A method and system for energy management control

Abstract

The application relates to the technical field of energy consumption control, and discloses an energy consumption management control method and system, which comprises the following steps: performing multi-dimensional feature fusion on standardized energy consumption data of a target device to obtain energy consumption state features; performing space adjacency analysis on energy consumption values, energy consumption change trends and energy consumption types in the energy consumption state features to construct a dynamic partition energy consumption graph; analyzing the space distribution features of the dynamic partition energy consumption graph to define abnormal regions, and performing risk assessment on the abnormal regions to obtain comprehensive abnormal grades and key influence factors; driving preliminary energy-saving regulation and control instructions to control the energy-saving operation of the target device; performing control parameter compensation on the preliminary energy-saving regulation and control instructions according to control feedback information to obtain optimized energy-saving regulation and control instructions; applying the optimized energy-saving regulation and control instructions to perform energy-saving control on the target device, and synchronously updating the dynamic partition energy consumption graph; and the application can improve the efficiency of energy consumption management control.

Description

Technical Field

[0001] This invention relates to the field of energy consumption control technology, and in particular to an energy consumption management and control method and system. Background Technology

[0002] Existing energy consumption visualization and control technologies lack in-depth integration capabilities for processing energy consumption data of target devices. They fail to effectively fuse the time-domain, frequency-domain, and sequence pattern features of standardized energy consumption data, resulting in insufficient accuracy in extracting energy consumption status features. This makes it difficult to serve as a reliable basis for constructing subsequent dynamic energy consumption maps, thus affecting the authenticity and effectiveness of energy consumption visualization.

[0003] Existing technologies have significant shortcomings in defining energy consumption anomaly areas, assessing risks, and controlling energy conservation: they cannot accurately locate anomaly areas by comprehensively combining spatial distribution characteristics such as energy density, variability, and fluctuation frequency; risk assessments do not fully consider the synergistic effects of spatial propagation, temporal persistence, and energy intensity; and energy conservation control lacks a parameter compensation mechanism for operational feedback, resulting in poor adaptability of control strategies. This not only makes it difficult to achieve energy conservation goals but may also affect equipment stability. Therefore, improving the fusion effect of multiple features of energy consumption data, enhancing the accuracy of anomaly definition and risk assessment, and perfecting the control feedback mechanism to ensure visualization authenticity and energy conservation reliability have become urgent problems to be solved. Summary of the Invention

[0004] This invention provides an energy consumption management and control method and system to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides an energy consumption management and control method, comprising:

[0006] S1. Perform multi-dimensional feature fusion on the standardized energy consumption data of the target device to obtain the energy consumption status characteristics of the target device;

[0007] S2. Based on the predefined visual channel mapping rules, perform spatial adjacency analysis on the energy consumption values, energy consumption change trends and energy consumption types in the energy consumption state characteristics to construct a dynamic partitioned energy consumption map of the energy consumption state characteristics.

[0008] S3. Analyze the spatial distribution characteristics of the dynamic partition energy consumption map to define the abnormal areas of the dynamic partition energy consumption map, and conduct a risk assessment on the abnormal areas to obtain the comprehensive abnormality level and key influencing factors of the abnormal areas.

[0009] S4. Based on the comprehensive anomaly level and the key influencing factors, drive the initial energy-saving control command of the target equipment to control the energy-saving operation of the target equipment;

[0010] S5. Based on the control feedback information of the target equipment after the energy-saving operation, the control parameters of the preliminary energy-saving control command are compensated to obtain the optimized energy-saving control command of the target equipment.

[0011] S6. Apply the optimized energy-saving control command to perform energy-saving control on the target device and update the dynamic partition energy consumption map simultaneously.

[0012] In a preferred embodiment, the step of performing multi-dimensional feature fusion on the standardized energy consumption data of the target device to obtain the energy consumption state characteristics of the target device includes:

[0013] Collect raw energy consumption monitoring data and equipment attribute data of the target equipment;

[0014] Outliers in the original energy consumption monitoring data are removed, and data of different dimensions in the original energy consumption monitoring data after removing outliers are unified to the standard unit of measurement to obtain the standardized energy consumption data of the target equipment.

[0015] Extract the time-domain features, frequency-domain features, and sequence pattern features of the standardized energy consumption data;

[0016] The time-domain features, frequency-domain features, and sequence pattern features are fused to obtain the energy consumption status features of the target device.

[0017] In a preferred embodiment, the step of performing spatial adjacency analysis on the energy consumption values, energy consumption change trends, and energy consumption types in the energy consumption state characteristics according to predefined visual channel mapping rules to construct a dynamic partitioned energy consumption map of the energy consumption state characteristics includes:

[0018] The energy consumption state characteristics are decoupled to obtain the energy consumption value, energy consumption change trend and energy consumption type of the energy consumption state characteristics;

[0019] According to the predefined visual channel mapping rules, the energy consumption value, the energy consumption change trend and the energy consumption type are visually channel separated and mapped to obtain the height encoding value, color encoding value and shape encoding value of the energy consumption state feature;

[0020] Based on the height encoding value, the color encoding value, and the shape encoding value, a visual primitive of the energy consumption state feature is generated;

[0021] Based on the spatial location and connection relationship of the target device, the coordinates of the visualized graphic elements are determined;

[0022] Based on the coordinates, spatial adjacency clustering analysis is performed on the visualized primitives to aggregate visualized primitives with similar visual attributes and spatial proximity into the same primitive region.

[0023] The visualized primitives in the same primitive region are fused and rendered to obtain a dynamic partitioned energy consumption map of the energy consumption state characteristics.

[0024] In a preferred embodiment, analyzing the spatial distribution characteristics of the dynamic partitioned energy consumption map to define the abnormal areas of the dynamic partitioned energy consumption map includes:

[0025] The energy consumption density, energy consumption difference, and energy consumption fluctuation frequency of the dynamic partition energy consumption map are used as the spatial distribution characteristics of the dynamic partition energy consumption map.

[0026] A difference analysis is performed on the spatial distribution characteristics to obtain the deviation data of the dynamic partition energy consumption map;

[0027] Based on the deviation data, abnormal partitioning is performed on the dynamic partitioning energy consumption map to obtain the abnormal areas of the dynamic partitioning energy consumption map.

[0028] In a preferred embodiment, the risk assessment of the abnormal area to obtain the comprehensive abnormality level and key influencing factors of the abnormal area includes:

[0029] The anomaly area is assessed for multi-dimensional risk levels to obtain its spatial propagation risk level, temporal persistence risk level, and energy consumption intensity risk level.

[0030] Based on preset weighting coefficients and synergistic effect amplification coefficients, the spatial propagation risk level, the temporal persistence risk level, and the energy consumption intensity risk level are fused and calculated to obtain the comprehensive anomaly level of the anomaly area.

[0031] By conducting a joint source tracing analysis on the equipment composition, operational sequence correlation, and external environment correlation data of the abnormal area, the key influencing factors of the abnormal area are obtained.

[0032] In a preferred embodiment, the formula for the fusion calculation is as follows:

[0033] ;

[0034] In the formula, This indicates the overall anomaly level. This indicates the level of risk for space propagation. This indicates the level of risk based on the duration of the risk. This indicates the energy consumption intensity risk level. This represents the preset spatial propagation risk level weighting coefficient. This represents the preset weighting coefficient for the duration of risk. This represents the preset weighting coefficient for energy consumption intensity risk level. This represents the preset synergistic amplification factor. This represents the preset power parameter. This represents the preset smallest positive number. This represents the cube root operation. Represents the hyperbolic tangent function. This indicates taking the maximum value.

[0035] In a preferred embodiment, the step of driving a preliminary energy-saving control command for the target equipment based on the comprehensive anomaly level and the key influencing factors to control the energy-saving operation of the target equipment includes:

[0036] Using the comprehensive anomaly level and the key influencing factors as query conditions, predefined energy-saving control strategies are retrieved to obtain candidate control strategies for the target equipment.

[0037] The candidate control strategy is adapted to the operating state parameters of the target device to eliminate conflicting strategies between the candidate control strategy and the operating state parameters, thereby obtaining the adapted control strategy for the target device.

