Digital supervision quality evaluation method based on big data model and storage medium

Abstract

The embodiment of the application provides an evaluation method for digital supervision quality based on a big data model and a storage medium, and belongs to the technical field of supervision quality evaluation. The evaluation method comprises the following steps: constructing an evaluation grade of a supervision model; acquiring output time sequence characteristics and real time sequence characteristics of a current supervision model; acquiring error time sequence characteristics of the current supervision model through the output time sequence characteristics and the real time sequence characteristics of the current supervision model, and combining the evaluation grade of the constructed supervision model, so that an evaluation matrix of the current supervision model can be obtained, the evaluation value of the supervision model can be obtained according to the evaluation matrix, and the evaluation value can be used to evaluate the current supervision model; the error time sequence characteristics of the supervision model are quantified into a specific evaluation value in this way, so that effective evaluation of the supervision model can be realized, that is, effective supervision, and the reliability and accuracy of power grid system supervision are ensured.

Description

Technical Field

[0001] This invention relates to the field of supervision quality evaluation technology, specifically to a digital supervision quality evaluation method and storage medium based on a big data model. Background Technology

[0002] Digital supervision models are based on digital technologies, especially information and intelligent technologies, and are applied in the fields of power grid engineering supervision or power grid operation supervision. Traditional supervision mainly relies on manual labor or the use of related supervision tools. Digital supervision models can improve the efficiency, accuracy, and transparency of supervision through digital tools and systems, and have already been applied in power grid systems. Specifically, the types of supervision models can include voltage supervision models, construction quality supervision models, etc.

[0003] Currently, with the gradual application of supervision models, there are no standards to measure the supervision quality of these models, resulting in poor optimization and iteration effects, which in turn affects the reliability and accuracy of power grid system supervision.

[0004] In the process of realizing this invention, the inventors of this application discovered that the above-mentioned solutions in the prior art have the defects of poor reliability and low accuracy in power grid system supervision. Summary of the Invention

[0005] The purpose of this invention is to provide a method and storage medium for evaluating the quality of digital supervision based on a big data model. This method and storage medium can improve the reliability and accuracy of power grid system supervision.

[0006] To achieve the above objectives, embodiments of the present invention provide a method for evaluating the quality of digital supervision based on a big data model, comprising:

[0007] The evaluation level of the construction supervision model;

[0008] Obtain the output time-series characteristics and the actual time-series characteristics of the current supervision model;

[0009] The error time series characteristics of the current supervision model are obtained based on the output time series characteristics and the actual time series characteristics of the current supervision model.

[0010] The evaluation matrix is ​​obtained based on the error time series characteristics and the evaluation level;

[0011] The evaluation value of the current supervision model is obtained based on the evaluation matrix;

[0012] The quality of the current supervision model is evaluated based on its evaluation value.

[0013] Optionally, the evaluation levels for constructing the supervision model include:

[0014] Obtain multiple historical output time-series features of the supervision model and their corresponding historical real time-series features;

[0015] Historical error time series features are obtained based on the historical output time series features and the historical true time series features.

[0016] Obtain the mean, maximum, and minimum values ​​of the historical error time series features;

[0017] The evaluation level of the supervision model is determined based on the mean, maximum, and minimum values ​​of the historical error time series characteristics.

[0018] Optionally, obtaining historical error time-series features based on the historical output time-series features and the historical true time-series features includes:

[0019] The historical error time series characteristics are obtained according to formula (1).

[0020]

[0021] in, Let be the value of the i-th historical error time series feature at time t. Let be the value of the i-th historical output time-series feature at time t. Let be the value of the i-th historical real time series feature at time t, where i is an integer number and t is the time.

[0022] Optionally, the evaluation level of the supervision model is determined based on the mean, maximum, and minimum values ​​of the historical error time-series characteristics, including:

[0023] The grade base value of the historical error time series characteristics is obtained according to formula (2).

[0024]

[0025] Where Δε is the base value of the historical error time series characteristics, ε max ε is the maximum value of the historical error time series characteristics. min σ is the minimum value of the historical error time series characteristics, and σ is the interval base value;

[0026] The level value of the historical error time series characteristics is obtained according to formula (3).

