Building air conditioning system energy consumption splitting method, device, equipment, medium and product

Abstract

The application discloses a building air conditioning system energy consumption splitting method, device, equipment, medium and product, and relates to the technical field of building energy consumption management. The method is to first acquire the total power consumption in a plurality of unit time periods, the service parameters and the meteorological parameters in the time periods, and the rated parameters of the power consumption equipment of the building air conditioning system, then construct a linear regression model, determine the upper and lower limits of the power consumption in the time periods of the air conditioning system, then apply the total power consumption, the service parameters, the meteorological parameters and the upper and lower limits of the power consumption, optimize the model parameters of the linear regression model based on an optimization algorithm, obtain the model parameters and use the optimization search results for making the total penalty coefficient lowest and the model input items and the model output items of the linear regression model have the highest adaptation degree, finally substitute the search results into the linear regression model, and calculate the power consumption in the time periods of the air conditioning system, so that the energy consumption conditions of the building air conditioning system with a large energy-saving space can be quickly identified.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of building energy consumption management, and particularly relates to a building air conditioning system energy consumption splitting method, device, equipment, medium and product. BACKGROUND

[0002] With the intensification of global climate change, the building industry, as a key industry of energy consumption, its energy saving and emission reduction has become the key battlefield to realize sustainable development. In recent years, many government office buildings and large public buildings are installed with building energy consumption monitoring systems, so as to timely grasp the real-time operation conditions of building energy consumption systems such as building air conditioning systems and domestic power systems, and then provide basis for building energy saving management and energy saving reconstruction. However, due to the high installation cost of the sub-metering system for realizing building energy consumption monitoring, a considerable number of traditional buildings still do not have sub-metering systems, so that the energy saving work of these buildings generally exists problems such as insufficient energy consumption data granularity, weak pertinence of energy saving measures and fuzzy responsibility subject, which seriously restricts the deep optimization of building energy efficiency.

[0003] At present, domestic and foreign scholars are researching on building electricity consumption splitting schemes: some scholars propose a non-embedded energy consumption monitoring method, which calculates the energy consumption value of each device according to the start / stop signal and real-time power of the electrical equipment, but this method is mainly used for residential buildings, and due to the complex composition and various types of electrical equipment in public buildings, the method has the problem of poor use effect (i.e. poor accuracy of energy consumption splitting results) when used in public buildings; in view of the complex distribution branch situation, some scholars have proposed a series of indirect metering methods such as "capacity proportion method", "small quantity not counting method", "stable real splitting method", "gear timing method" and "characteristic analysis method", which are simple and easy to implement, but too dependent on experience and measured data, so that human errors are easy to occur in actual application.

[0004] Based on the above situation, how to provide a building energy consumption splitting scheme with low requirement on original energy consumption data granularity and simple and easy to implement, so as to analyze the energy consumption of traditional public buildings lacking of basic sub-metering data, and quickly identify the energy consumption situation of building air conditioning systems with large energy saving space, and lay a data foundation for subsequent energy saving and carbon reduction work, is a subject that the technical personnel in the field need to research. SUMMARY

[0005] The purpose of the present application is to provide a building air conditioning system energy consumption splitting method, device, computer equipment, computer readable storage medium and computer program product, to solve the problem of poor accuracy of energy consumption splitting results of the existing building electricity consumption splitting scheme when facing traditional public buildings lacking of basic sub-metering data.

[0006] In order to achieve the above object, the present application adopts the following technical solutions:

[0007] In a first aspect, an energy consumption splitting method for a building air conditioning system is provided, comprising:

[0008] obtaining total segment energy consumption and segment business parameters of the target building in multiple unit time periods, obtaining segment meteorological parameters of the region where the target building is located in multiple unit time periods, and obtaining rated parameters of the power consumption equipment of the building air conditioning system in the target building;

[0009] constructing a linear regression model for reflecting the linear relationship between the segment energy consumption of the building air conditioning system in multiple unit time periods and the segment meteorological parameters / and segment business parameters;

[0010] determining the upper and lower limits of the segment energy consumption of the building air conditioning system in the first segment of multiple unit time periods according to the rated parameters of the power consumption equipment of the building air conditioning system;

[0011] applying the total segment energy consumption, segment business parameters, segment meteorological parameters and the upper and lower limits of the first segment energy consumption, and optimizing the model parameters of the linear regression model based on an optimization algorithm to obtain the model parameters and realize the optimal search result of multiple target optimization, wherein the multiple target optimization refers to the lowest total penalty coefficient / and the highest fitting degree between the model input and the model output of the linear regression model, and the total penalty coefficient is represented as follows:

[0012]

[0013] In the formula, denotes the total number of time periods in multiple unit time periods, denotes a positive integer less than or equal to , and denotes the first boundary crossing penalty coefficient determined according to the positional relationship between the segment energy consumption of the building air conditioning system in the first unit time period and the upper and lower limits of the first segment energy consumption and the first boundary crossing penalty preset rule, denotes the third boundary crossing penalty coefficient determined according to the positional relationship between the remaining energy consumption of the target building in the first unit time period and zero and the third boundary crossing penalty preset rule, denotes the total segment energy consumption of the target building in the first unit time period; substituting the optimal search result into the linear regression model, and for each unit time period, applying the linear regression model to calculate the segment energy consumption of the building air conditioning system in the corresponding time period according to the corresponding segment meteorological parameters / and segment business parameters.

