A fast and accurate calculation method for edge-cloud collaborative distribution network data

Abstract

The present invention discloses a method for quickly and accurately calculating distribution network data in an edge-cloud collaborative manner, which belongs to the field of distribution network management and edge computing technology. The method comprises: obtaining distribution network operation data of different dimensions in different substations of the distribution network, and inputting the data of each substation in historical time into a distribution network data substation differentiated attention network constructed by a cloud server to obtain the attention weight of each dimension of data in each substation; pre-analyzing the substation operation status according to the attention weight and the substation data in the previous observation time window, and obtaining the probability of each substation being in multiple operation statuses; adjusting the calculation position of the data according to the development trend of the substation operation status obtained in the above steps, and performing edge-cloud collaborative calculation and deployment of distribution network data based on the operation status perception results to achieve dynamic optimization of the data calculation position.

Description

Technical Field

[0001] The present invention belongs to the field of distribution network management and edge computing technology, and specifically relates to a method for quickly and accurately calculating edge-cloud collaborative distribution network data. Background Art

[0002] With the massive and high-proportion distributed renewable energy, distributed energy storage, and controllable flexible loads connected to the low-voltage distribution network, the structure and operation of the distribution network are becoming increasingly complex. On the one hand, a large number of monitoring devices are deployed in the distribution network to collect a large amount of multi-dimensional distribution network operation data such as current, voltage, load data, and equipment operation status. The distribution network is the last key link in power distribution. In order to support its safe and stable operation and ensure a stable energy supply, it is crucial to calculate the distribution network data quickly and accurately. On the other hand, due to the different operating equipment, user power consumption, area topology, power distribution and other factors in different areas, different dimensions of data in different areas have differentiated computing requirements. Analyzing the operating status of different areas can assist decision-making, optimize power distribution, and improve power supply reliability and safety. Therefore, in order to ensure efficient calculation of distribution network data, it is particularly important to analyze the operating status of each area of ​​the distribution network.

[0003] The edge-cloud collaborative architecture can effectively solve the data calculation problem of the distribution network. However, the existing methods do not consider the differentiated needs of different dimensions of data in different substations, and the accuracy of substation operation status analysis is low, which cannot meet the differentiated calculation needs of different dimensions of data in different substations of the distribution network. In addition, the existing edge-cloud collaborative calculation method of distribution network data does not consider the dynamic optimization of data calculation location according to the substation operation status, which is not suitable for complex and changeable distribution network substation scenarios and has high calculation latency. Therefore, it is urgent to design a fast and accurate calculation method for edge-cloud collaborative distribution network data. Summary of the invention

[0004] In order to solve the technical problems existing in the background technology, the present invention aims to provide a method for quickly and accurately calculating edge-cloud collaborative distribution network data.

[0005] In order to solve the technical problem, the technical solution of the present invention is:

[0006] A method for quickly and accurately calculating edge-cloud collaborative distribution network data, the method comprising:

[0007] Obtain the distribution network operation data of different dimensions in different areas of the distribution network, and input the data of each area in historical time into the distribution network data area differentiated attention network constructed by the cloud server to obtain the attention weight of each dimension of data in each area;

[0008] Pre-analyze the operation status of the substation according to the attention weight and the substation data in the previous observation time window, and obtain the probability of each substation being in multiple operation statuses;

[0009] According to the development trend of the substation operation status obtained in the above steps, the data calculation location is adjusted, and the distribution network data edge-cloud collaborative computing and deployment are carried out based on the operation status perception results to achieve dynamic optimization of the data calculation location.

[0010] Furthermore, the attention weight of each dimension of data in each area is obtained, specifically including:

[0011] Considering the discrete time window model, after each observation time window, the differentiated attention network based on the edge server obtains the attention weight and performs the operation status analysis of the substation area;

[0012] A total of T observation time windows are considered, and the set is expressed as Where t represents the tth observation time window, and the length of each observation time window is fixed to τ; a total of N stations are considered, and the set is expressed as Where n represents the nth substation. In each observation time window, each substation collects a total of M-dimensional distribution network operation data. The distribution network operation data set collected by the nth substation in the tth observation time window is expressed as where d n,m (t) represents the m-th dimension of distribution network operation data collected by the n-th substation in the t-th observation time window;

[0013] Input the data of each area in the past T0 observation time window to obtain the attention weight of each dimension of each area. The attention weight set of each dimension of the nth area in the tth observation time window is expressed as where w n,m (t) represents the attention weight of the m-th dimension distribution network operation data collected by the n-th substation in the t-th observation time window. The weight acquisition process of the n-th substation is expressed as:

[0014]

[0015] Among them, θ is the differential attention network parameter of the cloud server, f c [·] represents the differential attention network output function of the edge server.