[0027]

[0028] Where, ε l Let l be the level value of the historical error time series feature, and l be the level number of the historical error time series feature, where l = {1, 2}. The mean of the historical error time series characteristics;

[0029] Determine whether the current level value of the historical error time series feature is related to its nearest maximum or minimum value to the error time series feature;

[0030] If it is determined that there is an error time series feature between the current level value of the historical error time series feature and its nearest maximum or minimum value, the level value of the current historical error time series feature is obtained.

[0031] If it is determined that there is no error time series feature between the current level value of the historical error time series feature and its nearest maximum or minimum value, the interval base value is updated according to formula (4).

[0032] σ=σ+δ, (4)

[0033] Where δ is the adjustment base value;

[0034] Return to the steps of obtaining the grade base value of the historical error time series characteristics according to formula (2).

[0035] Optionally, obtaining the error time-series characteristics of the current supervision model based on the output time-series characteristics and the actual time-series characteristics includes:

[0036] The error time series characteristics of the current supervision model are obtained according to formula (5).

[0037]

[0038] in, Y represents the value of the error time series characteristics of the current supervision model at time t. t d The value of the output time-series characteristic of the current supervision model at time t. The value of the actual temporal characteristics of the current supervision model at time t.

[0039] Optionally, obtaining the evaluation matrix based on the error time series characteristics and the evaluation level includes:

[0040] The error time series characteristics of the current supervision model are classified according to the evaluation level.

[0041] According to formula (6), the evaluation probability of the error time series characteristics of the current supervision model at each level is obtained.

[0042]

[0043] Where, p kLet T be the evaluation probability of the error time series characteristics of the current supervision model at level k, where k is the level interval and k = {1, 2, 3}. n2 k Let T be the end time of the nth segment of the error time series characteristics of the current supervision model at level k. n1 k The error time series feature of the current supervision model is the start time of the nth segment at level k, where n is an integer number, j is an integer number, N is the total number of segments of the error time series feature of the current supervision model at level k, and T is the total duration of the error time series feature of the current supervision model.

[0044] The evaluation matrix of the current supervision model is obtained based on the evaluation probability of the error time series characteristics of the current supervision model at each level.

[0045] Optionally, obtaining the evaluation value of the current supervision model based on the evaluation matrix includes:

[0046] Obtain the decision values ​​of the current supervision model at each level, and construct a decision matrix;

[0047] The evaluation value of the current supervision model is obtained according to formula (7).

[0048] S = P 3×1 ×Q 1×3 (7)

[0049] Where S is the evaluation value of the current supervision model, and P 3×1 Let Q be the evaluation matrix of the current supervision model. 1×3 Let be the decision matrix.

[0050] Optionally, obtaining the decision values ​​of the current supervision model at each level includes:

[0051] Randomize the decision values ​​of the current supervision model at each level and construct an initial population;

[0052] The fitness value of each individual in the population is obtained according to formula (8).

[0053]

[0054] Among them, F fitness The fitness value is K, where K is the number of levels in the supervision model, and K = 3, q k p represents the decision value of the error time series characteristics of the supervision model at level k. k·l The evaluation probability of the historical error time series characteristics at level k;

[0055] Select the optimal individual in the population based on the fitness value;

[0056] Iterate through the remaining individuals in the population based on the optimal individual;

[0057] Determine whether the current iteration count of the population is greater than or equal to the iteration count threshold;

[0058] If the number of iterations of the current population is greater than or equal to the iteration threshold, output the optimal solution of the decision value of the current supervision model;

[0059] If it is determined that the number of iterations of the current population is less than the iteration threshold, the step of obtaining the fitness value of each individual in the population according to formula (8) is returned.

[0060] Optionally, evaluating the quality of the current supervision model based on the evaluation value of the current supervision module includes:

[0061] Determine whether the evaluation value of the current supervision model is less than or equal to the evaluation threshold;

[0062] If the evaluation value of the current supervision model is less than or equal to the evaluation threshold, the supervision quality of the current supervision model is determined to be good.