[0038] Based on the source type of the anomaly of the key influencing factors, the control parameters of the adaptive control strategy are assigned values, and the assigned control parameters are logically bound to generate the preliminary energy-saving control instructions for the target equipment.

[0039] The preliminary energy-saving control command is sent to the control interface of the target device, driving the target device to perform the energy-saving operation corresponding to the preliminary energy-saving control command.

[0040] In a preferred embodiment, the step of compensating the control parameters of the preliminary energy-saving control command based on the control feedback information of the target equipment after the energy-saving operation to obtain the optimized energy-saving control command for the target equipment includes:

[0041] The operating status data and real-time energy consumption data of the target device after the energy-saving operation are used as the control feedback information of the target device after the energy-saving operation.

[0042] By jointly analyzing the actual energy consumption change rate, equipment operation stability index, and control target achievement index of the control feedback information, the abnormal control links of the target equipment after the energy-saving operation are obtained.

[0043] Based on the abnormal control mechanism, a preset compensation rule library is invoked to obtain the compensation control parameters of the preliminary energy-saving control command;

[0044] Based on the compensation control parameters, the preliminary energy-saving control command is modified to obtain the optimized energy-saving control command for the target equipment.

[0045] In a preferred embodiment, applying the optimized energy-saving control command to perform energy-saving control on the target device and synchronously updating the dynamic partition energy consumption map includes:

[0046] Analyze the control logic and parameter set of the optimized energy-saving control command;

[0047] Based on the communication protocol and control interface type of the target device, the control logic and the parameter set are appropriately matched and encapsulated into the instruction frame of the target device to obtain the underlying control signal of the target device;

[0048] Through the control interface of the target device, the underlying control signal is sent to drive the target device to execute the energy-saving control action of the optimized energy-saving regulation command;

[0049] The updated energy consumption data generated by the target device after executing the energy-saving control action is collected, and the updated energy consumption data is input into the generation process of the dynamic partition energy consumption map to update the dynamic partition energy consumption map.

[0050] To address the above problems, the present invention also provides an energy consumption management and control system, the system comprising:

[0051] A multi-dimensional feature fusion module is used to perform multi-dimensional feature fusion on the standardized energy consumption data of the target device to obtain the energy consumption status characteristics of the target device.

[0052] The dynamic partitioned energy consumption map construction module is used to perform spatial adjacency analysis on the energy consumption values, energy consumption change trends and energy consumption types in the energy consumption state features according to predefined visual channel mapping rules, so as to construct a dynamic partitioned energy consumption map of the energy consumption state features.

[0053] The abnormal area risk assessment module is used to analyze the spatial distribution characteristics of the dynamic partition energy consumption map to define the abnormal areas of the dynamic partition energy consumption map, and to conduct risk assessment on the abnormal areas to obtain the comprehensive abnormality level and key influencing factors of the abnormal areas.

[0054] An energy-saving control command generation module is used to drive the initial energy-saving control command of the target equipment according to the comprehensive anomaly level and the key influencing factors, so as to control the energy-saving operation of the target equipment;

[0055] The control parameter compensation module is used to compensate the control parameters of the initial energy-saving control command based on the control feedback information of the target equipment after the energy-saving operation, so as to obtain the optimized energy-saving control command of the target equipment.

[0056] The closed-loop control execution and visualization update module is used to apply the optimized energy-saving control instructions, execute energy-saving control on the target equipment, and synchronously update the dynamic partition energy consumption map.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] 1. This invention can accurately extract energy consumption status features by performing multi-dimensional feature fusion on standardized energy consumption data of target equipment; combined with predefined visual channel mapping rules, it performs spatial adjacency analysis on energy consumption values, trends and types and constructs a dynamic partitioned energy consumption map, which can clearly and intuitively present the spatial distribution of energy consumption and improve the accuracy and readability of energy consumption visualization.

[0059] 2. This invention can accurately define energy consumption fluctuation areas, obtain comprehensive fluctuation levels and key influencing factors through multi-dimensional risk assessment, and generate appropriate preliminary energy-saving control instructions; then, based on equipment control feedback information, parameter compensation is performed to obtain optimized energy-saving control instructions and execute closed-loop control, while simultaneously updating the energy consumption map. This not only improves the accuracy and timeliness of energy-saving control, but also effectively enhances the overall efficiency of energy consumption visualization and control, while ensuring the stability of target equipment operation. Attached Figure Description

[0060] Figure 1 A flowchart illustrating an energy consumption management and control method according to an embodiment of the present invention;

[0061] Figure 2 A functional block diagram of an energy management and control system provided in an embodiment of the present invention;

[0062] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0063] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0064] This application provides an energy consumption management and control method. The executing entity of this energy consumption management and control method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application embodiment: a server, a terminal, etc. In other words, the energy consumption management and control method can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0065] Reference Figure 1 The diagram shown is a flowchart illustrating an energy consumption management and control method according to an embodiment of the present invention. In this embodiment, the energy consumption management and control method includes:

[0066] S1. Perform multi-dimensional feature fusion on the standardized energy consumption data of the target device to obtain the energy consumption status characteristics of the target device;

[0067] In this embodiment of the invention, the step of performing multi-dimensional feature fusion on the standardized energy consumption data of the target device to obtain the energy consumption status characteristics of the target device includes:

[0068] Collect raw energy consumption monitoring data and equipment attribute data of the target equipment;

[0069] Outliers in the original energy consumption monitoring data are removed, and data of different dimensions in the original energy consumption monitoring data after removing outliers are unified to the standard unit of measurement to obtain the standardized energy consumption data of the target equipment.

[0070] Extract the time-domain features, frequency-domain features, and sequence pattern features of the standardized energy consumption data;

[0071] The time-domain features, frequency-domain features, and sequence pattern features are fused to obtain the energy consumption status features of the target device.

[0072] Energy consumption monitoring sensors with real-time data acquisition capabilities are installed at key energy consumption monitoring points of the target equipment, namely the power input interface and the power supply end of the core working module. The sensors and the data acquisition terminal establish a stable connection through wired Ethernet or wireless Wi-Fi to continuously capture raw energy consumption monitoring data such as real-time energy consumption, total cumulative energy consumption, and energy consumption change per unit time generated during the operation of the target equipment. At the same time, the operator logs into the equipment asset management database system to which the target equipment belongs, enters the equipment's unique code, i.e., the equipment's factory serial number, in the database query interface, and retrieves equipment attribute data such as equipment model, rated operating power, design energy consumption limit, commissioning time, and energy consumption category, i.e., electricity or gas energy consumption, from the "Equipment Basic Information Table" of the database. Through the above operations, the raw energy consumption monitoring data and equipment attribute data of the target equipment are collected.

[0073] First, each piece of raw energy consumption monitoring data was verified. Based on the rated operating power of the target equipment and the normal operating energy consumption fluctuation range standard provided by the equipment manufacturer, the normal energy consumption range of the equipment under normal operating conditions was determined. Specifically, this range is defined as a 15% fluctuation around the energy consumption value corresponding to the rated power. Values ​​in the raw energy consumption monitoring data that exceed this normal range, specifically energy consumption values ​​that far exceed the rated power when the equipment is overloaded, and zero or invalid garbled values ​​that appear after data transmission interruption, are identified as outliers and deleted from the raw energy consumption monitoring data list. Subsequently, for the raw energy consumption monitoring data after removing outliers, "kilowatt-hour (kWh)" was determined as the unified standard unit of measurement. For energy consumption data in the raw data in "watt-hour (Wh)", each data value was multiplied by a conversion ratio of 0.001 to convert the unit to kilowatt-hour. For energy consumption data in the raw data in "degree", since 1 degree is equivalent to 1 kilowatt-hour, the data value was directly retained and the unit label was changed to kilowatt-hour. Through these operations, the raw energy consumption data of different units were unified to the standard unit of measurement, and the standardized energy consumption data of the target equipment was obtained.