[0014] substituting the optimal search result into the linear regression model, and for each unit time period, applying the linear regression model to calculate the segment energy consumption of the building air conditioning system in the corresponding time period according to the corresponding segment meteorological parameters / and segment business parameters. ​​

[0015] Based on the above-mentioned invention, a novel and simple energy consumption breakdown scheme for building air conditioning systems is provided, which does not require high granularity of raw energy consumption data. This involves first obtaining the total power consumption, operational parameters, and meteorological parameters of the target building within multiple time periods, as well as the rated parameters of the building's air conditioning system equipment. Then, a linear regression model is constructed to reflect the linear relationship between the building's power consumption within a given time period and the meteorological and operational parameters. The upper and lower limits of the building's power consumption within a given time period are determined. Finally, the upper and lower limits of the power consumption within a given time period are applied. The lower bound is determined by optimizing the model parameters of the linear regression model using an optimization algorithm. This yields the optimal search results that minimize the total penalty coefficient and maximize the fit between the model input and output terms. Finally, the search results are substituted into the linear regression model to calculate the energy consumption of the building's air conditioning system in each time period. This approach is applicable to energy consumption analysis of traditional public buildings lacking basic sub-item metering data. It can quickly identify the energy consumption of building air conditioning systems with significant energy-saving potential, providing a data foundation for subsequent energy conservation and carbon reduction efforts, and facilitating practical application and promotion.

[0016] In a possible design, when the target building is a hospital building, the building's air conditioning system includes air conditioning systems for clean areas and non-clean areas. A linear regression model is constructed to reflect the linear relationship between the building's air conditioning system's power consumption within a segment and the meteorological parameters and operational parameters within that segment over multiple time periods. This model includes:

[0017] The following univariate linear regression model is constructed using the least squares method to reflect the linear relationship between the power consumption of the air conditioning system in a non-clean area and the meteorological parameters within the segment over multiple time periods:

[0018]

[0019] In the formula, Indicates that the air conditioning system in the non-clean area is in the first Electricity consumption within a unit time period, This indicates that the parameters extracted from the meteorological parameters within the segment and in the first... Temperature parameters for a given time period. and These represent the model parameters in the univariate linear regression model;

[0020] A bivariate linear regression model is constructed using a multiple linear regression model to reflect the linear relationship between the power consumption of the air conditioning system in the clean area and the meteorological parameters and operational parameters within the area over multiple time periods.

[0021]

[0022] wherein, represents the first segment power consumption of the purification area air conditioning system in the i-th unit time period, represents the first segment power consumption of the non-purification area air conditioning system in the i-th unit time period, represents the surgery amount parameter in the i-th unit time period extracted from the segmental service parameters, represents the surgery amount parameter in the i-th unit time period extracted from the segmental service parameters, , and respectively represent the model parameters in the binary linear regression model.

[0023] In one possible design, the air temperature parameter is extracted from the segmental meteorological parameters in the following manner:

[0024] the average air temperature in the i-th unit time period of the region where the target building is located is extracted from the segmental meteorological parameters;

[0025] The air temperature parameter is calculated in the following formula:

[0026]

[0027] wherein, represents the average air temperature in the i-th unit time period of the region where the target building is located and has the unit of Celsius, represents the total number of natural days in the i-th unit time period and has . In one possible design, when the target building is a hospital building and the building air conditioning system comprises the purification area air conditioning system and the non-purification area air conditioning system, according to the rated parameters of the electrical equipment of the building air conditioning system, the lower limit and the upper limit of the first segment power consumption of the building air conditioning system in multiple unit time periods are determined, comprising:

[0028] For the non-purification area air conditioning system or the purification area air conditioning system, the minimum rated power and the maximum rated power of the corresponding electrical equipment are extracted from the corresponding rated parameters of the electrical equipment, and the lower limit and the upper limit

[0029] of the first segment power consumption of the corresponding system in the i-th unit time period are calculated in the following formula:

[0030]

[0031] wherein, represents the minimum rated power and has the unit of kilowatt, represents the maximum rated power and has the unit of kilowatt, represents the total number of natural days in the i-th unit time period and has​​​​ The total number of natural days in a given time period and having .

[0032] In one possible design, the method further includes:

[0033] Obtain the rated parameters of electrical equipment in the non-air conditioning systems of the target building;

[0034] Based on the rated parameters of the electrical equipment in the building's non-air-conditioned system, determine the upper and lower limits of the building's non-air-conditioned system's power consumption in the second segment of multiple time periods;

[0035] Total penalty coefficient Replace with the following formula:

[0036]

[0037] In the formula, This represents the total number of time periods across multiple time units. Indicates less than or equal to positive integers, This indicates that, according to the building's air conditioning system, in the [number]th [year]... Electricity consumption per unit time period The positional relationship between the upper and lower limits of the first segment's internal power consumption and the first boundary penalty coefficient determined by the first boundary penalty preset rule. This indicates that, according to the building's non-air conditioning system, in the [number]th [year]... Electricity consumption per unit time period The positional relationship between the upper and lower limits of the second segment's internal power consumption and the second boundary penalty coefficient determined by the second boundary penalty preset rule. Indicates that according to the target building in the first Remaining power consumption per unit time period The third boundary penalty coefficient is determined by the positional relationship with the zero value and the preset rules for the third boundary penalty. Indicates the target building is in the Total power consumption within a given time period.

[0038] In one possible design, the optimization algorithm may employ particle swarm optimization, gray wolf optimization, bat optimization, eagle optimization, vulture optimization, or genetic optimization.

[0039] Secondly, a building air conditioning system energy consumption decomposition device is provided, including a multi-parameter acquisition unit, a linear model construction unit, a power consumption range determination unit, a model parameter optimization unit, and an optimal parameter application unit;

[0040] The multi-parameter acquisition unit is configured to acquire the total power consumption in a segment and the service parameter in a segment of the target building in multiple unit time periods, acquire the meteorological parameter in a segment of the region where the target building is located in multiple unit time periods, and further acquire the rated parameter of the power consumption equipment of the building air conditioning system in the target building.

[0041] The linear model construction unit is in communication connection with the multi-parameter acquisition unit and is configured to construct a linear regression model reflecting the linear relationship between the power consumption in a segment and the meteorological parameter in a segment and / or the service parameter in a segment of the building air conditioning system in multiple unit time periods.

