Space visualization electric energy management optimization method

Abstract

The invention discloses a spatial visualization electric energy management optimization method, and relates to the technical field of electric energy management, and the method comprises the steps: training a simulation energy consumption prediction model, obtaining a spatial distribution region of all energy distribution paths, dividing the spatial distribution region into a first type of distribution region blocks, inputting the first type of distribution region blocks into a simulation energy consumption prediction model to perform secondary space region division to obtain second type of distribution region blocks, and screening out a first historical ring variation difference value and a second historical ring variation difference value from the counted to-be-tested historical environment data variation difference values, and inputting the historical loop variation difference values I and II and the preprocessed feature data belonging to the second-class distribution region block into a simulation energy consumption prediction model for testing to obtain an actual extra energy consumption value, and performing energy actual demand quantity distribution management on all energy distribution paths. According to the space visualization electric energy management optimization method provided by the invention, the efficiency of electric energy distribution management work can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of electric power energy management, and in particular to a method for optimizing electric power energy management using spatial visualization. Background Art

[0002] Spatial visualization of power energy management is an advanced concept that combines modern information technology, big data analysis and Internet of Things technology. It aims to improve the accuracy and efficiency of power energy management through three-dimensional modeling and data visualization technology.

[0003] In traditional technologies, no further judgment and analysis is made on whether additional energy consumption values ​​are generated between various energy consumption paths in the power energy management process, which leads to large errors in the actual energy demand required for allocation of some related energy consumption paths, reducing the efficiency of power energy management and energy utilization. Summary of the invention

[0004] In order to overcome the above-mentioned deficiencies of the prior art, the present application provides a spatial visualization power energy management optimization method.

[0005] In a first aspect, the present application provides a spatial visualization power energy management optimization method, the method comprising: Obtain all energy distribution paths that require energy distribution optimization management, and count the historical distance change values, historical environmental data change differences, and historical energy consumption values ​​between adjacent paths in all energy distribution paths in the historical period; Extract the historical energy consumption values ​​to be measured that are greater than or equal to the preset energy consumption threshold from the historical energy consumption values, and train a simulation energy consumption prediction model based on the historical environmental data change difference to be measured and the historical distance change value to be measured extracted from the historical distance change value and the historical environmental data change difference; Obtaining the spatial distribution area of ​​all energy distribution paths, dividing the spatial distribution area into first-type distribution area blocks, and inputting the first-type distribution area blocks into a simulation energy consumption prediction model to perform secondary spatial area division to obtain second-type distribution area blocks; Filter out a historical ring variation difference value 1 and a historical ring variation difference value 2 from the historical environmental data variation difference values ​​to be measured; The historical ring variation value 1, the historical ring variation value 2 and the pre-processed characteristic data belonging to the second type of distribution area block are input into the simulation energy consumption prediction model for testing to obtain the actual additional energy consumption value. According to the actual additional energy consumption value, the actual energy demand distribution management of each path is performed on all energy distribution paths, and the energy management optimization result is output.

[0006] Preferably, all energy distribution paths that require energy distribution optimization management are obtained; Count the historical distance change values ​​between adjacent paths in all energy distribution paths in the historical period; According to the historical distance change value, the value of the environmental data after the change in each distance change section in the historical distance change value is counted to obtain the historical change environmental data, and the historical original environmental data in each distance change section in the historical distance change value is counted; The historical environmental data change difference is obtained by performing a one-to-one numerical difference calculation between the historical environmental data change and the historical original environmental data; Obtain the historical original allocated energy values ​​of all energy allocation paths in the historical period; A preset interval time period is used to obtain a historical energy consumption value by counting the change in energy loss value of each path of the historical original allocated energy value after the interval time period.

