Building energy equipment energy consumption digital construction method and system based on digital twinning

Abstract

The invention relates to the technical field of digital twinning modeling, in particular to a digital twinning-based building energy equipment energy consumption digital construction method and system, and the method comprises the following steps: obtaining the operation state data of building energy equipment according to a digital twinning model, calculating the energy consumption increment in unit time and the energy consumption change rate of a time window, and calculating the energy consumption change rate of the building energy equipment; and obtaining equipment energy consumption abrupt change time sequence data. According to the method, the energy consumption increment and the change rate in the time window are calculated, the energy consumption abrupt change time sequence data are captured, the abrupt change point of the high-load equipment is accurately identified, the energy consumption trend parameters are adjusted based on the accumulated energy consumption change rate, the regional energy consumption gradient change rate is analyzed, and the contribution of equipment increase and decrease and mode adjustment to the energy consumption is calculated. The weight adjustment of the equipment in the overall building energy consumption is optimized, so that the influence of local load on the overall energy consumption is more accurate, the error value and the growth rate are calculated, the energy consumption calculation mode is adjusted, and the stability of error control is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twin modeling, and in particular to a method and system for digitally constructing energy consumption of building energy equipment based on digital twins. Background Art

[0002] The field of digital twin modeling technology includes the digital mapping of physical entities or systems, and the simulation, analysis and optimization of their entire life cycle by establishing a virtual model that is highly consistent with the real object. The core content includes data collection, model construction, real-time interaction and feedback control. Data collection obtains the operating parameters of physical entities through sensors and Internet of Things devices, model construction uses computer modeling technology to generate the corresponding virtual model, real-time interaction realizes the linkage between physical and digital space based on two-way information flow, and feedback control combines simulation calculations and optimization strategies to adjust the physical system. It is widely used to optimize resource allocation, improve system operation efficiency and predict failure risks.

[0003] Among them, the digital construction method of building energy equipment energy consumption based on digital twins refers to the use of digital twin technology to model and analyze the energy consumption data of building energy equipment to form a corresponding digital energy consumption system, covering technical matters such as energy consumption data collection, virtual model construction, parameter calibration and data fusion. Sensors installed on building equipment record operating parameters such as power consumption, voltage, and current. Virtual model construction uses computer modeling methods to generate an energy consumption simulation model of the equipment. Parameter calibration combines historical operating data to correct errors in the model. Data fusion uses multi-source data to correlate and calculate the energy consumption relationship between devices, and finally forms a visual energy consumption digital model to provide data support for building energy management.

[0004] In the energy consumption modeling of building energy equipment, the existing technology mainly relies on sensors to collect the operating parameters of the equipment, but does not effectively identify sudden changes in energy consumption, making it easy to ignore short-term energy consumption anomalies, resulting in limited data integrity. The construction of the energy consumption model is based on the equipment operating parameters, but lacks dynamic adjustment of the mutation trend, which makes the energy consumption calculation prone to errors when sudden changes occur. The regional energy consumption distribution mainly relies on historical data and current equipment operation information for statistical analysis, but fails to refine the contribution of equipment increase and decrease and mode changes to local energy consumption, resulting in insufficient accuracy of energy consumption gradient changes. The contribution of equipment to the overall building energy consumption has not formed a dynamic weight adjustment mechanism, so that the mapping relationship of equipment power consumption before and after the mutation cannot be effectively corrected, affecting the accuracy of energy consumption assessment. In terms of energy consumption error control, the calculation method mainly relies on static parameter calibration, which is difficult to make precise adjustments when the error offset exceeds the threshold, resulting in insufficient long-term stability of energy consumption calculation and affecting the optimization strategy of building energy management. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and propose a digital construction method for energy consumption of building energy equipment based on digital twins.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: a digital construction method of energy consumption of building energy equipment based on digital twin, comprising the following steps: S1: According to the digital twin model, the operating status data of the building energy equipment is obtained, the energy consumption increment per unit time and the energy consumption change rate in the time window are calculated, and the equipment energy consumption mutation time series data is obtained; S2: Based on the equipment energy consumption mutation time series data, screen high-load running equipment, judge and confirm the mutation point, calculate the cumulative energy consumption change rate before and after the mutation, adjust the equipment operation energy consumption trend coefficient, and obtain the mutation point corrected energy consumption trend data; S3: Based on the energy consumption trend data corrected at the mutation point, the energy consumption gradient change rate between regions is calculated, the region exceeding the preset amplitude threshold is screened, the contribution ratio of equipment increase / decrease and mode change to energy consumption is calculated, and the regional energy consumption gradient distribution data is obtained; S4: Based on the regional energy consumption gradient distribution data, calculate the impact weight of the equipment in the building energy consumption, determine the change in energy consumption contribution ratio before and after the mutation, adjust the equipment power consumption mapping weight and load participation, and obtain the equipment energy consumption mapping adjustment coefficient; S5: Based on the equipment energy consumption mapping adjustment coefficient, calculate the energy consumption error value and error growth rate of the building energy consumption area, mark the error exceeding the threshold area, adjust the energy consumption calculation method, and obtain a dynamic digital construction plan for the building energy equipment energy consumption.

[0007] As a further solution of the present invention, the equipment energy consumption mutation time series data includes the energy consumption increment per unit time, the energy consumption change rate of the time window, and the energy consumption mutation point time series information; the mutation point corrected energy consumption trend data includes the mutation point confirmation result, the cumulative energy consumption change rate, and the equipment operation energy consumption trend coefficient; the regional energy consumption gradient distribution data includes the energy consumption gradient change amplitude, the local load equipment type, and the contribution ratio of equipment increase or decrease to energy consumption; the equipment energy consumption mapping adjustment coefficient includes the change in the equipment energy consumption contribution ratio, the power consumption mapping weight adjustment value, and the equipment load participation adjustment value; the dynamic digital construction plan of building energy equipment energy consumption includes the energy consumption calculation error value, the error growth rate, the key energy-consuming equipment type, the equipment group power consumption ratio and the energy consumption calculation adjustment plan.

