A multi-stage correlation mining and optimization control system for building energy consumption data

Abstract

This application relates to the field of building energy consumption and discloses a multi-stage correlation mining and optimization control system for building energy consumption data, including: a data collection module, a data storage module, an analysis module, and a control module. The data collection module collects building energy consumption parameters and environmental parameters. The data storage module is interconnected with the data collection module and receives and stores the energy consumption parameters and environmental parameters, and performs preliminary data classification and caching. The analysis module is interconnected with the data storage module and analyzes the classified data, verifying and correcting the analysis results. By analyzing the relationship between the building's average temperature and the power consumption of temperature control equipment on each floor, the correlation between the power consumption of temperature control equipment on each floor and the building's average temperature can be obtained. Subsequently, the direct weighting method can be used to analyze the direct relationship between the power consumption of temperature control equipment on each floor and the building's average temperature.

Description

Technical Field

[0001] This invention relates to the field of building energy consumption technology, specifically to a multi-stage correlation mining and optimization control system for building energy consumption data. Background Technology

[0002] Building energy consumption is an important component of total social energy consumption. Globally, building operation energy consumption accounts for more than 30% of total energy consumption. With the progress of urbanization and the increasing complexity of building functions, energy consumption issues are becoming increasingly prominent. The energy consumption of temperature control equipment in buildings often accounts for a large portion of building energy consumption. Therefore, by reasonably controlling the energy consumption of temperature control equipment, the total energy consumption of buildings can be reduced.

[0003] When installing temperature control equipment, for multi-story buildings, each floor is often equipped with a separate set of master temperature control equipment. The temperature of a single floor can be adjusted by adjusting the output power of the temperature control equipment. However, in actual use, there will be mutual interference between the temperatures of different floors, especially in open shopping malls, where the mutual interference between floors is stronger. Current technology only considers the impact of temperature control equipment on the temperature of each floor, while ignoring the mutual interference between floors. It does not plan the building as a whole, which leads to energy waste. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a multi-stage correlation mining and optimization control system for building energy consumption data, which solves the problem that "existing technologies do not plan buildings as a complete whole, which leads to energy waste."

[0005] To achieve the above objectives, the present invention provides the following technical solution: a multi-stage correlation mining and optimization control system for building energy consumption data, comprising: a data collection module, a data storage module, an analysis module, and a control module.

[0006] The data collection module is used to collect building energy consumption parameters and environmental parameters;

[0007] The data storage module is interconnected with the data collection module and is used to receive and store energy consumption parameters and environmental parameters, and to perform preliminary classification and caching of the data;

[0008] The analysis module and the data storage module are interconnected and used to analyze the classified data and verify and correct the analysis results.

[0009] The control module and the analysis module are interconnected and used to control the operation of facilities within the building, and to cooperate with the analysis module to perform verification.

[0010] Preferably, the data collection module includes a temperature sensor and an energy consumption sensor. Multiple sets of both the temperature sensor and the energy consumption sensor are provided. The multiple sets of temperature sensors are installed at the same location on different floors. The temperature sensors are installed at the center of each floor, at a height of 1.5 meters to 2 meters above the ground. The temperature sensors are used to collect temperature data of each floor in the building. The energy consumption sensors are installed at the temperature control equipment on each floor to collect the output power data of the temperature control equipment on each floor.

[0011] Preferably, the data storage module includes a cloud storage module and a local storage module. The cloud storage module is used to store data for a long time, and the local storage module is used for temporary storage of data. The cloud storage module and the local storage module are interconnected through a communication network. The data collection module transmits the collected temperature data and output power data to the local storage module through the communication network.

[0012] Preferably, the analysis module includes an analysis unit, a virtual verification unit, and an execution verification unit. The local storage module transmits temperature data and output power data to the analysis unit via a communication network. The analysis unit analyzes the temperature data and output power data and transmits the analysis results to the virtual verification unit, the execution verification unit, and the adjustment module via the communication network.

