Building energy-saving diagnostic data analysis system

Abstract

The invention belongs to the technical field of building energy conservation, and relates to a building energy conservation diagnostic data analysis system which screens standard night power loss data in a reference period of a target building through environment temperature similarity and performs statistical characteristic analysis on the standard night power loss data to obtain a night power loss baseline of the target building. According to the night power loss data of the target building in the diagnosis period, the deviation characteristics of the target building relative to the night power loss base line are analyzed, whether the target building has an energy-saving optimization space or not is judged, and if yes, the air conditioner equipment is dynamically adjusted according to the activity characteristics of people on all floors; and the running number of the elevators at night and the standby floor positions are dynamically configured according to the use demand characteristics of elevator equipment, the energy-saving effect is evaluated and feedback is executed by comparing the night power loss conditions of the target building before and after optimization, the precision and efficiency of building energy-saving diagnosis are improved, and effective utilization of energy is achieved.

Description

Technical Field

[0001] The invention belongs to the technical field of building energy conservation, and relates to a building energy conservation diagnosis data analysis system. Background Art

[0002] Building energy conservation is a core component in promoting the development of green buildings and sustainable energy utilization. With the acceleration of urbanization, the proportion of building energy consumption continues to rise globally. Office buildings, with their high population density and complex equipment systems, face high operating costs and significant power loss. Therefore, there is an urgent need for energy-saving renovations and optimized management of office buildings to reduce energy waste and operating costs.

[0003] In the existing technology, there are also some related solutions related to energy-saving diagnosis of office buildings. For example, the batch diagnosis method, energy-saving method and system of office building operating performance with Chinese patent publication number CN114819766A obtains energy consumption indicators and energy consumption status based on the historical energy consumption information of the office building, and uses this to determine the energy consumption modification objects and modification directions of the office building, thereby improving energy utilization efficiency.

[0004] Another Chinese patent, CN114266187B, describes a method and system for optimizing the power network of an office building. This system uses building information and historical power consumption data from each power consumption area to construct a corresponding digital twin system. Based on the initial optimization parameters input into each digital twin subsystem, it obtains regional control signals for each power consumption area, and uses these signals to adjust the operating parameters of each power-consuming device, thereby improving the operating efficiency of the office building power network.

[0005] Although the above schemes have proposed some solutions for energy-saving diagnosis of office buildings, the existing technologies still have the following limitations, specifically: (1) Existing technologies rely on historical energy consumption averages or static prediction models, and do not consider the impact of environmental factors on power loss. This can easily lead to a disconnect between the formulated energy consumption optimization strategy and the actual energy consumption demand, and it is impossible to accurately adjust the actual energy consumption situation, thereby affecting the overall energy efficiency of the building.

[0006] (2) Existing technologies analyze and process the energy consumption throughout the day as a homogeneous whole, without considering the fact that the activities of people in office buildings in the evening time zone are significantly reduced compared to the daytime, but high-power consumption equipment such as air conditioners and elevators are still running, causing energy waste. As a result, the energy-saving strategies formulated subsequently cannot fully utilize the energy-saving space in this time zone.

[0007] (3) Existing technologies only focus on the comparison of overall energy consumption, while ignoring the intrinsic relationship between the operating status of equipment and the activity patterns of personnel, making the energy-saving optimization strategies formulated too extensive, sacrificing user experience and energy-saving potential, and resulting in the lack of scenario adaptability of energy-saving strategies. Summary of the Invention

[0008] In order to solve the problems raised in the above background technology, a building energy-saving diagnosis data analysis system is proposed.

[0009] The technical solution adopted by the present invention to solve its technical problem is: the present invention provides a building energy-saving diagnostic data analysis system, including: a loss baseline construction module, a power loss analysis module, an air-conditioning energy-saving optimization module, an elevator energy-saving optimization module and an energy-saving effect evaluation module.

[0010] The loss baseline construction module is connected to the power loss analysis module, the power loss analysis module is respectively connected to the air conditioning energy-saving optimization module and the elevator energy-saving optimization module, the air conditioning energy-saving optimization module is connected to the energy-saving effect evaluation module, and the elevator energy-saving optimization module is connected to the energy-saving effect evaluation module.

[0011] The loss baseline construction module divides the historical monitoring period into a reference period and a diagnostic period, screens the standard nighttime power loss data of the target building within the reference period based on the similarity of ambient temperature, and obtains the nighttime power loss baseline of the target building through statistical feature analysis.