[0016] Furthermore, the pre-analysis of the operation status of the substation based on the attention weight specifically includes:

[0017] A total of I substation operation situations are considered, and the set is represented by {1,...,i,...,I}, where i represents the operation situation of the i-th substation. After obtaining the attention weights of each dimension of the data in each substation, the operation situation of the substation in the current observation time window is pre-analyzed according to the attention weights of the data in each dimension of the substation in the current observation time window and the substation data in the previous observation time window. After the rough analysis, fine calculation and optimization are performed. The pre-analysis result of the operation situation of the n-th substation is expressed as:

[0018]

[0019] in, is the set of operation status of the nth substation in the tth observation time window obtained by pre-analysis, where p n,i (t) represents the probability that the nth substation is in the ith operating state in the tth observation time window, f o [·] represents the pre-analysis mapping function of the substation operation status.

[0020] Furthermore, the results of the area operation situation awareness analysis are carried out, including:

[0021] Assume that the operating status of the first I0 substations is normal, and the set is represented by {1,...,i,...,I0}, and the substation operating status is deteriorated as {I0+1,...,i,...,I}. According to the probability that the nth substation is the i-th operating status, the normal probability and deterioration probability of the operating status of the nth substation in the t-th observation time window can be calculated as follows:

[0022]

[0023]

[0024] Among them, a n (t) and b n (t) are the normal probability and deterioration probability of the operation status of the nth substation, and a n (t)+b n (t) = 1;

[0025] Considering the high uncertainty of the situation, the difference S of the operation situation of the nth substation in the tth observation time window is calculated. n (t), the closer the uncertainty is to 1, the higher the uncertainty of the operation situation; if the difference is greater than 1, it means that the probability of normal operation situation in the substation is higher than the probability of deterioration, which means that there is a high probability that the operation situation is good; if the difference is less than 1, it means that the probability of deterioration of the operation situation in the substation is higher than the normal probability, which means that there is a high probability that the operation situation is deteriorating:

[0026]

[0027] Furthermore, based on the results of operation situation awareness, the edge-cloud collaborative computing and deployment of distribution network data are carried out, including:

[0028] A total of k data calculation location allocation schemes are considered, and the set is represented by {1,...,k,...,5}, where k represents the kth data calculation location allocation scheme;

[0029] After obtaining the operation status of the substation, the deployment plan of the location is calculated according to the analysis of the results of the operation status perception of the substation, which is expressed as:

[0030]

[0031] Among them, σ>0 is a constant near 0, which is responsible for adjusting the size of the uncertainty interval, σ1 and σ2 are the normal threshold and deterioration threshold of the operating status respectively, σ1>1+σ,1-σ>σ2>0.

[0032] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements any one of the above-mentioned methods for quickly and accurately calculating edge-cloud collaborative distribution network data.

[0033] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any one of the above-mentioned methods for quickly and accurately calculating edge-cloud collaborative distribution network data.

[0034] Compared with the prior art, the advantages of the present invention are:

[0035] 1. The beneficial effect of the present invention is that it provides a method for analyzing the operation status of a substation based on differentiated attention, which can more accurately analyze the differentiated operation status of different substations in the distribution network and improve the accuracy of the analysis of the operation status of the distribution network. First, the distribution network operation data of different dimensions in different substations of the distribution network are obtained, and the data of each substation in the past certain period of time is input into the distribution network data substation differentiated attention network constructed by the cloud server to obtain the attention weight of each dimension of the data in each substation. Secondly, the substation operation status is pre-analyzed according to the attention weight and the substation data in the previous observation time window, and the probability of each substation being in a variety of operation statuses is obtained, which can more comprehensively consider the different operation statuses of different substations, and further improve the accuracy and reliability of the analysis of the operation status of different substations in the distribution network.

[0036] 2. The beneficial effect of the present invention is that it provides a method for collaborative edge-cloud computing of distribution network data based on operating situation awareness. First, the acquired operating situation awareness results of the distribution network substation are analyzed, the normal probability and deterioration probability of the substation operating situation are calculated, and the difference degree is introduced to reflect the uncertainty of the trend change of the substation operating situation. Secondly, the data calculation position is dynamically optimized based on the changing trend of the substation operating situation. When the operating situation change trend is the best, the calculation is only performed on the edge; when the operating situation change trend is the worst, the calculation is only performed on the cloud; in other cases, the edge and cloud are calculated simultaneously, so that the data calculation position can better match the actual substation operating status, and can effectively reduce the data calculation delay, thereby realizing the fast and accurate calculation of distribution network data. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 , flow chart of the method for fast and accurate calculation of edge-cloud collaborative distribution network data. DETAILED DESCRIPTION

