Effective mining method and device for distribution network terminal side data

Abstract

The present invention discloses an effective method and device for mining data on the distribution network end side, the method comprising: obtaining a user data set on the distribution network end side; determining the distribution network end side data information corresponding to each element in the user data set; performing weight distribution according to the distribution network end side data information to obtain data attribute values ​​of users on the distribution network end side; determining a transmission method for user data on the distribution network end side according to the data attribute values ​​of users on the distribution network end side; and obtaining the total delay and total energy consumption of user data on the distribution network end side based on the transmission method of user data on the distribution network end side. The present invention cleans, classifies and fuses the user data on the distribution network end side to obtain data attribute values, and uses the values ​​to determine the transmission direction of the data to determine the transmission scheme for the user data on the distribution network end side, thereby reducing transmission delay and transmission energy consumption, and alleviating transmission and storage pressure on the cloud, and has high application value.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network planning, and in particular to an effective method and device for mining distribution network terminal-side data. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. No statement herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] In the early 20th century, data collection on the distribution network's edge was relatively simple, providing only data support for basic tasks such as grid dispatching, maintenance, and planning. Since the beginning of the 21st century, however, grid infrastructure has become increasingly sophisticated. With the widespread integration of numerous monitoring devices, electric vehicle charging stations, and new energy sources, the demand for data collection and analysis on the distribution network's edge has become more stringent.

[0004] Currently, distribution networks utilize a vast number of terminals, collecting enormous amounts of data daily. Cloud computing is a key technology used in power grids. However, this approach presents several drawbacks: limited cloud storage and real-time processing capabilities are lacking. Furthermore, the rapid development of the power distribution Internet of Things (PoI) is driving the continuous generation and transmission of massive amounts of diverse and heterogeneous user data on the end-user side. This data is rapidly updated, diverse, of poor quality, and has a low value density, necessitating urgent exploration. These factors are hindering the development of the power distribution Internet of Things (PoI). Summary of the Invention

[0005] An embodiment of the present invention provides an effective method for mining data on the terminal side of a distribution network to improve the distribution network construction process of the power Internet of Things. The method includes:

[0006] Acquire a user data set on the distribution network end side, where each element in the user data set represents an amount of data generated by a corresponding user on the distribution network end side;

[0007] Determine the distribution network side data information corresponding to each element in the user data set;

[0008] According to the data information on the distribution network side, weights are allocated to obtain the data attribute values ​​of the users on the distribution network side;

[0009] Determining a transmission mode of the distribution network end-side user data according to the data attribute value of the distribution network end-side user;

[0010] Based on the transmission mode of the distribution network end-side user data, the total delay and the total energy consumption of the distribution network end-side user data are obtained.

[0011] An embodiment of the present invention further provides an effective mining device for distribution network terminal-side data, which is used to improve the distribution network construction process of the power Internet of Things. The device includes:

[0012] A data acquisition module is used to acquire a user data set at the distribution network end side, where each element in the user data set represents the amount of data generated by the corresponding distribution network end side user;

[0013] A data information determination module is used to determine the distribution network side data information corresponding to each element in the user data set;

[0014] A data attribute value determination module is used to assign weights based on the data information on the distribution network end side to obtain the data attribute values ​​of the users on the distribution network end side;

[0015] A transmission mode determination module, configured to determine a transmission mode for distribution network end-side user data according to a data attribute value of the distribution network end-side user;

[0016] The time delay and energy consumption determination module is used to obtain the total time delay and total energy consumption of the distribution network end-side user data based on the transmission mode of the distribution network end-side user data.

[0017] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned method for effectively mining distribution network terminal-side data is implemented.

[0018] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program for executing the above-mentioned method for effectively mining distribution network terminal-side data.

