules / units are stored in a memory and executed by a processor to complete the present invention. One or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device. For example, the abnormal value correction module 30 is used to correct the abnormal value in the real-time operation data to obtain the standard operation data of the target distribution network.

[0163] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the diagram, or may combine certain components, or different components. For example, the terminal device may also include an input / output device, a network access device, a bus, etc.

[0164] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0165] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile terminal, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0166] Among them, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0167] Correspondingly, an embodiment of the present invention further provides a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the power supply strategy adjustment method of any one of the above embodiments.

[0168] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A power supply strategy adjustment method, characterized in that: include: Obtain distribution network diagram model; Acquire real-time operation data of the target distribution network, and determine abnormal values ​​in the real-time operation data; Correcting abnormal values ​​in the real-time operation data to obtain standard operation data of the target distribution network; The current power supply strategy is adjusted according to the distribution network diagram model and the standard operation data.

2. The power supply strategy adjustment method according to claim 1, characterized in that: The determining of abnormal values ​​in the real-time operation data includes: Obtaining an average value of the real-time operation data in the preset sliding window within a preset time range, wherein the preset sliding window includes an initialization window and a moving window; Calculate the standard deviation of the real-time operation data within the preset time range according to the average value; An abnormality score of the real-time operation data at each moment is calculated according to the standard deviation, and an abnormal value of the real-time operation data is determined according to the abnormality score.

3. The power supply strategy adjustment method according to claim 2, characterized in that: The obtaining the average value of the real-time operation data in the preset sliding window within the preset time range includes: Acquire the operation data of the initialization window within a preset time range; Calculate a first average value according to the operation data of the initialization window; Moving the initialization window forward or backward by one data point at a time to obtain a plurality of moving windows, and obtaining the operation data of each moving window within the preset time range; Calculate a second average value according to the operating data of each moving window; According to the first average value and the second average value, a sequence of average values ​​of the initialization window and the moving window is calculated, and the average value of the real-time operation data is determined by the sequence of average values.

4. The power supply strategy adjustment method according to claim 1, characterized in that: The correcting of abnormal values ​​in the real-time operation data includes: Obtain a first estimated value of the outlier based on the neighborhood at each moment, and obtain a second estimated value of the outlier based on polynomial regression at each moment; Determining a final estimated value based on the first estimated value and the second estimated value; The outliers are corrected with the final estimated values.

5. The power supply strategy adjustment method according to claim 2, characterized in that: Calculating the standard deviation of the real-time operation data within the preset time range according to the average value includes: The standard deviation of the real-time operation data is calculated according to the following formula: Among them, σ(i) represents the standard deviation of the real-time running data at time i, is the average value, W is the moving window width, g(i) is the value of the real-time running data at time i, and t represents the tth moment.

6. The power supply strategy adjustment method according to claim 5, characterized in that: The calculating, according to the standard deviation, of the abnormal score of the real-time operation data at each moment includes: The standardized data value of the real-time running data at each moment is calculated according to the mean value and the standard deviation: The abnormality score of the real-time operation data at each moment is calculated according to the standardized data value.

7. The power supply strategy adjustment method according to claim 6, characterized in that: The calculation formula of the standardized data value is: Wherein, z(i) is the standardized data value of the real-time running data at time i.

8. The power supply strategy adjustment method according to claim 7, characterized in that: The calculation formula of the abnormal score is: Among them, s(i) is the anomaly score of the real-time running data at time i.

9. A power supply strategy adjustment device, characterized in that: include A distribution network diagram model acquisition module, used to acquire a distribution network diagram model; An abnormal value determination module, used to obtain real-time operation data of the target distribution network and determine abnormal values ​​in the real-time operation data; An abnormal value correction module, used to correct abnormal values ​​in the real-time operation data to obtain standard operation data of the target distribution network; The power supply strategy adjustment module is used to adjust the current power supply strategy according to the distribution network diagram model and the standard operation data.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the power supply strategy adjustment method according to any one of claims 1 to 8.

Images