Multi-dimensional aggregation analysis system applied to energy consumption heterogeneous data

Abstract

This invention discloses a multi-dimensional aggregation analysis system for heterogeneous energy consumption data, relating to the field of energy management technology. It includes: a front-end acquisition module for acquiring heterogeneous energy consumption data and environmental data within a target area, and synchronizing the acquired data with a clock; a database for storing historical heterogeneous energy consumption data and historical environmental data from different times within the target area, constructing a corresponding historical energy consumption-environment data map; a data processing module for processing the acquired heterogeneous energy consumption data and environmental data to obtain real-time energy consumption-environment time-series data; a data analysis module for analyzing the real-time energy consumption-environment time-series data based on the historical energy consumption-environment data map, and obtaining the assessment difference degree of the target area based on the analysis results; and a map update module for updating the historical energy consumption-environment data map based on the real-time energy consumption-environment time-series data and the assessment difference degree.

Description

Technical Field

[0001] This invention relates to the field of energy management technology, specifically to a multi-dimensional aggregation analysis system for heterogeneous energy consumption data. Background Technology

[0002] With the rapid development of IoT, cloud computing, and AI technologies, the energy management field is gradually moving towards digitalization and intelligence. In target areas such as industrial production and buildings, a large number of heterogeneous devices and environmental sensing terminals have been deployed, continuously generating massive amounts of heterogeneous energy consumption data and environmental data. The efficient aggregation and in-depth analysis of this multi-dimensional data is of great strategic significance for understanding energy consumption patterns, optimizing energy allocation, and improving energy utilization efficiency. Currently, using technologies such as knowledge graphs to explore the complex relationships between energy consumption behavior and environmental factors has become a key development direction for achieving refined energy consumption management and intelligent decision-making. Existing energy management systems typically deal with heterogeneous data from diverse sources and with complex structures, as well as environmental data. Current technologies often store and display energy consumption data and environmental data independently, lacking the ability to explore the deep relationships between the two. This makes it difficult to determine the triggering mechanisms and mapping relationships between changes in environmental parameters and the energy consumption behavior of specific equipment. To address this, we now provide a multi-dimensional aggregation analysis system for heterogeneous energy consumption data. Summary of the Invention

[0003] The purpose of this invention is to provide a multi-dimensional aggregation analysis system for heterogeneous energy consumption data.

[0004] The objective of this invention can be achieved through the following technical solution: a multi-dimensional aggregation analysis system for heterogeneous energy consumption data, comprising: The front-end acquisition module is used to acquire heterogeneous energy consumption data and environmental data within the target area, and to synchronize the acquired heterogeneous energy consumption data and environmental data with a clock. The database is used to store historical energy consumption heterogeneous data and historical environmental data at different times within the target area, and to construct the corresponding historical energy consumption-environment data map. The data processing module is used to process the acquired heterogeneous energy consumption data and environmental data to obtain real-time energy consumption-environment time-series data. The data analysis module is used to analyze real-time energy consumption and environmental time-series data based on historical energy consumption and environmental data maps, and to obtain the assessment difference degree of the target area based on the analysis results. The map update module updates the historical energy consumption-environment data map based on real-time energy consumption-environment time-series data and assessment differences.

[0005] Furthermore, the process by which the front-end acquisition module acquires heterogeneous energy consumption data within the target area includes: The front-end acquisition module consists of several data reading ports, used to acquire real-time operating data of heterogeneous modules within the target area; The real-time operating data includes key parameters of each heterogeneous module and the corresponding operating parameters of each key parameter. The key parameters of each heterogeneous module and the corresponding operating parameters are summarized to obtain the energy consumption heterogeneous data of the target area. The front-end acquisition module also includes several environmental sensing terminals deployed at various locations within the target area, used to acquire environmental data at various locations within the target area. The environmental data consists of several data items and environmental parameters corresponding to each data item.