[0063] If the evaluation value of the current supervision model is greater than the evaluation threshold, the supervision quality of the current supervision model is determined to be poor.

[0064] On the other hand, the present invention also provides a computer-readable storage medium storing instructions for being read by a machine to cause the machine to perform any of the evaluation methods described above.

[0065] Through the above technical solution, the digital supervision quality evaluation method and storage medium based on big data model provided by this invention obtains the error time series characteristics of the current supervision model through the output time series characteristics and the real time series characteristics of the current supervision model. Combined with the evaluation level of the constructed supervision model, the evaluation matrix of the current supervision model can be obtained. According to the evaluation matrix, the evaluation value of the supervision model can be obtained, and then the evaluation value can be used to evaluate the current supervision model. By adopting this method of quantifying the error time series characteristics of the supervision model into specific evaluation values, effective evaluation of the supervision model can be achieved, that is, effective supervision, thereby ensuring the reliability and accuracy of power grid system supervision.

[0066] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0067] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0068] Figure 1 This is a flowchart of a digital supervision quality evaluation method based on a big data model according to an embodiment of the present invention;

[0069] Figure 2 This is a flowchart illustrating the process of obtaining evaluation levels in a digital supervision quality evaluation method based on a big data model according to an embodiment of the present invention.

[0070] Figure 3 This is a flowchart illustrating the process of obtaining grade values ​​in a digital supervision quality evaluation method based on a big data model according to an embodiment of the present invention.

[0071] Figure 4 This is a flowchart of obtaining the evaluation matrix in a digital supervision quality evaluation method based on a big data model according to an embodiment of the present invention;

[0072] Figure 5 This is a flowchart illustrating the process of obtaining evaluation values ​​in a digital supervision quality evaluation method based on a big data model according to an embodiment of the present invention.

[0073] Figure 6 This is a flowchart of obtaining the decision matrix in a digital supervision quality evaluation method based on a big data model according to an embodiment of the present invention;

[0074] Figure 7 This is a flowchart of the evaluation of the supervision model in a digital supervision quality evaluation method based on a big data model according to an embodiment of the present invention. Detailed Implementation

[0075] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0076] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0077] Figure 1This is a flowchart of a digital supervision quality evaluation method based on a big data model according to an embodiment of the present invention. Figure 1 In this context, the evaluation method may include:

[0078] In step S10, the evaluation levels of the supervision model are constructed. The evaluation level of the supervision model can be determined based on the output error of the model in historical data, so that the multiple evaluation levels assigned to the supervision model can be more accurate and effective.

[0079] In step S11, the output time-series characteristics and the actual time-series characteristics of the current supervision model are obtained. Specifically, for the output time-series characteristics of the current supervision model, an output time period can be preset, and the output data of the supervision model within this time period is obtained. Specifically, the time-series characteristics can be discrete or continuous. If it is a discrete characteristic, output values ​​need to be obtained at equal time intervals. The time intervals can be set relatively small to ensure a relatively large amount of discrete data. Similarly, the actual time-series characteristics of the supervision model, i.e., the actual time-series characteristics of the supervised model, need to correspond to the output time-series characteristics during data collection.

[0080] In step S12, the error time-series characteristics of the current supervision model are obtained based on the output time-series characteristics and the actual time-series characteristics of the current supervision model. Specifically, after obtaining the output time-series characteristics and the actual time-series characteristics of the supervision model, the error time-series characteristics of the supervision model can be obtained. Specifically, the error time-series characteristics of the supervision model can be obtained according to formula (5).

[0081] The error time series characteristics of the current supervision model are obtained according to formula (5).

[0082]

[0083] in, Y represents the value of the error time series characteristics of the current supervision model at time t. t d The output time-series characteristic of the current supervision model is the value at time t. This represents the value of the true temporal characteristics of the current supervision model at time t.

[0084] In step S13, an evaluation matrix is ​​obtained based on the error time series characteristics and the evaluation level. Specifically, after obtaining the error time series characteristics of the current supervision model, the evaluation level of the supervision model is combined to classify the error time series characteristics into levels, thereby obtaining the evaluation matrix.