[0008] As a further solution of the present invention, the steps for acquiring the equipment energy consumption mutation time series data are as follows: S111: Based on the digital twin model, record the power input, load changes, operating time and instantaneous power consumption of the power equipment, calculate the energy consumption increment per unit time, and arrange them in time series to establish energy consumption increment time series data; S112: Based on the energy consumption increment time series data, a time window is set, using the formula: ; Calculation time window Energy consumption change rate , and establish the time series data of energy consumption change rate, where: Representing time point The increase in energy consumption at It's time point The increase in energy consumption at Represents the number of data points in the time window, Represents the length of the time window; S113: According to the energy consumption change rate time series data, identify the mutation point of the energy consumption change rate, select the time point of the energy consumption mutation and the corresponding change range, and establish the equipment energy consumption mutation time series data.

[0009] As a further solution of the present invention, the step of obtaining the mutation point corrected energy consumption trend data is: S211: Based on the equipment energy consumption mutation time series data, calculate the energy consumption increment change of adjacent time windows, obtain the energy consumption increment value of each time window, and compare the energy consumption increment change of the adjacent windows before and after, screen the high-load equipment whose energy consumption increment change exceeds the set change threshold, judge the existence of the mutation point according to the current input of the high-load running equipment, the equipment switch state, and the load adjustment range, and obtain the equipment energy consumption mutation point record; S212: Based on the record of the energy consumption mutation point of the equipment, the formula is used: ; Calculate the ratio of energy consumption change rate before and after mutation , and determine the mutation point to correct the energy consumption trend data, where: Represents the energy consumption value after the mutation point, Represents the energy consumption value before the mutation point, Represents the number of time windows before and after the mutation point, Represents the change in current input to the device, Represents the equipment load adjustment range; S213: Based on the energy consumption change rate ratio before and after the mutation, the equipment operation energy consumption trend coefficient is adjusted, the energy consumption trend data after the mutation point is corrected, and the mutation point corrected energy consumption trend data is generated.

[0010] As a further solution of the present invention, the steps for obtaining the regional energy consumption gradient distribution data are: S311: Based on the energy consumption trend data corrected by the mutation point, the energy consumption data, temperature and humidity distribution, equipment layout density and power consumption of the building partitions are counted, using the formula: ; Compute partitions and The energy consumption gradient between , obtain the energy consumption gradient change range data between partitions, where, and Represents the total energy consumption of the two partitions, and is the area of ​​the two partitions; S312: According to the energy consumption gradient change amplitude data between the partitions, the partitions exceeding the preset amplitude threshold are selected, and the local load device types, switching frequencies and operation modes of the corresponding areas are counted to establish the operation parameters of the load devices in the over-threshold area; S313: According to the operating parameters of the load device in the super-threshold region, the formula is used: ; The contribution of computing equipment increase / decrease and operation mode changes to regional energy consumption , generate regional energy consumption gradient distribution data, where, , , Respectively represent power, operating time and switching frequency of each device, , , Respectively represent the adjusted power, operating time and switching frequency of each device, is the total number of devices before adjustment, is the adjusted total number of devices.

[0011] As a further solution of the present invention, the step of obtaining the device energy consumption mapping adjustment coefficient is: S411: Based on the regional energy consumption gradient distribution data, calculate the energy consumption value per unit time of the local equipment, extract the power load proportion of each device per unit time, count the contribution rate of the difference equipment in the overall building energy consumption, and obtain the equipment power load proportion data; S412: Based on the equipment power load proportion data, the formula is used: ; Computing equipment The contribution rate change , filter out the equipment with increased and decreased contribution rates, and determine the contribution rate change trend of each equipment to obtain the equipment energy consumption contribution rate change data, among which, Representative equipment The energy consumption contribution rate in the period after the mutation, Representative equipment The energy consumption contribution rate in the period before the mutation, Represents the total number of all devices, Represents the total change in contribution rate of all equipment, Represents the total contribution rate of all devices before the mutation; S413: Based on the device energy consumption contribution rate change data, if the contribution ratio increases, the device power consumption mapping weight is adjusted to increase the load influence; if the contribution ratio decreases, the device load participation is reduced to obtain the device energy consumption mapping adjustment coefficient.

[0012] As a further solution of the present invention, the steps for obtaining the dynamic digital construction solution of building energy equipment energy consumption are: S511: Count the equipment operation status and energy consumption data of the energy consumption areas of the difference buildings, calculate the energy consumption calculation error value of each building energy consumption area, count the energy consumption calculation error growth rate, filter and mark the areas where the error deviation exceeds the set error range, and obtain the error deviation area mark set; S512: According to the error offset area mark set, count the key energy-consuming device types in the marked area, using the formula: ; Calculate the power consumption ratio of devices in the marked area ,in, Representative Unit power consumption of class equipment, Represents the frequency of use of this type of equipment. Represents the total running time of the device during the statistical period. Represents the power fluctuation of the device, Represents the power threshold of the device. Represents the total number of devices in the marked area; S513: Based on the power consumption proportion of the equipment in the marked area, the energy consumption calculation of the marked area is adjusted, and the error is corrected in combination with the equipment energy consumption mapping adjustment coefficient to obtain a dynamic digital construction plan for building energy equipment energy consumption.