[0006] Furthermore, the process of constructing a corresponding historical energy consumption-environment data map by storing heterogeneous historical energy consumption data and historical environmental data at different times within the target area in the database includes: Construct the corresponding master nodes of the graph for each data item in the environmental data, and import the historical environmental data into the corresponding master nodes of the graph; Construct corresponding graph sub-nodes based on each heterogeneous module, and import the obtained historical energy consumption heterogeneous data into the corresponding graph sub-nodes; Set the node state for each sub-node of the graph, including active state and inactive state; Obtain the time period during which each sub-node of the graph is in an active state, and obtain the corresponding key parameter items and running parameters within the active state time period; Obtain the environmental parameters at the start time of the time period when each sub-node of the graph is in an active state; And obtain the environmental parameters at the end of the time period when each sub-node of the graph is in an active state; Based on the environmental parameters corresponding to the start time of each activation state, the trigger correlation coefficient between each data item and the sub-node of the graph is obtained; Similarly, based on the environmental parameters corresponding to the end time of each activation state, the cutoff correlation coefficient between each data item and the sub-node of the graph can be obtained; Set an association threshold and compare the trigger association coefficient and cutoff association coefficient of each data item with the association threshold respectively; If the trigger association coefficient is less than the association threshold, it means that the corresponding data item has a trigger association with the secondary node of the graph; otherwise, there is no trigger association. If the cutoff correlation coefficient is less than the correlation threshold, it means that the corresponding data item has a cutoff correlation with the secondary node of the graph; otherwise, there is no cutoff correlation. If a trigger association exists, the node association relationship between the corresponding data item and the secondary node of the graph is generated, and the corresponding trigger conditions and trigger mapping relationship are set. Similarly, if a cutoff relationship exists, the node relationship between the corresponding data item and the secondary node of the graph is generated, and the corresponding cutoff condition is set. The node relationship mapping between all sub-nodes of the graph and each data item of the environmental parameter is completed in sequence, thereby completing the construction of the historical energy consumption-environment data graph.

[0007] Furthermore, the process of setting the corresponding trigger conditions and trigger mapping relationships is as follows: The environmental parameters corresponding to the data items that are associated with the secondary nodes of the graph are summarized at the start of each activation state. After removing the maximum and minimum values ​​of the summarized environmental parameters, the average value of the remaining environmental parameters is used as the trigger condition for the data item to the secondary node of the graph. Set a unit threshold value, and generate several trigger thresholds based on the trigger condition. It should be noted that the difference between each trigger threshold and the previous trigger threshold is the unit threshold value. Iterate through the environmental parameters during each activation state of the data item and mark the earliest time that is the same as each trigger threshold; Similarly, remove the maximum and minimum values ​​from the historical energy consumption heterogeneous data corresponding to the corresponding sub-node of the graph at the earliest time during each marked activation state period, and obtain the mean of the remaining historical energy consumption heterogeneous data as the trigger energy consumption value corresponding to the trigger threshold. The trigger energy consumption values ​​corresponding to each trigger threshold are summarized to obtain the trigger mapping relationship between the data item and the sub-node of the graph.

[0008] Furthermore, the process of setting the corresponding deadline conditions is as follows: The environmental parameters corresponding to the end time of each activation state of the data item that is associated with the secondary node of the graph are summarized. After removing the maximum and minimum values ​​of the summarized environmental parameters, the mean of the remaining environmental parameters is used as the cutoff condition of the data item for the secondary node of the graph.

[0009] Furthermore, the data processing module processes the acquired heterogeneous energy consumption data and environmental data to obtain real-time energy consumption-environment time-series data. This process includes: Construct a time axis and map the obtained environmental data onto the time axis to generate corresponding environmental parameter change curves; Based on the energy consumption heterogeneous data of each heterogeneous module, a corresponding energy consumption parameter change curve is generated and mapped onto the time axis. Set a data sampling period, sample the environmental parameter change curve and energy consumption parameter change curve according to the data sampling period, and record the sampling time. Summarize the environmental parameters of each data item of the environmental parameter change curve and energy consumption parameter change curve corresponding to the sampling time, as well as the energy consumption heterogeneous data of each heterogeneous module, to obtain the corresponding real-time energy consumption-environment time series data.