[0042] The power consumption range determination unit is in communication connection with the multi-parameter acquisition unit and is configured to determine the upper and lower limits of the power consumption in a first segment of the building air conditioning system in multiple unit time periods according to the rated parameter of the power consumption equipment of the building air conditioning system.

[0043] The model parameter optimization unit is in communication connection with the multi-parameter acquisition unit, the linear model construction unit and the power consumption range determination unit respectively, and is configured to apply the total power consumption in a segment, the service parameter in a segment, the meteorological parameter in a segment and the upper and lower limits of the power consumption in a first segment, optimize the model parameters of the linear regression model based on an optimization algorithm, obtain the model parameters and realize the optimal search result of multiple target optimization, wherein the multiple target optimization refers to the lowest total penalty coefficient and / or the highest fitting degree between the model input term and the model output term of the linear regression model, and the total penalty coefficient is represented as follows:

[0044]

[0045] In the formula, n represents the total number of segments in multiple unit time periods, m represents a positive integer less than or equal to n, a represents the first out-of-limit penalty coefficient determined according to the positional relationship between the power consumption in a segment of the building air conditioning system in the mth unit time period and the upper and lower limits of the power consumption in a first segment and a first out-of-limit penalty preset rule, b represents the third out-of-limit penalty coefficient determined according to the positional relationship between the remaining power consumption in the mth unit time period of the target building and zero and a third out-of-limit penalty preset rule, and c represents the total power consumption in a segment of the target building in the mth unit time period.

[0046] ​​​​​​The optimal parameter application unit is respectively connected in communication with the model parameter optimization unit and the multiple parameter acquisition unit, configured to substitute the optimization search result into the linear regression model, and according to the corresponding in-segment meteorological parameter and in-segment business parameter, apply the linear regression model to calculate the in-segment power consumption of the building air conditioning system in the corresponding time period.

[0047] In a third aspect, the present application provides a computer device, comprising a memory, a processor and a transceiver connected in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to receive and send messages, and the processor is configured to read the computer program and execute the building air conditioning system energy consumption splitting method as described in the first aspect or any possible design of the first aspect.

[0048] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores instructions, and when the instructions are executed on a computer, the building air conditioning system energy consumption splitting method as described in the first aspect or any possible design of the first aspect is executed.

[0049] In a fifth aspect, the present application provides a computer program product, comprising a computer program or instructions, and when the computer program or the instructions are executed on a computer, the building air conditioning system energy consumption splitting method as described in the first aspect or any possible design of the first aspect is implemented.

[0050] The above-mentioned scheme has the following beneficial effects:

[0051] (1) The present application creatively provides a new building air conditioning system energy consumption splitting scheme which has low granularity requirement for original energy consumption data and is simple and easy to implement, that is, first, the in-segment total power consumption of the target building in multiple unit time periods, in-segment business parameters, in-segment meteorological parameters and rated parameters of the power consumption equipment of the building air conditioning system are acquired, then a linear regression model reflecting the linear relationship between the in-segment power consumption of the building air conditioning system and the in-segment meteorological parameters and in-segment business parameters is constructed, and the upper and lower limits of the in-segment power consumption of the building air conditioning system are determined, then the in-segment total power consumption, in-segment business parameters, in-segment meteorological parameters and in-segment power consumption upper and lower limits are applied, and the model parameters of the linear regression model are optimized based on an optimization algorithm to obtain the model parameters and the optimization search result for minimizing the total penalty coefficient and maximizing the fitting degree of the model input and model output of the linear regression model, finally, the search result is substituted into the linear regression model, and the in-segment power consumption of the building air conditioning system in each time period is calculated, thus the energy consumption analysis of traditional public buildings lacking basic sub-metering data can be performed, and the energy consumption of the building air conditioning system with large energy-saving space can be quickly identified, thereby laying a data foundation for subsequent energy-saving and carbon-reducing work.

[0052] (2) Without the need to install sub-metering equipment, only the monthly total power consumption, public meteorological data and building and air conditioning equipment basic information are needed to complete the monthly air conditioning energy consumption and sub-energy consumption splitting, solving the problem of lack of sub-data in most public buildings, and the marginal cost tends to be zero;

[0053] (3) The single running time of the optimized algorithm is less than or equal to 0.8 seconds, and the overall optimization and calculation time is only within 5 minutes, which is suitable for large-scale building group analysis;

[0054] (4) According to the error analysis results, the monthly error is less than or equal to ±10%, and the annual error is less than or equal to ±3%, which has high accuracy, can provide accurate data basis for subsequent energy saving and consumption reduction work, and is convenient for practical application and popularization. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, without creative labor, other drawings can also be obtained according to these drawings.

[0056] Figure 1 The flowchart of the building air conditioning system energy consumption splitting method provided by the embodiment of the present application.

[0057] Figure 2 The structural diagram of the building air conditioning system energy consumption splitting device provided by the embodiment of the present application.

[0058] Figure 3 The structural diagram of the computer device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will combine the drawings and the description of the embodiments or the prior art to briefly introduce the present application. Obviously, the following description of the drawings structure is only some embodiments of the present application, and for those skilled in the art, without creative labor, other embodiments can also be obtained according to these embodiments. It should be noted that the description of these embodiment modes is used to help understand the present application, but does not constitute a limitation on the present application.

[0060] It should be understood that although the terms "first" and "second", etc., may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another. For example, the first object may be referred to as the second object, and similarly, the second object may be referred to as the first object, without departing from the scope of the exemplary embodiments of the invention.

[0061] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, or A and B exist simultaneously. Another example is A, B and / or C, which can mean that any one of A, B, and C or any combination thereof exists. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone or A and B exist simultaneously. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0062] Example

[0063] like Figure 1 As shown, the energy consumption breakdown method for building air conditioning systems provided in the first aspect of this embodiment can be executed, but is not limited to, by computer equipment with certain computing resources, such as building energy management servers, cloud servers, personal computers (PCs, referring to a type of multi-purpose computer suitable for personal use in terms of size, price, and performance; desktop computers, laptops, mini-laptops, tablets, and ultrabooks are all considered personal computers), smartphones, personal digital assistants (PDAs), or wearable devices. Figure 1 As shown, the energy consumption breakdown method for the building air conditioning system may include, but is not limited to, the following steps S1 to S5.