[0013] The digital twin-based building energy equipment energy consumption digital construction system includes: The energy consumption data acquisition module obtains the power input, load change, operating time, and instantaneous power consumption of building energy equipment based on the digital twin model, calculates the energy consumption increment per unit time, sets the time window to calculate the change rate, and obtains the equipment energy consumption mutation time series data; The energy consumption mutation point correction module selects high-load running equipment based on the equipment energy consumption mutation time series data, and determines the mutation point according to the current input of the high-load running equipment, the equipment switch state, and the load adjustment range, calculates the cumulative energy consumption change rate before and after the mutation, adjusts the equipment operation energy consumption trend coefficient, and obtains the mutation point correction energy consumption trend data; The regional energy consumption gradient analysis module corrects the energy consumption trend data based on the mutation point, counts the energy consumption of the building partition, the temperature and humidity distribution, the equipment density, and the power consumption, calculates the change amplitude of the regional energy consumption gradient, screens the area exceeding the preset amplitude threshold, calculates the contribution ratio of the regional energy consumption, and obtains the energy consumption gradient distribution data of the building area; The equipment energy consumption weight adjustment module calculates the influence weight of local high-power equipment in building energy consumption based on the energy consumption gradient distribution data of the building area, determines the change in contribution ratio before and after the mutation, adjusts the equipment power consumption mapping weight and equipment load participation, and obtains the equipment energy consumption mapping adjustment coefficient; The energy consumption error balance calculation module calculates the error value and error growth rate of the building energy consumption area based on the equipment energy consumption mapping adjustment coefficient, screens the error exceeding the threshold area and adjusts the energy consumption calculation to obtain a dynamic digital construction plan for the building energy equipment energy consumption.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by calculating the rate of change of energy consumption increment and time window, capturing the time series data of energy consumption mutation, accurately identifying the mutation point of high-load equipment, adjusting the energy consumption trend parameters based on the cumulative energy consumption change rate, analyzing the regional energy consumption gradient change rate, calculating the contribution of equipment increase and decrease and mode adjustment to energy consumption, optimizing the weight adjustment of equipment in the overall building energy consumption, making the impact of local load on the overall energy consumption more accurate, calculating the error value and growth rate, adjusting the energy consumption calculation method, improving the stability of error control, enhancing the real-time response capability of energy consumption evaluation, reducing the interference of high-load equipment on the overall energy consumption, and making the regional energy consumption optimization more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a main step flow chart of the present invention; Figure 2 A flowchart for obtaining the time series data of energy consumption mutation of the equipment of the present invention; Figure 3 A flowchart for obtaining energy consumption trend data corrected at a mutation point according to the present invention; Figure 4 This is a flow chart for obtaining regional energy consumption gradient distribution data of the present invention; Figure 5 A flowchart for obtaining the energy consumption mapping adjustment coefficient of the device of the present invention; Figure 6This is a flow chart for obtaining a solution for dynamically digitizing the energy consumption of building energy equipment according to the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0018] See also Figure 1 , a digital construction method for energy consumption of building energy equipment based on digital twins includes the following steps: S1: According to the digital twin model, the operating status data of the building energy equipment is obtained, including the power input, load change, operating time and instantaneous power consumption of the power equipment, the energy consumption increment per unit time is calculated, the time window is set, the energy consumption change rate of each time window is calculated, and the equipment energy consumption mutation time series data is obtained; S2: Based on the equipment energy consumption mutation time series data, compare the energy consumption increment changes in adjacent time windows, screen high-load running equipment whose energy consumption increment changes exceed the set change threshold, call the current input, equipment switch status, and load adjustment range of the high-load running equipment, judge and confirm the mutation point, calculate the cumulative energy consumption change rate before and after the mutation, adjust the equipment operation energy consumption trend coefficient, and obtain the energy consumption trend data corrected at the mutation point; S3: Based on the mutation point, correct the energy consumption trend data, collect statistics on the energy consumption data, temperature and humidity distribution, equipment layout density and power consumption of the building partitions, calculate the energy consumption gradient change amplitude between the regions, screen the regions where the energy consumption gradient change amplitude exceeds the preset amplitude threshold, collect the local load equipment type, switching frequency, and operation mode of the corresponding region, calculate the contribution ratio of equipment increase and decrease, and operation mode change to regional energy consumption, and obtain regional energy consumption gradient distribution data; S4: Based on the regional energy consumption gradient distribution data, calculate the impact weight of local high-power equipment in the overall building energy consumption, and determine the change in the energy consumption contribution ratio of the equipment before and after the mutation. If the energy consumption contribution ratio of the equipment increases after the mutation, increase the equipment power consumption mapping weight; if the contribution ratio decreases, reduce the equipment load participation, and obtain the equipment energy consumption mapping adjustment coefficient; S5: Based on the equipment energy consumption mapping adjustment coefficient, calculate the energy consumption calculation error value and error growth rate of each building energy consumption area, screen and mark the areas where the error deviation exceeds the set error range, count the key energy-consuming equipment types and power consumption proportions of the equipment group in the marked area, and adjust the energy consumption calculation of the marked area to obtain a dynamic digital construction plan for building energy equipment energy consumption.

[0019] The equipment energy consumption mutation time series data includes the energy consumption increment per unit time, the energy consumption change rate in the time window, and the energy consumption mutation point time series information; the mutation point corrected energy consumption trend data includes the mutation point confirmation result, the cumulative energy consumption change rate, and the equipment operation energy consumption trend coefficient; the regional energy consumption gradient distribution data includes the energy consumption gradient change amplitude, the local load equipment type, and the contribution ratio of equipment increase or decrease to energy consumption; the equipment energy consumption mapping adjustment coefficient includes the change in the equipment energy consumption contribution ratio, the power consumption mapping weight adjustment value, and the equipment load participation adjustment value; the dynamic digital construction plan of building energy equipment energy consumption includes the energy consumption calculation error value, the error growth rate, the key energy-consuming equipment type, the equipment group power consumption ratio and the energy consumption calculation adjustment plan.

[0020] See also Figure 2 ,The steps for obtaining the equipment energy consumption mutation time series data are: S111: Based on the digital twin model, record the power input, load changes, operating time and instantaneous power consumption of the power equipment, calculate the energy consumption increment per unit time, and arrange them in time series to establish energy consumption increment time series data; Based on the digital twin model, the operating status data of the building's energy equipment is obtained, including the power input of the power equipment, load changes, operating time and instantaneous power consumption. First, the real-time monitoring function of the digital twin model is used to collect the power input data of each power equipment in the building. Specifically, smart meters and sensors are installed in the building's power distribution system to record the voltage, current and other parameters of each device in real time and calculate its power input. For example, for an air-conditioning unit with a rated power of 10 kilowatts, its actual operating current and voltage are recorded by sensors, and it is calculated that its real-time power input may be 8 kilowatts. Next, the load changes of the monitoring equipment can be achieved by analyzing the changes in the power input of the equipment in different time periods. For example, in the work During peak hours of the working day, the load of the air conditioner may be close to full load, while during non-working hours, the load may drop to 30%. Then, record the operating time of the equipment, which can be determined by the start and stop status of the equipment. For example, the air conditioner runs for 8 hours in a day. Finally, collect the instantaneous power consumption data of the equipment, that is, the energy consumption at a specific moment. This can be achieved through high-frequency data collection. For example, record the power consumption data of the equipment once a minute, summarize the above data, and calculate the energy consumption increment per unit time. Assuming that the unit is hour, for the above air conditioner, its power input is 7 kilowatts on average in a certain hour, then the energy consumption increment for that hour is 7 kilowatt-hours. Arrange the energy consumption increment data in chronological order to establish energy consumption increment time series data.