[0010] Furthermore, the data analysis module analyzes real-time energy consumption-environment time-series data based on historical energy consumption-environment data maps. The process of obtaining the assessment difference degree of the target area based on the analysis results includes: The environmental parameters of each data item in the obtained real-time energy consumption-environment time series data are marked, and the environmental parameters of each data item are input into the historical energy consumption-environment data map. The graph sub-nodes that are associated with each data item are obtained sequentially, and the environmental parameters of the data items are matched with the trigger thresholds of each graph sub-node; The trigger threshold that is closest to the environmental parameter of the data item is marked, and the trigger energy consumption value corresponding to the trigger threshold is obtained; The obtained trigger energy consumption value is compared with the corresponding heterogeneous energy consumption data in the real-time energy consumption-environment time series data to obtain the energy consumption difference value; Then, the energy consumption difference values ​​corresponding to the secondary nodes of the graph with triggering correlations for each data item are obtained sequentially; The energy consumption difference values ​​are fitted to offset each other, and the offset fitting result is used as the evaluation difference degree of the target area.

[0011] Furthermore, the process by which the map update module updates the historical energy consumption-environment data map based on real-time energy consumption-environment time-series data and assessment differences includes: Set the evaluation difference fluctuation range, compare the obtained evaluation difference degree with the evaluation difference fluctuation range. If the evaluation difference degree is within the evaluation difference fluctuation range, it means that the energy consumption of the corresponding sub-node of the graph is within the expected range. If the assessment difference is less than the lower limit of the assessment difference fluctuation range, it means that the energy consumption of the corresponding sub-node of the graph is lower than expected, and an energy consumption upward adjustment instruction is generated based on the assessment difference. If the assessment difference is greater than the upper limit of the assessment difference fluctuation range, it means that the energy consumption of the corresponding sub-node of the graph is higher than expected, and an energy consumption reduction instruction is generated based on the assessment difference. The management personnel adjust the generated instructions and adjust the energy consumption of the corresponding heterogeneous modules according to the final executed instructions. The environmental parameters of each data item and the heterogeneous energy consumption data of each heterogeneous module after adjustment are imported into the historical energy consumption-environment data map, thereby completing the update of the historical energy consumption-environment data map.

[0012] Compared with the prior art, the beneficial effects of the present invention are: 1. By analyzing the correlation coefficients between environmental parameters and equipment activation / shutdown states in historical data, a trigger mapping relationship between environmental data items and heterogeneous modules was established, thereby breaking down data silos between different dimensions of data. This enables accurate identification of the specific impact mechanism of environmental factors on equipment energy consumption, providing a more reliable basis for energy consumption analysis. 2. Based on the map, the real-time energy consumption-environment time series data are compared and analyzed to quantitatively assess the degree of difference. Energy consumption adjustment instructions are automatically generated according to the difference. At the same time, the map is updated in real time using the adjusted data, forming a closed-loop management of "analysis-assessment-control-learning", which effectively improves the intelligence level and control accuracy of energy consumption management in the target area. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0014] Figure 1 This is a schematic diagram of the present invention. Detailed Implementation

[0015] like Figure 1 As shown, the multi-dimensional aggregation analysis system applied to heterogeneous energy consumption data includes: The front-end acquisition module is used to acquire heterogeneous energy consumption data and environmental data within the target area, and to synchronize the acquired heterogeneous energy consumption data and environmental data with a clock. The database is used to store historical energy consumption heterogeneous data and historical environmental data at different times within the target area, and to construct the corresponding historical energy consumption-environment data map. The data processing module is used to process the acquired heterogeneous energy consumption data and environmental data to obtain real-time energy consumption-environment time-series data. The data analysis module is used to analyze real-time energy consumption and environmental time-series data based on historical energy consumption and environmental data maps, and to obtain the assessment difference degree of the target area based on the analysis results. The map update module updates the historical energy consumption-environment data map based on real-time energy consumption-environment time-series data and assessment differences.

[0016] It should be further explained that, in the specific implementation process, the process by which the front-end acquisition module obtains heterogeneous energy consumption data within the target area includes: The front-end acquisition module consists of several data reading ports, which are used to acquire real-time operating data of heterogeneous modules in the target area, including photovoltaic modules, energy storage modules, power supply and distribution modules, heating modules, and power consumption modules, etc. The real-time operating data includes key parameters of each heterogeneous module and the corresponding operating parameters for each key parameter. It should be noted that the key parameters of different heterogeneous modules may differ. The key parameters of each heterogeneous module and the corresponding operating parameters are summarized to obtain the energy consumption heterogeneous data of the target area.