[0085] In step S14, the evaluation value of the current supervision model is obtained based on the evaluation matrix. Specifically, the evaluation matrix of the current supervision model is transformed to obtain the evaluation value of the current supervision model, which reflects the output characteristics of the current supervision model over a period of time.

[0086] In step S15, the quality of the current supervision model is evaluated based on its evaluation value. This evaluation value is used to assess the quality of the current supervision model.

[0087] In steps S10 to S15, the evaluation level of the supervision model is first constructed based on the historical data of the supervision model. Then, the output time-series characteristics and the actual time-series characteristics of the current supervision model are obtained. Processing these two characteristics yields the error time-series characteristics of the current supervision model. Based on these error time-series characteristics and the constructed evaluation level, the evaluation matrix of the current supervision model is obtained. Further transformation of this evaluation matrix yields the evaluation value of the current supervision model, which is used to evaluate the quality of the current supervision model.

[0088] Traditional supervision models for power grid systems can only achieve digital supervision, but they cannot measure the quality / effectiveness of the supervision, thus affecting the reliability and accuracy of power grid system supervision. In this embodiment of the invention, a method that quantifies the time-series error characteristics of the supervision model into specific evaluation values ​​enables effective evaluation of the supervision model, i.e., effective supervision, thereby ensuring the reliability and accuracy of power grid system supervision.

[0089] In this embodiment of the invention, when classifying the evaluation level of the supervision model, it is necessary to perform a conversion based on the historical data of the supervision model. The specific conversion steps can be as follows: Figure 2 As shown. Specifically, in Figure 2 In addition, the evaluation method may also include:

[0090] In step S100, multiple historical output time-series features and corresponding historical real time-series features of the supervision model are acquired. Specifically, multiple sets of corresponding historical output time-series features and historical real time-series features of the supervision model can be collected. Specifically, the multiple sets of historical output time-series features are continuous output time-series features separated at equal intervals, that is, a whole time-series feature is divided into multiple smaller time-series features. Alternatively, a single historical output time-series feature and its corresponding historical real time-series feature can also be used here.

[0091] In step S101, historical error time-series features are obtained based on historical output time-series features and historical true time-series features. The historical error time-series features can be obtained as shown in formula (1).

[0092] Historical error time series characteristics are obtained according to formula (1).

[0093]

[0094] in, Let be the value of the i-th historical error time series feature at time t. Let be the value of the i-th historical output time series feature at time t. Let be the value of the i-th historical real time series feature at time t, where i is an integer number and t is the time.

[0095] In step S102, the mean, maximum, and minimum values ​​of historical error time-series features are obtained. Specifically, for the mean of multiple historical error time-series features, they can be merged into a single, larger error time-series feature, and the mean can be directly obtained. Alternatively, the mean of each historical error time-series feature can be calculated, and then the average of these multiple means is taken. Similarly, the maximum and minimum values ​​of multiple historical error time-series features can also be obtained. Specifically, for obtaining the maximum and minimum values, the K largest or smallest values ​​can be obtained and averaged to avoid the influence of outliers.

[0096] In step S103, the evaluation levels of the supervision model are divided according to the mean, maximum, and minimum values ​​of the historical error time-series characteristics. The number of evaluation levels can be determined based on the actual evaluation accuracy requirements. In this embodiment of the invention, two evaluation levels are used to divide the model into three evaluation regions. Specifically, as shown... Figure 3 As shown, the steps for obtaining this evaluation level may include:

[0097] In step S1030, the level base value of the historical error time series characteristics is obtained according to formula (2).

[0098]

[0099] Where Δε is the base value of the historical error time series characteristics, ε max ε represents the maximum value of the historical error time series characteristics. min σ represents the minimum value of the historical error time series characteristics, and σ is the interval base value. Specifically, the value of this interval base value σ is generally σ>2, but it cannot be too large, generally within 10, to ensure that the intermediate level range is not too small.

[0100] In step S1031, the level value of the historical error time series characteristics is obtained according to formula (3).

[0101]

[0102] Where, ε lLet l represent the level value of the historical error time series characteristic, and l be the level number of the historical error time series characteristic, where l = {1, 2}. This represents the mean of the historical error time series characteristics. Specifically, there are two values ​​for this level, that is, two values ​​symmetrical above and below the mean, which can divide the historical error time series characteristics into three level regions.