[0021] S112: Based on the energy consumption increment time series data, set the time window and use the formula: ; Calculation time window Energy consumption change rate , and establish the time series data of energy consumption change rate, where: Representing time point The increase in energy consumption at It's time point The increase in energy consumption at Represents the number of data points in the time window, Represents the length of the time window; Call the energy consumption increment time series data, set the time window, and calculate the energy consumption change rate of each time window. First, determine the size of the time window for analysis, for example, select 1 hour as the time window, and then calculate the change rate of the energy consumption increment in each time window.

[0022] In a certain time window, there are 5 data points, and their energy consumption increments are 2, 3, 5, 4, and 6 kWh respectively. The calculation process is: Through the above calculation, it is obtained that the energy consumption change rate in the time window is 1.2 kilowatts per hour, and then the energy consumption change rate time series data is established.

[0023] S113: According to the energy consumption change rate time series data, identify the mutation point of the energy consumption change rate, select the time point of the energy consumption mutation and the corresponding change range, and establish the equipment energy consumption mutation time series data; Based on the time series of energy consumption change rate, identify the mutation points of energy consumption change rate, screen out the time points of energy consumption mutation and their corresponding change amplitudes. First, set the threshold of energy consumption change rate. For example, when the energy consumption change rate exceeds twice the average value, it is considered a mutation point. Assuming that the average energy consumption change rate is 1.5 kWh / h, the threshold is 3 kWh / h. Then, traverse the time series of energy consumption change rate to find the time points that exceed the threshold. For example, at a certain time point, the energy consumption change rate is 3.5 kWh / h, which exceeds the set threshold. Then, mark the time point as an energy consumption mutation point, record its occurrence time and change amplitude, summarize all mutation point information, and establish the equipment energy consumption mutation time series data.

[0024] See also Figure 3 , the steps for obtaining the mutation point corrected energy consumption trend data are: S211: Based on the equipment energy consumption mutation time series data, calculate the energy consumption increment change of adjacent time windows, obtain the energy consumption increment value of each time window, and compare the energy consumption increment change of the adjacent windows before and after, screen the high-load equipment whose energy consumption increment change exceeds the set change threshold, judge the existence of the mutation point according to the current input of the high-load running equipment, the equipment switch state, and the load adjustment range, and obtain the equipment energy consumption mutation point record; Based on the equipment energy consumption mutation time series data, first, obtain the energy consumption data of the equipment at different time points. Suppose there is an industrial air conditioner, whose energy consumption data is recorded once an hour in a day. The obtained data sequence is: 5kWh at 8:00, 5.2kWh at 9:00, 5.1kWh at 10:00, 7kWh at 11:00, 5.3kWh at 12:00, 5.1kWh at 13:00, 5.2kWh at 14:00, and 5.3kWh at 15:00. Then, calculate the energy consumption increment change in adjacent time windows. For the above data, the energy consumption increment between 9:00 and 8:00 is calculated as 5.2kWh-5kWh=0.2kWh, and between 10:00 and 9:00 is 5.1kWh-5.2kWh=-0.1kWh. Similarly, a series of energy consumption increment values ​​are obtained. Subsequently, the energy consumption increment changes of the adjacent windows are compared, with a focus on the magnitude of the incremental changes. Assuming that the set change threshold is 1.5kWh, when the energy consumption increment change exceeds this threshold, it is considered that the device may be in a high-load operation state. In the above data, the energy consumption increment at 11:00 is 7kWh-5.1kWh=1.9kWh, which exceeds the threshold of 1.5kWh. Therefore, it is determined that the device is in a high-load operation state at this time. Next, the current input, device switch status, load adjustment range and other parameters of the high-load operation device are called to determine the existence of the mutation point. For example, the current input at 11:00 is 15A, the device is in the on state, and the load adjustment range is 80%. Combined with this information, 11:00 is confirmed to be the energy consumption mutation point.

[0025] S212: Based on the record of equipment energy consumption mutation points, the formula is used: ; Calculate the ratio of energy consumption change rate before and after mutation , and determine the mutation point to correct the energy consumption trend data, where: Represents the energy consumption value after the mutation point, Represents the energy consumption value before the mutation point, Represents the number of time windows before and after the mutation point, Represents the change in current input to the device, Represents the equipment load adjustment range; Based on the equipment energy consumption mutation point, calculate the cumulative energy consumption change rate before and after the mutation point. First, determine the time window before and after the mutation point. For example, if the mutation point is 11:00, the previous time window is 10:00-11:00, and the next time window is 11:00-12:00. Calculate the cumulative energy consumption of these two time windows. Assuming that the cumulative energy consumption from 10:00 to 11:00 is 5.1 kWh and the cumulative energy consumption from 11:00 to 12:00 is 7 kWh, the cumulative energy consumption change rate is (7 kWh-5.1 kWh) / 5.1 kWh≈0.37, which is an increase of 37%. Then, compare the set change benchmark. Assuming that the change benchmark is 20%. Since 37% is greater than 20%, the energy consumption change rate is determined to be significant. Subsequently, the energy consumption change rate before and after the mutation point is calculated. The energy consumption change rate is defined as the change in energy consumption per unit time. Assuming the time window is 1 hour, the energy consumption rate before the mutation is 5.1kWh / h, and the energy consumption rate after the mutation is 7kWh / h. The change rate is 7kWh / h-5.1kWh / h=1.9kWh / h. Then, the fluctuation range of the change rate is compared. The set fluctuation range is ±0.5kWh / h. Since 1.9kWh / h exceeds this range, it is determined to be an abnormal fluctuation. The formula is used to calculate the ratio of the energy consumption change rate before and after the mutation.

[0026] According to the data N=1, kWh, kWh, A, , substitute into the formula to calculate: The calculated energy consumption change rate ratio before and after the mutation is 2.4. Based on the result of the change rate ratio, the energy consumption trend data of the mutation point correction is determined.