[0012] The power loss analysis module extracts the target building's nighttime power loss data during the diagnostic cycle, analyzes its deviation characteristics relative to the nighttime power loss baseline, and determines whether there is room for energy-saving optimization in the target building. If so, energy-saving optimization is performed on the air-conditioning equipment and elevator equipment respectively.

[0013] The air conditioning energy-saving optimization module extracts the nighttime operating data of lighting equipment on each floor of the target building during the diagnosis period, estimates the characteristics of personnel activity at each floor and each night time, adjusts the parameters of air conditioning equipment at low personnel activity times, and disables air conditioning equipment when personnel are about to leave.

[0014] The elevator energy-saving optimization module extracts the night call data of the target building's elevator equipment during the diagnosis period, analyzes the usage demand characteristics of each floor, and dynamically configures the number of elevator operations and the location of standby floors at night.

[0015] The energy-saving effect evaluation module compares the nighttime power loss of the target building before and after optimization, evaluates the energy-saving effect and provides feedback.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention comprehensively analyzes the differences in ambient temperature between different diagnostic working days and reference working days, constructs ambient temperature feature vectors and similarity matrices, screens out the reference working days that are most similar to the ambient temperature of the diagnostic period, and uses this to obtain standard evening power loss data, ensuring the accuracy of the power loss data and making the energy-saving optimization strategy fit the actual energy consumption needs.

[0017] The present invention focuses on power loss analysis in the evening time zone. Through the power loss analysis module, the evening power loss data of the target building within the diagnosis period is extracted, and its deviation characteristics relative to the evening power loss baseline are analyzed. This helps locate the optimization potential of the evening time zone and fully utilize the energy-saving space in this time zone, overcoming the limitation of existing technologies that analyze and process energy consumption throughout the day as a homogeneous whole.

[0018] The present invention calculates the characteristics of human activity at each floor and in each evening period, adjusts the parameters of the air-conditioning equipment when human activity is low, and disables the air-conditioning equipment when people are about to leave. At the same time, it analyzes the demand for elevator usage on each floor and dynamically configures the number of elevators running at night and the locations of standby floors. This avoids the existing strategy of focusing only on overall energy consumption comparison and improves the scenario adaptability of the energy-saving strategy.

[0019] By comparing the nighttime power loss of the target building before and after optimization, the present invention evaluates the energy-saving effect and performs feedback, so as to accurately judge whether the building energy saving has achieved the expected effect, and then continuously optimize and improve the building energy-saving strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 Schematic diagram of module connection of the present invention.

[0022] Figure 2 This is a logical flow chart for obtaining the nighttime power loss baseline of a target building in the loss baseline building module of the present invention.

[0023] Figure 3 This is a logic flow chart for determining whether there is room for energy-saving optimization in the power loss analysis module of the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0025] See also Figure 1As shown, the present invention provides a building energy-saving diagnostic data analysis system, which includes: a loss baseline construction module, a power loss analysis module, an air conditioning energy-saving optimization module, an elevator energy-saving optimization module and an energy-saving effect evaluation module.

[0026] The loss baseline construction module is connected to the power loss analysis module, the power loss analysis module is respectively connected to the air conditioning energy-saving optimization module and the elevator energy-saving optimization module, the air conditioning energy-saving optimization module is connected to the energy-saving effect evaluation module, and the elevator energy-saving optimization module is connected to the energy-saving effect evaluation module.

[0027] The loss baseline construction module divides the historical monitoring period into a reference period and a diagnostic period, screens the standard nighttime power loss data of the target building within the reference period based on the similarity of ambient temperature, and obtains the nighttime power loss baseline of the target building through statistical feature analysis.

[0028] As a preferred embodiment, the process of screening the standard nighttime power loss data of the target building within the reference period based on the similarity of ambient temperature includes: retrieving the ambient temperature data of the evening time zone of each diagnostic working day in the diagnostic period and each reference working day in the reference period, and constructing the ambient temperature feature vectors of each diagnostic working day and each reference working day based on the ambient temperature difference and the average ambient temperature in the evening time zone.

[0029] Based on the cosine similarity calculation formula, the similarity of the ambient temperature between each reference working day and each diagnosis working day is calculated respectively, and a similarity matrix is ​​constructed based on this. The rows and columns of the matrix correspond to the diagnosis working day and the reference working day respectively, and the element values ​​of the matrix correspond to the similarity of the ambient temperature between the diagnosis working day and the reference working day.