[0017] The process of the front-end data acquisition module obtaining environmental data includes: The front-end acquisition module also includes several environmental sensing terminals deployed at various locations within the target area, used to acquire environmental data at various locations within the target area. The environmental data consists of several data items and environmental parameters corresponding to each data item, including brightness, temperature, humidity, etc.

[0018] It should be further explained that, in the specific implementation process, the database stores heterogeneous historical energy consumption data and historical environmental data from different times within the target area. The process of constructing the corresponding historical energy consumption-environment data map includes: Construct the corresponding master nodes of the graph for each data item in the environmental data, and import the historical environmental data into the corresponding master nodes of the graph; Construct corresponding graph sub-nodes based on each heterogeneous module, and import the obtained historical energy consumption heterogeneous data into the corresponding graph sub-nodes; Each sub-node of the graph is assigned a node state, which includes an active state and an inactive state. It should be noted that the active state means that the corresponding heterogeneous module is running, while the inactive state means that the corresponding heterogeneous module is not running. Obtain the time period during which each sub-node of the graph is in an active state, and obtain the corresponding key parameter items and running parameters within the active state time period; Obtain the environmental parameters at the start time of the time period when each sub-node of the graph is in an active state; And obtain the environmental parameters at the end of the time period when each sub-node of the graph is in an active state; Each activation state of a sub-node in the graph is labeled and denoted as i, where i = 1, 2, ..., n; Let the environmental parameters at the start of the activation state labeled i be denoted as . And the environmental parameters at the end time, denoted as ; Where j represents the data items corresponding to the historical environmental data. For the environment parameter with data item j; Based on the environmental parameters corresponding to the start time of each activation state, the trigger correlation coefficient between each data item and the sub-node of the graph is obtained, denoted as . ,in: ; Similarly, based on the environmental parameters corresponding to the end time of each activation state, the cutoff correlation coefficient between each data item and the sub-node of the graph is obtained, denoted as . ,in: ; Set an association threshold and compare the trigger association coefficient and cutoff association coefficient of each data item with the association threshold respectively; If the trigger association coefficient is less than the association threshold, it means that the corresponding data item has a trigger association with the secondary node of the graph; otherwise, there is no trigger association. If the cutoff correlation coefficient is less than the correlation threshold, it means that the corresponding data item has a cutoff correlation with the secondary node of the graph; otherwise, there is no cutoff correlation. If a trigger association exists, the node association relationship between the corresponding data item and the secondary node of the graph is generated, and the corresponding trigger conditions and trigger mapping relationship are set. Similarly, if a cutoff relationship exists, the node relationship between the corresponding data item and the secondary node of the graph is generated, and the corresponding cutoff condition is set. The node relationship mapping between all sub-nodes of the graph and each data item of the environmental parameter is completed in sequence, thereby completing the construction of the historical energy consumption-environment data graph.

[0019] It should be further explained that, in the specific implementation process, the process of setting the corresponding trigger conditions and trigger mapping relationships is as follows: The environmental parameters corresponding to the data items that are associated with the secondary nodes of the graph are summarized at the start of each activation state. After removing the maximum and minimum values ​​of the summarized environmental parameters, the average value of the remaining environmental parameters is used as the trigger condition for the data item to the secondary node of the graph. Set a unit threshold value, and generate several trigger thresholds based on the trigger condition. It should be noted that the difference between each trigger threshold and the previous trigger threshold is the unit threshold value. Iterate through the environmental parameters of each data item during its activation state and mark the earliest time that is the same as each trigger threshold; it should be noted that the earliest time refers to the moment when the corresponding trigger threshold is first reached during the current activation state. Similarly, remove the maximum and minimum values ​​from the historical energy consumption heterogeneous data corresponding to the corresponding sub-node of the graph at the earliest time during each marked activation state period, and obtain the mean of the remaining historical energy consumption heterogeneous data as the trigger energy consumption value corresponding to the trigger threshold. The trigger energy consumption values ​​corresponding to each trigger threshold are summarized to obtain the trigger mapping relationship between the data item and the sub-node of the graph.