[0019] In an embodiment of the present invention, a user data set on the distribution network end side is obtained; the distribution network end side data information corresponding to each element in the user data set is determined; weights are assigned based on the distribution network end side data information to obtain data attribute values ​​of users on the distribution network end side; a transmission method for user data on the distribution network end side is determined based on the data attribute values ​​of users on the distribution network end side; and the total delay and total energy consumption of user data on the distribution network end side are obtained based on the transmission method for user data on the distribution network end side. The present invention cleans, classifies, and integrates user data on the distribution network end side, can monitor abnormal data on the distribution network end side, reduce data redundancy, improve the value density of end-side data, optimize the quality of end-side data, and perform threshold comparison and judgment on the processed data attribute values ​​to determine the transmission scheme for user data on the distribution network end side, thereby greatly reducing transmission delay and energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0021] Figure 1 This is a flow chart of an effective method for mining data on the distribution network side according to an embodiment of the present invention. Figure 1 ;

[0022] Figure 2 This is a flow chart of an effective method for mining data on the distribution network side according to an embodiment of the present invention. Figure 2 ;

[0023] Figure 3 This is a flow chart of an effective method for mining data on the distribution network side according to an embodiment of the present invention. Figure 3 ;

[0024] Figure 4 The structure of an effective mining device for distribution network terminal side data in an embodiment of the present invention is shown in FIG. Figure 1 ;

[0025] Figure 5 The structure of an effective mining device for distribution network terminal side data in an embodiment of the present invention is shown in FIG. Figure 2 . DETAILED DESCRIPTION

[0026] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0027] Figure 1 This is a flow chart of an effective method for mining data on the distribution network side according to an embodiment of the present invention. Figure 1 ,like Figure 1 As shown, the method includes:

[0028] Step 102: Acquire a user data set on the distribution network end side, where each element in the user data set represents the amount of data generated by the corresponding distribution network end side user;

[0029] Step 104: Determine the distribution network side data information corresponding to each element in the user data set;

[0030] Step 106: performing weight allocation based on the data information on the distribution network end side to obtain data attribute values ​​of the distribution network end side user;

[0031] Step 108: determining a transmission mode of the distribution network side user data according to the data attribute value of the distribution network side user;

[0032] Step 110: Obtain the total time delay and total energy consumption of the distribution network end-side user data based on the transmission mode of the distribution network end-side user data.

[0033] In the embodiment of the present invention, Figure 1 and 2 As shown, step 102 is to obtain the user data set Ω on the distribution network side from the selected project. N ; where Ω N ={D1,D2,D3...D N-1 ,D N Each element in} represents the amount of data generated by the corresponding end-side user.

[0034] In the embodiment of the present invention, Figure 1 and Figure 2 As shown, the method may further include:

[0035] Ω N The user data set performs a preliminary identification of the elements in the user data set to determine whether there is pre-set special user data. For example, in a large and important event venue, the venue has a direct communication channel with the cloud center. The venue uploads its future event schedule to the cloud center, which accurately predicts its daily load and arranges a power supply plan to ensure the smooth progress of the venue event. If no special user data exists, the process proceeds to step 104.

[0036] In the embodiment of the present invention, Figure 1 and Figure 2 As shown, for any element D∈Ω N , obtain the end-side data information corresponding to the element (the data's real-time attributes, complexity attributes, and energy consumption attributes, that is, the complexity of the data volume, the latency and energy consumption of transmission to the cloud);

[0037] The specific steps 104 are as follows:

[0038] (2-1) Let the number of users on the distribution network side of the selected project be N;

[0039] (2-2) Determine the objective function of the user data complexity model on the distribution network side:

[0040] FuzzyEn(m,r,N)=InΦ m (r)-InΦ m+1 (r);

[0041] Among them, m is the dimension of the reconstructed phase space, r is the similarity tolerance and N is the sequence length, and the function Membership function It is the distance between window vectors after reconstructing the phase space of the original sequence. The phase space dimension m is obtained based on the correlation dimension (fractal dimension).