[0064] S1. Obtain the total power consumption and service parameters of the target building within multiple unit time periods, obtain the meteorological parameters of the area where the target building is located within the multiple unit time periods, and also obtain the rated parameters of the electrical equipment of the building air conditioning system in the target building.

[0065] In step S1, the target building may be, but is not limited to, a traditional public building lacking basic sub-item metering data, such as a traditional hospital building. The unit time period is the smallest granularity of total power consumption in the time dimension, and may be, but is not limited to, a week, month, quarter, or year (i.e., the unit time period is an integer multiple of natural days); the total number of the multiple unit time periods... Generally, the total power consumption in the segment is greater than or equal to 10. The total power consumption in the segment refers to the total power consumption of the target building in the corresponding time segment, which can be obtained by conventional means such as reading the meter data. The business parameter in the segment refers to the business parameter of the target building in the corresponding time segment, such as occupancy rate, number of occupants, and / or hospital operation volume, which can be obtained by conventional means such as accessing the building business server. The meteorological parameter in the segment refers to the meteorological parameter of the region where the target building is located in the corresponding time segment, such as average temperature, average rainfall, and / or average sunshine duration, which can be obtained by conventional means such as accessing the meteorological service website. The power consumption equipment rated parameter can include, but is not limited to, the minimum rated power and maximum rated power of air conditioning equipment, which can be obtained by conventional means such as manual input.

[0066] S2. Construct a linear regression model for reflecting the linear relationship between the power consumption in the segment of the building air conditioning system in the plurality of unit time segments and the meteorological parameter in the segment and / or the business parameter in the segment.

[0067] In the step S2, in the linear regression model, the power consumption in the segment is the function dependent variable, and the meteorological parameter in the segment and / or the business parameter in the segment (i.e., the meteorological parameter in the segment, or the meteorological parameter in the segment and the business parameter in the segment) is the function independent variable. Specifically, when the target building is a hospital building, the building air conditioning system includes, but is not limited to, a purification area air conditioning system and a non-purification area air conditioning system, etc. Constructing a linear regression model for reflecting the linear relationship between the power consumption in the segment of the building air conditioning system in the plurality of unit time segments and the meteorological parameter in the segment and / or the business parameter in the segment includes, but is not limited to, constructing the following one-dimensional linear regression model for reflecting the linear relationship between the power consumption in the segment of the non-purification area air conditioning system in the plurality of unit time segments and the meteorological parameter in the segment by using the least squares method principle:

[0068]

[0069] In the formula, represents the power consumption in the segment of the non-purification area air conditioning system in the i-th unit time segment of the plurality of unit time segments, represents a positive integer, represents the temperature parameter extracted from the meteorological parameter in the segment and in the i-th unit time segment, and ​​These represent the model parameters in the univariate linear regression model. A bivariate linear regression model is constructed using a multiple linear regression model to reflect the linear relationship between the power consumption of the air conditioning system in the clean area within multiple time periods and the meteorological parameters and operational parameters within those periods:

[0070]

[0071] In the formula, This indicates that the air conditioning system in the clean area is in the first... Electricity consumption within a unit time period, This indicates that the data is extracted from the service parameters within the segment and is in the first... Surgical volume parameters per unit time period , and These represent the model parameters in the binary linear regression model. The aforementioned least squares method and multiple linear regression model are existing technologies. Since there is a significant relationship between temperature and air conditioning operation, the univariate linear regression model can be established based on the temperature parameter; similarly, since there is a strong correlation between surgical volume and air conditioning operation in the clean area, the binary linear regression model can be established based on both the temperature parameter and the surgical volume parameter. Specifically, the temperature parameter... It can be, but is not limited to, extracted from the meteorological parameters within the segment in the following manner: first, the location of the target building is extracted from the meteorological parameters within the segment in the [number]th [section]. The average temperature within a given time period is calculated; then the temperature parameters are obtained using the following formula. :

[0072]

[0073] In the formula, The location of the target building is indicated in the [number]th [year]. The average temperature within a given time period, expressed in degrees Celsius. Indicated in the first The total number of natural days in a given time period and having (For example, when the first) When the unit time period is February, The value is 29 in leap years or 28 in non-leap years; when the... When the unit time period is March, The value is 31).

[0074] S3. Based on the rated parameters of the electrical equipment of the building air conditioning system, determine the upper and lower limits of the power consumption of the building air conditioning system in the first segment of the multiple unit time periods.

[0075] In the step S3, since the electric equipment rated parameters can include the minimum rated power and the maximum rated power of the electric equipment, the first segment power consumption upper and lower limits can be determined based on these parameters. Specifically, when the target building is a hospital building and the building air conditioning system includes a purification area air conditioning system and a non-purification area air conditioning system, according to the electric equipment rated parameters of the building air conditioning system, the first segment power consumption upper and lower limits of the building air conditioning system in the plurality of unit time periods are determined, including but not limited to: for the non-purification area air conditioning system or the purification area air conditioning system, the minimum rated power and the maximum rated power of the corresponding electric equipment are extracted from the corresponding electric equipment rated parameters, and the first segment power consumption lower limit and the first segment power consumption upper limit of the corresponding system in the first unit time period are calculated according to the following formulas:

[0076]

[0077] In addition, considering that there can also be building non-air conditioning systems such as electric systems for supplying domestic hot water in the target building, in order to further accurately and finely divide the energy consumption results, preferably, the method further includes but is not limited to: first obtaining the electric equipment rated parameters of the building non-air conditioning systems in the target building; then according to the electric equipment rated parameters of the building non-air conditioning systems, determining the second segment power consumption upper and lower limits of the building non-air conditioning systems in the plurality of unit time periods (the specific determination process can be referred to the foregoing non-purification area air conditioning system or purification area air conditioning system, which is not described here again).