[0007] Preferably, an energy consumption threshold is preset, and historical energy consumption values ​​to be measured that are greater than or equal to the energy consumption threshold are extracted from the historical energy consumption values; According to the historical energy consumption value to be measured, extract the historical environmental data change difference to be measured between the corresponding adjacent path segments from the historical environmental data change difference, and extract the historical distance change value to be measured between the corresponding adjacent path segments from the historical distance change value; A simulation energy consumption prediction model is trained based on the historical energy consumption values ​​to be measured, the historical environmental data change differences to be measured, and the historical distance change values ​​to be measured.

[0008] Preferably, the spatial distribution areas of all energy distribution paths are obtained, and the spatial distribution areas are divided into area blocks where every two path distribution areas are adjacent or every three path distribution areas are adjacent to obtain a first type of distribution area block; Counting the distance change values ​​between adjacent paths in the first type of distribution area block to obtain the current distance change value to be measured; The current distance change value to be measured and the first type of distribution area block are input into the simulation energy consumption prediction model for testing, so as to divide the first type of distribution area block into a secondary spatial area to obtain a second type of distribution area block.

[0009] Preferably, the pre-processed distance change values ​​belonging to the second type of distribution area block are screened out from the current distance change values ​​to be measured; According to the pre-processed distance change value, obtaining current original environment data between corresponding adjacent path segments in the second type distribution area block; Get the current raw allocated energy values ​​of all energy allocation paths; The current original allocated energy value, the current original environmental data and the pre-processed distance change value are combined into pre-processed characteristic data; A historical ring variation difference value 1 and a historical ring variation difference value 2 are selected from the historical environmental data change differences to be tested, and the differences between the historical original allocated energy values ​​to which the historical ring variation difference value 1 and the historical ring variation difference value 2 respectively belong and the current original allocated energy values ​​are respectively the smallest, and the historical distance change value to be tested of the historical ring variation difference value 1 is the same as the preprocessing distance change value, and the historical original environmental data of the historical ring variation difference value 1 is the same as the current original environmental data, and the historical distance change value to be tested of the historical ring variation difference value 2 is the same as the preprocessing distance change value, and the historical original environmental data of the historical ring variation difference value 2 is the same as the current original environmental data.

[0010] Preferably, the historical ring variation value 1 and the preprocessed characteristic data are input into a simulation energy consumption prediction model for testing to obtain a first additional energy consumption value; Inputting the second historical ring variation value and the preprocessed characteristic data into a simulation energy consumption prediction model for testing to obtain a second additional energy consumption value; averaging the first extra energy consumption value and the second extra energy consumption value to obtain an actual extra energy consumption value; According to the actual additional energy consumption value, the difference compensation is performed on the current original allocated energy value to obtain the actual required energy allocation amount of all energy allocation paths, and energy allocation management is performed on each path of all energy allocation paths to output energy management optimization results.

[0011] The second aspect is the spatial visualization power energy management optimization system, including: The historical data analysis module is used to obtain all energy distribution paths that need to be managed for energy distribution optimization, and to count the historical distance change values ​​between adjacent paths, the historical environmental data change differences, and the historical energy consumption values ​​in all energy distribution paths in the historical period; A model building module is used to extract the historical energy consumption values ​​to be measured that are greater than or equal to the preset energy consumption threshold from the historical energy consumption values, and train a simulation energy consumption prediction model according to the historical environmental data change difference to be measured and the historical distance change value to be measured extracted from the historical distance change value and the historical environmental data change difference; A distribution area division module is used to obtain the spatial distribution area of ​​all energy distribution paths, divide the spatial distribution area into first-class distribution area blocks, and input the first-class distribution area blocks into the simulation energy consumption prediction model to perform secondary spatial area division to obtain second-class distribution area blocks; The actual energy demand analysis module 1 is used to select the historical ring change difference value 1 and the historical ring change difference value 2 from the historical environmental data change difference values ​​to be measured; The actual energy demand analysis module 2 is used to input the historical ring variation value 1, the historical ring variation value 2 and the pre-processed characteristic data belonging to the second type of distribution area block into the simulation energy consumption prediction model for testing to obtain the actual additional energy consumption value. According to the actual additional energy consumption value, the actual energy demand distribution management of each path is performed for all energy distribution paths, and the energy management optimization results are output.