[0103] In step S1032, it is determined whether there is an error time series characteristic between the current historical error time series characteristic level value and its nearest maximum or minimum value. The nearest maximum or minimum value includes the maximum level value and the maximum value, and the minimum level value and the minimum value.

[0104] In step S1033, if it is determined that there is an error time series characteristic between the current historical error time series characteristic level value and its nearest maximum or minimum value, the level value of the current historical error time series characteristic is obtained. Specifically, if there is an error time series characteristic between the level value and its nearest maximum or minimum value, it indicates that each level value has an analyzable error value, thus indicating that the level division is accurate, and the level value corresponding to the current division is obtained.

[0105] In step S1034, if it is determined that there is no error time series feature between the current historical error time series feature level value and its nearest maximum or minimum value, the interval base value is updated according to formula (4).

[0106] σ=σ+δ, (4)

[0107] Wherein, δ is the adjustment base value, which satisfies 0 < δ ≤ 1. Specifically, if there is no error time series characteristic between the level value and its nearest maximum or minimum value, it indicates that the division is unreasonable. Such a division results in a constant value of 0 under a certain level, which has no reference value.

[0108] In step S1035, the step of obtaining the grade base value of the historical error time series characteristics according to formula (2) is returned.

[0109] In steps S1030 to S1035, a grade base value is first obtained based on the maximum and minimum values ​​of the historical error time series characteristics. Based on this base value, it is converted into two grade values. The rationality of the grade division is confirmed by the presence or absence of historical error time series characteristics between the two grade values ​​and their nearest maximum or minimum values. If historical error time series characteristics exist between the two grade values ​​and their nearest maximum or minimum values, it indicates that each grade region has analytical value, and the currently divided grade value can be obtained. Conversely, if no historical error time series characteristics exist, it indicates that some grade regions lack analytical value, and the interval base value needs to be updated to continuously adjust the grade base value until the optimal grade value is obtained. This method enables reliable division of the historical error feature sequence.

[0110] In steps S100 to S103, the historical error time series characteristics can be obtained based on the historical output time series characteristics and the historical actual time series characteristics of the supervision model. The mean, maximum, and minimum values ​​are then determined based on these historical error time series characteristics. Analyzing the mean, maximum, and minimum values ​​of these historical time series characteristics allows for the reasonable determination of multiple evaluation levels for the supervision model.

[0111] In this embodiment of the invention, after obtaining the error time-series characteristics of the current supervision model, it is also necessary to obtain its evaluation matrix according to the evaluation level. The specific steps for obtaining this matrix are as follows: Figure 4 As shown. Specifically, in Figure 4 In addition, the evaluation method may also include:

[0112] In step S130, the error time-series characteristics of the current supervision model are divided according to the evaluation level. The two evaluation levels divide the error time-series characteristics of the current supervision model into three level regions.

[0113] In step S131, the evaluation probability of the error time series characteristics of the current supervision model at each level is obtained according to formula (6).

[0114]

[0115] Where, p k Let T be the evaluation probability of the error time series characteristics of the current supervision model at level k, where k is the level interval and k = {1, 2, 3}. n2 k Let T be the end time of the nth segment of the error time series characteristics of the current supervision model at level k. n1 k Let N be the start time of the nth segment of the error time series feature of the current supervision model at level k, where n is an integer number, j is an integer number, N is the total number of segments of the error time series feature of the current supervision model at level k, and T is the total duration of the error time series feature of the current supervision model.

[0116] In step S132, the evaluation matrix of the current supervision model is obtained based on the evaluation probability of the error time series characteristics of the current supervision model at each level. This evaluation matrix is ​​P. 3×1 =[p1p2p3].