[0074] For the obtained standardized energy consumption data, when extracting time-domain features, a fixed time interval of 1 hour is set. The standardized energy consumption data is distributed into each interval in chronological order. For all energy consumption data within each interval, the average energy consumption for that interval is calculated by summing all data points and dividing by the number of data points. The maximum energy consumption is obtained by selecting the largest value from all data points within the interval, and the minimum energy consumption is obtained by selecting the smallest value from all data points within the interval. Simultaneously, the difference between the average energy consumption of two adjacent intervals is calculated (the average of the later interval minus the average of the earlier interval). These averages, maximum values, minimum values, and adjacent differences together constitute the time-domain features of the standardized energy consumption data. When extracting frequency-domain features, the standardized energy consumption data is divided according to time periods, constructing 1 day (24 hours) and 1 week (1 week) respectively. The 7-day cycle analysis framework statistically analyzes energy consumption data changes hourly within each cycle, identifying periods where energy consumption remains consistently high (e.g., peak energy consumption during daytime operation of commercial equipment) and periods where energy consumption remains consistently low (e.g., low energy consumption during nighttime idleness). The distribution of these peak and low periods and their corresponding energy consumption patterns constitute the frequency domain characteristics of the standardized energy consumption data. When extracting sequence pattern features, the standardized energy consumption data is arranged into a continuous data sequence in chronological order. The sequence is then broken down into 12-hour segments, and the data change trends in different segments are compared to identify recurring fixed change segments. For example, the fixed segment from 9 AM to 9 PM each day where energy consumption rises from low to high and then falls back is identified. These recurring fixed segments constitute the sequence pattern characteristics of the standardized energy consumption data.

[0075] The extracted time-domain features, frequency-domain features, and sequence pattern features are categorized and organized. First, the average, maximum, minimum, and adjacent differences in the time-domain features are sorted in time interval order to ensure that each data item matches the corresponding time interval precisely. In the frequency-domain features, peak and trough periods of different cycles, i.e., 1 day and 1 week, are archived according to cycle type, and the start and end times of each period and the corresponding energy consumption range are clearly defined. In the sequence pattern features, each repeatedly changing segment is sorted by frequency of occurrence, and the duration of the segment, the data change nodes, and the corresponding energy consumption value are recorded. Then, the organized time-domain features, frequency-domain features, and sequence pattern features are integrated into a single feature set to ensure that the three types of feature information are not duplicated or missing. This integrated feature set is the energy consumption status feature of the target device.

[0076] The beneficial effects are as follows: Through specific sensor deployment and database retrieval processes, the collected raw energy consumption monitoring data and equipment attribute data are ensured to be complete and accurate, laying a reliable foundation for subsequent data processing; by using an outlier judgment method based on the equipment's rated power and clear dimensional conversion operations, interference in the raw data is effectively removed and units are standardized, resulting in accurate and standardized energy consumption data; by comprehensively acquiring three types of features through multi-dimensional feature extraction, and then standardizing and integrating them to form energy consumption status features, these features can completely and accurately reflect the energy consumption of the target equipment, providing high-quality feature support for the subsequent construction of dynamic partitioned energy consumption maps, and ensuring the smooth and efficient implementation of subsequent energy consumption visualization and control processes.

[0077] S2. Based on the predefined visual channel mapping rules, perform spatial adjacency analysis on the energy consumption values, energy consumption change trends and energy consumption types in the energy consumption state characteristics to construct a dynamic partitioned energy consumption map of the energy consumption state characteristics.

[0078] In this embodiment of the invention, the step of performing spatial adjacency analysis on the energy consumption values, energy consumption change trends, and energy consumption types in the energy consumption state characteristics according to predefined visual channel mapping rules, in order to construct a dynamic partitioned energy consumption map of the energy consumption state characteristics, includes:

[0079] The energy consumption state characteristics are decoupled to obtain the energy consumption value, energy consumption change trend and energy consumption type of the energy consumption state characteristics;

[0080] According to the predefined visual channel mapping rules, the energy consumption value, the energy consumption change trend and the energy consumption type are visually channel separated and mapped to obtain the height encoding value, color encoding value and shape encoding value of the energy consumption state feature;

[0081] Based on the height encoding value, the color encoding value, and the shape encoding value, a visual primitive of the energy consumption state feature is generated;

[0082] Based on the spatial location and connection relationship of the target device, the coordinates of the visualized graphic elements are determined;

[0083] Based on the coordinates, spatial adjacency clustering analysis is performed on the visualized primitives to aggregate visualized primitives with similar visual attributes and spatial proximity into the same primitive region.

[0084] The visualized primitives in the same primitive region are fused and rendered to obtain a dynamic partitioned energy consumption map of the energy consumption state characteristics.

[0085] In the process of feature decoupling of energy consumption status features, the internal data structure of energy consumption status features is first clarified. This structure contains independent data fields related to energy consumption values, energy consumption change trends, and energy consumption types. By extracting the information corresponding to these fields one by one, specific energy consumption values ​​are separated from energy consumption status features, such as the specific energy consumption of 10 kilowatt-hours per hour, the energy consumption change trend, such as the direction of change of energy consumption gradually increasing and remaining stable or continuously decreasing over 3 consecutive hours, and the energy consumption type, such as specific categories like electricity consumption, gas consumption, and thermal consumption. Finally, the energy consumption values, energy consumption change trends, and energy consumption types of energy consumption status features are obtained.

[0086] Visual channel separation and mapping are performed according to predefined visual channel mapping rules. These rules clearly define the correspondence between various types of energy consumption information and visual channels: energy consumption values ​​correspond to the height dimension in the visual channel, with higher energy consumption values ​​resulting in larger height codes; for example, an energy consumption value of 5 kWh corresponds to a height code of 3, and an energy consumption value of 10 kWh corresponds to a height code of 6. Energy consumption change trends correspond to the color dimension in the visual channel; for example, an upward trend in energy consumption is mapped to a red color code, a stable trend is mapped to a yellow color code, and a downward trend is mapped to a green color code. Energy consumption types correspond to the shape dimension in the visual channel; for example, electricity energy consumption is mapped to a circular shape code, gas energy consumption to a square shape code, and thermal energy consumption to a triangular shape code. Following these rules, energy consumption values, energy consumption change trends, and energy consumption types are mapped to obtain the height code, color code, and shape code values ​​for the energy consumption status characteristics.

[0087] When generating visual primitives based on height encoding values, color encoding values, and shape encoding values, the basic outline shape of the primitive is first determined by the shape encoding value. For example, if the shape encoding value is circle, a circular outline is drawn first; if the shape encoding value is square, a square outline is drawn first. Then, a three-dimensional structure is constructed in the vertical direction of the basic outline according to the height encoding value. For example, if the height encoding value is 3, the circular outline is extended upward by 3 units to form a three-dimensional circular block; if the height encoding value is 6, the square outline is extended upward by 6 units to form a three-dimensional square block. Finally, the three-dimensional structure is filled with the color corresponding to the color encoding value. For example, if the color encoding value is red, it is filled with red; if the color encoding value is yellow, it is filled with yellow. Through the above steps, visual primitives of energy consumption status characteristics are generated.

[0088] When determining the coordinates of visualized elements based on the spatial location and connection relationships of the target equipment, first obtain the location parameters of the target equipment in the actual physical space, such as the horizontal and vertical distances of the equipment within the factory building, as well as the connection relationships between the equipment. For example, equipment A is connected to equipment B through a pipe and equipment A is located 2 meters to the left of equipment B; equipment B is connected to equipment C through a line and equipment B is located 1 meter in front of equipment C. Then, convert the location parameters of the actual physical space into coordinate system parameters of the visualization interface according to a preset ratio. For example, 1 meter in the actual space corresponds to 10 pixels in the visualization interface. Combined with the equipment connection relationships, adjust the relative positions of the visualized elements corresponding to each equipment in the coordinate system, and finally confirm the specific coordinates of each visualized element in the visualization interface.

[0089] When performing spatial adjacency clustering analysis on visualized primitives based on coordinates, spatial adjacency judgment criteria and visual attribute similarity judgment criteria are first set. The spatial adjacency judgment criteria are that two visualized primitives are considered spatially adjacent when the horizontal and vertical distances between their coordinates in the visualization interface are both less than 5 pixels. The visual attribute similarity judgment criteria are that two visualized primitives are considered visually similar when the difference in their height encoding values ​​is less than 2, their color encoding values ​​belong to the same color family, and their shape encoding values ​​correspond to the same shape. Then, the coordinates and visual attributes of all visualized primitives are compared one by one, and visualized primitives that simultaneously meet the conditions of spatial adjacency and visual attribute similarity are grouped together. Finally, visualized primitives with similar visual attributes and spatial adjacency are aggregated into the same primitive region.