[0038] The specific implementation mode of the present invention is described below in conjunction with embodiments:

[0039] It should be noted that the structures, proportions, sizes, etc. shown in this specification are only used to match the contents disclosed in the specification so that people familiar with this technology can understand and read them, and are not used to limit the conditions under which the present invention can be implemented. Any structural modification, change in proportional relationship or adjustment of size should still fall within the scope of the technical content disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0040] At the same time, the terms such as "upper", "lower", "left", "right", "middle" and "one" cited in this specification are only for the convenience of description and are not used to limit the scope of implementation of the present invention. Changes or adjustments to their relative relationships should be regarded as the scope of implementation of the present invention without substantially changing the technical content.

[0041] Embodiment 1:

[0042] The present invention proposes a method for fast and accurate calculation of edge-cloud collaborative distribution network data. The method flow is as follows: Figure 1 As shown in the figure, it includes two parts: a substation operation situation analysis method based on differentiated attention and a distribution network data edge-cloud collaborative computing method based on operation situation awareness. The specific steps are described as follows:

[0043] 1. Analysis method of substation operation status based on differentiated attention

[0044] In order to accurately and efficiently process the key data of the distribution network, a differentiated attention network for distribution areas is constructed on the cloud server and deployed to the edge servers of each area to obtain the attention weight of the data of each area, and the operation status of the area is preliminarily analyzed based on the attention weight. The area operation status analysis method based on differentiated attention can be specifically divided into the following steps:

[0045] S1: Obtaining the attention weight of each dimension of data in each area

[0046] The proposed method considers a discrete time window model. After each observation time window, the attention weight is obtained based on the differentiated attention network of the edge server, and the operation status analysis of the substation is performed. A total of T observation time windows are considered, and the set is expressed as Where t represents the tth observation time window, and the length of each observation time window is fixed to τ. A total of N stations are considered, and the set is expressed as Where n represents the nth substation. In each observation time window, each substation collects a total of M-dimensional distribution network operation data. The distribution network operation data set collected by the nth substation in the tth observation time window is expressed as where d n,m (t) represents the m-th dimension distribution network operation data collected by the n-th substation in the t-th observation time window.

[0047] Input the data of each area in the past T0 observation time window to obtain the attention weight of each dimension of each area. The attention weight set of each dimension of the nth area in the tth observation time window is expressed as where w n,m (t) represents the attention weight of the m-th dimension distribution network operation data collected by the n-th substation in the t-th observation time window. The weight acquisition process of the n-th substation is expressed as:

[0048]

[0049] Among them, θ is the differential attention network parameter of the cloud server, f c [·] represents the differential attention network output function of the edge server.

[0050] S2: Pre-analysis of the operation status of the substation based on attention weight

[0051] A total of I substation operation situations are considered, and the set is represented as {1,...,i,...,I}, where i represents the operation situation of the i-th substation. After obtaining the attention weights of each dimension of the data in each substation, the operation situation of the substation in the current observation time window is pre-analyzed according to the attention weights of the data in each dimension of the substation in the current observation time window and the substation data in the previous observation time window. After the rough analysis, fine calculation and optimization are performed. The pre-analysis result of the operation situation of the n-th substation is expressed as:

[0052]

[0053] in, is the set of operation status of the nth substation in the tth observation time window obtained by pre-analysis, where p n,i (t) represents the probability that the nth substation is in the ith operating state in the tth observation time window, f o [·] represents the pre-analysis mapping function of the substation operation status.

[0054] 2. Distribution network data edge-cloud collaborative computing method based on operation situation awareness

[0055] According to the development trend of the substation operation status obtained in the above steps, the calculation location of the data is adjusted, and the edge-cloud collaborative calculation and deployment of distribution network data are carried out based on the operation status perception results to achieve dynamic optimization of the data calculation location. It can be specifically divided into the following steps:

[0056] S1: Analysis of the results of the awareness of the substation operation situation

[0057] Assume that the first I0 substations are in normal operation, and the set is represented by {1,...,i,...,I0}, and the substations in which the operation situation is deteriorating are represented by {I0+1,...,i,...,I}. Based on the obtained probability that the nth substation is in the i-th operation situation, the normal probability and deterioration probability of the operation situation of the nth substation in the t-th observation time window can be calculated respectively.

[0058]

[0059]

[0060] Among them, a n (t) and b n (t) are the normal probability and deterioration probability of the operation status of the nth substation, and a n (t)+b n (t)=1.