[0012] Compared with the prior art, the present invention has the following characteristics and beneficial effects: By dividing the distribution areas between adjacent paths of all energy distribution paths, it is convenient to make a further judgment and analysis on the additional energy consumption of adjacent paths after the environmental data in the common spatial area changes induced by the energy consumption between adjacent paths. In order to reduce the influence of other interfering characteristic data on the large error of data analysis results, the interfering area blocks of the first type of distribution area blocks initially divided are eliminated, that is, the secondary area blocks are divided. In order to improve the accuracy of the division results, the test division processing is carried out through the established simulation energy consumption prediction model to make full use of the historical data resource information, and the historical data resource information is developed for research analysis to enhance the reliability of the data analysis results. Finally, the additional energy consumption value of the characteristic data information in the second type of distribution area block divided is predicted, and two additional energy consumption values ​​are predicted. Finally, the two predicted additional energy consumption values ​​are comprehensively calculated to reduce the error. Through the above processing method, the rigor of the entire data processing process and the accuracy of the prediction of the energy required for all actual energy distribution paths are improved to further distribute the efficiency of optimization management. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a flowchart of the steps of the spatial visualization power energy management optimization method mainly embodied in this embodiment.

[0014] Figure 2 It is a structural block diagram of the spatial visualization power energy management optimization system mainly embodied in this embodiment. DETAILED DESCRIPTION

[0015] The present invention is further described in detail below in conjunction with the following examples.

[0016] Reference Figure 1 , a spatial visualization power energy management optimization method, the method comprising the following steps: S1. Obtain all energy distribution paths that require energy distribution optimization management, and count the historical distance change values, historical environmental data change differences, and historical energy consumption values ​​between adjacent paths in all energy distribution paths in the historical period.

[0017] S2. Extract the historical energy consumption values ​​to be tested that are greater than or equal to the preset energy consumption threshold from the historical energy consumption values, and train a simulation energy consumption prediction model based on the historical environmental data change differences to be tested and the historical distance change values ​​to be tested extracted from the historical distance change values ​​and the historical environmental data change differences.

[0018] S3. Obtain the spatial distribution areas of all energy distribution paths, divide the spatial distribution areas into first-class distribution area blocks, and input the first-class distribution area blocks into the simulation energy consumption prediction model to perform secondary spatial area division to obtain second-class distribution area blocks.

[0019] S4. Filter out historical ring variation difference value 1 and historical ring variation difference value 2 from the historical environmental data change differences to be measured.

[0020] S5. Input the historical ring variation value 1, the historical ring variation value 2 and the pre-processed characteristic data belonging to the second type of distribution area block into the simulation energy consumption prediction model for testing to obtain the actual additional energy consumption value. According to the actual additional energy consumption value, the actual energy demand distribution management of each path is performed for all energy distribution paths, and the energy management optimization result is output.

[0021] Specifically, by dividing the distribution areas between adjacent paths of all energy distribution paths, it is convenient to make a further judgment and analysis on the additional energy consumption of adjacent paths after the environmental data in the common spatial area changes induced by the energy consumption between adjacent paths. In order to reduce the influence of other interfering characteristic data on the large error of the data analysis results, the interfering area blocks of the first type of distribution area blocks initially divided are eliminated, that is, the secondary area blocks are divided. In order to improve the accuracy of the division results, the test division processing is carried out through the established simulation energy consumption prediction model to make full use of the historical data resource information, and the historical data resource information is developed for research analysis to enhance the reliability of the data analysis results. Finally, the additional energy consumption value of the characteristic data information in the second type of distribution area blocks divided is predicted, and two additional energy consumption values ​​are predicted. Finally, the two predicted additional energy consumption values ​​are comprehensively calculated to reduce the error. Through the above processing method, the rigor of the entire data processing process and the accuracy of the prediction of the energy required for all actual energy distribution paths are improved, so as to further distribute the efficiency of the optimization management work.

