A building carbon reduction method and device based on multi-objective optimization

Abstract

The present invention discloses a method and device for reducing carbon emissions in buildings based on multi-objective optimization. The method comprises: obtaining an environmental parameter range for adjusting the carbon emissions and personnel comfort of a target building area; obtaining a carbon emission prediction model and a personnel comfort prediction model associated with each target partition of the target building area; wherein the carbon emission prediction model and the personnel comfort prediction model are respectively used to predict the carbon emissions and personnel comfort of the target partition based on environmental parameters within the environmental parameter range; setting the carbon emissions and personnel comfort of the target building area as optimization targets; using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, calculating the optimal solution of the optimization target within the environmental parameter range, so that each target partition operates under the optimal solution; wherein the optimal solution includes the optimal environmental parameters of each target partition.

Description

Technical Field

[0001] The present invention relates to the technical field of building energy conservation and carbon reduction, and in particular to a building carbon reduction method and device based on multi-objective optimization. Background Art

[0002] The construction industry accounts for about one-third of global carbon emissions, and excessive carbon emissions will cause a series of ecological problems. Traditional building carbon reduction solutions take the building as a whole as a consideration, which is rough and has insignificant carbon reduction effects. In addition, traditional carbon reduction solutions only involve a small number of optimization targets and cannot achieve linkage control and refined management of equipment and environment.

[0003] There is currently no effective solution to a series of problems with existing carbon reduction solutions. Summary of the invention

[0004] The purpose of the present invention is to provide a building carbon reduction method and device based on multi-objective optimization, which can solve the problems of poor refinement of existing carbon reduction schemes and unsatisfactory carbon reduction effects.

[0005] According to one aspect of the present invention, a building carbon reduction method based on multi-objective optimization comprises:

[0006] Obtain the environmental parameter range for adjusting the carbon emissions and occupant comfort of the target building area;

[0007] Obtaining a carbon emission prediction model and a personnel comfort prediction model associated with each target partition of the target building area; wherein the carbon emission prediction model and the personnel comfort prediction model are respectively used to predict the carbon emission and personnel comfort of the target partition based on the environmental parameters within the environmental parameter range;

[0008] Setting the carbon emissions and occupant comfort of the target building area as optimization targets;

[0009] By using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, the optimal solution of the optimization objective is calculated within the range of the environmental parameters so that each target partition can operate under the optimal solution; wherein the optimal solution includes the optimal environmental parameters of each target partition.

[0010] Optionally, before acquiring the carbon emission prediction model and the occupant comfort prediction model associated with each target partition of the target building area, the method further includes:

[0011] Constructing a plurality of target environmental parameter samples; wherein the target environmental parameter samples are environmental parameters within the environmental parameter range that meet preset constraint conditions;

[0012] Estimate the carbon emissions and personnel comfort of the target zone under each target environmental parameter sample;

[0013] Determine each target environmental parameter sample and the corresponding carbon emission as a carbon emission sample, count all carbon emission samples as a carbon emission sample set, and train the first preset model based on the carbon emission sample set to obtain the carbon emission prediction model;

[0014] Each target environmental parameter sample and the corresponding personnel comfort are determined as a personnel comfort sample, all personnel comfort samples are counted as a personnel comfort sample set, and the second preset model is trained based on the personnel comfort sample set to obtain the personnel comfort prediction model.

[0015] Optionally, estimating the carbon emissions and personnel comfort of the target partition under each target environmental parameter sample includes:

[0016] Applying the target environmental parameter sample to a pre-constructed target partition simulation model; wherein the target partition simulation model is located within a pre-constructed target building area simulation model, and the accuracy of predicting the carbon emissions of the target building area based on the target building area simulation model is greater than a preset accuracy threshold;

[0017] Calculating the carbon emissions of the target partition simulation model within a first time range as the carbon emissions of the target partition under the target environmental parameter sample;

[0018] The comfort level of personnel in the target partition simulation model within a first time range is calculated as the comfort level of personnel in the target partition under the target environmental parameter sample.

[0019] Optionally, the multi-objective optimization algorithm is used to calculate the optimal solution of the optimization objective within the environmental parameter range based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, so that each target partition operates under the optimal solution, including:

[0020] The environmental parameter range and the carbon emission prediction model and the personnel comfort prediction model associated with each target partition are used as inputs of the multi-objective optimization algorithm, so that the multi-objective optimization algorithm outputs a Pareto optimal solution set and a Pareto frontier of the optimization target; wherein the Pareto optimal solution set includes multiple target solutions, each target solution includes the environmental parameters of each target partition; the Pareto front includes target frontiers corresponding to each target solution, each target front includes the carbon emission and personnel comfort of each target partition;

[0021] Obtaining an ideal optimization plan; wherein the ideal plan includes the ideal carbon emissions and ideal personnel comfort of the target building area;

[0022] Calculating the Euclidean distance between each target front and the ideal optimization solution;

[0023] Selecting a target solution corresponding to a target frontier with a maximum Euclidean distance from the Pareto optimal solution set;

[0024] The screened target solution is determined as the optimal solution.