[0078] S4. The segment total power consumption, the segment service parameters, the segment meteorological parameters, and the first segment power consumption upper and lower limits are applied to optimize the model parameters of the linear regression model based on an optimization algorithm, to obtain the model parameters and realize a multi-objective optimal optimization search result, wherein the multi-objective optimization is to minimize the total penalty coefficient and maximize the fitting degree of the model input and the model output of the linear regression model. The total penalty coefficient may but is not limited to represent as follows:

[0079]

[0080] wherein,​​​​​​​​ a total number of time periods representing the plurality of unit time periods, a positive integer less than or equal to , a first intra-period power consumption in the th unit time period of the plurality of unit time periods according to the building air conditioning system, a first out-of-bound penalty coefficient determined according to a position relationship between the first intra-period power consumption upper and lower limits and a first out-of-bound penalty preset rule, a remaining power consumption in the th unit time period of the target building, a third out-of-bound penalty coefficient determined according to a position relationship between the zero value and a third out-of-bound penalty preset rule, a total intra-period power consumption in the th unit time period of the target building.

[0081] In the step S4, the model parameters of the linear regression model specifically include but are not limited to the model parameters and in the unary linear regression model, and / or the model parameters , and in the binary linear regression model. Specifically, the model input item is the air temperature parameter in the unary linear regression model and / or the air temperature parameter and the operation amount parameter in the binary linear regression model, and the model output item is the intra-period power consumption in the unary linear regression model and the intra-period power consumption in the binary linear regression model. Therefore, specifically, for the unary linear regression model, the fitting degree of the corresponding model input item and the model output item can specifically be but is not limited to measured by using the correlation coefficient of the intra-period power consumption and the air temperature parameter in the plurality of unit time periods, for example, the Pearson correlation coefficient represented by the following formula

[0082]

[0083] In the formula, the intra-period power consumption is represented by , the air temperature parameter is represented by , the covariance of the two variables (i.e., the intra-period power consumption and the air temperature parameter) in the plurality of unit time periods is represented by , the standard deviation of the intra-period power consumption in the plurality of unit time periods is represented by , and the standard deviation of the air temperature parameter in the plurality of unit time periods is represented by ​This represents the standard deviation of the temperature parameter over multiple time units. The higher the correlation coefficient between the electricity consumption within a given period and the temperature parameter over these multiple time units, the higher the fit; conversely, the lower the correlation coefficient, the lower the fit. For the binary linear regression model, the fit between the corresponding model input and output terms can be measured, but is not limited to, by the correlation coefficient between the electricity consumption within a given period and the temperature and surgical volume parameters over these multiple time units (the specific calculation formula is the same as the Pearson correlation coefficient calculation formula mentioned above, and will not be repeated here). That is, the higher their correlation coefficient over these multiple time units, the higher the fit; conversely, the lower the correlation coefficient, the lower the fit.

[0084] In step S4, the total penalty coefficient In the specific calculation process, the first boundary violation penalty preset rule is designed in advance based on the optimization strategy; generally, the first boundary violation penalty preset rule includes the following: if the building air conditioning system is in the first... Electricity consumption per unit time period Smaller than the building air conditioning system in the first The larger the difference between the first segment's lower limit of power consumption and the lower limit of power consumption within a unit time period, the larger the first out-of-bounds penalty coefficient; if the building air conditioning system in the first segment's lower limit of power consumption... Electricity consumption per unit time period Greater than or equal to the lower limit of the first internal power consumption and less than or equal to the building air conditioning system in the first... If the building air conditioning system has an upper limit on the power consumption of the first segment within a unit time period, then the first over-limit penalty coefficient is equal to zero; Electricity consumption per unit time period The greater the difference between the first segment's power consumption limit and the first segment's power consumption limit, the larger the first out-of-bounds penalty coefficient. The third out-of-bounds penalty preset rule is also pre-designed based on the optimization strategy; generally, the third out-of-bounds penalty preset rule includes the following: if the target building is in the first segment's power consumption limit... Remaining power consumption per unit time period The larger the value is less than zero and the greater the difference from zero, the larger the third boundary violation penalty coefficient; and if the target building is in the third boundary violation penalty coefficient... Remaining power consumption per unit time period If the value is greater than or equal to zero, then the third boundary violation penalty coefficient is equal to zero. Furthermore, when the target building is a hospital building and the building's air conditioning system includes a clean area air conditioning system and a non-clean area air conditioning system, the first boundary violation penalty preset rule and the first boundary violation penalty coefficient can be further refined for the clean area air conditioning system and the non-clean area air conditioning system, respectively.

[0085] In step S4, specifically, the optimization algorithm may include, but is not limited to, particle swarm optimization, gray wolf optimization, bat optimization, eagle optimization, vulture optimization, or genetic optimization, etc.; these algorithms are all existing algorithms, and the specific optimization process can be derived conventionally based on existing algorithms. Taking the particle swarm optimization algorithm as an example, it may include, but is not limited to, the following operations (A) to (D).

[0086] (A) Initialize the population: The population size is designed as follows: Each individual in the population represents a set of model parameters to be selected (i.e., specifically containing the model parameters in the univariate linear regression model). and And / or, the model parameters in the binary linear regression model , and ), and randomly generate initialization The model parameter set is configured with the following optimization parameters: number of iterations: 200; inertia weight range: 0.9→0.4; acceleration constant: c1=2.0, c2=2.0; speed limit ratio: 0.2.

[0087] (B) Fitness calculation: For each individual in the population, the fitness is calculated based on the fitness of the model input and output terms of the linear regression model and the total penalty coefficient, according to the corresponding model parameter set.

[0088] (C) Population update: Determine the optimal position of an individual and the global optimal position based on fitness, and update the position of each individual in the population based on these positions, the inertia weight range, the acceleration constant and the velocity limit ratio.