[0022] The specific step S1 includes the following sub-steps: Obtain all energy distribution paths that require energy distribution optimization management.

[0023] Statistics are given for the historical distance changes between adjacent paths in all energy distribution paths during the historical period.

[0024] According to the historical distance change value, the numerical value after the environmental data change in each distance change section in the historical distance change value is counted to obtain the historical change environmental data, and the historical original environmental data in each distance change section in the historical distance change value is counted.

[0025] The difference between the historical environmental data changes and the historical original environmental data is calculated one by one to obtain the difference in historical environmental data changes.

[0026] Get the historical raw allocated energy values ​​of all energy allocation paths in the historical period.

[0027] A preset interval time period is used to obtain a historical energy consumption value by counting the change in energy loss values ​​of each path of the historical original allocated energy value after the interval time period.

[0028] Specifically, such as historical distance change values ​​(if two of the paths are used as examples for subsequent explanations: path 1 and path 2, where the distance value change between path 1 and path 2 is 1 meter, 0.5 meter, and 1 meter, then path 1 and path 2 are divided into three sections: a1, a2, and a3, and the distance value change between the two paths in these three sections is 1 meter-0.5 meter-1 meter), historical change environmental data (that is, statistics on the environmental data change status of the common space area (if it is k1, k2, k3) between a1, a2, and a3 of path 1 and path 2 respectively: such as the change status of temperature and humidity values, and it is the value after the change, this changed data value is allocated between path 1 and path 2 A certain energy demand value is reached, and the ambient temperature and humidity values ​​increase or decrease after a period of time), the difference in historical environmental data changes (i.e. the difference in ambient temperature and humidity changes of k1, k2, and k3), a preset interval time period (if it is two hours), and historical energy consumption values ​​(if within these two hours, both path 1 and path 2 cause energy consumption, and induce changes in the ambient temperature and humidity values ​​of k1, k2, and k3, and the degree of change is more obvious, then the energy consumption values ​​in the three sections a1, a2, and a3 in path 1 are counted, and the energy consumption values ​​in the three sections a1, a2, and a3 in path 2 are counted, and the total energy consumption values ​​in the three sections of path 1 and path 2 are summed up, if they are n1, n2, and n3 respectively).

[0029] The specific step S2 includes the following sub-steps: An energy consumption threshold is preset, and historical energy consumption values ​​to be measured that are greater than or equal to the energy consumption threshold are extracted from historical energy consumption values.

[0030] According to the historical energy consumption value to be measured, the historical environmental data change difference to be measured between corresponding adjacent path segments is extracted from the historical environmental data change difference, and the historical distance change value to be measured between corresponding adjacent path segments is extracted from the historical distance change value.

[0031] A simulation energy consumption prediction model is trained based on the historical energy consumption values ​​to be measured, the historical environmental data change differences to be measured, and the historical distance change values ​​to be measured.

[0032] Specifically, such as the preset energy consumption threshold (if it is N), the historical energy consumption value to be measured (extract the energy consumption value greater than or equal to N from n1, n2, and n3. If n2 meets the conditions, then n2 is the historical energy consumption value to be measured), the difference in the change of the historical environmental data to be measured (that is, the segment to which n2 belongs is a2, and the spatial area corresponding to a2 is K2, then the difference in the change of the ambient temperature and humidity within k2 is the difference in the change of the historical environmental data to be measured), the change of the historical distance to be measured (that is, the distance between the a2 segment in path 1 and the a2 segment in path 2 is the change of the historical distance to be measured), and the simulation energy consumption prediction model (such as establishing a column matching table for the three types of characteristic data information, namely the historical energy consumption value to be measured, the difference in the change of the historical environmental data to be measured, and the change of the historical distance to be measured, or performing machine algorithm learning based on these three types of historical characteristic data information, so as to perform data For example, the historical energy consumption value to be measured, the difference value of the change in the historical environmental data to be measured and the change value of the historical distance to be measured in the first historical period are L11, L12 and L13 respectively; the second historical period is L21, L22 and L23; the third historical period is L31, L32 and L33 respectively. Then, the first change trend value between the same data in the first historical period and the second historical period and the second change trend value between the same data in the second historical period and the third historical period are counted. According to the data change trends in the two cases, y=bx is trained, where y is the second change trend value and x is the first change trend value, or Y=A(z+r) is trained, where Y is the historical energy consumption value to be measured, A is the historical original allocated energy value, z is the difference value of the change in the historical environmental data to be measured, and r is the change value of the historical distance to be measured, and the data is substituted for testing and training).