[0013] Preferably, the control module includes a signal transmission device and a signal receiving device. The execution verification unit sends control signals to the signal transmission device through a communication network, and the signal transmission device sends control signals to the signal receiving device through a communication network. The signal receiving device is installed at the temperature control equipment on each floor. After receiving the control signal, it controls the temperature control equipment to work. The execution verification unit realizes the transmission and implementation of the scheme through the signal transmission device and the signal receiving device.

[0014] Preferably, the analysis unit is interconnected with the cloud storage module and the local storage module through a communication network, and obtains the classified data from the cloud storage module and the local storage module through the communication network. The analysis unit analyzes the correlation between building power consumption and environmental parameters by designing a multiple linear regression model.

[0015] Preferably, the analysis unit analyzes the correlation between building energy consumption and environmental parameters by designing a multiple linear regression model. Specifically, it collects various environmental parameters within the building every 15 minutes and classifies the collected data according to the collection time and location. Here, i represents the floor number, t represents the time point of data recording, T represents the temperature value, P represents the energy consumption value, Tit refers to the temperature value of the i-th floor at time t, Tt represents the average temperature of the entire building at time t, Pit represents the output power of the temperature control device on the i-th floor at time t, and Pt represents the total output power of the temperature control devices in the entire building at time t.

[0016] Preferably, the analysis unit performs analysis based on the overall building average temperature data set Tt = {T1, T2…Tt} and the output power Pi = {Pi1, Pi2…Pit} of each floor's temperature control equipment. It calculates the value of Rxy using the Pearson correlation coefficient formula, where Rxy represents the correlation between the output power of a single floor's temperature control equipment and the overall building average temperature. It then calculates the weight of each floor's temperature control equipment output power Pi on the overall building average temperature Tt using a direct weighting method. Based on the calculated weight values, it derives the relationship between each floor's temperature control equipment output power Pi and Tt. Subsequently, it uses linear programming to solve the obtained relationship, obtaining the allocation of each floor's temperature control equipment output power Pi to minimize the sum of the output power of each floor's temperature control equipment, assuming the overall building average temperature Tt is a fixed value.

[0017] Preferably, the virtual verification unit filters the solutions provided by the analysis unit. The specific filtering method includes: limiting the output power of a single-floor temperature control device to not exceed the maximum output power Pimax and not be lower than the minimum power Pimin of the single-floor temperature control device. The virtual verification unit sends the solution data that meets the filtering conditions to the execution verification unit. After receiving the signal, the execution verification unit sends a control signal to the signal transmission device. After receiving the signal, the signal transmission device sends a signal to the signal receiving device. After receiving the signal, the signal receiving device controls the temperature control device to start working according to the power obtained by the solution.

[0018] Preferably, the adjustment module collects feasible solutions, classifies them according to the season, and saves specific solutions according to spring, summer, autumn, and winter.

[0019] This invention provides a multi-stage correlation mining and optimization control system for building energy consumption data. It has the following beneficial effects:

[0020] 1. This invention analyzes the relationship between the average building temperature and the power consumption of temperature control equipment on each floor, thereby obtaining the correlation between the power consumption of temperature control equipment on each floor and the average building temperature. Then, the direct weighting method can be used to analyze the direct relationship between the power consumption of temperature control equipment on each floor and the average building temperature, so as to carry out overall regulation and reduce the total building energy consumption.

[0021] 2. By classifying and collecting data from different environments, this invention allows for the selection of different implementation schemes based on varying environments, thereby further improving the accuracy of energy consumption control and reducing the overall energy consumption of the building. Attached Figure Description

[0022] Figure 1 This is a structural block diagram of the present invention.

[0023] The system includes: 1. Data collection module; 11. Temperature sensor; 12. Energy consumption sensor; 2. Data storage module; 21. Cloud storage module; 22. Local storage module; 3. Analysis module; 31. Analysis unit; 32. Virtual verification unit; 33. Execution verification unit; 34. Adjustment module; 4. Control module; 41. Signal transmission device; 42. Signal receiving device. Detailed Implementation

[0024] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] Example:

[0026] Please see the appendix Figure 1 This invention provides a multi-stage correlation mining and optimization control system for building energy consumption data, comprising: a data collection module 1, a data storage module 2, an analysis module 3, and a control module 4.