[0089] (D) Iterative optimization: Update particle velocity and position, retaining individual optimal and global optimal solutions; Termination condition: Reaching the maximum number of iterations (e.g., 200 times) or fitness threshold.

[0090] In step S4, in order to further refine and improve the energy consumption breakdown results, preferably, the total penalty coefficient is... Replace with the following formula:

[0091]

[0092] In the formula, This represents the total number of time periods of the multiple unit time periods. Indicates less than or equal to positive integers, This indicates that, according to the building air conditioning system, in the plurality of unit time periods, the first... Electricity consumption per unit time period The first boundary penalty coefficient is determined by the positional relationship between the upper and lower limits of the first segment's internal power consumption and the first boundary penalty preset rule. This indicates that, according to the building's non-air conditioning system, in the [number]th [year]... Electricity consumption per unit time period (It may be, but is not limited to, an estimated value obtained from a prediction model based on historical experience / time series data) and the positional relationship between the upper and lower limits of the second segment's internal power consumption and the second boundary violation penalty coefficient determined by the second boundary violation penalty preset rule. Indicates that according to the target building in the first Remaining power consumption per unit time period The third boundary penalty coefficient is determined by the positional relationship with the zero value and the preset rules for the third boundary penalty. Indicates that the target building is in the first The total power consumption within a unit time period. The second boundary violation penalty preset rule is also designed in advance based on the optimization strategy; generally, the second boundary violation penalty preset rule includes the following: if the building's non-air conditioning system in the first unit time period... Electricity consumption per unit time period Smaller than the building's non-air conditioning system in the first The larger the difference between the lower limit of the second segment's internal power consumption and the lower limit of the second segment's internal power consumption, the larger the second boundary violation penalty coefficient; if the building's non-air conditioning system in the second segment's internal power consumption lower limit... Electricity consumption per unit time period Greater than or equal to the lower limit of the second internal power consumption and less than or equal to the building's non-air conditioning system in the first... If the upper limit of the power consumption in the second segment of a unit time period is reached, then the second over-limit penalty coefficient is equal to zero; if the building's non-air conditioning system is in the second segment of the unit time period... Electricity consumption per unit time period The greater the difference between the power consumption limit of the second segment and the power consumption limit of the second segment, the greater the second over-limit penalty coefficient.

[0093] S5. Substitute the optimized search results into the linear regression model, and for each of the multiple unit time periods, calculate the power consumption of the building air conditioning system in the corresponding time period based on the corresponding meteorological parameters and business parameters within the segment using the linear regression model.

[0094] In step S5, the power consumption of the building air conditioning system within each unit time period is the energy consumption breakdown result of the building air conditioning system.

[0095] Thus, based on the building air conditioning system energy consumption splitting method described in the foregoing steps S1-S5, a new building air conditioning system energy consumption splitting scheme with low granularity requirement for original energy consumption data and simple and easy implementation is provided, that is, first, the total power consumption in a segment, the segment business parameter and the segment meteorological parameter of the target building in multiple unit time periods are obtained, and the rated parameters of the power consumption equipment of the building air conditioning system are obtained, then a linear regression model reflecting the linear relationship between the power consumption in a segment and the segment meteorological parameter / and the segment business parameter of the building air conditioning system is constructed, and the upper and lower limits of the power consumption in a segment of the building air conditioning system are determined, and then the total power consumption in a segment, the segment business parameter, the segment meteorological parameter and the upper and lower limits of the power consumption in a segment are applied, the model parameters of the linear regression model are optimized based on the optimization algorithm, the model parameters are obtained and used to obtain the optimal search result of minimizing the total penalty coefficient / and maximizing the fitting degree of the model input and the model output of the linear regression model, and finally the search result is substituted into the linear regression model, and the power consumption in a segment of the building air conditioning system in each time period is calculated, so that the energy consumption analysis of traditional public buildings lacking basic sub-metering data can be performed, and the energy consumption of the building air conditioning system with large energy-saving space can be quickly identified, which provides a data basis for subsequent energy-saving and carbon-reducing work, and facilitates actual application and promotion.

[0096] As shown in Figure 2 The second aspect of the present embodiment provides a virtual device for implementing the building air conditioning system energy consumption splitting method of the first aspect, comprising a multi-parameter acquisition unit, a linear model construction unit, a power consumption range determination unit, a model parameter optimization unit and an optimal parameter application unit.

[0097] The multi-parameter acquisition unit is configured to acquire the total power consumption in a segment and the segment business parameter of the target building in multiple unit time periods, and acquire the segment meteorological parameter of the region where the target building is located in multiple unit time periods, and further acquire the rated parameters of the power consumption equipment of the building air conditioning system in the target building.

[0098] The linear model construction unit is in communication connection with the multi-parameter acquisition unit and is configured to construct a linear regression model reflecting the linear relationship between the power consumption in a segment and the segment meteorological parameter / and the segment business parameter of the building air conditioning system in multiple unit time periods.

[0099] The power consumption range determination unit is in communication connection with the multi-parameter acquisition unit and is configured to determine the upper and lower limits of the power consumption in a first segment of the building air conditioning system in multiple unit time periods according to the rated parameters of the power consumption equipment of the building air conditioning system.