[0033] The specific step S3 includes the following sub-steps: The spatial distribution areas of all energy distribution paths are obtained, and the spatial distribution areas are divided into area blocks where every two path distribution areas are adjacent or every three path distribution areas are adjacent to obtain the first type of distribution area blocks.

[0034] The distance change values ​​between adjacent paths in the first type of distribution area block are counted to obtain the current distance change value to be measured.

[0035] The current distance change value to be measured and the first type of distribution area block are input into the simulation energy consumption prediction model for testing, so as to divide the first type of distribution area block into a secondary spatial area to obtain the second type of distribution area block.

[0036] Specifically, such as the spatial distribution area (such as the distribution of the path: J1, J2, J3, J4, J5, J6), the first type of distribution area block (that is, J1 and J2 are divided into one area, and the subsequent energy consumption analysis is mainly performed on J1, because the energy consumption of J1 will be affected by the correlation of J2, J1, J2, and J3 are divided into one area, and the subsequent energy consumption analysis is mainly performed on J2, because J2 will be affected by the correlation of J1 and J3), the current distance change value to be measured (the interpretation is the same as the historical distance change value to be measured, this No further explanation is given here), the second type of distribution area block (such as the first type of distribution area block is the same as the above-mentioned path 1 and path 2, such as the segments of J1 and J2 have b1, b2, b3 respectively, for the distance values ​​between the three segments b1, b2, b3 corresponding to the segments of J1 and J2, if the distance in b3 is less than or equal to the historical distance change value to be measured, then the spatial area where the b3 segment of the segments of the paths J1 and J2 is located is extracted, if it is k4, it is the second type of distribution area block).

[0037] The specific step S4 includes the following sub-steps: The pre-processed distance change values ​​belonging to the second type of distribution area block are screened out from the current distance change values ​​to be measured.

[0038] According to the preprocessed distance change value, the current original environment data between corresponding adjacent path segments in the second type distribution area block is obtained.

[0039] Get the current raw allocated energy values ​​for all energy allocation paths.

[0040] The current raw allocated energy value, the current raw environmental data and the pre-processed distance change value are combined into pre-processed feature data.

[0041] The historical ring variation difference value 1 and the historical ring variation difference value 2 are selected from the historical environmental data change differences to be tested, and the differences between the historical original allocated energy values ​​to which the historical ring variation difference value 1 and the historical ring variation difference value 2 respectively belong and the current original allocated energy values ​​are the smallest, and the historical distance change value to be tested of the historical ring variation difference value 1 is the same as the preprocessing distance change value, and the historical original environmental data of the historical ring variation difference value 1 is the same as the current original environmental data, and the historical distance change value to be tested of the historical ring variation difference value 2 is the same as the preprocessing distance change value, and the historical original environmental data of the historical ring variation difference value 2 is the same as the current original environmental data.