[0027] Data collection module 1 is used to collect building energy consumption parameters and environmental parameters. This system mainly minimizes overall building energy consumption by adjusting the power of temperature control equipment, so this module mainly collects temperature and energy consumption data. Data storage module 2 is interconnected with data collection module 1 and is used to receive and store energy consumption parameters and environmental parameters. It also performs preliminary classification and caching of the data. Indoor temperature is greatly affected by seasonal factors, so the data is classified and stored according to the season. Analysis module 3 is interconnected with data storage module 2 and is used to analyze the classified data and verify and correct the analysis results. By analyzing the data, the relationship between building temperature and building energy consumption can be obtained, which can facilitate the design of energy-saving schemes. Control module 4 is interconnected with analysis module 3 and is used to control the operation of facilities in the building. It also works with analysis module 3 to verify the results. After analysis module 3 transmits the analyzed scheme to control module 4, control module 4 will control the equipment in the building to operate according to the predetermined scheme.

[0028] The data collection module 1 includes a temperature sensor 11 and an energy consumption sensor 12. The temperature sensor 11 includes, but is not limited to, an NTC thermistor module, and the energy consumption sensor 12 includes, but is not limited to, a current sensor and a voltage sensor. Multiple sets of temperature sensors 11 and energy consumption sensors 12 are provided. Multiple sets of temperature sensors 11 are installed in the same location on different floors to ensure the consistency of data sources. The temperature sensors 11 are installed at the center of each floor, at a height of 1.5 meters to 2 meters above the ground. This installation height is consistent with the height of most people and can represent the perceived temperature. The temperature sensors 11 are used to collect temperature data of each floor in the building. The energy consumption sensors 12 are installed at the temperature control equipment on each floor to collect the output power data of the temperature control equipment on each floor. The energy consumption sensors 12 can detect the instantaneous power and total power consumption of the temperature control equipment.

[0029] The data storage module 2 includes a cloud storage module 21 and a local storage module 22. The cloud storage module 21 is used to store data for a long time. The cloud storage module 21 includes, but is not limited to, Alibaba Cloud data storage platform and Tencent Cloud data storage platform. The local storage module 22 is used for temporary storage of data. The cloud storage module 21 and the local storage module 22 are interconnected through a communication network. The data collection module 1 transmits the collected temperature data and output power data to the local storage module 22 through the communication network. After receiving the data, the local data storage module 22 will classify the data according to the season.

[0030] Analysis module 3 includes analysis unit 31, virtual verification unit 32, and execution verification unit 33. Analysis unit 31 is used to analyze data and provide the optimal solution. Virtual verification unit 32 and execution verification unit 33 are used to implement the optimal solution. Local storage module 22 transmits temperature data and output power data to analysis unit 31 through communication network. After receiving the data, analysis unit 31 can perform analysis. At the same time, analysis unit 31 can also download data from cloud storage module 21 for analysis. Analysis unit 31 analyzes temperature data and output power data and transmits the analysis results to virtual verification unit 32, execution verification unit 33, and adjustment module 34 through communication network. Since the data calculation is a virtual operation, it must be implemented to determine whether the solution is reasonable and reliable.

[0031] The control module 4 includes a signal transmission device 41 and a signal receiving device 42. The execution verification unit 33 sends control signals to the signal transmission device 41 through a communication network. In this embodiment, the communication network is mainly used to realize data transmission, which is relatively simple and fast. The signal transmission device 41 sends control signals to the signal receiving device 42 through the communication network. The signal receiving device 42 is installed at the temperature control equipment on each floor. After receiving the control signal, it controls the temperature control equipment to work. The temperature control equipment includes, but is not limited to, the central air conditioning thermostat, which can work according to the data given by the signal. The execution verification unit 33 realizes the transmission and implementation of the scheme through the signal transmission device 41 and the signal receiving device 42.