[0090] When merging and rendering visual elements in the same area, the edges of all visual elements within the same area are first smoothed to eliminate obvious boundary lines between elements and make the area appear as a coherent whole. Then, the average height and main color of the area are calculated based on the height and color coding values ​​of the visual elements in the area. The average height is used to enhance the three-dimensional visual effect of the area, and the main color is used to unify the overall color of the area. At the same time, labels are added to the edges of the area to indicate the energy consumption type and average energy consumption value of the area, and a dynamic update mechanism is set to ensure that the shape and color of the area can be adjusted in real time as the energy consumption data changes. Through the above fusion and rendering operations, a dynamic partitioned energy consumption map with energy consumption status characteristics is obtained.

[0091] The beneficial effects are as follows: key information in energy consumption status features is accurately separated through a clear feature decoupling process; abstract energy consumption data is transformed into concrete high-color shape encoding values ​​by combining predefined visual channel mapping rules, thereby generating intuitive visual primitives; primitive coordinates are then determined based on the spatial location and connection relationship of the equipment; similar primitives are aggregated through spatial adjacency clustering analysis; and finally, a dynamic partitioned energy consumption map is constructed through fusion rendering. This not only clearly presents the trend of energy consumption value changes and the distribution pattern of types, but also updates energy consumption information in real time, providing an accurate visual basis for subsequent abnormal area definition and energy-saving control, effectively improving the intuitiveness, real-time performance and practicality of energy consumption visualization.

[0092] S3. Analyze the spatial distribution characteristics of the dynamic partition energy consumption map to define the abnormal areas of the dynamic partition energy consumption map, and conduct a risk assessment on the abnormal areas to obtain the comprehensive abnormality level and key influencing factors of the abnormal areas.

[0093] In this embodiment of the invention, the step of analyzing the spatial distribution characteristics of the dynamic partition energy consumption map to define the abnormal regions of the dynamic partition energy consumption map includes:

[0094] The energy consumption density, energy consumption difference, and energy consumption fluctuation frequency of the dynamic partition energy consumption map are used as the spatial distribution characteristics of the dynamic partition energy consumption map.

[0095] A difference analysis is performed on the spatial distribution characteristics to obtain the deviation data of the dynamic partition energy consumption map;

[0096] Based on the deviation data, abnormal partitioning is performed on the dynamic partitioning energy consumption map to obtain the abnormal areas of the dynamic partitioning energy consumption map.

[0097] The risk assessment of the abnormal area yields a comprehensive abnormality level and key influencing factors, including:

[0098] The anomaly area is assessed for multi-dimensional risk levels to obtain its spatial propagation risk level, temporal persistence risk level, and energy consumption intensity risk level.

[0099] Based on preset weighting coefficients and synergistic effect amplification coefficients, the spatial propagation risk level, the temporal persistence risk level, and the energy consumption intensity risk level are fused and calculated to obtain the comprehensive anomaly level of the anomaly area.

[0100] By conducting a joint source tracing analysis on the equipment composition, operational sequence correlation, and external environment correlation data of the abnormal area, the key influencing factors of the abnormal area are obtained.

[0101] The formula for the fusion calculation is as follows:

[0102] ;

[0103] In the formula, This indicates the overall anomaly level. This indicates the level of risk for space propagation. This indicates the level of risk based on the duration of the risk. This indicates the energy consumption intensity risk level. This represents the preset spatial propagation risk level weighting coefficient. This represents the preset weighting coefficient for the duration of risk. This represents the preset weighting coefficient for energy consumption intensity risk level. This represents the preset synergistic amplification factor. This represents the preset power parameter. This represents the preset smallest positive number. This represents the cube root operation. Represents the hyperbolic tangent function. This indicates taking the maximum value.

[0104] When analyzing the spatial distribution characteristics of the dynamic partition energy consumption map, the energy consumption density, energy consumption difference, and energy consumption fluctuation frequency of each element region in the dynamic partition energy consumption map are calculated separately: the energy consumption density is obtained by summing the energy consumption values ​​of all visualized elements in each element region and then dividing it by the area occupied by that element region in the visualization interface, calculated in pixels; the energy consumption difference is obtained by calculating the difference between the energy consumption density of each element region and the energy consumption density of its surrounding adjacent element regions, and taking the average of the absolute values ​​of all differences; the energy consumption fluctuation frequency is obtained by counting the number of times the energy consumption value of the element region exceeds the preset normal energy consumption fluctuation range per unit time, such as 1 hour. The calculated energy consumption density, energy consumption difference, and energy consumption fluctuation frequency are used together as the spatial distribution characteristics of the dynamic partition energy consumption map.

[0105] When performing differential analysis on spatial distribution characteristics, the preset normal range of energy consumption spatial distribution is first retrieved. This range is determined based on the energy consumption density, energy consumption difference, and energy consumption fluctuation frequency data during the historical normal operation of the target equipment. Then, the energy consumption density, energy consumption difference, and energy consumption fluctuation frequency of each graphic element area are compared with the corresponding normal range: if the energy consumption density is higher than the upper limit of the normal range, the value exceeding the upper limit is calculated; if the energy consumption difference is higher than the average value of the normal range, the value exceeding the average value is calculated; if the energy consumption fluctuation frequency is higher than the upper limit of the normal range, the number of times it exceeds the upper limit is calculated. These excess values ​​and excess times are summarized to obtain the deviation data of the dynamic partition energy consumption map.

[0106] When calibrating abnormal zones in the dynamic partitioned energy consumption map based on deviation data, anomaly judgment thresholds are first set. For example, energy consumption density exceeding the normal upper limit by 10%, energy consumption difference exceeding the normal average by 15%, and energy consumption fluctuation frequency exceeding the normal upper limit by 5 times are all set as abnormal thresholds. Then, the deviation data of each map element area is checked one by one. If any one of the deviations in energy consumption density, energy consumption difference, or energy consumption fluctuation frequency in the area reaches the abnormal threshold, the area is judged as an abnormal partition. These abnormal partitions are marked in the dynamic partitioned energy consumption map with a preset special identifier, such as a red border, to obtain the abnormal areas of the dynamic partitioned energy consumption map.

[0107] When assessing the risk level of an abnormal area across multiple dimensions, determining the spatial propagation risk level requires statistical analysis of the number of connections between the abnormal area and other normal areas, such as the number of pipe and line connections and the speed at which abnormal signs spread to surrounding areas. The more connections and the faster the spread, the higher the spatial propagation risk level. For example, if there are more than 5 connections and the spread rate exceeds 2 areas per hour, it is classified as a high-level risk. Determining the time-duration risk level requires recording the duration of the abnormal area from the first occurrence of the anomaly to the present. The longer the duration, the higher the time-duration risk level. For example, if the duration exceeds 4 hours, it is classified as a high-level risk. Determining the energy consumption intensity risk level requires calculating the ratio of the actual energy consumption value of the abnormal area to the rated energy consumption value of the equipment in that area. The larger the ratio, the higher the energy consumption intensity risk level. For example, if the ratio exceeds 1.5, it is classified as a high-level risk. Through the above assessments, the spatial propagation risk level, time-duration risk level, and energy consumption intensity risk level of the abnormal area are obtained.

[0108] When calculating the fusion of three risk levels based on preset weighting coefficients and synergy amplification coefficients, the process begins by first calculating the product of each risk level and its corresponding weight using preset weighting coefficients, such as 0.3 for spatial propagation risk level, 0.4 for temporal persistence risk level, and 0.3 for energy intensity risk level. The three products are then summed to obtain the base risk value. Next, the synergy of the three risk levels is assessed. If all three levels are medium to high, a preset synergy amplification coefficient of 1.2 is applied, and the base risk value is multiplied by this coefficient. If only two levels are medium to high, the amplification coefficient is set to 1.1. If only one level is medium to high, the amplification coefficient is set to 1.0. The final result is the comprehensive anomaly level of the anomaly area.

[0109] The spatial propagation risk level is derived from the multi-dimensional risk level assessment of the abnormal area. Specifically, the assessment requires counting the number of connections between the abnormal area and other normal areas, such as the number of pipe and line connections and the speed at which abnormal signs spread to the surrounding areas. The more connections and the faster the spread, the higher the spatial propagation risk level. The spatial propagation risk level of the abnormal area is finally obtained through this assessment process.