[0020] It should be further explained that, in the specific implementation process, the process of setting the corresponding cutoff conditions is as follows: The environmental parameters corresponding to the end time of each activation state of the data item that is associated with the secondary node of the graph are summarized. After removing the maximum and minimum values ​​of the summarized environmental parameters, the mean of the remaining environmental parameters is used as the cutoff condition of the data item for the secondary node of the graph.

[0021] It should be further explained that, in the specific implementation process, the data processing module processes the acquired heterogeneous energy consumption data and environmental data to obtain real-time energy consumption-environment time-series data. The process includes: Construct a time axis and map the obtained environmental data onto the time axis to generate corresponding environmental parameter change curves; Based on the energy consumption heterogeneous data of each heterogeneous module, a corresponding energy consumption parameter change curve is generated and mapped onto the time axis. Set a data sampling period, sample the environmental parameter change curve and energy consumption parameter change curve according to the data sampling period, and record the sampling time. Summarize the environmental parameters of each data item of the environmental parameter change curve and energy consumption parameter change curve corresponding to the sampling time, as well as the energy consumption heterogeneous data of each heterogeneous module, to obtain the corresponding real-time energy consumption-environment time series data.

[0022] It should be further explained that, in the specific implementation process, the data analysis module analyzes the real-time energy consumption-environment time-series data based on the historical energy consumption-environment data map, and the process of obtaining the assessment difference degree of the target area based on the analysis results includes: The environmental parameters of each data item in the obtained real-time energy consumption-environment time series data are marked, and the environmental parameters of each data item are input into the historical energy consumption-environment data map. The graph sub-nodes that are associated with each data item are obtained sequentially, and the environmental parameters of the data items are matched with the trigger thresholds of each graph sub-node; The trigger threshold that is closest to the environmental parameter of the data item is marked, and the trigger energy consumption value corresponding to the trigger threshold is obtained; The obtained trigger energy consumption value is compared with the corresponding heterogeneous energy consumption data in the real-time energy consumption-environment time series data to obtain the energy consumption difference value; Then, the energy consumption difference value corresponding to the secondary nodes of the graph with triggering correlation for each data item is obtained in sequence. The energy consumption difference value can be positive, negative or 0. The energy consumption difference values ​​are offset and fitted, and the offset fitting result is used as the evaluation difference degree of the target area. It should be noted that offsetting fitting refers to summing the energy consumption differences of the same sub-nodes in the graph to obtain the evaluation difference degree of the corresponding sub-nodes in the graph. It should be noted that if there is a graph sub-node that is related to the data item by a cutoff, a heterogeneous module closure request instruction corresponding to that graph sub-node will be generated directly.

[0023] It should be further explained that, in the specific implementation process, the process by which the map update module updates the historical energy consumption-environment data map based on real-time energy consumption-environment time-series data and assessment differences includes: Set the evaluation difference fluctuation range, compare the obtained evaluation difference degree with the evaluation difference fluctuation range. If the evaluation difference degree is within the evaluation difference fluctuation range, it means that the energy consumption of the corresponding sub-node of the graph is within the expected range. If the assessment difference is less than the lower limit of the assessment difference fluctuation range, it means that the energy consumption of the corresponding sub-node of the graph is lower than expected, and an energy consumption upward adjustment instruction is generated based on the assessment difference. If the assessment difference is greater than the upper limit of the assessment difference fluctuation range, it means that the energy consumption of the corresponding sub-node of the graph is higher than expected, and an energy consumption reduction instruction is generated based on the assessment difference. Managers can adjust the generated instructions and adjust the energy consumption of the corresponding heterogeneous modules according to the final executed instructions. The environmental parameters of each data item and the heterogeneous energy consumption data of each heterogeneous module after adjustment are imported into the historical energy consumption-environment data map, thereby completing the update of the historical energy consumption-environment data map. When a heterogeneous module shutdown request command is generated, if the administrator directly confirms the heterogeneous module shutdown request command, the historical energy consumption-environment data map will not be updated. If the administrator adjusts the content of the heterogeneous module shutdown request command, the environmental parameters of each data item and the energy consumption heterogeneous data of each heterogeneous module will be imported into the historical energy consumption-environment data map to complete the update of the map sub-nodes with cutoff correlation.