[0032] The analysis unit 31 is interconnected with the cloud storage module 21 and the local storage module 22 through a communication network. It obtains classified data from the cloud storage module 21 and the local storage module 22 through the communication network. The data provided by the local storage module 22 can be analyzed in real time according to the current situation, while the data collected from the cloud storage can be analyzed to obtain phased data. The analysis unit 31 analyzes the correlation between building power consumption and environmental parameters by calculating the Pearson correlation coefficient. The Pearson correlation coefficient is a statistical indicator used to measure the degree of linear correlation between two continuous variables, mainly used to determine whether there is a linear dependence between variables.

[0033] Analysis unit 31 analyzes the correlation between building energy consumption and environmental parameters by calculating the Pearson correlation coefficient. Specifically, it collects various environmental parameters in the building every 15 minutes and classifies the collected data according to the collection time and location. i represents the floor number, t represents the time point of data recording, T represents the temperature value, and P represents the energy consumption value. Tit refers to the temperature value of the i-th floor at time t, Tt represents the average temperature of the entire building at time t, Pit represents the output power of the temperature control equipment on the i-th floor at time t, and Pt represents the total output power of the temperature control equipment of the entire building at time t.

[0034] Analysis unit 31 analyzes the data based on the overall building average temperature set Tt = {T1, T2…Tt} and the output power Pi = {Pi1, Pi2…Pit} of the temperature control equipment on each floor. It calculates the value of Ri using the Pearson correlation coefficient formula. Ri represents the correlation between the output power of a single floor's temperature control equipment and the overall building average temperature. The specific calculation formula for the Pearson correlation coefficient includes…

[0035]

[0036] Where n represents the number of data sets, and a set Ri{R1, R2, ..., Ri} can be established based on the obtained data. Here, the research object is a five-story shopping mall building, and the correlation between the output power of the temperature control equipment on each floor and the average temperature of the entire building is as follows. 1 = 0.85; 2 = 0.78; 3 = 0.92; 4 = 0.88; 5 = 0.81. Therefore, it can be seen that for a five-story building, the temperature of the middle floors has a greater impact on the overall building average. Subsequently, the weight of the output power Pi of the temperature control equipment on each floor on the overall building average temperature Tt is calculated using the direct weighting method. The specific calculation formula for the direct weighting method includes...

[0037]

[0038] Where Xi represents the weight of the output power of the temperature control device on the i-th floor on the overall temperature, then X1=0.20; X2=0.18; X3=0.22; X4=0.21; X5=0.18. Based on the calculated weight values, the relationship between the output power Pi of the temperature control device on each floor and Tt is derived. The specific relationship is as follows:

[0039] Specifically:

[0040] Subsequently, using linear programming, the obtained relationship is solved to determine how to allocate the output power Pi of the temperature control equipment on each floor to minimize the sum of the output power Pmin of the temperature control equipment on each floor, given a fixed overall building average temperature Tt. The specific calculation method is as follows.

[0041] The solution is obtained using the `linprog` function from the `scipy` library in Python.

[0042] The virtual verification unit 32 filters the solutions provided by the analysis unit 31. The specific filtering method includes: limiting the output power of a single-floor temperature control device to not exceed the maximum output power Pimax and not be lower than the minimum power Pmin of the single-floor temperature control device.

[0043] Based on this requirement, further constraints can be added to the linprog function.

[0044] Pmin <P

[0045] Pmax>P

[0046] The specific restrictions here are:

[0047] 3kW <P<8kW

[0048] The data obtained from this screening includes, but is not limited to:

[0049] P1=6.0kW;P1=5.0kW;P1=6.5kW;P1=5.5kW;P1=5.0kW

[0050] The virtual verification unit 32 sends the scheme data that meets the screening conditions to the execution verification unit 33. After receiving the signal, the execution verification unit 33 sends a control signal to the signal transmission device 41. After receiving the signal, the signal transmission device 41 sends a signal to the signal receiving device 42. After receiving the signal, the signal receiving device 42 controls the temperature control device to start working according to the power obtained by the solution.