[0110] The time-duration risk level is derived from the multi-dimensional risk level assessment of the abnormal area. Specifically, the duration of the abnormal area from the first occurrence of the anomaly to the present needs to be recorded. The longer the duration, the higher the time-duration risk level. The time-duration risk level of the abnormal area is finally obtained through this assessment process.

[0111] The energy consumption intensity risk level is derived from the multi-dimensional risk level assessment of the abnormal area. Specifically, the ratio of the actual energy consumption value of the abnormal area to the rated energy consumption value of the equipment in that area needs to be calculated. The larger the ratio, the higher the energy consumption intensity risk level. The energy consumption intensity risk level of the abnormal area is finally obtained through this assessment process.

[0112] The preset weighting coefficients for spatial propagation risk level, time persistence risk level, and energy intensity risk level are based on historical energy consumption management data of the target equipment and energy consumption risk assessment standards for similar equipment in the industry. When setting these coefficients, the impact of different risk dimensions on energy consumption anomaly management is taken into account. For example, considering that time persistence has a greater impact on the accumulation of energy consumption anomalies, the time persistence risk level weighting coefficient is set to a relatively high value. Finally, these three preset weighting coefficients are determined and stored.

[0113] The preset synergy amplification coefficient is based on the energy consumption anomaly impact data of the three risk levels in the abnormal area occurring simultaneously in history. When setting it, the additional impact on equipment energy consumption control when the three risk levels are at the medium to high level at the same time is analyzed to determine the coefficient value that can reflect the additional impact, which is stored as the preset synergy amplification coefficient for later use.

[0114] The preset power parameter is based on multiple energy consumption risk assessment test data. When setting it, the parameter value is adjusted to observe the matching degree between the risk level fusion result under different parameters and the actual energy consumption anomaly. The parameter value with the highest matching degree is selected as the preset power parameter.

[0115] The preset minimum positive number is set in advance to avoid the denominator being zero during the calculation process. When setting it, a positive number with a very small value that will not have a significant impact on the overall calculation result is selected as the preset minimum positive number for calculation.

[0116] The comprehensive anomaly level is derived from the formula by integrating the spatial propagation risk level, the temporal persistence risk level, and the energy consumption intensity risk level. It is the final result of the formula calculation and is used to reflect the overall risk level of the anomaly area.

[0117] The significance of the formula lies in its comprehensive integration of information from the three risk dimensions of the abnormal area through two-part calculation processes, resulting in a comprehensive abnormality level that objectively reflects the overall risk level of the abnormal area.

[0118] The first part of the calculation process combines three preset weighting coefficients to process the risk levels of spatial propagation, temporal persistence, and energy intensity. During the processing, exponentiation and averaging are used to reflect the weight of different risk levels in the overall risk assessment, thus avoiding the excessive influence of a single risk level on the results.

[0119] The second part of the calculation process combines a preset synergy amplification factor and a hyperbolic tangent function to process the synergistic impact of the three risk levels. During the processing, the ratio of the cube root of the three risk levels to the maximum value is calculated, then transformed by the hyperbolic tangent function, added to 1, and multiplied by the synergy amplification factor. This reflects the additional synergistic risk generated when the three risk levels are at a high level at the same time.

[0120] The final result obtained by multiplying the two calculation results is the comprehensive anomaly level of the anomaly area. This process can take into account the individual and synergistic effects of different risk dimensions, ensuring that the comprehensive anomaly level can fully and accurately reflect the actual risk situation of the anomaly area.

[0121] When the risk level of space propagation increases, in the calculation of the first part of the formula, the result of multiplying the risk level by the corresponding weight coefficient after exponentiation will increase, which in turn increases the sum of the numerators in the first part. With the denominator fixed, the overall result of the first part will increase, ultimately leading to an increase in the comprehensive anomaly level.

[0122] When the time-dependent risk level increases, similarly, the result of multiplying the risk level by the corresponding weight coefficient after exponentiation will increase, thus increasing the sum of the numerators in the first part, increasing the overall result of the first part, and consequently increasing the comprehensive anomaly level.

[0123] When the energy consumption intensity risk level increases, the result of multiplying the risk level by the corresponding weight coefficient after exponentiation will increase, which in turn increases the sum of the numerators in the first part, thus increasing the overall result of the first part and further increasing the comprehensive anomaly level.

[0124] When all three risk levels are at a high level, the ratio of the cube root of the three risk levels to the maximum value in the second part of the formula will approach 1. After the hyperbolic tangent function transformation, the value will increase. Adding it to 1 and multiplying it by the synergy amplification factor will increase the result of the second part, thereby further increasing the comprehensive anomaly level after multiplying the two parts, which can better reflect the overall risk level under high-risk synergy.

[0125] When any one or more of the three risk levels decrease, the contribution value of the corresponding risk level in the first part of the calculation will decrease, and the overall result of the first part will decrease. If the three risk levels decrease in tandem, the result of the second part will also decrease, ultimately leading to a decrease in the overall anomaly level.

[0126] If the preset weight coefficient for a certain risk level is high, such as the weight coefficient for the time-duration risk level, then the change of this risk level will have a more significant impact on the calculation results of the first part than other risk levels, and thus have a more significant impact on the trend of the overall anomaly level.

[0127] When conducting joint source tracing analysis on the equipment composition, operational sequence correlation, and external environment correlation data of the abnormal area, the analysis of equipment composition requires verifying the model, service life, and recent maintenance records of all equipment in the abnormal area to check for old or unmaintained equipment; the analysis of operational sequence correlation requires retrieving equipment operation logs to check the start-up and shutdown sequence and operating parameter adjustment records of equipment during the abnormal period to determine whether there are timing conflicts or parameter setting errors; the analysis of external environment correlation data requires collecting data such as ambient temperature, voltage stability, and power supply pressure during the abnormal period to check whether there are energy consumption anomalies caused by environmental factors. The key influencing factors of the abnormal area are obtained by summarizing the equipment problems, timing problems, or environmental problems identified in the above analysis.

[0128] The beneficial effects are as follows: by calculating and analyzing the spatial distribution characteristics, abnormal areas in the dynamic zoning energy consumption map can be accurately defined, avoiding omissions or misjudgments of abnormal areas; the multi-dimensional risk level judgment combined with the fusion calculation of weights and synergistic effect amplification coefficients can comprehensively and objectively assess the risk level of abnormal areas, ensuring the accuracy of the comprehensive abnormality level; the joint source tracing analysis of equipment composition, operating sequence and external environment can deeply explore the core reasons for energy consumption abnormalities, providing a precise basis for subsequent formulation of targeted energy-saving control instructions, and improving the overall targeting and effectiveness of energy consumption anomaly management.

[0129] S4. Based on the comprehensive anomaly level and the key influencing factors, drive the initial energy-saving control command of the target equipment to control the energy-saving operation of the target equipment;

[0130] In this embodiment of the invention, the step of driving the initial energy-saving control command of the target device based on the comprehensive anomaly level and the key influencing factors to control the energy-saving operation of the target device includes:

[0131] Using the comprehensive anomaly level and the key influencing factors as query conditions, predefined energy-saving control strategies are retrieved to obtain candidate control strategies for the target equipment.

[0132] The candidate control strategy is adapted to the operating state parameters of the target device to eliminate conflicting strategies between the candidate control strategy and the operating state parameters, thereby obtaining the adapted control strategy for the target device.

[0133] Based on the source type of the anomaly of the key influencing factors, the control parameters of the adaptive control strategy are assigned values, and the assigned control parameters are logically bound to generate the preliminary energy-saving control instructions for the target equipment.

[0134] The preliminary energy-saving control command is sent to the control interface of the target device, driving the target device to perform the energy-saving operation corresponding to the preliminary energy-saving control command.

[0135] Candidate control strategies are retrieved by using a predefined energy-saving control strategy library. This library pre-stores energy-saving control schemes corresponding to different comprehensive anomaly levels and different combinations of key influencing factors. Each scheme clearly defines the control direction for a specific risk level and influencing factor. During the search, the strategy category that is completely consistent with the current comprehensive anomaly level is first located in the strategy library. Then, under this category, control schemes that are completely matched with key influencing factors, such as equipment aging time-series conflicts and high environmental temperatures, are screened one by one. All successfully matched control schemes are compiled and summarized to obtain the candidate control strategies for the target equipment.