[0027] S213: Based on the ratio of the energy consumption change rate before and after the mutation, the equipment operation energy consumption trend coefficient is adjusted, the energy consumption trend data after the mutation point is corrected, and the mutation point corrected energy consumption trend data is generated; According to the ratio of the energy consumption change rates before and after the mutation, the energy consumption trend coefficient of the equipment operation is adjusted. First, the energy consumption trend coefficient of the current equipment is obtained. Assuming that the current coefficient is 1.0, based on the change rate ratio of 2.4 calculated above, the energy consumption trend coefficient is adjusted. The new coefficient is 1.0×2.4=2.4. Then, the energy consumption trend data after the mutation point is corrected. Assuming that the originally predicted energy consumption in the first hour after the mutation point is 6kWh, the corrected energy consumption is 6kWh×2.4=14.4kWh, and so on, to generate the mutation point corrected energy consumption trend data.

[0028] See also Figure 4 , the steps for obtaining regional energy consumption gradient distribution data are: S311: Based on the energy consumption trend data corrected by the mutation point, the energy consumption data, temperature and humidity distribution, equipment layout density and power consumption of the building partitions are counted using the formula: ; Compute partitions and The energy consumption gradient between , obtain the energy consumption gradient change range data between partitions, where, and Represents the total energy consumption of the two partitions, and is the area of ​​the two partitions; Based on the energy consumption trend data corrected by the mutation point, we first need to obtain the energy consumption data of each building partition. This data can be collected in real time through smart meters and energy consumption monitoring sensors. For example, different floors of a commercial complex are equipped with energy consumption monitors, and the power consumption data of each floor can be recorded once an hour. The recorded energy consumption data includes the consumption of high-energy consumption equipment such as lighting equipment, air-conditioning systems, and elevators. Next, the temperature and humidity distribution data can be provided by environmental monitoring sensors. For example, temperature and humidity monitoring points are arranged in a certain office area, and the temperature and humidity values ​​are recorded every 5 minutes. The collection of these data ensures that the environmental influencing factors of the partition can be included in the analysis. After that, for the calculation of the equipment layout density, it is necessary to count the number of different types of equipment in each partition and calculate the number of equipment distribution per square meter. For example, in a 100-square-meter conference room, there are 20 computers, 5 projectors and 1 central air conditioner, then the equipment layout density is Unit / square meter, power consumption is calculated by calculating the rated power and running time of each device. For example, if there is an air conditioner with a power of 1000W in a certain zone and it runs for 10 hours a day, its daily energy consumption is Wh, after counting all devices, calculate the total energy consumption of the partition, then calculate the energy consumption gradient change amplitude of each partition, and use the formula for gradient calculation.

[0029] Assuming that the total energy consumption of an office area is 50,000Wh and the area is 200 square meters, while the total energy consumption of the adjacent conference room is 30,000Wh and the area is 150 square meters, the energy consumption gradient change is calculated as follows: The energy consumption gradient change between partitions is obtained to be 57.14.

[0030] S312: According to the energy consumption gradient change amplitude data between the partitions, the partitions exceeding the preset amplitude threshold are selected, and the local load device types, switching frequencies and operation modes of the corresponding areas are counted to establish the operation parameters of the load devices in the over-threshold area; The energy consumption gradient change amplitude between partitions is called. Next, the partitions that exceed the preset amplitude threshold need to be screened. Assume that the preset threshold of the energy consumption gradient change is set to 50. The setting of this threshold is based on historical data and industry standards, and is obtained through statistical analysis of energy consumption data of a large number of office areas, commercial complexes, and residential areas. That is, if the energy consumption gradient change amplitude between a certain area and an adjacent area is greater than 50, then the area is regarded as an abnormal energy consumption area. Combined with the above calculation result 57.14, this value exceeds the threshold 50. Therefore, the energy consumption change of the above partition exceeds the set range, and the area is marked as an over-threshold area. Next, the local load device types in the area are counted, such as computers, servers, air conditioners, etc., and their switching frequencies and operating modes are counted. For example, the switching frequency of the server is 24 hours a day, while the switching frequency of the conference room air conditioner is 8 hours a day. By obtaining the power and operating time of all devices, a set of load device operating parameters in the area is formed. Finally, the load device operating parameters in the over-threshold area are obtained.

[0031] S313: Based on the operating parameters of the load equipment in the super-threshold area, the formula is used: ; The contribution of computing equipment increase / decrease and operation mode changes to regional energy consumption , generate regional energy consumption gradient distribution data, where, , , Respectively represent power, operating time and switching frequency of each device, , , Respectively represent the adjusted power, operating time and switching frequency of each device, is the total number of devices before adjustment, is the total number of devices after adjustment; Call the operating parameters of the load equipment in the super-threshold area, calculate the contribution ratio of the increase or decrease of equipment and the change of operating mode to the regional energy consumption, suppose that the equipment operation strategy is adjusted in a certain office area, 5 printers with a power of 500W are reduced, and 2 servers with a power of 2000W are adjusted to the low power consumption mode at night (reducing the operating time by 5 hours), calculate the impact of the equipment adjustment on energy consumption, and use the formula for calculation.

[0032] The total energy consumption of the equipment before adjustment is: The total energy consumption of the equipment after adjustment is: The contribution ratio of equipment adjustment to energy consumption: That is, equipment adjustment reduces energy consumption by 34.48%, and then the contribution ratio of equipment adjustment to energy consumption is obtained, and regional energy consumption gradient distribution data is generated.

[0033] See also Figure 5 , the steps to obtain the equipment energy consumption mapping adjustment coefficient are: S411: Based on the regional energy consumption gradient distribution data, the energy consumption value per unit time of the local equipment is calculated, the power load proportion of each equipment per unit time is extracted, the contribution rate of the difference equipment to the overall building energy consumption is counted, and the equipment power load proportion data is obtained; Based on the regional energy consumption gradient distribution data, it is first necessary to obtain the energy consumption data of each area in the building and conduct spatial distribution analysis. Specifically, through intelligent sensors and energy consumption monitoring equipment, collect the power consumption data of each area within a unit time (for example, 1 hour), normalize the collected data so that the data in different areas can be compared on the same scale, calculate the unit time energy consumption value of each local high-power device, set the calculation time window to 24 hours, and classify the data according to the equipment type, such as lighting equipment, air-conditioning equipment, elevator system, etc., calculate the total energy consumption value of each device within a unit time, for example, an air-conditioning device consumes 2.5kWh in 1 hour, while an elevator system consumes 3.1kWh in the same time period, after accumulating the energy consumption values ​​of all devices, calculate the power load proportion of each device, the calculation method is the percentage of the energy consumption value of a certain device to the total energy consumption value, for example, if the total energy consumption of the building is 500kWh, and the energy consumption of a certain device is 25kWh, then its power load proportion is , further count the contribution rates of different devices in the overall building energy consumption, and classify them according to the equipment type to facilitate subsequent analysis and optimization adjustments. For example, if the power load of lighting equipment in a certain area accounts for as much as 30%, it means that the lighting energy consumption in this area accounts for a high proportion, and it is necessary to focus on its energy consumption management, and finally obtain the equipment power load proportion data.