[0042] (2-3) Using the result of step (2-2), the delay of user data transmission to the cloud is obtained and energy consumption

[0043]

[0044]

[0045]

[0046]

[0047]

[0048]

[0049] The above formulas can be combined into:

[0050]

[0051]

[0052] in, represents the total delay of user data transmission to the cloud, represents the transmission delay of computing tasks offloaded to the cloud, represents the execution delay of computing tasks offloaded to the cloud, represents the total energy consumption transmitted to the cloud, represents the transmission energy consumption offloaded to the cloud, represents the local computing energy consumption in the cloud, c i Indicates the user data corresponding to the i-th distribution network end side The complexity property of represents the amount of data offloaded to the cloud by the end-user, W i c Indicates the bandwidth transmitted to the cloud, snr i c Indicates the signal-to-noise ratio transmitted to the cloud, pc trans represents the transmission power during offloading to the cloud, f i c Indicates the local computing power of the cloud, pl c Indicates the local computing power of the cloud.

[0053] In the embodiment of the present invention, Figure 1 and 2As shown, step 106 is to allocate weights based on the requirements of the distribution network end-side user for the real-time attributes, complexity attributes, and energy consumption attributes of the application data, and obtain the data attribute objective function of the end-side user, which is recorded as Minf:

[0054]

[0055] Wherein, Minf represents the data attribute value of the user at the distribution network end; I C ,I D ,I P They correspond to the weighted distribution values ​​of the complexity attribute, real-time attribute and energy consumption attribute of the user data on the distribution network side, and I C ,I D ,I P Satisfy I C +I D +I P =1,c i , They correspond to the complexity attribute, real-time attribute and energy consumption attribute of the user data on the i-th distribution network side respectively.

[0056] In the embodiment of the present invention, Figure 1 and Figure 2 As shown, step 108 determines a transmission scheme for the user data on the terminal side according to the data attribute value obtained in step 106. The specific steps are as follows:

[0057] (5-1) Compare the data attribute value with the given threshold value. If the value is greater than the upper limit of the given threshold value (i.e., Minf>th max ), the data is judged as emergency data and is directly transmitted from the distribution network end to the cloud for processing. Its delay and energy consumption function model are consistent with the function model of step (2-3). If it does not belong to this type of situation, go to step (5-2);

[0058] (5-2) If the data attribute value is lower than the lower limit of the given threshold (i.e., Minf<th min ), the data is considered invalid and will not be processed and discarded. If it does not belong to this category, go to step (5-3);

[0059] (5-3) If the data attribute value is between the upper and lower limits of the given threshold, it is judged as wide data and is directly uploaded from the distribution network end to the edge end for processing. The transmission delay to the edge end is and energy consumption The constraint function model is:

[0060]

[0061]

[0062] The transmission delay of computing tasks offloaded to edge nodes is:

[0063]

[0064] The transmission energy consumption offloaded to the edge node is:

[0065]

[0066] The execution delay of offloading computing tasks to edge nodes is:

[0067]

[0068] Local computing energy consumption of edge nodes:

[0069]

[0070] The above formulas can be combined into:

[0071]

[0072]

[0073] Where, Indicates the total delay of data transmission from the end side to the edge side. represents the transmission delay of computing tasks offloaded to edge nodes, represents the execution delay of offloading computing tasks to edge nodes, Indicates the total energy consumption of transmitting data from the end side to the edge side. represents the transmission energy consumption offloaded to the edge node, represents the local computing energy consumption of edge nodes, represents the amount of data offloaded to the cloud by the end-users, c i For the corresponding end-side user data The data complexity, W i e Indicates the bandwidth transmitted to the edge node, snr i e Indicates the signal-to-noise ratio transmitted to the edge node, pe trans represents the transmission power during offloading to the edge node, f i e Indicates the local computing power of edge computing, pl e Indicates the local computing power of edge computing.

[0074] In the embodiment of the present invention, Figure 3 As shown, step 110 specifically includes:

[0075] Step 1101: When data is directly transmitted from the distribution network end side to the cloud for processing, determine the total delay and total energy consumption of the data transmitted from the distribution network end side to the cloud side;

[0076] Step 1102: When data is directly uploaded from the distribution network end side to the edge end for processing, determine the total delay and total energy consumption of the data transmitted from the distribution network end side to the edge end;

[0077] Step 1103: Add the total delay and total energy consumption of the distribution network side data transmitted to the cloud, and the total delay and total energy consumption of the distribution network side data transmitted to the edge end, respectively, to obtain the total delay and total energy consumption of the distribution network side user data.