[0024] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any modifications or equivalent substitutions made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A multi-dimensional aggregation analysis system for heterogeneous energy consumption data, characterized in that, include: The front-end acquisition module is used to acquire heterogeneous energy consumption data and environmental data within the target area, and to synchronize the acquired heterogeneous energy consumption data and environmental data with a clock. The database is used to store historical energy consumption heterogeneous data and historical environmental data at different times within the target area, and to construct the corresponding historical energy consumption-environment data map. The data processing module is used to process the acquired heterogeneous energy consumption data and environmental data to obtain real-time energy consumption-environment time-series data. The data analysis module is used to analyze real-time energy consumption and environmental time-series data based on historical energy consumption and environmental data maps, and to obtain the assessment difference degree of the target area based on the analysis results. The map update module updates the historical energy consumption-environment data map based on real-time energy consumption-environment time-series data and assessment differences.

2. The multi-dimensional aggregation analysis system for heterogeneous energy consumption data according to claim 1, characterized in that, The process by which the front-end acquisition module obtains heterogeneous energy consumption data within the target area includes: The front-end acquisition module consists of several data reading ports, used to acquire real-time operating data of heterogeneous modules within the target area; The real-time operating data includes key parameters of each heterogeneous module and the corresponding operating parameters of each key parameter. The key parameters of each heterogeneous module and the corresponding operating parameters are summarized to obtain the energy consumption heterogeneous data of the target area. The front-end acquisition module also includes several environmental sensing terminals deployed at various locations within the target area, used to acquire environmental data at various locations within the target area. The environmental data consists of several data items and environmental parameters corresponding to each data item.

3. The multi-dimensional aggregation analysis system for heterogeneous energy consumption data according to claim 2, characterized in that, The process of constructing a corresponding historical energy consumption-environment data map, which stores heterogeneous historical energy consumption and historical environmental data of a target area at different times in the database, includes: Construct the corresponding master nodes of the graph for each data item in the environmental data, and import the historical environmental data into the corresponding master nodes of the graph; Construct corresponding graph sub-nodes based on each heterogeneous module, and import the obtained historical energy consumption heterogeneous data into the corresponding graph sub-nodes; Set the node state for each sub-node of the graph, including active state and inactive state; Obtain the time period during which each sub-node of the graph is in an active state, and obtain the corresponding key parameter items and running parameters within the active state time period; Obtain the environmental parameters at the start time of the time period when each sub-node of the graph is in an active state; And obtain the environmental parameters at the end of the time period when each sub-node of the graph is in an active state; Based on the environmental parameters corresponding to the start time of each activation state, the trigger correlation coefficient between each data item and the sub-node of the graph is obtained; Similarly, based on the environmental parameters corresponding to the end time of each activation state, the cutoff correlation coefficient between each data item and the sub-node of the graph can be obtained; Set an association threshold and compare the trigger association coefficient and cutoff association coefficient of each data item with the association threshold respectively; If the trigger association coefficient is less than the association threshold, it means that the corresponding data item has a trigger association with the secondary node of the graph; otherwise, there is no trigger association. If the cutoff correlation coefficient is less than the correlation threshold, it means that the corresponding data item has a cutoff correlation with the secondary node of the graph; otherwise, there is no cutoff correlation. If a trigger association exists, the node association relationship between the corresponding data item and the secondary node of the graph is generated, and the corresponding trigger conditions and trigger mapping relationship are set. Similarly, if a cutoff relationship exists, the node relationship between the corresponding data item and the secondary node of the graph is generated, and the corresponding cutoff condition is set. The node relationship mapping between all sub-nodes of the graph and each data item of the environmental parameter is completed in sequence, thereby completing the construction of the historical energy consumption-environment data graph.

4. The multi-dimensional aggregation analysis system for heterogeneous energy consumption data according to claim 3, characterized in that, The process of setting the corresponding trigger conditions and trigger mapping relationships is as follows: The environmental parameters corresponding to the data items that are associated with the secondary nodes of the graph are summarized at the start of each activation state. After removing the maximum and minimum values ​​of the summarized environmental parameters, the average value of the remaining environmental parameters is used as the trigger condition for the data item to the secondary node of the graph. Set a unit threshold value, and generate several trigger thresholds based on the trigger condition. It should be noted that the difference between each trigger threshold and the previous trigger threshold is the unit threshold value. Iterate through the environmental parameters during each activation state of the data item and mark the earliest time that is the same as each trigger threshold; Similarly, remove the maximum and minimum values ​​from the historical energy consumption heterogeneous data corresponding to the corresponding sub-node of the graph at the earliest time during each marked activation state period, and obtain the mean of the remaining historical energy consumption heterogeneous data as the trigger energy consumption value corresponding to the trigger threshold. The trigger energy consumption values ​​corresponding to each trigger threshold are summarized to obtain the trigger mapping relationship between the data item and the sub-node of the graph.