[0030] The similarity matrix is ​​summed up by columns to obtain the cumulative similarity of each reference working day relative to the diagnosis period.

[0031] The reference working days are sorted in descending order according to the cumulative similarity, a preset number of reference working days before the sequence are selected as standard reference working days, and the power loss data of the evening time zone of each standard reference working day are integrated to obtain the standard evening power loss data.

[0032] It should be noted that the formula for calculating the similarity between the ambient temperature of each reference working day and each diagnosis working day based on the cosine similarity calculation formula is: ,in 、 Corresponding to the Reference working day, The ambient temperature difference during the diagnostic working day is 、 Corresponding to the Reference working day, The average ambient temperature of the diagnostic working days, where is the number of each reference working day, , is the number of each diagnostic working day, .

[0033] It should be noted that the preset number should be more than twice the number of diagnostic working days.

[0034] The embodiment of the present invention comprehensively analyzes the ambient temperature differences between different diagnostic working days and reference working days, constructs an ambient temperature feature vector and a similarity matrix, screens out the reference working days that are most similar to the ambient temperature of the diagnostic period, and uses this to obtain standard nighttime power loss data, thereby ensuring the accuracy of the power loss data and making the energy-saving optimization strategy fit the actual energy consumption needs.

[0035] See also Figure 2 As shown, as a preferred embodiment, the process of obtaining the target building's nighttime power loss baseline through statistical feature analysis includes: dividing the nighttime time zone according to a preset time interval to generate each nighttime period.

[0036] The power loss data of the same evening time period on weekdays for each standard reference are arranged in ascending order to construct an ascending data set of power loss for each evening time period.

[0037] Based on the preset percentile value, a quantile calculation is performed on each ascending power loss data set, and the corresponding percentile value is extracted as the power loss baseline value, thereby obtaining the power loss baseline value for each evening time period, wherein the preset percentile value is a statistical parameter used to specify the relative position in the ascending order of data, and the percentile value is the specific value of the preset percentile value in the ascending power loss data set.

[0038] The power loss baseline values ​​of the evening time periods are combined in chronological order to construct a nighttime power loss baseline of the target building.

[0039] It should be noted that the above-mentioned preset percentile values ​​are pre-set based on the statistical characteristics of the historical energy consumption data of the target building during the reference period. The setting principle is: select a lower percentile value, which can be exemplified as the 25% percentile value, to reflect the lower energy consumption level that can actually be achieved under normal operating conditions after excluding abnormally high energy consumption days.

[0040] The above quantile calculation can be implemented through linear interpolation or the nearest neighbor method.

[0041] Here, the power loss data set in ascending order during a certain evening period is listed as According to the 25% quantile value, the quantile value can be calculated by linear interpolation to be 93.5, which is used as the benchmark value of power loss during the evening period. The default unit here is kWh.

[0042] The power loss analysis module extracts the nighttime power loss data of the target building during the diagnosis period, analyzes its deviation characteristics relative to the nighttime power loss baseline, and determines whether there is room for energy-saving optimization in the target building. If so, energy-saving optimization is performed on the air-conditioning equipment and elevator equipment respectively.

[0043] See Figure 3 As shown, as a preferred embodiment, the determination of whether there is room for energy-saving optimization in the target building is specifically carried out as follows: for the power loss data of the same evening time period on each diagnostic working day, after removing the maximum and minimum values, the arithmetic mean of the remaining data is calculated to obtain the average power loss data of each evening time period, and the average power loss line of the evening time zone of the diagnostic period is drawn, and it is compared with the evening power loss baseline for each time period, and the positive deviation value and positive deviation duration of the power loss in each evening time period are counted.

[0044] Taking the duration of the positive deviation of power loss in each evening period as the weight factor, the positive deviation values ​​of power loss in each evening period are linearly weighted and fused to obtain the diagnostic period deviation parameters.

[0045] A linear weighted calculation is performed on the duration of each evening period and its corresponding power loss benchmark value to obtain the power loss benchmark parameter, and the ratio of the diagnostic cycle deviation parameter to the diagnostic cycle deviation parameter is calculated as the power loss deviation evaluation index.

[0046] If the power loss deviation evaluation index is greater than a preset optimization judgment threshold, it is determined that there is room for energy-saving optimization in the target building.