[0117] In steps S130 to S132, the error time-series characteristics of the current supervision model are first divided according to the evaluation level to obtain multiple segments of error time-series characteristics. Each evaluation level may contain multiple discontinuous segments of error time-series characteristics. Therefore, the multiple segments of error time-series characteristics in each evaluation level can be integrated, and the ratio of the integrated segment to the total duration of the error time-series characteristics is used as the distribution probability of the error time-series characteristics under that level, i.e., the evaluation probability. Finally, the evaluation probabilities under the three levels are summarized to obtain the evaluation matrix of the error time-series characteristics.

[0118] In this embodiment of the invention, after obtaining the evaluation matrix of the current supervision model, it needs to be converted into evaluation values ​​to evaluate the currently established model. The specific conversion steps can be as follows: Figure 5 As shown.

[0119] Specifically, in Figure 5 In addition, the evaluation method may also include:

[0120] In step S140, the decision values ​​of the current supervision model at each level are obtained, and a decision matrix is ​​constructed. The decision values ​​of the supervision model at each level can be determined based on the historical output time-series characteristics and historical true time-series characteristics of the supervision model. Specific steps can be as follows: Figure 6 As shown. Specifically, in Figure 6 In addition, the evaluation method may also include:

[0121] In step S1400, the decision values ​​of the current supervision model at each level are randomized, and an initial population is constructed. The particle swarm optimization algorithm can be used to process the decision values ​​of the supervision model at each level.

[0122] In step S1401, the fitness value of each individual in the population is obtained according to formula (8).

[0123]

[0124] Among them, F fitness The fitness value is K, where K is the number of levels in the supervision model, and K = 3. k p represents the decision value of the error time series characteristics of the current supervision model at level k. k·l Let p be the evaluation probability of the historical error time series feature at level k. Specifically, let p be the evaluation probability of the historical error time series feature at level k. k·l The time series features with smaller differences between the output values ​​of the supervision model and the actual values ​​can be used, that is, the time series features with better / optimal output effects of the supervision model can be used as the optimization calculation of the objective function.

[0125] In step S1402, the optimal individual in the population is selected based on its fitness value. This optimal individual is the one with the lowest fitness value.

[0126] In step S1403, the remaining individuals in the population are iterated based on the optimal individual.

[0127] In step S1404, it is determined whether the number of iterations for the current population is greater than or equal to an iteration count threshold. This iteration count threshold is a preset value.

[0128] In step S1405, if the number of iterations of the current population is greater than or equal to the iteration threshold, the optimal solution of the decision value of the current supervision model is output. Specifically, if the number of iterations of the current population is greater than the iteration threshold, it indicates that the iteration is complete, and the globally optimal solution is obtained as the optimal solution of the current supervision model.

[0129] In step S1406, if the number of iterations of the current population is less than the iteration threshold, the process returns to the step of obtaining the fitness value of each individual in the population according to formula (8). Wherein, if the number of iterations of the current population is less than the iteration threshold, it indicates that the iteration is not complete, and the current iteration count needs to be updated and the fitness value of the next population needs to be recalculated.

[0130] In steps S1400 to S1406, the decision values ​​are first randomized to obtain an initial population. Then, the fitness value of each individual in the population is calculated to select the optimal individual in the current population. Based on this optimal individual, the remaining individuals in the current population are iterated, and the iteration count of the current population is compared with an iteration count threshold. If the iteration count of the current population is greater than or equal to the iteration count threshold, the iteration is complete, and the global optimal solution is output. Otherwise, the current iteration count needs to be updated, and the fitness value of the population needs to be recalculated, and this process is repeated. Using this method, the optimal decision values ​​for the error time series characteristics in each level region can be effectively obtained. Specifically, the decision matrix for the supervision model can be...

[0131]

[0132] In step S141, the evaluation value of the current supervision model is obtained according to formula (7).

[0133] S = P 3×1 ×Q 1×3 (7)

[0134] Where S is the evaluation value of the current supervision model, and P 3×1 Let Q be the evaluation matrix of the current supervision model. 1×3 This is the decision matrix.

[0135] In steps S140 to S141, the decision matrix of the supervision model is first obtained based on the historical error time series characteristics. Then, the decision matrix is ​​multiplied with the evaluation matrix of the current supervision model to obtain the evaluation value of the current supervision model, which can then be used to evaluate the current supervision model.