[0136] The compatibility of candidate control strategies with the operating status parameters of the target device is verified. The operating status parameters of the target device include the current real-time power, core temperature, and operating mode, such as continuous operation, intermittent operation, and current load rate. These parameters are collected in real time by the device's built-in sensors and transmitted to the control terminal. During the verification, the execution requirements of each candidate control strategy are compared with the current operating status parameters. For example, if a candidate control strategy requires the device power to be reduced to a specific value, but the current core temperature of the device has exceeded the preset safety threshold, reducing the power will lead to a decrease in the device's heat dissipation efficiency and thus exacerbate the temperature anomaly. In this case, the candidate control strategy conflicts with the operating status parameters. All conflicting candidate control strategies are removed from the list, and the remaining control strategies are the compatible control strategies for the target device.

[0137] Based on the root cause type of the key influencing factors, control parameters for the adaptive control strategy are assigned values ​​and logically bound. The root cause types of key influencing factors include equipment composition issues, such as aging equipment components, failures in operating sequence, incorrect start-up and shutdown sequences, unreasonable operating cycles, and external environmental issues, such as excessively high ambient temperatures and unstable voltage. Control parameters for the adaptive control strategy are assigned values ​​for different root cause types. For example, if the root cause is equipment aging, the control parameters for the adaptive control strategy include power adjustment value and operating interval duration. In this case, the power adjustment value is set to a reasonable proportion of the equipment's rated power to ensure stable equipment operation and reduce energy consumption, and the operating interval duration is set to a longer time than normal equipment to reduce equipment wear. After assignment, the execution order and associated conditions of the control parameters are defined. For example, the power adjustment operation is executed first. After the equipment runs for 10 minutes, the core temperature of the equipment is monitored by sensors. If the temperature is within the preset normal range, the current power output is maintained; if the temperature exceeds the normal range, the operating interval duration is adjusted. Through this logical binding process, preliminary energy-saving control instructions for the target equipment are generated.

[0138] The initial energy-saving control command is sent to the control interface of the target device to drive energy-saving operation. The control interface of the target device includes hardware interfaces, such as RS485 interfaces and Ethernet interfaces, and corresponding communication protocols, such as Modbus protocols. First, according to the communication protocol format adapted to the target device, the initial energy-saving control command is converted into a binary command signal that the device can recognize. Then, the command signal is transmitted to the hardware control interface of the device through a wired connection, such as a network cable signal line. After receiving the command signal, the control unit inside the device parses the execution requirements in the command line by line and drives the execution components inside the device, such as the power regulator and timer, to perform the corresponding operation according to the parsing result. For example, the power output is adjusted according to the command, and the device's operating sequence is modified, so that the target device performs the energy-saving operation corresponding to the initial energy-saving control command.

[0139] The beneficial effects are as follows: by retrieving a predefined energy-saving control strategy library using comprehensive anomaly levels and key influencing factors as query conditions, the system ensures accurate matching between candidate control strategies and the energy consumption anomalies of the target equipment; by verifying compatibility with real-time operating parameters of the equipment and eliminating conflicting strategies, the system ensures that the adapted control strategies conform to the current operating conditions of the equipment and do not cause new operational problems; by assigning values ​​to control parameters and logically binding them according to the anomaly root cause type, the initial energy-saving control commands have clear execution basis and operational logic, improving the targeting and executability of the commands; finally, by sending commands to the control interface through a standardized command conversion and transmission process, the system ensures that energy-saving operations are effectively implemented, thereby improving the accuracy and adaptability of the initial energy-saving control commands, ensuring that the energy-saving operations of the target equipment are scientific and reasonable, and laying a reliable foundation for the optimization of subsequent energy-saving control commands.

[0140] S5. Based on the control feedback information of the target equipment after the energy-saving operation, the control parameters of the preliminary energy-saving control command are compensated to obtain the optimized energy-saving control command of the target equipment.

[0141] In this embodiment of the invention, the step of compensating the control parameters of the preliminary energy-saving control command based on the control feedback information of the target device after the energy-saving operation to obtain the optimized energy-saving control command for the target device includes:

[0142] The operating status data and real-time energy consumption data of the target device after the energy-saving operation are used as the control feedback information of the target device after the energy-saving operation.

[0143] By jointly analyzing the actual energy consumption change rate, equipment operation stability index, and control target achievement index of the control feedback information, the abnormal control links of the target equipment after the energy-saving operation are obtained.

[0144] Based on the abnormal control mechanism, a preset compensation rule library is invoked to obtain the compensation control parameters of the preliminary energy-saving control command;

[0145] Based on the compensation control parameters, the preliminary energy-saving control command is modified to obtain the optimized energy-saving control command for the target equipment.

[0146] The target device collects operational status data and real-time energy consumption data after energy-saving operations using various built-in sensors. The operational status data includes the device's core temperature, operating voltage, and operating speed. Temperature data is collected every 5 minutes by an internal temperature sensor, voltage data is collected in real time by a voltage sensor, and speed data is recorded synchronously by a speed sensor. Real-time energy consumption data is collected by energy consumption monitoring sensors, showing the cumulative energy consumption value per hour and the energy consumption value per unit time. All collected operational status data and real-time energy consumption data are integrated to ensure that there are no missing or duplicate data. The integrated data constitutes the control feedback information of the target device after the energy-saving operation.

[0147] A joint analysis was conducted on the actual energy consumption change rate, equipment operation stability indicators, and control target achievement indicators in the control feedback information: When calculating the actual energy consumption change rate, the average energy consumption value for the same period before the energy-saving operation was subtracted from the average energy consumption value for the three consecutive hours after the energy-saving operation, and then the difference was divided by the average energy consumption value before the energy-saving operation to obtain the actual energy consumption change rate. When evaluating the equipment operation stability indicators, the collected core temperature, operating voltage, and operating speed of the equipment were compared with the preset normal operating range. The number of times each parameter exceeded the normal range was counted. If the cumulative number of times any parameter exceeded the normal range exceeded 3 times, the equipment was deemed to be operating stably. If the energy consumption rate is lower than the expected decrease, the equipment operation stability index is not met, and the control target achievement index is not met. When calculating the control target achievement index, the actual average energy consumption value after the energy-saving operation is subtracted from the preset energy-saving control target energy consumption value, and the difference is divided by the preset energy-saving control target energy consumption value. If the ratio is less than 10%, the control target achievement index is judged to be not met. The analysis results of the three indicators are combined. If the actual energy consumption change rate is lower than the expected decrease, the equipment operation stability index is not met, and the control target achievement index is not met, the specific links that cause these problems are comprehensively judged. For example, if the power adjustment range in the initial instruction is too large, resulting in abnormal equipment temperature, this link is the abnormal control link of the target equipment after the energy-saving operation.

[0148] The pre-set compensation rule library stores the matching relationships between different abnormal control links and corresponding compensation control parameters. Each matching relationship clarifies the specific manifestation of the abnormal link and the control parameters and adjustment values ​​that need to be adjusted. For example, when the abnormal control link is "the power adjustment range is too large, causing abnormal equipment temperature", the corresponding compensation control parameter is "reduce the power adjustment range from 20% to 12%". Based on the identified abnormal control link, a precise match is performed in the compensation rule library to find the matching relationship that completely corresponds to the abnormal link. The specific control parameter adjustment requirements are extracted from the relationship. The parameter values ​​corresponding to these adjustment requirements are the compensation control parameters of the preliminary energy-saving control command.

[0149] First, review all control parameters in the initial energy-saving control command to identify the types of parameters that need to be modified. For example, the control parameters in the initial command include power adjustment range and operating interval duration, among which the power adjustment range needs to be modified. Then, modify the corresponding parameters in the initial command according to the requirements of the compensation control parameters. If the compensation control parameter requires "reducing the power adjustment range from 20% to 12%", then directly replace the power adjustment range value in the initial command with 12%. After modification, check whether there are any logical conflicts between all the modified control parameters. For example, whether the modified power adjustment range matches the operating interval duration. After ensuring there are no conflicts, form a new command. This new command is the optimized energy-saving control command for the target equipment.