[0051] The adjustment module 34 collects feasible solutions and categorizes them according to season, saving specific solutions based on spring, summer, autumn, and winter. Since ambient temperature changes with the seasons, the weight of the output power of the temperature control equipment on each floor also changes, specifically as follows:

[0052] In spring, when the outside temperature is low and fluctuates greatly, buildings need a certain amount of heat to maintain the indoor temperature. At this time, the ground floor is more affected by the low ground temperature because it is closer to the ground, so the equipment weight is relatively high. The upper floors are less affected by the cold air outside, so the weight is slightly lower. The weight of the middle floors is between the two. Common weight distributions include X1=0.22; X2=0.21; X3=0.20; X4=0.19; X5=0.18.

[0053] In summer, the ambient temperature rises rapidly, and buildings are mainly driven by cooling needs. Higher floors have greater cooling needs due to longer periods of direct sunlight and greater absorption of solar radiation, so the weight of temperature control equipment increases. Lower floors are relatively cooler, so their weight decreases. A common weight distribution is X1=0.19; X2=0.20; X3=0.21; X4=0.22; X5=0.22.

[0054] In autumn, the ambient temperature gradually decreases, but it is still relatively hot, similar to the summer. Higher floors dissipate heat relatively slowly, so the weight of temperature control devices remains stable. However, the further decrease in ground temperature will cause the weight of lower floors to decrease further. This will lead to an increase in the weight of temperature control devices on the middle and upper floors. A common weight distribution is X1=0.23; X2=0.22; X3=0.20; X4=0.19; X5=0.18.

[0055] In winter, temperatures drop significantly, and buildings enter full heating mode. The ground floor loses more heat due to direct contact with the cold ground, so the weight of temperature control equipment is increased. The upper floors also have a relatively high weight due to strong winds and rapid heat dissipation, while the middle floors have a slightly lower weight. A common weight distribution is X1=0.24; X2=0.23; X3=0.22; X4=0.21; X5=0.20.

[0056] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A multi-stage correlation mining and optimization control system for building energy consumption data, characterized in that, include: The data collection module (1), data storage module (2), analysis module (3), and control module (4) are as follows: The data collection module (1) is used to collect building energy consumption parameters and environmental parameters; The data storage module (2) is interconnected with the data collection module (1) and is used to receive and store energy consumption parameters and environmental parameters, and to perform preliminary classification and caching of the data; The analysis module (3) is interconnected with the data storage module (2) and is used to analyze the classified data and verify and correct the analysis results. The control module (4) is interconnected with the analysis module (3) to control the operation of facilities in the building and to cooperate with the analysis module (3) to perform verification.

2. The multi-stage correlation mining and optimization control system for building energy consumption data according to claim 1, characterized in that: The data collection module (1) includes a temperature sensor (11) and an energy consumption sensor (12). Multiple sets of the temperature sensor (11) and the energy consumption sensor (12) are provided. Multiple sets of the temperature sensor (11) are installed at the same location in different floors. The temperature sensor (11) is installed at the center of each floor, at a height of 1.5 meters to 2 meters from the ground. The temperature sensor (11) is used to collect temperature data of each floor in the building. The energy consumption sensor (12) is installed at the temperature control equipment on each floor to collect the output power data of the temperature control equipment on each floor.

3. The multi-stage correlation mining and optimization control system for building energy consumption data according to claim 1, characterized in that: The data storage module (2) includes a cloud storage module (21) and a local storage module (22). The cloud storage module (21) is used to store data for a long time, and the local storage module (22) is used for temporary storage of data. The cloud storage module (21) and the local storage module (22) are interconnected through a communication network. The data collection module (1) transmits the collected temperature data and output power data to the local storage module (22) through the communication network.