[0078] The total latency of user data on the distribution network side of the project finally selected is:

[0079]

[0080] And the total energy consumption:

[0081]

[0082] The present invention also provides an effective mining device for distribution network end-side data, as described in the following embodiments. Since the principle of solving the problem of this device is similar to the effective mining method for distribution network end-side data, the implementation of this device can refer to the implementation of the effective mining method for distribution network end-side data, and the repeated parts will not be repeated.

[0083] Figure 4 The structure of an effective mining device for distribution network terminal side data in an embodiment of the present invention is shown in FIG. Figure 1 ;like Figure 4 As shown, the device includes:

[0084] Data acquisition module 02, used to acquire a user data set at the distribution network end side, where each element in the user data set represents the amount of data generated by the corresponding distribution network end side user;

[0085] The data information determination module 04 is used to determine the distribution network side data information corresponding to each element in the user data set;

[0086] The data attribute value determination module 06 is used to allocate weights based on the data information on the distribution network end side to obtain the data attribute values ​​of the users on the distribution network end side;

[0087] A transmission mode determination module 08 is configured to determine a transmission mode for the distribution network end-side user data according to the data attribute value of the distribution network end-side user;

[0088] The delay and energy consumption determination module 10 is used to obtain the total delay and total energy consumption of the distribution network end-side user data based on the transmission mode of the distribution network end-side user data.

[0089] In the embodiment of the present invention, Figure 5 As shown, the device also includes: a data processing module 12, which is used to determine whether there is preset special user data in the elements of the user data set. If so, the corresponding elements are transmitted to the cloud for data processing. If not, the distribution network side data information corresponding to each element in the user data set is obtained.

[0090] In the embodiment of the present invention, the transmission mode determination module 08 is specifically configured to:

[0091] If the data attribute value is greater than the upper limit of the given threshold, the corresponding user data on the distribution network side is judged as emergency data and is directly transmitted to the cloud for processing by the distribution network side; if the data attribute value is lower than the lower limit of the given threshold, the corresponding user data on the distribution network side is judged as invalid data, is not processed, and is discarded; if the data attribute value is between the upper and lower limits of the given threshold, the corresponding user data on the distribution network side is judged as wide and data and is directly uploaded to the edge for processing by the distribution network side.

[0092] In this embodiment of the present invention, the delay and energy consumption determination module 10 is specifically configured to:

[0093] When data is transmitted directly from the distribution network end to the cloud for processing, determine the total delay and total energy consumption of the data transmitted from the distribution network end to the cloud;

[0094] When data is directly uploaded from the distribution network end to the edge end for processing, the total delay and total energy consumption of the data transmitted from the distribution network end to the edge end are determined;

[0095] The total delay and total energy consumption of the distribution network end-side data transmitted to the cloud, and the total delay and total energy consumption of the distribution network end-side data transmitted to the edge are added together to obtain the total delay and total energy consumption of the distribution network end-side user data.

[0096] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned method for effectively mining distribution network terminal-side data is implemented.

[0097] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program for executing the above-mentioned method for effectively mining distribution network terminal-side data.

[0098] In an embodiment of the present invention, a user data set on the distribution network end side is obtained; the distribution network end side data information corresponding to each element in the user data set is determined; weights are allocated based on the distribution network end side data information to obtain data attribute values ​​of users on the distribution network end side; a transmission method for user data on the distribution network end side is determined based on the data attribute values ​​of users on the distribution network end side; and the total delay and total energy consumption of user data on the distribution network end side are obtained based on the transmission method for user data on the distribution network end side. The present invention cleans, classifies and integrates user data on the distribution network end side, can monitor abnormal data on the distribution network Internet of Things end side, and reduce data redundancy. The processed data is not only improved in terms of accuracy and effectiveness, but also optimized in terms of data quality. Threshold comparison and discrimination are performed on the processed data attribute values ​​to determine the transmission scheme for user data on the distribution network end side, so that the transmission delay and energy consumption are greatly reduced.