[0034] S412: Based on the equipment power load percentage data, use the formula: ; Computing equipment The contribution rate change , filter out the equipment with increased and decreased contribution rates, and determine the contribution rate change trend of each equipment to obtain the equipment energy consumption contribution rate change data, among which, Representative equipment The energy consumption contribution rate in the period after the mutation, Representative equipment The energy consumption contribution rate in the period before the mutation, Represents the total number of all devices, Represents the total change in contribution rate of all devices, Represents the total contribution rate of all devices before the mutation; Based on the equipment power load ratio data, the energy consumption contribution ratio of the equipment before and after the mutation is calculated. First, the time node of the mutation is set. For example, the equipment operation mode changes at 12:00 on a certain day. The energy consumption data before the mutation can be taken as the average energy consumption value of the hour before 12:00, and the energy consumption data after the mutation can be taken as the average energy consumption value of the hour after 12:00. The difference in contribution rate of each device before and after the mutation is calculated. The calculation formula is: , if the energy consumption contribution rate of a device before the mutation is 7.5% and rises to 10% after the mutation, then the difference in contribution rate is , by calculating the contribution rate change trend of all equipment and summarizing the change direction of the overall energy consumption contribution rate before and after the mutation.

[0035] Substitute the data for calculation. The contribution rate of a certain device was 7.5% before the mutation and increased to 10% after the mutation. Substitute the data for calculation: Among them, the change in total contribution rate is assumed to be 10%, and the base value of total contribution rate is 100%, then the calculation is: This value indicates that the contribution rate of the equipment has changed significantly (about 37%), and can be used as a key adjustment target to ultimately obtain the equipment energy consumption contribution rate change data.

[0036] S413: Based on the change data of the device energy consumption contribution rate, if the contribution ratio increases, the device power consumption mapping weight is adjusted to increase the load influence; if the contribution ratio decreases, the device load participation is reduced to obtain the device energy consumption mapping adjustment coefficient; According to the change data of the equipment energy consumption contribution rate, determine whether the contribution ratio of the equipment after the mutation increases or decreases. If the contribution ratio increases, adjust the equipment power consumption mapping weight to increase the load influence. If the contribution ratio decreases, reduce the equipment load participation. First, set the baseline value of the adjustment parameter. Assuming that the power consumption mapping weight is initially set to 1, if the contribution ratio of a certain equipment changes If it is greater than 0.2, the weight is adjusted to increase by 10%, that is, the new power consumption mapping weight is ; If the contribution rate change value is less than -0.2, the weight is reduced by 10%, that is, the new weight is , for example, the above-mentioned calculated contribution rate change value , when it is greater than 0.2, the power consumption mapping weight is adjusted to 1.1, and then the device energy consumption mapping adjustment coefficient is obtained.

[0037] See also Figure 6,The steps to obtain the dynamic digital construction plan of building energy equipment energy consumption are: S511: Count the equipment operation status and energy consumption data of the energy consumption areas of the difference buildings, calculate the energy consumption calculation error value of each building energy consumption area, count the energy consumption calculation error growth rate, filter and mark the areas where the error deviation exceeds the set error range, and obtain the error deviation area mark set; The equipment operation status and historical energy consumption data of different building energy consumption areas are collected to calculate the energy consumption calculation error value. The energy consumption calculation error value is obtained by the difference between the actual energy consumption value and the calculated energy consumption value. The specific calculation method is: first determine the actual energy consumption of each area in unit time , which can be obtained through meter data, and the computing energy consumption predicted by the calculation model The difference between the two is the error value , the calculation formula is: ; To further measure the error change, it is necessary to calculate the error growth rate, which is the ratio of the error value change per unit time. The calculation method is: ;in, is the error value at the current time point, is the error value at the previous time point. The positive or negative value of the error growth rate can reflect whether the energy consumption calculation error is expanding or shrinking. By calculating the data of different time periods, it can be determined whether the error continues to grow. If the error growth rate continues to be greater than the set threshold , then the area is considered as an error deviation area. For example, if the error value of a certain area in the previous hour was 10kWh, and the current error value is 12kWh, then the error growth rate is: Assuming that the error growth threshold is set to 15%, and 20% is greater than 15%, the area is marked as an error offset area. This process needs to be performed for all energy consumption areas, and the areas that exceed the error range are counted to finally form an error offset area marking set.

[0038] S512: According to the error offset area marking set, the key energy-consuming device types in the marking area are counted using the formula: ; Calculate the power consumption ratio of devices in the marked area ,in, Representative Unit power consumption of class equipment, Represents the frequency of use of this type of equipment. Represents the total running time of the device during the statistical period. Represents the power fluctuation amount of the device, Represents the power threshold of the device. Represents the total number of devices in the marked area; Based on the error offset area tag set, the key energy-consuming devices in these areas are counted and the power consumption proportion of the device group is calculated. First, the main equipment types of each tag area are determined. These devices may include air conditioners, lighting systems, elevators, etc. The power consumption proportion of each type of equipment is calculated through the equipment running time data and power data. The specific calculation method is as follows: Assume that there are n types of equipment in an area, and the power consumption of each type of equipment is , the frequency of use of the device is , the running time is , the power fluctuation of the equipment is .

[0039] For example, in a certain area of ​​an office building, the unit power consumption of the air conditioner is 3 kW, it runs 10 times a day, each time for 2 hours, the power fluctuation is 0.2 kW, and the set power threshold is 0.15 kW. Then the power consumption proportion of the device is: Calculate and sum all devices in the area to get the power consumption ratio of the total device group, and perform the same calculation process in all marked areas to finally obtain the power consumption ratio of devices in the marked area for subsequent energy consumption calculation correction.