[0047] It should be noted that the positive deviation value of the power loss in each evening time period is the deviation amplitude of the corresponding line segment of the average power loss line of the evening time zone of the diagnostic period in each evening time period that is higher than the evening power loss baseline, and the positive deviation duration is the duration that the corresponding line segment of the average power loss line of the evening time zone of the diagnostic period in each evening time period is higher than the evening power loss baseline.

[0048] The embodiment of the present invention focuses on power loss analysis in the evening time zone. The power loss analysis module extracts the evening power loss data of the target building during the diagnosis period and analyzes its deviation characteristics relative to the evening power loss baseline. This helps locate the optimization potential of the evening time zone and fully utilize the energy-saving space in this time zone, overcoming the limitation of existing technologies that analyze and process all-day energy consumption as a homogeneous whole.

[0049] The air conditioning energy-saving optimization module extracts the nighttime operating data of lighting equipment on each floor of the target building during the diagnosis period, estimates the activity characteristics of people on each floor during each night time period, adjusts the parameters of the air conditioning equipment at times of low human activity, and deactivates the air conditioning equipment when people are about to leave.

[0050] As a preferred embodiment, the process of estimating the activity characteristics of personnel in each evening time period on each floor includes: retrieving the switch circuit status data of the office area lighting equipment on a certain floor in the evening time zone of a certain diagnostic working day; when the switch circuit status of the office area lighting equipment is disconnected at a certain time point, and the disconnection duration is greater than the preset duration, the time point is recorded as the reference personnel departure time point on that floor.

[0051] The power loss data of the lighting equipment on this floor is monitored according to the preset sampling period, and the power loss change rate of each sampling time point and its previous sampling node is calculated. When the absolute power loss change rate of a certain sampling time point is greater than the preset change threshold and the power loss data is less than the preset power loss threshold, the sampling time point is recorded as a reference low-personnel activity time point.

[0052] Obtain the reference personnel departure time point dataset and reference low personnel activity time point dataset for each diagnostic working day on that floor.

[0053] Take each time point in the reference personnel departure time point dataset as the reference time point in turn, obtain the absolute cumulative deviation duration of the remaining time points from the reference time point, select the reference time point corresponding to the minimum absolute cumulative deviation duration as the personnel departure time point, and similarly obtain the low personnel activity time point from the reference low personnel activity time point dataset, and thereby obtain the personnel departure time points and low personnel activity time points on each floor of the target building.

[0054] It should be noted that the switches of each lighting device in the switch circuit of the office area lighting equipment are connected in parallel. When any lighting device switch is not disconnected, the switch circuit remains connected, and it can be inferred that there are human activities in the office area. When all lighting device switches are disconnected, the switch circuit is in a disconnected state, and it can be preliminarily inferred that there are no human activities in the office area on this floor. By analyzing whether the duration of the lighting circuit disconnection is greater than the preset duration, it can be more accurately determined whether there are human activities in the office area on this floor. Therefore, the reference personnel departure time point can be obtained by analyzing the switch circuit status data and the disconnection duration.

[0055] It should be noted that when human activities are frequent, the absolute rate of change of power loss will be smaller, and when human activities are reduced, the absolute rate of change of power loss will be relatively larger. Therefore, when the absolute rate of change of power loss is greater than the preset change threshold, it can be preliminarily inferred that human activities during this period are at a low level. The power loss data directly reflects the energy consumption of the building at a specific time point. When the power loss data is less than the preset power loss threshold, it can be ensured that the determined time point is a reference to a time point with low human activities.

[0056] As a preferred embodiment, the air-conditioning equipment parameters are adjusted at low-activity time points, and the air-conditioning equipment is deactivated when people are about to leave. The specific process includes: according to the season in which the diagnosis cycle is located, the temperature of the air-conditioning equipment on each floor is directional adjusted at low-activity time points.

[0057] The time point preset time before the departure time of personnel on each floor is defined as the departure time point of personnel, and the air-conditioning equipment is disabled at the departure time point of personnel on each floor.

[0058] It should be noted that the process of directional adjustment of the temperature of air-conditioning equipment on each floor at a time of low human activity includes: adjusting the temperature of the air-conditioning equipment according to preset temperature adjustment parameters, performing positive adjustment if the target building diagnosis period is in a high temperature season, and performing reverse adjustment if it is in a low temperature season.