[0099] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] 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 flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts 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, 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 flowcharts and / or block diagrams. 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.

[0101] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0103] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An effective method for mining data on the distribution network side, characterized in that: include: Acquire a user data set on the distribution network end side, where each element in the user data set represents an amount of data generated by a corresponding user on the distribution network end side; Determine the distribution network side data information corresponding to each element in the user data set; the distribution network side data information includes the real-time attributes, complexity attributes, and energy consumption attributes of the data; the real-time attributes, complexity attributes, and energy consumption attributes of the data are the delay of transmission to the cloud, the complexity of the data volume, and the energy consumption of transmission to the cloud; According to the data information on the distribution network side, weights are allocated to obtain the data attribute values ​​of the users on the distribution network side; Determining a transmission mode of the distribution network end-side user data according to the data attribute value of the distribution network end-side user; Obtaining the total time delay and total energy consumption of the distribution network end-side user data based on the transmission mode of the distribution network end-side user data; The transmission mode of the user data on the distribution network end side is determined according to the data attribute value of the user on the distribution network end side, including: if the data attribute value is greater than the upper limit of a given threshold, the corresponding user data on the distribution network end side is judged as emergency data and is directly transmitted to the cloud for processing by the distribution network end side; if the data attribute value is lower than the lower limit of the given threshold, the corresponding user data on the distribution network end side is judged as invalid data, is not processed, and is discarded; if the data attribute value is between the upper limit and the lower limit of the given threshold, the corresponding user data on the distribution network end side is judged as wide and data, and is directly uploaded to the edge end for processing by the distribution network end side.

2. The method for effectively mining distribution network terminal side data according to claim 1, characterized in that: Also includes: Determine whether there is preset special user data for the elements in the user data set. If so, transmit the corresponding elements to the cloud for data processing. If not, obtain the distribution network side data information corresponding to each element in the user data set.

3. The method for effectively mining distribution network terminal side data according to claim 1, characterized in that: The complexity attribute is calculated as follows: FuzzyEn(m,r,N)=InΦ m (r)-InΦ m+1 (r); Among them, FuzzyEn(,,) represents the complexity attribute of the data; m is the dimension of the reconstructed phase space; r is the similarity tolerance; N is the sequence length, i, j = 1, 2, ..., N; function Membership function is the distance between window vectors after reconstructing the phase space of the original sequence.

4. The method for effectively mining distribution network terminal side data according to claim 1, characterized in that: The real-time attributes and energy consumption attributes are calculated as follows: in, represents the total delay of user data transmission to the cloud, represents the transmission delay of computing tasks offloaded to the cloud, represents the execution delay of computing tasks offloaded to the cloud, represents the total energy consumption transmitted to the cloud, represents the transmission energy consumption offloaded to the cloud, represents the local computing energy consumption in the cloud, c i Indicates the user data corresponding to the i-th distribution network end side The complexity property of represents the amount of data offloaded to the cloud by the end-user, W i c Indicates the bandwidth transmitted to the cloud. Indicates the signal-to-noise ratio transmitted to the cloud, pc trans represents the transmission power during offloading to the cloud, f i c Indicates the local computing power of the cloud, pl c Indicates the local computing power of the cloud.

5. The method for effectively mining distribution network terminal side data according to claim 1, characterized in that: The following formula is used to assign weights based on the data information on the distribution network side to obtain the data attribute values ​​of the users on the distribution network side: Among them, Minf represents the data attribute value of the user at the distribution network end; I C ,I D ,I P They correspond to the weighted distribution values ​​of the complexity attribute, real-time attribute and energy consumption attribute of the user data on the distribution network side, and I C ,I D ,I P Satisfy I C +I D +I P =1, They correspond to the complexity attribute, real-time attribute and energy consumption attribute of the user data on the i-th distribution network side respectively.