[0100] The model parameter optimization unit is communicatively connected to the multi-parameter acquisition unit, the linear model construction unit, and the power consumption range determination unit. It is used to optimize the model parameters of the linear regression model based on the total power consumption within the segment, the business parameters within the segment, the meteorological parameters within the segment, and the upper and lower limits of power consumption within the first segment, using an optimization algorithm to obtain model parameters that achieve the optimal search result for multi-objective optimization. Here, multi-objective optimization refers to minimizing the total penalty coefficient and maximizing the fit between the model input and output terms of the linear regression model. The total penalty coefficient... It is expressed as follows:

[0101]

[0102] In the formula, This represents the total number of time periods across multiple time units. Indicates less than or equal to positive integers, This indicates that, according to the building's air conditioning system, in the [number]th [year]... Electricity consumption per unit time period The positional relationship between the upper and lower limits of the first segment's internal power consumption and the first boundary penalty coefficient determined by the first boundary penalty preset rule. Indicates that according to the target building in the first Remaining power consumption per unit time period The third boundary penalty coefficient is determined by the positional relationship with the zero value and the preset rules for the third boundary penalty. Indicates the target building is in the Total power consumption within a unit time period;

[0103] The optimal parameter application unit is communicatively connected to the model parameter optimization unit and the multi-parameter acquisition unit, respectively. It is used to substitute the optimal search results into the linear regression model, and for each unit time period, according to the corresponding meteorological parameters and business parameters within the segment, apply the linear regression model to calculate the power consumption of the building air conditioning system within the corresponding time period.

[0104] The working process, working details and technical effects of the aforementioned device provided in the second aspect of this embodiment can be found in the energy consumption decomposition method of building air conditioning system described in the first aspect, and will not be repeated here.

[0105] like Figure 3As shown, the third aspect of the embodiment provides a computer device for performing the building air conditioning system energy consumption splitting method according to the first aspect, which comprises a memory, a processor and a transceiver connected in sequence, wherein the memory is used for storing a computer program, the transceiver is used for transmitting and receiving messages, and the processor is used for reading the computer program and performing the building air conditioning system energy consumption splitting method according to the first aspect. Specifically, the memory can include, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a flash memory, a first input first output (FIFO) memory and / or a first input last output (FILO) memory, etc.; and the processor can be, but is not limited to, a microprocessor of STM32F105 series. In addition, the computer device can further include, but is not limited to, a power module, a display screen and other necessary components.

[0106] The working process, working details and technical effects of the aforementioned computer device provided by the third aspect of the embodiment can be referred to the building air conditioning system energy consumption splitting method according to the first aspect, which will not be described here again.

[0107] The fourth aspect of the embodiment provides a computer readable storage medium storing instructions of the building air conditioning system energy consumption splitting method according to the first aspect, i.e., the computer readable storage medium stores instructions, and when the instructions are run on a computer, the building air conditioning system energy consumption splitting method according to the first aspect is performed. The computer readable storage medium refers to a carrier for storing data, which can include, but is not limited to, floppy disks, optical disks, hard disks, flash memories, USB flash drives and / or memory sticks, etc. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices.

[0108] The working process, working details and technical effects of the aforementioned computer readable storage medium provided by the fourth aspect of the embodiment can be referred to the building air conditioning system energy consumption splitting method according to the first aspect, which will not be described here again.

[0109] The fifth aspect of the embodiment provides a computer program product comprising a computer program or instructions, which, when executed by a computer, implement the building air conditioning system energy consumption splitting method according to the first aspect. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices.

[0110] Finally, it should be noted that the above description is only the preferred embodiment of the present application, and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for decomposing energy consumption in a building air conditioning system, characterized in that, include: The system obtains the total power consumption and business parameters of the target building within multiple time periods, as well as the meteorological parameters of the area where the target building is located within multiple time periods, and the rated parameters of the electrical equipment of the building's air conditioning system within the target building. A linear regression model is constructed to reflect the linear relationship between the power consumption of a building air conditioning system within a segment and the parameters within the segment over multiple time periods. The parameters within the segment refer to meteorological parameters within the segment or a combination of meteorological parameters and operational parameters within the segment. Based on the rated parameters of the electrical equipment in the building air conditioning system, determine the upper and lower limits of the power consumption of the building air conditioning system in the first segment of multiple time periods; Using the total power consumption within the segment, segment business parameters, segment meteorological parameters, and the upper and lower limits of power consumption in the first segment, the model parameters of the linear regression model are optimized based on an optimization algorithm. The resulting model parameters are used to achieve the optimal search results for multiple objectives. The optimal multi-objective objective refers to minimizing the total penalty coefficient, or minimizing the total penalty coefficient while maximizing the fit between the model input and output terms of the linear regression model. The total penalty coefficient... It is expressed as follows: In the formula, This represents the total number of time periods across multiple time units. Indicates less than or equal to positive integers, This indicates that, according to the building's air conditioning system, in the [number]th [year]... Electricity consumption per unit time period The positional relationship between the upper and lower limits of the first segment's internal power consumption and the first boundary penalty coefficient determined by the first boundary penalty preset rule. Indicates that according to the target building in the first Remaining power consumption per unit time period The third boundary penalty coefficient is determined by the positional relationship with the zero value and the preset rules for the third boundary penalty. Indicates the target building is in the Total power consumption within a unit time period; The optimized search results are substituted into the linear regression model, and for each unit time period, the linear regression model is applied to calculate the power consumption of the building air conditioning system in the corresponding time period based on the corresponding intra-segment parameters.

2. The method for energy consumption breakdown of a building air conditioning system according to claim 1, characterized in that, When the target building is a hospital building, the building's air conditioning system includes air conditioning systems for clean areas and air conditioning systems for non-clean areas. A linear regression model is constructed to reflect the linear relationship between the building's air conditioning system's power consumption and parameters over multiple time periods, including: The following univariate linear regression model is constructed using the least squares method to reflect the linear relationship between the power consumption of the air conditioning system in a non-clean area and the meteorological parameters within the segment over multiple time periods: In the formula, Indicates that the air conditioning system in the non-clean area is in the first Electricity consumption within a unit time period, This indicates that the parameters extracted from the meteorological parameters within the segment and in the first... Temperature parameters for a given time period. and These represent the model parameters in the univariate linear regression model; A bivariate linear regression model is constructed using a multiple linear regression model to reflect the linear relationship between the power consumption of the air conditioning system in the clean area and the meteorological parameters and operational parameters within the area over multiple time periods. In the formula, Indicates the air conditioning system in the clean area in the first Electricity consumption within a unit time period, This indicates that the data extracted from the service parameters within the segment and that is in the [missing information] section. Surgical volume parameters per unit time period , and These represent the model parameters in the binary linear regression model.