5. The multi-dimensional aggregation analysis system for heterogeneous energy consumption data according to claim 3, characterized in that, The process of setting the corresponding cutoff condition is as follows: The environmental parameters corresponding to the end time of each activation state of the data item that is associated with the secondary node of the graph are summarized. After removing the maximum and minimum values ​​of the summarized environmental parameters, the mean of the remaining environmental parameters is used as the cutoff condition of the data item for the secondary node of the graph.

6. The multi-dimensional aggregation analysis system for heterogeneous energy consumption data according to claim 3, characterized in that, The data processing module processes the acquired heterogeneous energy consumption data and environmental data to obtain real-time energy consumption-environment time-series data. The process includes: Construct a time axis and map the obtained environmental data onto the time axis to generate corresponding environmental parameter change curves; Based on the energy consumption heterogeneous data of each heterogeneous module, a corresponding energy consumption parameter change curve is generated and mapped onto the time axis. Set a data sampling period, sample the environmental parameter change curve and energy consumption parameter change curve according to the data sampling period, and record the sampling time. Summarize the environmental parameters of each data item of the environmental parameter change curve and energy consumption parameter change curve corresponding to the sampling time, as well as the energy consumption heterogeneous data of each heterogeneous module, to obtain the corresponding real-time energy consumption-environment time series data.

7. The multi-dimensional aggregation analysis system for heterogeneous energy consumption data according to claim 6, characterized in that, The data analysis module analyzes real-time energy consumption and environmental time-series data based on historical energy consumption-environment data maps. The process of obtaining the assessment difference of the target area based on the analysis results includes: The environmental parameters of each data item in the obtained real-time energy consumption-environment time series data are marked, and the environmental parameters of each data item are input into the historical energy consumption-environment data map. The graph sub-nodes that are associated with each data item are obtained sequentially, and the environmental parameters of the data items are matched with the trigger thresholds of each graph sub-node; The trigger threshold that is closest to the environmental parameter of the data item is marked, and the trigger energy consumption value corresponding to the trigger threshold is obtained; The obtained trigger energy consumption value is compared with the corresponding heterogeneous energy consumption data in the real-time energy consumption-environment time series data to obtain the energy consumption difference value; Then, the energy consumption difference values ​​corresponding to the secondary nodes of the graph with triggering correlations for each data item are obtained sequentially; The energy consumption difference values ​​are fitted to offset each other, and the offset fitting result is used as the evaluation difference degree of the target area.

8. The multi-dimensional aggregation analysis system for heterogeneous energy consumption data according to claim 7, characterized in that, The process by which the map update module updates the historical energy consumption-environment data map based on real-time energy consumption-environment time-series data and assessment differences includes: Set the evaluation difference fluctuation range, compare the obtained evaluation difference degree with the evaluation difference fluctuation range. If the evaluation difference degree is within the evaluation difference fluctuation range, it means that the energy consumption of the corresponding sub-node of the graph is within the expected range. If the assessment difference is less than the lower limit of the assessment difference fluctuation range, it means that the energy consumption of the corresponding sub-node of the graph is lower than expected, and an energy consumption upward adjustment instruction is generated based on the assessment difference. If the assessment difference is greater than the upper limit of the assessment difference fluctuation range, it means that the energy consumption of the corresponding sub-node of the graph is higher than expected, and an energy consumption reduction instruction is generated based on the assessment difference. The management personnel adjust the generated instructions and adjust the energy consumption of the corresponding heterogeneous modules according to the final executed instructions. The environmental parameters of each data item and the heterogeneous energy consumption data of each heterogeneous module after adjustment are imported into the historical energy consumption-environment data map, thereby completing the update of the historical energy consumption-environment data map.

Images