6. The method for effectively mining distribution network terminal side data according to claim 1, characterized in that: Obtaining the total time delay and total energy consumption of the distribution network end-side user data based on the transmission mode of the distribution network end-side user data includes: When data is transmitted directly from the distribution network end to the cloud for processing, determine the total delay and total energy consumption of the data transmitted from the distribution network end to the cloud; When data is directly uploaded from the distribution network end to the edge end for processing, the total delay and total energy consumption of the data transmitted from the distribution network end to the edge end are determined; The total delay and total energy consumption of the distribution network end-side data transmitted to the cloud, and the total delay and total energy consumption of the distribution network end-side data transmitted to the edge are added together to obtain the total delay and total energy consumption of the distribution network end-side user data.

7. The method for effectively mining distribution network terminal side data according to claim 1, characterized in that: The total delay and total energy consumption of data transmitted from the distribution network end to the edge end are determined by the following formula: The transmission delay of computing tasks offloaded to edge nodes is: The transmission energy consumption offloaded to the edge node is: The execution delay of offloading computing tasks to edge nodes is: Local computing energy consumption of edge nodes: in, Indicates the total delay of data transmission from the end side to the edge side. represents the transmission delay of computing tasks offloaded to edge nodes, represents the execution delay of offloading computing tasks to edge nodes, Indicates the total energy consumption of transmitting data from the end side to the edge side. represents the transmission energy consumption offloaded to the edge node, represents the local computing energy consumption of edge nodes, c i Indicates the amount of user data corresponding to the i-th distribution network end side The complexity property of represents the amount of data offloaded to the edge node, W i e Indicates the bandwidth transmitted to the edge node, snr i e Indicates the signal-to-noise ratio transmitted to the edge node, pe trans represents the transmission power during offloading to the edge node, f i e Indicates the local computing power of edge computing, pl e Indicates the local computing power of edge computing.

8. The method for effectively mining data on the distribution network side according to claim 1, characterized in that: The total time delay and total energy consumption of the user data on the distribution network side are obtained based on the transmission mode of the user data on the distribution network side according to the following formula: Among them, t total is the total delay, e total is the total energy consumption; represents the total latency of transmission to the cloud, Indicates the total delay of data transmission from the end side to the edge side. represents the total energy consumption transmitted to the cloud, Indicates the total energy consumption of transmitting data from the device side to the edge side.

9. An effective mining device for distribution network terminal side data, characterized in that: include: A data acquisition module is used to acquire a user data set at the distribution network end side, where each element in the user data set represents the amount of data generated by the corresponding distribution network end side user; A data information determination module is configured to determine the distribution network-side data information corresponding to each element in the user data set; the distribution network-side data information includes the real-time attributes, complexity attributes, and energy consumption attributes of the data; the real-time attributes, complexity attributes, and energy consumption attributes of the data are the delay in transmission to the cloud, the complexity of the data volume, and the energy consumption of transmission to the cloud; A data attribute value determination module is used to assign weights based on the data information on the distribution network end side to obtain the data attribute values ​​of the users on the distribution network end side; A transmission mode determination module, configured to determine a transmission mode for distribution network end-side user data according to a data attribute value of the distribution network end-side user; A time delay and energy consumption determination module, configured to obtain a total time delay and a total energy consumption of the distribution network end-side user data based on a transmission mode of the distribution network end-side user data; The transmission mode determination module is specifically used to: if the data attribute value is greater than the upper limit of a given threshold, the corresponding user data on the distribution network side is judged as emergency data and is directly transmitted to the cloud for processing by the distribution network side; if the data attribute value is lower than the lower limit of a given threshold, the corresponding user data on the distribution network side is judged as invalid data, is not processed, and is discarded; if the data attribute value is between the upper and lower limits of a given threshold, the corresponding user data on the distribution network side is judged as wide and data and is directly uploaded to the edge for processing by the distribution network side.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program for executing the method according to any one of claims 1 to 8.

Images