[0042] Specifically, such as the pre-processed distance change value (that is, the distance between the b3 segments of each segment of the paths J1 and J2), the current original environmental data (such as the original environmental data detected in the k4 spatial area), the historical original allocated energy values ​​to which the historical ring variation difference value one and the historical ring variation difference value two belong respectively have the smallest difference with the current original allocated energy value (if the historical original allocated energy value to which the historical ring variation difference value one belongs is N0, the historical original allocated energy value to which the historical ring variation difference value two belongs is N2, and the current original allocated energy value is N1, wherein N0 is less than N1, and N2 is greater than N1, it should be noted that there are multiple historical original allocated energy values ​​stored in the historical data set, and under the condition that multiple historical original allocated energy values ​​are less than the current original allocated energy value: only the difference between N1 and N0 is the smallest, and under the condition that multiple historical original allocated energy values ​​are greater than the current original allocated energy value: only the difference between N2 and N1 is the smallest).

[0043] The specific step S5 includes the following sub-steps: The historical ring variation value 1 and the pre-processed characteristic data are input into the simulation energy consumption prediction model for testing to obtain the first additional energy consumption value.

[0044] The second historical ring variation value and the preprocessed characteristic data are input into the simulation energy consumption prediction model for testing to obtain the second additional energy consumption value.

[0045] The first extra energy consumption value and the second extra energy consumption value are averaged to obtain an actual extra energy consumption value.

[0046] According to the actual additional energy consumption value, the difference compensation is performed on the current original allocated energy value to obtain the actual required energy allocation amount of all energy allocation paths, and energy allocation management is performed on each path of all energy allocation paths to output the energy management optimization result.

[0047] Specifically, such as the first additional energy consumption value (substitute the historical ring variation value 1, the current original allocated energy value in the preprocessing characteristic data, and the preprocessing distance change value into Y=A(z+r) to test and obtain Y1, which is the first additional energy consumption value), the second additional energy consumption value (the explanation is the same as the first additional energy consumption value, and no further explanation is given here), the actual required energy allocation amount (such as A+(Y1+Y2) / 2, if the result is A1, it is the actual required energy allocation amount, if the above-mentioned current original allocated energy value is for path J1, then the actual required energy allocation amount of A1 is the actual required energy allocation amount of path J1, and so on. The same steps are performed on the remaining paths, that is, the actual required energy allocation amounts of all energy allocation paths are obtained, and the corresponding energy demand allocation of each path is optimized).

[0048] The spatial visualization power energy management optimization system, by applying the spatial visualization power energy management optimization method as described above, includes a historical data analysis module, a model building module, a distribution area division module, an actual energy demand analysis module 1 and an actual energy demand analysis module 2, referring to Figure 2 , obtain all energy distribution paths that need to be managed for energy distribution optimization through the historical data analysis module, and count the historical distance change values, historical environmental data change differences and historical energy consumption values ​​between adjacent paths in all energy distribution paths in the historical period; extract the historical energy consumption values ​​to be tested that are greater than or equal to the preset energy consumption threshold value from the historical energy consumption values ​​through the model building module, and train a simulation energy consumption prediction model based on the historical environmental data change differences and historical distance change values ​​to be tested extracted from the historical distance change values ​​and historical environmental data change differences; obtain the spatial distribution areas of all energy distribution paths through the distribution area division module, and divide the spatial distribution areas into The system is divided into first-class distribution area blocks, and the first-class distribution area blocks are input into the simulation energy consumption prediction model for secondary space area division to obtain second-class distribution area blocks; the historical ring variation difference value 1 and the historical ring variation difference value 2 are screened out from the historical environmental data change difference to be tested through the actual energy demand analysis module 1; the historical ring variation difference value 1, the historical ring variation difference value 2 and the pre-processed characteristic data belonging to the second-class distribution area blocks are input into the simulation energy consumption prediction model for testing to obtain the actual additional energy consumption value, and according to the actual additional energy consumption value, the actual energy demand distribution management of each path is performed on all energy distribution paths, and the energy management optimization result is output.