[0040] S513: Based on the power consumption ratio of the equipment in the marked area, the energy consumption calculation of the marked area is adjusted, and the error is corrected in combination with the equipment energy consumption mapping adjustment coefficient to obtain a dynamic digital construction plan for energy consumption of building energy equipment; According to the power consumption ratio of the equipment in the marked area, the energy consumption calculation of each error offset area is adjusted. First, the power consumption of each device is corrected based on the equipment energy consumption mapping adjustment coefficient. The adjustment coefficient is calculated and obtained from historical data. The adjustment method is: if the power consumption ratio of the equipment in a certain area is higher than the baseline value, the calculated value of the equipment energy consumption is adjusted. , which is calculated as follows: ; in is the benchmark power consumption ratio of the device category. For example, if the device power consumption ratio of a certain area is 16, based on the above judgment, assuming that the device energy consumption mapping adjustment coefficient is to increase the adjustment weight by 10% (0.1), if the calculated device energy consumption value is 100kWh, then the adjusted calculated value is: This calculation method ensures that the energy consumption calculation in the error offset area is more accurate, and ultimately a dynamic digital construction plan for the energy consumption of building energy equipment is obtained.

[0041] The digital twin-based building energy equipment energy consumption digital construction system includes: The energy consumption data acquisition module obtains the power input, load change, operating time, and instantaneous power consumption of building energy equipment based on the digital twin model, calculates the energy consumption increment per unit time, sets the time window to calculate the change rate, and obtains the equipment energy consumption mutation time series data; The energy consumption mutation point correction module selects high-load running equipment based on the equipment energy consumption mutation time series data, and determines the mutation point according to the current input, equipment switch status, and load adjustment range of the high-load running equipment, calculates the cumulative energy consumption change rate before and after the mutation, adjusts the equipment operation energy consumption trend coefficient, and obtains the mutation point correction energy consumption trend data; The regional energy consumption gradient analysis module corrects the energy consumption trend data based on the mutation point, counts the energy consumption of building partitions, temperature and humidity distribution, equipment density, power consumption, calculates the range of regional energy consumption gradient changes, screens areas exceeding the preset range threshold, calculates the contribution ratio of regional energy consumption, and obtains the energy consumption gradient distribution data of the building area; The equipment energy consumption weight adjustment module calculates the impact weight of local high-power equipment in building energy consumption based on the energy consumption gradient distribution data of the building area, determines the change in contribution ratio before and after the mutation, adjusts the equipment power consumption mapping weight and equipment load participation, and obtains the equipment energy consumption mapping adjustment coefficient; The energy consumption error balance calculation module calculates the error value and error growth rate of the building energy consumption area based on the equipment energy consumption mapping adjustment coefficient, screens the error exceeding the threshold area and adjusts the energy consumption calculation to obtain a dynamic digital construction plan for the energy consumption of building energy equipment.

[0042] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A digital construction method for energy consumption of building energy equipment based on digital twins, characterized in that: The following steps are involved: S1: According to the digital twin model, the operating status data of the building energy equipment is obtained, the energy consumption increment per unit time and the energy consumption change rate in the time window are calculated, and the equipment energy consumption mutation time series data is obtained; S2: Based on the equipment energy consumption mutation time series data, screen high-load running equipment, judge and confirm the mutation point, calculate the cumulative energy consumption change rate before and after the mutation, adjust the equipment operation energy consumption trend coefficient, and obtain the mutation point corrected energy consumption trend data; S3: Based on the energy consumption trend data corrected at the mutation point, the energy consumption gradient change rate between regions is calculated, the region exceeding the preset amplitude threshold is screened, the contribution ratio of equipment increase / decrease and mode change to energy consumption is calculated, and the regional energy consumption gradient distribution data is obtained; S4: Based on the regional energy consumption gradient distribution data, calculate the impact weight of the equipment in the building energy consumption, determine the change in energy consumption contribution ratio before and after the mutation, adjust the equipment power consumption mapping weight and load participation, and obtain the equipment energy consumption mapping adjustment coefficient; S5: Based on the equipment energy consumption mapping adjustment coefficient, calculate the energy consumption error value and error growth rate of the building energy consumption area, mark the error exceeding the threshold area, adjust the energy consumption calculation method, and obtain a dynamic digital construction plan for the building energy equipment energy consumption.

2. The method for digitally constructing energy consumption of building energy equipment based on digital twin according to claim 1 is characterized in that: The equipment energy consumption mutation time series data includes energy consumption increment per unit time, energy consumption change rate in a time window, and energy consumption mutation point time series information; The mutation point corrected energy consumption trend data includes the mutation point confirmation result, the cumulative energy consumption change rate, and the equipment operation energy consumption trend coefficient; the regional energy consumption gradient distribution data includes the energy consumption gradient change amplitude, the local load equipment type, and the contribution ratio of equipment increase or decrease to energy consumption; the equipment energy consumption mapping adjustment coefficient includes the change in the equipment energy consumption contribution ratio, the power consumption mapping weight adjustment value, and the equipment load participation adjustment value; the dynamic digital construction plan of building energy equipment energy consumption includes the energy consumption calculation error value, the error growth rate, the key energy-consuming equipment type, the power consumption ratio of the equipment group and the energy consumption calculation adjustment plan.

3. The method for digitally constructing energy consumption of building energy equipment based on digital twin according to claim 1 is characterized in that: The steps for obtaining the equipment energy consumption mutation time series data are as follows: S111: Based on the digital twin model, record the power input, load changes, operating time and instantaneous power consumption of the power equipment, calculate the energy consumption increment per unit time, and arrange them in time series to establish energy consumption increment time series data; S112: Based on the energy consumption increment time series data, a time window is set, using the formula: ； Calculation time window Energy consumption change rate , and establish the time series data of energy consumption change rate, where: Representing time point The increase in energy consumption at It's time point The increase in energy consumption at Represents the number of data points in the time window, Represents the length of the time window; S113: According to the energy consumption change rate time series data, identify the mutation point of the energy consumption change rate, select the time point of the energy consumption mutation and the corresponding change range, and establish the equipment energy consumption mutation time series data.