[0059] It should be noted that setting a reasonable buffer period before personnel leave can make full use of the indoor residual heat to maintain the relative stability of the indoor temperature and avoid energy waste due to sudden stop of equipment. The preset time can be set to 30 minutes for example, which can not only ensure the efficiency of residual heat utilization before personnel leave, but also effectively balance energy saving goals and indoor comfort requirements.

[0060] The elevator energy-saving optimization module extracts the night call data of the target building's elevator equipment within the diagnosis period, analyzes the usage demand characteristics of each floor, and dynamically configures the number of elevator operations and the location of standby floors at night.

[0061] As a preferred embodiment, the process of analyzing the usage demand characteristics of each floor includes: extracting the evening call data of the elevator equipment on each diagnostic working day, screening the operation combinations with the same calling floors and target floors in each evening period and counting their operation times, thereby constructing the elevator equipment transfer matrix for each evening period, wherein the rows and columns of the matrix correspond to the calling floors and target floors respectively, and the element values ​​of the matrix correspond to the counted operation times.

[0062] The elevator equipment transfer matrix is ​​normalized to obtain the elevator equipment transfer probability matrix for each evening time period on each diagnosis working day.

[0063] The arithmetic mean of the corresponding elements of the elevator equipment transfer probability matrix of each diagnosis working day is calculated by grouping by evening time period to obtain the reference elevator equipment transfer probability matrix of each evening time period.

[0064] Retrieve the collection of elevator equipment calling time points on each diagnostic working day to obtain the number of elevator equipment calls in each evening period on each diagnostic working day.

[0065] The number of elevator calls in the same evening time period on different diagnostic working days was averaged to obtain the reference number of elevator calls in each evening time period, and the elevator call frequency in each evening time period was calculated based on this.

[0066] As a preferred embodiment, the process of dynamically configuring the number of elevator operations at night is as follows: calling a preset configuration table of the number of elevator operations at night stored in a cloud database, determining the elevator equipment demand level based on the elevator equipment call frequency in each evening time period, and matching the number of elevator operations of the corresponding level, thereby dynamically configuring the number of elevator operations in each evening time period.

[0067] It should be noted that the preset evening elevator operation quantity configuration table includes the elevator equipment calling frequency and the adapted elevator operation quantity for each evening time period corresponding to different elevator equipment demand levels.

[0068] As a preferred embodiment, the process of dynamically configuring the position of the elevator standby floor at night is as follows: according to the reference elevator equipment transfer probability matrix of each evening time period, the calling floor with the highest probability of calling the elevator equipment in each evening time period is selected, and the floor is used as the elevator equipment standby floor in each evening time period.

[0069] The embodiment of the present invention calculates the characteristics of human activity at each floor and in each evening period, adjusts the parameters of the air-conditioning equipment when human activity is low, and disables the air-conditioning equipment when people are about to leave. At the same time, it analyzes the demand for elevator usage on each floor and dynamically configures the number of elevators running at night and the locations of standby floors. This avoids the strategy of existing technologies that only focuses on overall energy consumption comparison, and improves the scenario adaptability of the energy-saving strategy.

[0070] As a preferred embodiment, the energy-saving effect evaluation is specifically obtained as follows: starting from the end time of the diagnosis period, extending backward by the same number of days as the diagnosis period to define the optimization period, and executing energy-saving optimization measures for air-conditioning equipment and elevator equipment within the optimization period.

[0071] The evening power loss data of the target building during the optimization period is retrieved. The average power loss line of the evening time zone of the optimization period is drawn in the same way as the method for obtaining the average power loss line of the evening time zone of the diagnosis period. The average power loss line of the evening time zone of the optimization period is then integrated with the average power loss line of the evening time zone of the diagnosis period to obtain the power loss coefficient of the optimization period and the power loss coefficient of the diagnosis period.

[0072] The relative change rate of the optimization cycle power loss coefficient relative to the diagnosis cycle power loss coefficient is calculated, and the negative value thereof is taken as the energy-saving effect evaluation index.

[0073] The embodiment of the present invention compares the nighttime power loss of the target building before and after optimization, evaluates the energy-saving effect and performs feedback, so as to accurately determine whether the building energy saving has achieved the expected effect, and then continuously optimize and improve the building energy-saving strategy.

[0074] The system of the present invention uses a cloud database during execution to store a preset configuration table of the number of elevator operations at night. All parameters in the cloud database are provided externally.