[0049] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A spatial visualization power energy management optimization method, characterized in that: The following steps are involved: Obtain all energy distribution paths that require energy distribution optimization management, and count the historical distance change values, historical environmental data change differences, and historical energy consumption values ​​between adjacent paths in all energy distribution paths in the historical period; Extract the historical energy consumption values ​​to be measured that are greater than or equal to the preset energy consumption threshold from the historical energy consumption values, and train a simulation energy consumption prediction model based on the historical environmental data change difference to be measured and the historical distance change value to be measured extracted from the historical distance change value and the historical environmental data change difference; Obtaining the spatial distribution area of ​​all energy distribution paths, dividing the spatial distribution area into first-type distribution area blocks, and inputting the first-type distribution area blocks into a simulation energy consumption prediction model to perform secondary spatial area division to obtain second-type distribution area blocks; Filter out a historical ring variation difference value 1 and a historical ring variation difference value 2 from the historical environmental data variation difference values ​​to be measured; The historical ring variation value 1, the historical ring variation value 2 and the pre-processed characteristic data belonging to the second type of distribution area block are input into the simulation energy consumption prediction model for testing to obtain the actual additional energy consumption value. According to the actual additional energy consumption value, the actual energy demand distribution management of each path is performed on all energy distribution paths, and the energy management optimization result is output.

2. The spatial visualization power energy management optimization method according to claim 1 is characterized in that: The steps of obtaining all energy distribution paths that need to be managed for energy distribution optimization and counting the historical distance change values, historical environmental data change differences and historical energy consumption values ​​between adjacent paths in all energy distribution paths in the historical period are specifically as follows: Obtain all energy distribution paths that require energy distribution optimization management; Count the historical distance change values ​​between adjacent paths in all energy distribution paths in the historical period; According to the historical distance change value, the value of the environmental data after the change in each distance change section in the historical distance change value is counted to obtain the historical change environmental data, and the historical original environmental data in each distance change section in the historical distance change value is counted; The historical environmental data change difference is obtained by performing a one-to-one numerical difference calculation between the historical environmental data change and the historical original environmental data; Obtain the historical original allocated energy values ​​of all energy allocation paths in the historical period; A preset interval time period is used to obtain a historical energy consumption value by counting the change in energy loss value of each path of the historical original allocated energy value after the interval time period.

3. The spatial visualization power energy management optimization method according to claim 2 is characterized in that: The steps of extracting the historical energy consumption values ​​to be measured that are greater than or equal to the preset energy consumption threshold from the historical energy consumption values, and training the simulation energy consumption prediction model according to the historical environmental data change difference to be measured and the historical distance change value to be measured extracted from the historical distance change value and the historical environmental data change difference, are specifically as follows: Preset an energy consumption threshold, and extract the historical energy consumption values ​​to be measured that are greater than or equal to the energy consumption threshold from the historical energy consumption values; According to the historical energy consumption value to be measured, extract the historical environmental data change difference to be measured between the corresponding adjacent path segments from the historical environmental data change difference, and extract the historical distance change value to be measured between the corresponding adjacent path segments from the historical distance change value; A simulation energy consumption prediction model is trained based on the historical energy consumption values ​​to be measured, the historical environmental data change differences to be measured, and the historical distance change values ​​to be measured.

4. The spatial visualization power energy management optimization method according to claim 3 is characterized in that: The steps of obtaining the spatial distribution area of ​​all energy distribution paths, dividing the spatial distribution area into first-type distribution area blocks, and inputting the first-type distribution area blocks into the simulation energy consumption prediction model to perform secondary spatial area division to obtain second-type distribution area blocks are specifically as follows: Obtaining the spatial distribution areas of all energy distribution paths, dividing the spatial distribution areas into area blocks where every two path distribution areas are adjacent or every three path distribution areas are adjacent to obtain first-type distribution area blocks; Counting the distance change values ​​between adjacent paths in the first type of distribution area block to obtain the current distance change value to be measured; The current distance change value to be measured and the first type of distribution area block are input into the simulation energy consumption prediction model for testing, so as to divide the first type of distribution area block into a secondary spatial area to obtain a second type of distribution area block.