4. The method for digitally constructing energy consumption of building energy equipment based on digital twin according to claim 1 is characterized in that: The steps for obtaining the mutation point corrected energy consumption trend data are as follows: S211: Based on the equipment energy consumption mutation time series data, calculate the energy consumption increment change of adjacent time windows, obtain the energy consumption increment value of each time window, and compare the energy consumption increment change of the adjacent windows before and after, screen the high-load equipment whose energy consumption increment change exceeds the set change threshold, judge the existence of the mutation point according to the current input of the high-load running equipment, the equipment switch state, and the load adjustment range, and obtain the equipment energy consumption mutation point record; S212: Based on the record of the energy consumption mutation point of the equipment, the formula is used: ； Calculate the energy consumption change rate ratio before and after the mutation , and determine the mutation point to correct the energy consumption trend data, where: Represents the energy consumption value after the mutation point, Represents the energy consumption value before the mutation point, Represents the number of time windows before and after the mutation point, Represents the change in current input to the device, Represents the equipment load adjustment range; S213: Based on the energy consumption change rate ratio before and after the mutation, the equipment operation energy consumption trend coefficient is adjusted, the energy consumption trend data after the mutation point is corrected, and the mutation point corrected energy consumption trend data is generated.

5. The method for digitally constructing energy consumption of building energy equipment based on digital twin according to claim 1 is characterized in that: The steps for obtaining the regional energy consumption gradient distribution data are as follows: S311: Based on the energy consumption trend data corrected by the mutation point, the energy consumption data, temperature and humidity distribution, equipment layout density and power consumption of the building partitions are counted, using the formula: ； Compute partitions and The energy consumption gradient between , obtain the energy consumption gradient change range data between partitions, where, and Represents the total energy consumption of the two partitions, and is the area of ​​the two partitions; S312: According to the energy consumption gradient change amplitude data between the partitions, the partitions exceeding the preset amplitude threshold are selected, and the local load device types, switching frequencies and operation modes of the corresponding areas are counted to establish the operation parameters of the load devices in the over-threshold area; S313: According to the operating parameters of the load device in the super-threshold region, the formula is used: ； The contribution of computing equipment increase / decrease and operation mode changes to regional energy consumption , generate regional energy consumption gradient distribution data, where, , , Respectively represent power, operating time and switching frequency of each device, , , Respectively represent the adjusted power, operating time and switching frequency of each device, is the total number of devices before adjustment, is the adjusted total number of devices.

6. The method for digitally constructing energy consumption of building energy equipment based on digital twin according to claim 1 is characterized in that: The steps for obtaining the device energy consumption mapping adjustment coefficient are as follows: S411: Based on the regional energy consumption gradient distribution data, calculate the energy consumption value per unit time of the local equipment, extract the power load proportion of each device per unit time, count the contribution rate of the difference equipment in the overall building energy consumption, and obtain the equipment power load proportion data; S412: Based on the equipment power load proportion data, the formula is used: ； Computing equipment The contribution rate change , filter out the equipment with increased and decreased contribution rates, and determine the contribution rate change trend of each equipment to obtain the equipment energy consumption contribution rate change data, among which, Representative equipment The energy consumption contribution rate in the period after the mutation, Representative equipment The energy consumption contribution rate in the period before the mutation, Represents the total number of all devices, Represents the total change in contribution rate of all devices, Represents the total contribution rate of all devices before the mutation; S413: Based on the device energy consumption contribution rate change data, if the contribution ratio increases, the device power consumption mapping weight is adjusted; if the contribution ratio decreases, the device load participation is reduced to obtain the device energy consumption mapping adjustment coefficient.

7. The method for digitally constructing energy consumption of building energy equipment based on digital twin according to claim 1 is characterized in that: The steps for obtaining the dynamic digital construction scheme of building energy equipment energy consumption are as follows: S511: Count the equipment operation status and energy consumption data of the energy consumption areas of the difference buildings, calculate the energy consumption calculation error value of each building energy consumption area, count the energy consumption calculation error growth rate, filter and mark the areas where the error deviation exceeds the set error range, and obtain the error deviation area mark set; S512: According to the error offset area mark set, count the key energy-consuming device types in the marked area, using the formula: ； Calculate the power consumption ratio of devices in the marked area ,in, Representative Unit power consumption of class equipment, Represents the frequency of use of this type of equipment. Represents the total running time of the device during the statistical period. Represents the power fluctuation amount of the device, Represents the power threshold of the device. Represents the total number of devices in the marked area; S513: Based on the power consumption proportion of the equipment in the marked area, the energy consumption calculation of the marked area is adjusted, and the error is corrected in combination with the equipment energy consumption mapping adjustment coefficient to obtain a dynamic digital construction plan for building energy equipment energy consumption.

8. A digital construction system for energy consumption of building energy equipment based on digital twins, characterized by: The system is used to execute the method according to any one of claims 1 to 7, comprising: The energy consumption data acquisition module obtains the power input, load change, operating time, and instantaneous power consumption of building energy equipment based on the digital twin model, calculates the energy consumption increment per unit time, sets the time window to calculate the change rate, and obtains the equipment energy consumption mutation time series data; The energy consumption mutation point correction module selects high-load running equipment based on the equipment energy consumption mutation time series data, and determines the mutation point according to the current input of the high-load running equipment, the equipment switch state, and the load adjustment range, calculates the cumulative energy consumption change rate before and after the mutation, adjusts the equipment operation energy consumption trend coefficient, and obtains the mutation point correction energy consumption trend data; The regional energy consumption gradient analysis module corrects the energy consumption trend data based on the mutation point, counts the energy consumption of the building partition, the temperature and humidity distribution, the equipment density, and the power consumption, calculates the change amplitude of the regional energy consumption gradient, screens the area exceeding the preset amplitude threshold, calculates the contribution ratio of the regional energy consumption, and obtains the energy consumption gradient distribution data of the building area; The equipment energy consumption weight adjustment module calculates the influence weight of local high-power equipment in building energy consumption based on the energy consumption gradient distribution data of the building area, determines the change in contribution ratio before and after the mutation, adjusts the equipment power consumption mapping weight and equipment load participation, and obtains the equipment energy consumption mapping adjustment coefficient; The energy consumption error balance calculation module calculates the error value and error growth rate of the building energy consumption area based on the equipment energy consumption mapping adjustment coefficient, screens the error exceeding the threshold area and adjusts the energy consumption calculation to obtain a dynamic digital construction plan for the building energy equipment energy consumption.

Images