[0150] The beneficial effects are as follows: by collecting equipment operating status and real-time energy consumption data to construct control feedback information, it ensures a comprehensive understanding of the actual equipment situation after energy-saving operations; by jointly analyzing three key indicators, it accurately locates abnormal control links, avoiding omissions or misjudgments of problems; based on the abnormal links, it calls the compensation rule library to obtain appropriate compensation control parameters, ensuring the rationality of parameter adjustments; based on the compensation parameters, it corrects the initial instructions to obtain optimized energy-saving control instructions, effectively improving the accuracy of energy-saving control, ensuring that the target equipment maintains stable operation while achieving energy-saving effects, and further optimizing the quality of energy consumption management.

[0151] S6. Apply the optimized energy-saving control command to perform energy-saving control on the target device and update the dynamic partition energy consumption map simultaneously.

[0152] In this embodiment of the invention, applying the optimized energy-saving control command to perform energy-saving control on the target device and synchronously updating the dynamic partition energy consumption map includes:

[0153] Analyze the control logic and parameter set of the optimized energy-saving control command;

[0154] Based on the communication protocol and control interface type of the target device, the control logic and the parameter set are appropriately matched and encapsulated into the instruction frame of the target device to obtain the underlying control signal of the target device;

[0155] Through the control interface of the target device, the underlying control signal is sent to drive the target device to execute the energy-saving control action of the optimized energy-saving regulation command;

[0156] The updated energy consumption data generated by the target device after executing the energy-saving control action is collected, and the updated energy consumption data is input into the generation process of the dynamic partition energy consumption map to update the dynamic partition energy consumption map.

[0157] After obtaining the optimized energy-saving control instruction, its internal components are broken down according to the preset structured format of the instruction. First, the specific execution steps of the control logic are identified one by one, such as "first adjust the equipment operating power to the specified value, and after the equipment operating status is stable for 5 minutes, set the periodic operation interval of the equipment". Then, the specific numerical information corresponding to each execution step in the parameter set is extracted, such as the target value of power adjustment and the duration of the periodic operation interval. The extracted control logic steps and parameter values ​​are cross-verified to ensure that each control logic link has a unique corresponding parameter value to support it. Finally, a clear and complete control logic and parameter set of the optimized energy-saving control instruction are obtained.

[0158] First, confirm the compatible communication protocol of the target device through its equipment manual or management system, such as the Modbus protocol and the control interface type, such as the RS485 interface. According to the data encoding format specified by the confirmed communication protocol, convert the parsed control logic into protocol-specific opcodes. For example, the "power adjustment" step corresponds to the 0x06 opcode in the protocol, and the "running interval setting" step corresponds to the 0x03 opcode. Then, convert the specific values ​​in the parameter set into the byte length and hexadecimal format required by the protocol. For example, convert the power target value into 2 bytes of hexadecimal data. Then, according to the standard structure of the instruction frame, including the start flag, device address code, opcode field, parameter data area, check bit, and stop flag, integrate the opcode and the converted parameter data into a complete instruction frame. This instruction frame is the underlying control signal that the target device can directly respond to.

[0159] First, use a multimeter or interface testing tool to confirm the target device's control interface. If the electrical connection of the RS485 interface is normal, ensure the physical connection between the control terminal and the device's control interface. For example, ensure a secure connection with a shielded signal cable and no signal interference. Then, transmit the generated low-level control signal to the target device's core control unit through this control interface. After receiving the low-level control signal, the core control unit parses the operation code and parameter information bit by bit according to the byte order of the signal. Based on the parsing results, it drives the corresponding execution components inside the device to perform actions. For example, based on the "power adjustment" operation code and corresponding parameters, it drives the power adjustment module to reduce the device's output power to the target value. Based on the "running interval setting" operation code and corresponding parameters, it drives the timing control module to set the device's start and stop interval, thereby enabling the target device to accurately execute and optimize the energy-saving control actions corresponding to the energy-saving control instructions.

[0160] By using high-precision energy consumption monitoring sensors pre-deployed on the target equipment, during the energy-saving control process, real-time energy consumption values, energy consumption changes per unit time, and total cumulative energy consumption are acquired every 15 minutes. The acquisition time point for each data point is recorded simultaneously to ensure that the data accurately corresponds to the equipment's operating stage. The acquired updated energy consumption data is then organized according to the standardized format required for generating a dynamic partitioned energy consumption map, replacing the historical energy consumption data used in the original dynamic partitioned energy consumption map generation process. The energy consumption density, energy consumption difference, energy consumption fluctuation frequency, and corresponding height, color, and shape encoding values ​​corresponding to the updated energy consumption data are recalculated. Following the spatial adjacency clustering and fusion rendering rules of the dynamic partitioned energy consumption map, the newly calculated encoding values ​​are then subjected to region aggregation and color filling, ultimately completing the update of the dynamic partitioned energy consumption map.

[0161] The beneficial effects include: optimizing energy-saving control commands through structured parsing to ensure that the control logic and parameter information of the commands are clear and unambiguous, avoiding erroneous actions by the equipment due to parsing deviations; encapsulating the underlying control signals according to the target equipment's specific communication protocol and control interface type to ensure that the signals can be accurately identified and received by the equipment, reducing the probability of errors in signal transmission and parsing; ensuring stable transmission of underlying control signals to the core control unit of the equipment by confirming the interface connection status before sending signals, driving the execution components to accurately execute energy-saving control actions, and improving the execution accuracy of energy-saving control; collecting updated energy consumption data after the equipment executes energy-saving actions in real time and organizing it according to a standard format, replacing historical data to regenerate a dynamic partitioned energy consumption map, realizing real-time synchronization between energy consumption visualization and the actual energy consumption status of the equipment, providing accurate dynamic data basis for subsequent energy consumption anomaly monitoring and control strategy optimization, and improving the timeliness and reliability of energy consumption visualization and control as a whole.

[0162] like Figure 2 The diagram shown is a functional block diagram of an energy consumption management and control system provided in an embodiment of the present invention.

[0163] The energy consumption management and control system 100 described in this invention can be installed in an electronic device. Depending on the functions implemented, the energy consumption management and control system 100 may include a multi-dimensional feature fusion module 101, a dynamic zone energy consumption map construction module 102, an abnormal area risk assessment module 103, an energy-saving control instruction generation module 104, a control parameter compensation module 105, and a closed-loop control execution and visualization update module 106. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, stored in the memory of the electronic device.

[0164] In this embodiment, the functions of each module / unit are as follows:

[0165] The multi-dimensional feature fusion module 101 is used to perform multi-dimensional feature fusion on the standardized energy consumption data of the target device to obtain the energy consumption status features of the target device.

[0166] The dynamic partitioned energy consumption map construction module 102 is used to perform spatial adjacency analysis on the energy consumption value, energy consumption change trend and energy consumption type in the energy consumption state features according to the predefined visual channel mapping rules, so as to construct a dynamic partitioned energy consumption map of the energy consumption state features.

[0167] The abnormal area risk assessment module 103 is used to analyze the spatial distribution characteristics of the dynamic partition energy consumption map to define the abnormal areas of the dynamic partition energy consumption map, and to conduct risk assessment on the abnormal areas to obtain the comprehensive abnormality level and key influencing factors of the abnormal areas.

[0168] The energy-saving control command generation module 104 is used to drive the initial energy-saving control command of the target equipment according to the comprehensive anomaly level and the key influencing factors, so as to control the energy-saving operation of the target equipment;

[0169] The control parameter compensation module 105 is used to compensate the control parameters of the preliminary energy-saving control command based on the control feedback information of the target equipment after the energy-saving operation, so as to obtain the optimized energy-saving control command of the target equipment.

[0170] The closed-loop control execution and visualization update module 106 is used to apply the optimized energy-saving control command to execute energy-saving control on the target device and simultaneously update the dynamic partition energy consumption map.