[0075] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0076] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0077] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0078] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0079] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0080] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A building energy-saving diagnostic data analysis system, characterized in that: include: The historical monitoring period is divided into a reference period and a diagnostic period. The standard nighttime power loss data of the target building within the reference period is screened based on the similarity of ambient temperature. The nighttime power loss baseline of the target building is obtained through statistical feature analysis. Extract the target building's nighttime power consumption data during the diagnostic period, analyze its deviation characteristics relative to the nighttime power consumption baseline, and determine whether there is room for energy-saving optimization in the target building. If so, perform energy-saving optimization on the air conditioning equipment and elevator equipment respectively; otherwise, maintain normal operation; Extract the nighttime operating data of lighting equipment on each floor of the target building during the diagnosis period, infer the characteristics of personnel activity at each floor and each night time, adjust the parameters of air conditioning equipment during low personnel activity times, and disable air conditioning equipment when personnel are about to leave the building; Extract the nighttime call data of the target building's elevator equipment during the diagnosis period, analyze the usage demand characteristics of each floor, and dynamically configure the number of elevators running at night and the locations of waiting floors; Compare the nighttime power loss of the target building before and after optimization, evaluate the energy-saving effect and provide feedback.

2. A building energy-saving diagnostic data analysis system according to claim 1, characterized in that: The process of screening the standard nighttime power loss data of the target building within the reference period based on the similarity of the ambient temperature includes: Retrieve the ambient temperature data of the evening time zone for each diagnostic working day in the diagnostic period and each reference working day in the reference period, and construct the ambient temperature feature vectors for each diagnostic working day and each reference working day based on the ambient temperature difference and average ambient temperature in the evening time zone; Based on the cosine similarity calculation formula, the similarity of the ambient temperature between each reference working day and each diagnosis working day is calculated respectively, and a similarity matrix is ​​constructed based on this. The rows and columns of the matrix correspond to the diagnosis working day and the reference working day respectively, and the element values ​​of the matrix correspond to the similarity of the ambient temperature between the diagnosis working day and the reference working day. The similarity matrix is ​​summed up by column to obtain the cumulative similarity of each reference working day relative to the diagnosis cycle; The reference working days are sorted in descending order according to the cumulative similarity, a preset number of reference working days before the sequence are selected as standard reference working days, and the power loss data of the evening time zone of each standard reference working day are integrated to obtain the standard evening power loss data.

3. A building energy-saving diagnostic data analysis system according to claim 2, characterized in that: The process of obtaining the nighttime power loss baseline of the target building through statistical feature analysis includes: According to the preset time interval, the evening time zone is divided to generate each evening time period; Arrange the power loss data of the same evening time period on weekdays in ascending order for each standard reference, and construct an ascending data set of power loss for each evening time period; Based on the preset percentile value, quantile calculation is performed on each ascending power loss data set, and the corresponding percentile value is extracted as the power loss baseline value, thereby obtaining the power loss baseline value for each evening time period; The power loss baseline values ​​of the evening time periods are combined in chronological order to construct a nighttime power loss baseline of the target building.

4. A building energy-saving diagnostic data analysis system according to claim 3, characterized in that: The specific process of determining whether there is room for energy-saving optimization in the target building is as follows: For the power loss data of the same evening time period on each diagnostic working day, after removing the maximum and minimum values, the arithmetic mean of the remaining data is calculated to obtain the average power loss data for each evening time period. Based on this, the average power loss line of the evening time zone of the diagnostic period is drawn. This line is then compared with the evening power loss baseline for each time period, and the positive deviation value and positive deviation duration of the power loss in each evening time period are calculated; The duration of the positive deviation of power loss in each evening period is used as a weight factor, and the positive deviation values ​​of power loss in each evening period are linearly weighted and fused to obtain the diagnostic period deviation parameter. Perform linear weighted calculation on the duration of each evening period and its corresponding power loss benchmark value to obtain the power loss benchmark parameter, and calculate the ratio of the diagnostic cycle deviation parameter to the diagnostic cycle deviation parameter as the power loss deviation evaluation index; If the power loss deviation evaluation index is greater than a preset optimization judgment threshold, it is determined that there is room for energy-saving optimization in the target building.