4. The multi-stage correlation mining and optimization control system for building energy consumption data according to claim 2, characterized in that: The analysis module (3) includes an analysis unit (31), a virtual verification unit (32), and an execution verification unit (33). The local storage module (22) transmits temperature data and output power data to the analysis unit (31) through a communication network. The analysis unit (31) analyzes the temperature data and output power data and transmits the analysis results to the virtual verification unit (32), the execution verification unit (33), and the adjustment module (34) through the communication network.

5. A multi-stage correlation mining and optimization control system for building energy consumption data according to claim 4, characterized in that: The control module (4) includes a signal transmission device (41) and a signal receiving device (42). The execution verification unit (33) sends a control signal to the signal transmission device (41) through a communication network. The signal transmission device (41) sends a control signal to the signal receiving device (42) through a communication network. The signal receiving device (42) is installed at the temperature control equipment on each floor. After receiving the control signal, it controls the temperature control equipment to work. The execution verification unit (33) realizes the transmission and implementation of the scheme through the signal transmission device (41) and the signal receiving device (42).

6. The multi-stage correlation mining and optimization control system for building energy consumption data according to claim 4, characterized in that: The analysis unit (31) is connected to the cloud storage module (21) and the local storage module (22) through a communication network. The analysis unit (31) obtains the classified data from the cloud storage module (21) and the local storage module (22) through the communication network. The analysis unit (31) analyzes the correlation between building power consumption and environmental parameters by designing a multiple linear regression model.

7. A multi-stage correlation mining and optimization control system for building energy consumption data according to claim 6, characterized in that: The analysis unit (31) analyzes the correlation between building power consumption and environmental parameters by designing a multiple linear regression model. Specifically, it collects various environmental parameters in the building every 15 minutes and classifies the collected data according to the collection time and collection location. i represents the floor number, t represents the time point of data recording, T represents the temperature value, P represents the energy consumption value, Tit refers to the temperature value of the i-th floor at time t, Tt represents the average temperature of the entire building at time t, Pit represents the output power of the temperature control equipment on the i-th floor at time t, and Pt represents the total output power of the temperature control equipment of the entire building at time t.

8. A multi-stage correlation mining and optimization control system for building energy consumption data according to claim 7, characterized in that: The analysis unit (31) analyzes the data set of the overall building average temperature Tt = {T1, T2…Tt} and the output power Pi = {Pi1, Pi2…Pit} of the temperature control equipment on each floor. It calculates the value of Rxy using the Pearson correlation coefficient formula. Rxy represents the correlation between the output power of the temperature control equipment on a single floor and the overall building average temperature. It calculates the weight of the influence of the output power Pi of the temperature control equipment on the overall building average temperature Tt using the direct weighting method. Based on the calculated weight value, it derives the relationship between the output power Pi of the temperature control equipment on each floor and Tt. Then, it uses the linear programming method to solve the obtained relationship. When the overall building average temperature Tt is a fixed value, it allocates the output power Pi of the temperature control equipment on each floor so that the sum of the output power of the temperature control equipment on each floor reaches the minimum value Pmin.

9. A multi-stage correlation mining and optimization control system for building energy consumption data according to claim 8, characterized in that: The virtual verification unit (32) filters the schemes given by the analysis unit (31). The specific filtering method includes limiting the output power of a single floor temperature control device to not exceed the maximum output power Pimax and not be lower than the minimum power Pimin of the single floor temperature control device. The virtual verification unit (32) sends the scheme data that meets the filtering conditions to the execution verification unit (33). After receiving the signal, the execution verification unit (33) sends a control signal to the signal transmission device (41). After receiving the signal, the signal transmission device (41) sends a signal to the signal receiving device (42). After receiving the signal, the signal receiving device (42) controls the temperature control device to start working according to the power obtained by the solution.

10. A multi-stage correlation mining and optimization control system for building energy consumption data according to claim 9, characterized in that: The adjustment module (34) collects feasible solutions and classifies them according to the season, and saves specific solutions according to spring, summer, autumn and winter.

Images