[0061] Considering the high uncertainty of the situation, the difference S of the operation situation of the nth substation in the tth observation time window is calculated. n (t). The closer the uncertainty is to 1, the higher the uncertainty of the operation situation; if the difference is greater than 1, it means that the probability of normal operation situation in the substation is higher than the probability of deterioration, which means that there is a high probability that the operation situation is good; if the difference is less than 1, it means that the probability of deterioration of the operation situation in the substation is higher than the normal probability, which means that there is a high probability that the operation situation will deteriorate.

[0062]

[0063] S2: Edge-cloud collaborative computing and deployment of distribution network data based on operational situation awareness results

[0064] A total of 5 data calculation location allocation schemes are considered, and the set is represented as {1,...,k,...,5}, where k represents the kth data calculation location allocation scheme. The details of each data calculation location allocation scheme are shown in Table 1.

[0065] Table 1 Data calculation and deployment plan

[0066]

[0067]

[0068] After obtaining the operation status of the substation, the deployment plan of the location is calculated according to the analysis of the results of the operation status perception of the substation, which is expressed as:

[0069]

[0070] Among them, σ>0 is a constant near 0, which is responsible for adjusting the size of the uncertainty interval, σ1 and σ2 are the normal threshold and deterioration threshold of the operating status respectively, σ1>1+σ,1-σ>σ2>0.

[0071] It can be understood that the method of substation operation status analysis based on differentiated attention aims to improve the accuracy and reliability of the operation status analysis of different substations in the distribution network, thereby improving the efficiency of distribution network data calculation. The distribution network operation data of different dimensions of different substations in the distribution network in the past certain period of time are input into the distribution network data substation differentiated attention network constructed by the cloud server to obtain the attention weight of each dimension of data in each substation, and further pre-analyze the substation operation status based on the attention weight and the substation data in the previous observation time window to obtain the probability of each substation being in multiple operation statuses, which can accurately analyze the changes in different operation statuses of different substations and optimize the calculation strategy of distribution network data.

[0072] It can be understood that the edge-cloud collaborative computing method for distribution network data based on operating situation awareness is aimed at reducing the data computing delay and improving the data computing capability of the distribution network. First, the obtained operating situation awareness results of the distribution network substation are analyzed, the normal probability and deterioration probability of the substation operating situation are calculated, and the difference degree is introduced to reflect the uncertainty of the trend change of the substation operating situation. Secondly, the data calculation position is dynamically optimized based on the substation operating situation, and the data calculation position of each substation is adaptively adjusted based on the results of the substation operating situation awareness, so that the data calculation position can better match the actual substation operating status, which can effectively reduce the data calculation delay, and thus realize the fast and accurate calculation of distribution network data.

[0073] Embodiment 2:

[0074] This embodiment provides a terminal device, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of a method for fast and accurate calculation of edge-cloud collaborative distribution network data, including the following steps:

[0075] Obtain the distribution network operation data of different dimensions in different areas of the distribution network, and input the data of each area in historical time into the distribution network data area differentiated attention network constructed by the cloud server to obtain the attention weight of each dimension of data in each area;

[0076] Pre-analyze the operation status of the substation according to the attention weight and the substation data in the previous observation time window, and obtain the probability of each substation being in multiple operation statuses;

[0077] According to the development trend of the substation operation status obtained in the above steps, the data calculation location is adjusted, and the distribution network data edge-cloud collaborative computing and deployment are carried out based on the operation status perception results to achieve dynamic optimization of the data calculation location.

[0078] Embodiment 3:

[0079] This embodiment provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understandable that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory.

[0080] One or more instructions stored in a computer-readable storage medium may be loaded and executed by a processor to implement the corresponding steps of a method for quickly and accurately calculating edge-cloud collaborative distribution network data in the above embodiment; one or more instructions in the computer-readable storage medium are loaded and executed by the processor in the following steps:

[0081] Obtain the distribution network operation data of different dimensions in different areas of the distribution network, and input the data of each area in historical time into the distribution network data area differentiated attention network constructed by the cloud server to obtain the attention weight of each dimension of data in each area;

[0082] Pre-analyze the operation status of the substation according to the attention weight and the substation data in the previous observation time window, and obtain the probability of each substation being in multiple operation statuses;

[0083] According to the development trend of the substation operation status obtained in the above steps, the data calculation location is adjusted, and the distribution network data edge-cloud collaborative computing and deployment are carried out based on the operation status perception results to achieve dynamic optimization of the data calculation location.

[0084] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented 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.

[0085] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0086] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0088] The preferred embodiments of the present invention are described in detail above, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in this field without departing from the purpose of the present invention.