5. A building energy-saving diagnostic data analysis system according to claim 1, characterized in that: The process of estimating the activity characteristics of people at each floor and each night time period includes: Retrieve the switch circuit status data of the office area lighting equipment on a certain floor in the evening time zone of a diagnostic workday. When the switch circuit status of the office area lighting equipment is disconnected at a certain time point, and the disconnection duration is greater than the preset duration, record this time point as the departure time point of the reference personnel on this floor; Monitor the power loss data of the lighting equipment on this floor according to the preset sampling period, calculate the power loss change rate of each sampling time point compared to the previous sampling node, and when the absolute power loss change rate at a certain sampling time point is greater than the preset change threshold, and the power loss data is less than the preset power loss threshold, record the sampling time point as a reference low-personnel activity time point; Obtain the reference personnel departure time point dataset and reference low personnel activity time point dataset for each diagnostic working day on that floor; Take each time point in the reference personnel departure time point dataset as the reference time point in turn, obtain the absolute cumulative deviation duration of the remaining time points from the reference time point, select the reference time point corresponding to the minimum absolute cumulative deviation duration as the personnel departure time point, and similarly obtain the low personnel activity time point from the reference low personnel activity time point dataset, and thereby obtain the personnel departure time points and low personnel activity time points on each floor of the target building.

6. A building energy-saving diagnostic data analysis system according to claim 1, characterized in that: The process of adjusting the air conditioning equipment parameters at low-personnel activity time and deactivating the air conditioning equipment when people are about to leave the venue includes: According to the season of the diagnosis cycle, the temperature of the air-conditioning equipment on each floor is adjusted in a targeted manner during the time of low personnel activity; The time point preset time before the departure time of personnel on each floor is defined as the departure time point of personnel, and the air-conditioning equipment is disabled at the departure time point of personnel on each floor.

7. A building energy-saving diagnostic data analysis system according to claim 1, characterized in that: The process of analyzing the usage demand characteristics of each floor includes: The evening call data of elevator equipment on each diagnostic workday is extracted. Operation combinations with the same call floor and target floor in each evening period are selected and their operation times are counted. This is used to construct the elevator equipment transfer matrix for each evening period. The rows and columns of the matrix correspond to the call floor and target floor, respectively, and the elements of the matrix correspond to the counted operation times. Normalizing the elevator equipment transfer matrix to obtain an elevator equipment transfer probability matrix for each evening time period on each diagnosis working day; Calculate the arithmetic mean of the corresponding elements of the elevator equipment transfer probability matrix for each diagnosis working day by grouping them in the evening time period, and obtain the reference elevator equipment transfer probability matrix for each evening time period; Retrieve the collection of elevator equipment calling time points on each diagnostic working day and obtain the number of elevator equipment calling times in each evening period on each diagnostic working day; The number of elevator calls in the same evening time period on different diagnostic working days was averaged to obtain the reference number of elevator calls in each evening time period, and the elevator call frequency in each evening time period was calculated based on this.

8. A building energy-saving diagnostic data analysis system according to claim 7, characterized in that: The process of dynamically configuring the number of elevator operations at night is as follows: The preset evening elevator operation quantity configuration table stored in the cloud database is called, and the elevator equipment demand level is determined according to the elevator equipment call frequency in each evening time period, and the number of elevator operations of the corresponding level is matched, so as to dynamically configure the number of elevator operations in each evening time period.

9. A building energy-saving diagnostic data analysis system according to claim 7, characterized in that: The process of dynamically configuring the elevator standby floor position at night is as follows: According to the reference elevator equipment transfer probability matrix of each evening time period, the calling floor with the highest probability of calling the elevator equipment in each evening time period is screened and used as the elevator equipment standby floor in each evening time period.

10. A building energy-saving diagnosis data analysis system according to claim 4, characterized in that: The specific acquisition process of evaluating the energy saving effect is as follows: Starting from the end of the diagnosis period, extend the number of days back to define the optimization period. During the optimization period, implement energy-saving optimization measures for air conditioning equipment and elevator equipment. Retrieve the nighttime power loss data of the target building during the optimization period. Use the same method as that used to obtain the average power loss line for the nighttime time zone during the diagnosis period to draw the average power loss line for the nighttime time zone during the optimization period. Integrate the average power loss line with the average power loss line for the nighttime time zone during the diagnosis period to obtain the power loss coefficient for the optimization period and the power loss coefficient for the diagnosis period. The relative change rate of the optimization cycle power loss coefficient relative to the diagnosis cycle power loss coefficient is calculated, and the negative value thereof is taken as the energy-saving effect evaluation index.

Images