5. The spatial visualization power energy management optimization method according to claim 4 is characterized in that: The step of selecting the historical ring variation difference value 1 and the historical ring variation difference value 2 from the historical environmental data variation difference value to be tested is specifically: Filter out the pre-processed distance change value belonging to the second type of distribution area block from the current distance change value to be measured; According to the pre-processed distance change value, obtaining current original environment data between corresponding adjacent path segments in the second type distribution area block; Get the current raw allocated energy values ​​of all energy allocation paths; The current original allocated energy value, the current original environmental data and the pre-processed distance change value are combined into pre-processed characteristic data; A historical ring variation difference value 1 and a historical ring variation difference value 2 are selected from the historical environmental data change differences to be tested, and the differences between the historical original allocated energy values ​​to which the historical ring variation difference value 1 and the historical ring variation difference value 2 respectively belong and the current original allocated energy values ​​are respectively the smallest, and the historical distance change value to be tested of the historical ring variation difference value 1 is the same as the preprocessing distance change value, and the historical original environmental data of the historical ring variation difference value 1 is the same as the current original environmental data, and the historical distance change value to be tested of the historical ring variation difference value 2 is the same as the preprocessing distance change value, and the historical original environmental data of the historical ring variation difference value 2 is the same as the current original environmental data.

6. The spatial visualization power energy management optimization method according to claim 5 is characterized in that: The steps of inputting the historical ring variation value 1, the historical ring variation value 2 and the pre-processed characteristic data belonging to the second type of distribution area block into the simulation energy consumption prediction model for testing to obtain the actual additional energy consumption value, and performing energy actual demand allocation management for each path for all energy distribution paths according to the actual additional energy consumption value, and outputting the energy management optimization result are specifically as follows: Inputting the historical ring variation value 1 and the preprocessed characteristic data into a simulation energy consumption prediction model for testing to obtain a first additional energy consumption value; Inputting the second historical ring variation value and the preprocessed characteristic data into a simulation energy consumption prediction model for testing to obtain a second additional energy consumption value; averaging the first extra energy consumption value and the second extra energy consumption value to obtain an actual extra energy consumption value; According to the actual additional energy consumption value, the difference compensation is performed on the current original allocated energy value to obtain the actual required energy allocation amount of all energy allocation paths, and energy allocation management is performed on each path of all energy allocation paths to output energy management optimization results.

7. Spatial visualization power energy management optimization system, characterized by: The system is used to implement the spatial visualization power energy management optimization method according to any one of claims 1 to 6, comprising: The historical data analysis module is used to obtain all energy distribution paths that need to be managed for energy distribution optimization, and to count the historical distance change values ​​between adjacent paths, the historical environmental data change differences, and the historical energy consumption values ​​in all energy distribution paths in the historical period; A model building module is used to extract the historical energy consumption values ​​to be measured that are greater than or equal to the preset energy consumption threshold from the historical energy consumption values, and train a simulation energy consumption prediction model according to the historical environmental data change difference to be measured and the historical distance change value to be measured extracted from the historical distance change value and the historical environmental data change difference; A distribution area division module is used to obtain the spatial distribution area of ​​all energy distribution paths, divide the spatial distribution area into first-class distribution area blocks, and input the first-class distribution area blocks into the simulation energy consumption prediction model to perform secondary spatial area division to obtain second-class distribution area blocks; The actual energy demand analysis module 1 is used to select the historical ring change difference value 1 and the historical ring change difference value 2 from the historical environmental data change difference values ​​to be measured; The actual energy demand analysis module 2 is used to input the historical ring variation value 1, the historical ring variation value 2 and the pre-processed characteristic data belonging to the second type of distribution area block into the simulation energy consumption prediction model for testing to obtain the actual additional energy consumption value. According to the actual additional energy consumption value, the actual energy demand distribution management of each path is performed for all energy distribution paths, and the energy management optimization results are output.

Images