[0089] Many other changes and modifications may be made without departing from the concept and scope of the present invention.It should be understood that the present invention is not limited to the specific embodiments, and the scope of the present invention is defined by the appended claims.

Claims

1. A method for fast and accurate calculation of edge-cloud collaborative distribution network data, characterized in that: The method comprises: Obtain the distribution network operation data of different dimensions in different areas of the distribution network, and input the data of each area in historical time into the distribution network data area differentiated attention network constructed by the cloud server to obtain the attention weight of each dimension of data in each area; Pre-analyze the operation status of the substation according to the attention weight and the substation data in the previous observation time window, and obtain the probability of each substation being in multiple operation statuses; According to the development trend of the substation operation situation, the data calculation location is adjusted, and the edge-cloud collaborative calculation and deployment of distribution network data are carried out based on the operation situation perception results to achieve dynamic optimization of the data calculation location; Based on the results of operation situation awareness, the edge-cloud collaborative computing and deployment of distribution network data are carried out, including: A total of k data calculation location allocation schemes are considered, and the set is represented by {1,...,k,...,5}, where k represents the kth data calculation location allocation scheme; After obtaining the operation status of the substation, the deployment plan of the location is calculated according to the analysis of the results of the operation status perception of the substation, which is expressed as: Among them, σ>0 is a constant near 0, which is responsible for adjusting the size of the uncertainty interval, σ1, σ2 are the normal threshold and deterioration threshold of the operating situation respectively, σ1>1+σ,1-σ>σ2>0; The acquisition of attention weights of each dimension of data in each area specifically includes: Considering the discrete time window model, after each observation time window, the differentiated attention network based on the edge server obtains the attention weight and performs the operation status analysis of the substation area; A total of T observation time windows are considered, and the set is expressed as Where t represents the tth observation time window, and the length of each observation time window is fixed to τ; a total of N stations are considered, and the set is expressed as Where n represents the nth substation. In each observation time window, each substation collects a total of M-dimensional distribution network operation data. The distribution network operation data set collected by the nth substation in the tth observation time window is expressed as where d n,m (t) represents the m-th dimension of distribution network operation data collected by the n-th substation in the t-th observation time window; Input the data of each area in the past T0 observation time window to obtain the attention weight of each dimension of each area. The attention weight set of each dimension of the nth area in the tth observation time window is expressed as where w n,m (t) represents the attention weight of the m-th dimension distribution network operation data collected by the n-th substation in the t-th observation time window. The weight acquisition process of the n-th substation is expressed as: Where θ is the differential attention network parameter of the cloud server, fc[ ] represents the differential attention network output function of the edge server; Preliminary analysis of the operation status of the substation area based on attention weight includes: A total of I substation operation situations are considered, and the set is represented by {1,...,i,...,I}, where i represents the operation situation of the i-th substation. After obtaining the attention weights of each dimension of the data in each substation, the operation situation of the substation in the current observation time window is pre-analyzed according to the attention weights of the data in each dimension of the substation in the current observation time window and the substation data in the previous observation time window. After the rough analysis, fine calculation and optimization are performed. The pre-analysis result of the operation situation of the n-th substation is expressed as: in, is the set of operation status of the nth substation in the tth observation time window obtained by pre-analysis, where p n,i (t) represents the probability that the nth substation is in the ith operating state in the tth observation time window, f o [ ] represents the pre-analysis mapping function of the substation operation status; Conduct analysis of the results of the area operation situation awareness, including: Assume that the operating status of the first I0 substations is normal, and the set is represented by {1,...,i,...,I0}, and the substation operating status is deteriorated as {I0+1,...,i,...,I}. According to the probability that the nth substation is the i-th operating status, the normal probability and deterioration probability of the operating status of the nth substation in the t-th observation time window can be calculated as follows: Among them, a n (t) and b n (t) are the normal probability and deterioration probability of the operation status of the nth substation, and a n (t)+b n (t) = 1; Considering the high uncertainty of the situation, the difference S of the operation situation of the nth substation in the tth observation time window is calculated. n (t), the closer the uncertainty is to 1, the higher the uncertainty of the operation situation; if the difference is greater than 1, it means that the probability of normal operation situation in the substation is higher than the probability of deterioration, which means that there is a high probability that the operation situation is good; if the difference is less than 1, it means that the probability of deterioration of the operation situation in the substation is higher than the normal probability, which means that there is a high probability that the operation situation is deteriorating:

2. A computer device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements a method for quickly and accurately calculating edge-cloud collaborative distribution network data as described in claim 1.

3. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method for quickly and accurately calculating edge-cloud collaborative distribution network data as described in claim 1.

Images