3. The method for energy consumption breakdown of a building air conditioning system according to claim 2, characterized in that, Temperature parameters The meteorological parameters within the segment were extracted as follows: The location of the target building was extracted from the meteorological parameters within the segment. The average temperature within a given time period; The temperature parameters are calculated using the following formula. : In the formula, Indicates the location of the target building in the [number]th [location]. The average temperature within a given time period, expressed in degrees Celsius. Indicates the first The total number of natural days in a given time period and having .

4. The method for energy consumption breakdown of a building air conditioning system according to claim 1, characterized in that, When the target building is a hospital building and its air conditioning system includes both clean area and non-clean area air conditioning systems, the upper and lower limits of the building's air conditioning system's power consumption in the first segment of multiple time periods are determined based on the rated parameters of the electrical equipment. These limits include: For air conditioning systems in non-clean areas or clean areas, extract the minimum and maximum rated power of the equipment from the rated parameters of the corresponding electrical equipment, and calculate the corresponding system's power rating in the following formula. Lower limit of power consumption in the first segment of each unit time period and the first segment's internal power consumption limit : In the formula, This indicates the minimum rated power, and the unit is kilowatt. This indicates the maximum rated power, and the unit is kilowatts. Indicates the first The total number of natural days in a given time period and having .

5. The method for energy consumption breakdown of a building air conditioning system according to claim 1, characterized in that, The method further includes: Obtain the rated parameters of electrical equipment in the non-air conditioning systems of the target building; Based on the rated parameters of the electrical equipment in the building's non-air-conditioned system, determine the upper and lower limits of the building's non-air-conditioned system's power consumption in the second segment of multiple time periods; Total penalty coefficient Replace with the following formula: In the formula, This represents the total number of time periods across multiple time units. Indicates less than or equal to positive integers, This indicates that, according to the building's air conditioning system, in the [number]th [year]... Electricity consumption per unit time period The positional relationship between the upper and lower limits of the first segment's internal power consumption and the first boundary penalty coefficient determined by the first boundary penalty preset rule. This indicates that, according to the building's non-air conditioning system, in the [number]th [year]... Electricity consumption per unit time period The positional relationship between the upper and lower limits of the second segment's internal power consumption and the second boundary penalty coefficient determined by the second boundary penalty preset rule. Indicates that according to the target building in the first Remaining power consumption per unit time period The third boundary penalty coefficient is determined by the positional relationship with the zero value and the preset rules for the third boundary penalty. Indicates the target building is in the Total power consumption within a given time period.

6. The method for energy consumption breakdown of a building air conditioning system according to claim 1, characterized in that, The optimization algorithm used is Particle Swarm Optimization, Gray Wolf Optimization, Bat Optimization, Skyhawk Optimization, Vulture Optimization, or Genetic Optimization.

7. A device for splitting energy consumption in a building air conditioning system, characterized in that, It includes a multi-parameter acquisition unit, a linear model construction unit, a power consumption range determination unit, a model parameter optimization unit, and an optimal parameter application unit; The multi-parameter acquisition unit is used to acquire the total power consumption and business parameters of the target building within multiple unit time periods, as well as the meteorological parameters of the area where the target building is located within multiple unit time periods, and the rated parameters of the electrical equipment of the building air conditioning system in the target building. The linear model construction unit is communicatively connected to the multi-parameter acquisition unit and is used to construct a linear regression model that reflects the linear relationship between the power consumption of the building air conditioning system within a segment and the parameters within the segment in multiple unit time periods. The parameters within the segment refer to meteorological parameters within the segment or meteorological parameters within the segment and business parameters within the segment. The power consumption range determination unit is communicatively connected to the multi-parameter acquisition unit and is used to determine the upper and lower limits of power consumption of the building air conditioning system in the first segment of multiple unit time periods based on the rated parameters of the electrical equipment of the building air conditioning system. The model parameter optimization unit is communicatively connected to the multi-parameter acquisition unit, the linear model construction unit, and the power consumption range determination unit. It is used to optimize the model parameters of the linear regression model based on the total power consumption within the segment, the business parameters within the segment, the meteorological parameters within the segment, and the upper and lower limits of power consumption within the first segment, using an optimization algorithm. The resulting model parameters are used to achieve the optimal search result for multi-objective optimization. Multi-objective optimization refers to minimizing the total penalty coefficient or minimizing the total penalty coefficient while maximizing the fit between the model input and output terms of the linear regression model. The total penalty coefficient... It is expressed as follows: In the formula, This represents the total number of time periods across multiple time units. Indicates less than or equal to positive integers, This indicates that, according to the building's air conditioning system, in the [number]th [year]... Electricity consumption per unit time period The positional relationship between the upper and lower limits of the first segment's internal power consumption and the first boundary penalty coefficient determined by the first boundary penalty preset rule. Indicates that according to the target building in the first Remaining power consumption per unit time period The third boundary penalty coefficient is determined by the positional relationship with the zero value and the preset rules for the third boundary penalty. Indicates the target building is in the Total power consumption within a unit time period; The optimal parameter application unit is communicatively connected to the model parameter optimization unit and the multi-parameter acquisition unit, respectively. It is used to substitute the optimal search result into the linear regression model, and for each unit time period, according to the corresponding intra-segment parameters, apply the linear regression model to calculate the intra-segment power consumption of the building air conditioning system in the corresponding time period.

8. A computer device, characterized in that, The system includes a memory, a processor, and a transceiver connected in sequence for communication. The memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the energy consumption decomposition method for a building air conditioning system as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that... The computer-readable storage medium stores instructions that, when executed on a computer, perform the energy consumption splitting method for a building air conditioning system as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or the instructions are executed by the computer, they implement the energy consumption breakdown method for building air conditioning systems as described in any one of claims 1 to 6.

Images