[0136] In this embodiment of the invention, after obtaining the evaluation value of the current supervision model, it can be compared with the evaluation threshold to determine the quality of the current supervision model. Specifically, the evaluation steps can be as follows: Figure 7 As shown. Specifically, in Figure 7 In addition, the evaluation method may also include:

[0137] In step S150, it is determined whether the evaluation value of the current supervision model is less than or equal to the evaluation threshold.

[0138] In step S151, if the evaluation value of the current supervision model is less than or equal to the evaluation threshold, the supervision quality of the current supervision model is determined to be good. Specifically, if the evaluation value of the current supervision model is less than or equal to the evaluation threshold, it indicates that the output error of the current supervision model is small, meaning the supervision quality is good.

[0139] In step S152, if the evaluation value of the current supervision model is greater than the evaluation threshold, the supervision quality of the current supervision model is determined to be poor. Specifically, if the evaluation value of the current supervision model is greater than the evaluation threshold, it indicates that the output error of the current supervision model is large, meaning the supervision quality is poor.

[0140] In steps S150 to S152, the evaluation value of the current supervision model is compared with the evaluation threshold. If the evaluation value is less than or equal to the evaluation threshold, it indicates that the output error of the current supervision model is small and the supervision quality / effect of the supervision model is good. Otherwise, the supervision quality / effect is poor.

[0141] On the other hand, the present invention also provides a computer-readable storage medium storing instructions for being read by a machine to cause the machine to perform any of the evaluation methods described above.

[0142] Through the above technical solution, the digital supervision quality evaluation method and storage medium based on big data model provided by this invention obtains the error time series characteristics of the current supervision model through the output time series characteristics and the real time series characteristics of the current supervision model. Combined with the evaluation level of the constructed supervision model, the evaluation matrix of the current supervision model can be obtained. According to the evaluation matrix, the evaluation value of the supervision model can be obtained, and then the evaluation value can be used to evaluate the current supervision model. By adopting this method of quantifying the error time series characteristics of the supervision model into specific evaluation values, effective evaluation of the supervision model can be achieved, that is, effective supervision, thereby ensuring the reliability and accuracy of power grid system supervision.

[0143] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0145] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0146] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0147] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0148] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0149] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0150] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0151] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. An evaluation method for digital supervision quality based on a big data model, characterized in that, The method comprises the following steps: constructing an evaluation level of a supervision model; obtaining an output time sequence feature and a real time sequence feature of a current supervision model; obtaining an error time sequence feature of the current supervision model according to the output time sequence feature and the real time sequence feature of the current supervision model; obtaining an evaluation matrix according to the error time sequence feature and the evaluation level; obtaining an evaluation value of the current supervision model according to the evaluation matrix; evaluating the quality of the current supervision model according to the evaluation value of the current supervision model. The step of constructing an evaluation level of a supervision model comprises the following steps: obtaining a plurality of historical output time sequence features and corresponding historical real time sequence features of the supervision model; obtaining a historical error time sequence feature according to the historical output time sequence feature and the historical real time sequence feature; obtaining a mean value, a maximum value and a minimum value of the historical error time sequence feature; dividing the evaluation level of the supervision model according to the mean value, the maximum value and the minimum value of the historical error time sequence feature; obtaining a historical error time sequence feature according to the historical output time sequence feature and the historical real time sequence feature comprises the following steps: obtaining the historical error time sequence feature according to formula (1), ，（1） in, For the first The aforementioned historical error time series features The value at time, For the first The aforementioned historical output time-series features The value at time, For the first The aforementioned historical time sequence characteristics The value at time, Numbered by integer. For a specific moment; dividing the evaluation level of the supervision model according to the mean value, the maximum value and the minimum value of the historical error time sequence feature comprises the following steps: obtaining a level base value of the historical error time sequence feature according to formula (2), ，（2） wherein, is a level base value for the history error temporal feature, is a maximum value for the history error temporal feature, is a minimum value for the history error temporal feature, is an interval base value; obtaining a level value of the historical error time sequence feature according to formula (3), ，（3） wherein, is a rank value of the historical error temporal feature, is a rank serial number of the historical error temporal feature, , is a mean value of the historical error temporal feature; determining whether there is an error time sequence feature between the level value of the current historical error time sequence feature and its adjacent maximum value or minimum value; in the case that there is an error time sequence feature between the level value of the current historical error time sequence feature and its adjacent maximum value or minimum value, obtaining the level value of the current historical error time sequence feature; in the case that there is no error time sequence feature between the level value of the current historical error time sequence feature and its adjacent maximum value or minimum value, updating the interval base value according to formula (4), ，（4） wherein is a base value; returning to the step of obtaining the level base value of the historical error time sequence feature according to formula (2).