[0171] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0172] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0173] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0174] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0175] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0176] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An energy consumption management and control method, characterized in that, The method includes: S1. Perform multi-dimensional feature fusion on the standardized energy consumption data of the target device to obtain the energy consumption status characteristics of the target device; S2. Based on predefined visual channel mapping rules, perform spatial adjacency analysis on the energy consumption values, energy consumption change trends, and energy consumption types in the energy consumption state characteristics to construct a dynamic partitioned energy consumption map of the energy consumption state characteristics, including: The energy consumption state characteristics are decoupled to obtain the energy consumption value, energy consumption change trend and energy consumption type of the energy consumption state characteristics; According to the predefined visual channel mapping rules, the energy consumption value, the energy consumption change trend and the energy consumption type are visually channel separated and mapped to obtain the height encoding value, color encoding value and shape encoding value of the energy consumption state feature; Based on the height encoding value, the color encoding value, and the shape encoding value, a visual primitive of the energy consumption state feature is generated; Based on the spatial location and connection relationship of the target device, the coordinates of the visualized graphic elements are determined; Based on the coordinates, spatial adjacency clustering analysis is performed on the visualized primitives to aggregate visualized primitives with similar visual attributes and spatial proximity into the same primitive region. The visualized primitives in the same primitive region are fused and rendered to obtain a dynamic partitioned energy consumption map of the energy consumption state characteristics; S3. Analyze the spatial distribution characteristics of the dynamic partition energy consumption map to define the abnormal areas of the dynamic partition energy consumption map, and conduct a risk assessment on the abnormal areas to obtain the comprehensive abnormality level and key influencing factors of the abnormal areas. S4. Based on the comprehensive anomaly level and the key influencing factors, drive the initial energy-saving control command of the target equipment to control the energy-saving operation of the target equipment; S5. Based on the control feedback information of the target equipment after the energy-saving operation, the control parameters of the preliminary energy-saving control command are compensated to obtain the optimized energy-saving control command of the target equipment. S6. Apply the optimized energy-saving control command to perform energy-saving control on the target device and update the dynamic partition energy consumption map simultaneously.

2. The energy consumption management and control method as described in claim 1, characterized in that, The process of fusing multi-dimensional features into the standardized energy consumption data of the target device to obtain the energy consumption status features of the target device includes: Collect raw energy consumption monitoring data and equipment attribute data of the target equipment; Outliers in the original energy consumption monitoring data are removed, and data of different dimensions in the original energy consumption monitoring data after removing outliers are unified to the standard unit of measurement to obtain the standardized energy consumption data of the target equipment. Extract the time-domain features, frequency-domain features, and sequence pattern features of the standardized energy consumption data; The time-domain features, frequency-domain features, and sequence pattern features are fused to obtain the energy consumption status features of the target device.

3. The energy consumption management and control method as described in claim 1, characterized in that, The analysis of the spatial distribution characteristics of the dynamic partition energy consumption map to define the abnormal areas of the dynamic partition energy consumption map includes: The energy consumption density, energy consumption difference, and energy consumption fluctuation frequency of the dynamic partition energy consumption map are used as the spatial distribution characteristics of the dynamic partition energy consumption map. A difference analysis is performed on the spatial distribution characteristics to obtain the deviation data of the dynamic partition energy consumption map; Based on the deviation data, abnormal partitioning is performed on the dynamic partitioning energy consumption map to obtain the abnormal areas of the dynamic partitioning energy consumption map.

4. The energy consumption management and control method as described in claim 1, characterized in that, The risk assessment of the abnormal area yields a comprehensive abnormality level and key influencing factors, including: The anomaly area is assessed for multi-dimensional risk levels to obtain its spatial propagation risk level, temporal persistence risk level, and energy consumption intensity risk level. Based on preset weighting coefficients and synergistic effect amplification coefficients, the spatial propagation risk level, the temporal persistence risk level, and the energy consumption intensity risk level are fused and calculated to obtain the comprehensive anomaly level of the anomaly area. By conducting a joint source tracing analysis on the equipment composition, operational sequence correlation, and external environment correlation data of the abnormal area, the key influencing factors of the abnormal area are obtained.

5. The energy consumption management and control method as described in claim 4, characterized in that, The formula for the fusion calculation is as follows: ； In the formula, This indicates the overall anomaly level. This indicates the level of risk for space propagation. This indicates the level of risk based on the duration of the risk. This indicates the energy consumption intensity risk level. This represents the preset spatial propagation risk level weighting coefficient. This represents the preset weighting coefficient for the duration of risk. This represents the preset weighting coefficient for energy consumption intensity risk level. This represents the preset synergistic amplification factor. This represents the preset power parameter. This represents the preset smallest positive number. This represents the cube root operation. Represents the hyperbolic tangent function. This indicates taking the maximum value.

6. The energy consumption management and control method as described in claim 1, characterized in that, The step of driving the initial energy-saving control command of the target equipment based on the comprehensive anomaly level and the key influencing factors to control the energy-saving operation of the target equipment includes: Using the comprehensive anomaly level and the key influencing factors as query conditions, predefined energy-saving control strategies are retrieved to obtain candidate control strategies for the target equipment. The candidate control strategy is adapted to the operating state parameters of the target device to eliminate conflicting strategies between the candidate control strategy and the operating state parameters, thereby obtaining the adapted control strategy for the target device. Based on the source type of the anomaly of the key influencing factors, the control parameters of the adaptive control strategy are assigned values, and the assigned control parameters are logically bound to generate the preliminary energy-saving control instructions for the target equipment. The preliminary energy-saving control command is sent to the control interface of the target device, driving the target device to perform the energy-saving operation corresponding to the preliminary energy-saving control command.

7. The energy consumption management and control method as described in claim 1, characterized in that, The step of compensating the control parameters of the initial energy-saving control command based on the control feedback information of the target equipment after the energy-saving operation to obtain the optimized energy-saving control command for the target equipment includes: The operating status data and real-time energy consumption data of the target device after the energy-saving operation are used as the control feedback information of the target device after the energy-saving operation. By jointly analyzing the actual energy consumption change rate, equipment operation stability index, and control target achievement index of the control feedback information, the abnormal control links of the target equipment after the energy-saving operation are obtained. Based on the abnormal control mechanism, a preset compensation rule library is invoked to obtain the compensation control parameters of the preliminary energy-saving control command; Based on the compensation control parameters, the preliminary energy-saving control command is modified to obtain the optimized energy-saving control command for the target equipment.

8. The energy consumption management and control method as described in claim 1, characterized in that, The application of the optimized energy-saving control command executes energy-saving control on the target device and synchronously updates the dynamic partition energy consumption map, including: Analyze the control logic and parameter set of the optimized energy-saving control command; Based on the communication protocol and control interface type of the target device, the control logic and the parameter set are appropriately matched and encapsulated into the instruction frame of the target device to obtain the underlying control signal of the target device; Through the control interface of the target device, the underlying control signal is sent to drive the target device to execute the energy-saving control action of the optimized energy-saving regulation command; The updated energy consumption data generated by the target device after executing the energy-saving control action is collected, and the updated energy consumption data is input into the generation process of the dynamic partition energy consumption map to update the dynamic partition energy consumption map.

9. An energy consumption management and control system, characterized in that, The system for implementing the energy consumption management and control method according to claim 1 includes: A multi-dimensional feature fusion module is used to perform multi-dimensional feature fusion on the standardized energy consumption data of the target device to obtain the energy consumption status characteristics of the target device. The dynamic partitioned energy consumption map construction module is used to perform spatial adjacency analysis on the energy consumption values, energy consumption change trends and energy consumption types in the energy consumption state features according to predefined visual channel mapping rules, so as to construct a dynamic partitioned energy consumption map of the energy consumption state features. The abnormal area risk assessment module is used to analyze the spatial distribution characteristics of the dynamic partition energy consumption map to define the abnormal areas of the dynamic partition energy consumption map, and to conduct risk assessment on the abnormal areas to obtain the comprehensive abnormality level and key influencing factors of the abnormal areas. An energy-saving control command generation module is used to drive the initial energy-saving control command of the target equipment according to the comprehensive anomaly level and the key influencing factors, so as to control the energy-saving operation of the target equipment; The control parameter compensation module is used to compensate the control parameters of the initial energy-saving control command based on the control feedback information of the target equipment after the energy-saving operation, so as to obtain the optimized energy-saving control command of the target equipment. The closed-loop control execution and visualization update module is used to apply the optimized energy-saving control instructions, execute energy-saving control on the target equipment, and synchronously update the dynamic partition energy consumption map.

Images