2. The evaluation method according to claim 1, characterized by obtaining an error time sequence feature of the current supervision model according to the output time sequence feature and the real time sequence feature of the current supervision model comprises the following steps: obtaining the error time sequence feature of the current supervision model according to formula (5), ，（5） wherein, is a value of an error time series characteristic of the current supervisory model at time is a value of an output time series characteristic of the current supervisory model at time is a value of a true time series characteristic of the current supervisory model at time is a value of an error time series characteristic of the current supervisory model at time is a value of an output time series characteristic of the current supervisory model at time is a value of a true time series characteristic of the current supervisory model at time 3. The evaluation method according to claim 2, characterized by, obtaining an evaluation matrix according to the error time sequence feature and the evaluation level comprises the following steps: dividing the error time sequence feature of the current supervision model according to the evaluation level; obtaining an evaluation probability of the error time sequence feature of the current supervision model in each level according to formula (6), ，（6） in, The error time series characteristics of the current supervision model at the level The probability of evaluation at that time It is a grade range, and , The error time series characteristics of the current supervision model at the level Time End time of the segment The error time series characteristics of the current supervision model at the level Time The start time of the segment Numbered by integer. Numbered by integer. The error time series characteristics of the current supervision model at the level Total number of segments, This represents the total duration of the error time-series characteristics of the current supervision model; obtaining the evaluation matrix of the current supervision model according to the evaluation probability of the error time sequence feature of the current supervision model in each level.

4. The evaluation method according to claim 3, characterized by obtaining an evaluation value of the current supervision model according to the evaluation matrix comprises the following steps: obtaining a decision value of the current supervision model in each level and constructing a decision matrix; obtaining the evaluation value of the current supervision model according to formula (7), ，（7） wherein, is an evaluation value of the current supervision model, is an evaluation matrix of the current supervision model, is the decision matrix.

5. The evaluation method according to claim 4, characterized by obtaining a decision value of the current supervision model in each level comprises the following steps: randomizing the decision value of the current supervision model in each level and constructing an initial population; According to formula (8), the fitness value of each individual in the population is obtained, ，（8） in, The fitness value is... The number of levels in the supervision model, and , The error time series characteristics of the supervision model at the level The decision value at that time, Historical error time series characteristics at the level The evaluation probability at that time, the historical error time series characteristics at the level The evaluation probability at that time includes time-series characteristics where the output value of the supervision model differs little from the actual value; According to the fitness value, the optimal individual in the population is selected; According to the optimal individual, the remaining individuals in the population are iterated; Determine whether the iteration number of the current population is greater than or equal to the iteration number threshold value; In the case where the iteration number of the current population is greater than or equal to the iteration number threshold value, the optimal solution of the decision value of the current supervision model is outputted; In the case where the iteration number of the current population is less than the iteration number threshold value, the step of obtaining the fitness value of each individual in the population according to formula (8) is returned.

6. The evaluation method according to claim 1, characterized by According to the evaluation value of the current supervision model, the quality of the current supervision model is evaluated, including: Determine whether the evaluation value of the current supervision model is less than or equal to the evaluation threshold value; In the case where the evaluation value of the current supervision model is less than or equal to the evaluation threshold value, it is determined that the supervision quality of the current supervision model is good; In the case where the evaluation value of the current supervision model is greater than the evaluation threshold value, it is determined that the supervision quality of the current supervision model is poor.

7. A computer-readable storage medium, characterized in that, The computer readable storage medium stores instructions for being read by a machine to make the machine execute the evaluation method of any one of claims 1-6.

Images