[0025] Optionally, calculating the Euclidean distance between each target frontier and the ideal optimization solution includes:

[0026] Calculating the carbon emissions of the target building area under the target solution;

[0027] Calculating the comfort level of personnel in the target building area under the target solution;

[0028] Based on the carbon emissions and occupant comfort of the target building area under the target solution and the ideal carbon emissions and ideal occupant comfort of the target building area, the Euclidean distance between the target frontier and the ideal optimization solution is calculated.

[0029] Optionally, the calculating the carbon emissions of the target building area under the target solution includes:

[0030] Calculate the sum of all carbon emissions in the target frontier as the carbon emissions of the target building area under the target solution;

[0031] The calculating the comfort level of personnel in the target building area under the target solution comprises:

[0032] The average of the comfort levels of all personnel in the target front is calculated as the comfort level of personnel in the target building area under the target solution.

[0033] Optionally, the method further comprises:

[0034] The Latin hypercube sampling algorithm is used to sample the population density within the second time range of each target partition to obtain the population density variable parameter value of each target partition;

[0035] Determine an optimal population density value from each optimal environmental parameter of the optimal solution, and modify the corresponding optimal population density value based on each population density variable parameter value to obtain an updated optimal population density value for each target partition;

[0036] Replacing the population density range in the environmental parameter range with all the obtained updated optimal population density values ​​to obtain a new environmental parameter range;

[0037] Using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, a new optimal solution of the optimization objective is calculated within a new environmental parameter range, so that each target partition operates under the new optimal solution;

[0038] The new optimal solution includes new optimal environmental parameters of each target partition, and each new optimal environmental parameter includes an updated personnel density value of the corresponding target partition.

[0039] Optionally, the method further comprises:

[0040] Get multiple preset weather temperature ranges;

[0041] The step of obtaining the carbon emission prediction model and the occupant comfort prediction model associated with each target partition of the target building area includes:

[0042] Obtain the carbon emission prediction model and personnel comfort prediction model associated with each target zone under each weather temperature range;

[0043] The method of using a multi-objective optimization algorithm and calculating the optimal solution of the optimization objective within the range of the environmental parameters based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, so that each target partition operates under the optimal solution, includes:

[0044] By utilizing a multi-objective optimization algorithm and based on the carbon emission prediction model and personnel comfort prediction model associated with each target partition in each weather temperature range, the optimal solution of the optimization objective in each weather temperature range is calculated within the range of environmental parameters, so that each target partition can operate based on the optimal solution in each weather temperature range.

[0045] Optionally, the environmental parameter range includes: a refrigeration equipment temperature range, a natural ventilation temperature range and a personnel density range; wherein the refrigeration equipment temperature range represents the operating temperature range of the refrigeration equipment, and the natural ventilation temperature range represents the temperature range allowed for ventilation of the target partition; the personnel density range represents the range of personnel density allowed for the target partition, and the environmental parameters include the refrigeration equipment temperature value, the natural ventilation temperature value and the personnel density value.

[0046] In order to achieve the above object, the present invention also provides a building carbon reduction device based on multi-objective optimization, the device comprising:

[0047] A first acquisition module is used to acquire the environmental parameter range for adjusting the carbon emission and occupant comfort of the target building area;

[0048] A second acquisition module is used to acquire a carbon emission prediction model and a personnel comfort prediction model associated with each target partition of the target building area; wherein the carbon emission prediction model and the personnel comfort prediction model are used to predict the carbon emission and personnel comfort of the target partition based on the environmental parameters within the environmental parameter range, respectively;

[0049] A setting module, used to set the carbon emissions and occupant comfort of the target building area as optimization targets;

[0050] A calculation module is used to calculate the optimal solution of the optimization objective within the range of the environmental parameters by using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, so that each target partition can operate under the optimal solution; wherein the optimal solution includes the optimal environmental parameters of each target partition.

[0051] In order to achieve the above-mentioned purpose, the present invention further provides a computer device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor is used to implement the steps of the building carbon reduction method based on multi-objective optimization introduced above when executing the computer program.

[0052] In order to achieve the above objectives, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the building carbon reduction method based on multi-objective optimization introduced above are implemented.

[0053] The building carbon reduction method based on multi-objective optimization provided by the present invention realizes refined building management by dividing the target building area into multiple sub-areas. The optimization is carried out with the carbon emissions and personnel comfort of the entire target building area as the target, which is actually decomposed into the carbon emissions and personnel comfort of each partition as the optimization target, and the optimal solution containing the optimal environmental parameters of each partition is obtained, which solves the problems of insufficient refinement of current building carbon reduction optimization and small number of optimization targets. In addition, when each partition is operated under the optimal solution, the target building area can reduce carbon emissions to the maximum extent while ensuring the comfort of personnel, thereby improving the rationality of the carbon reduction effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0055] Figure 1A schematic diagram of a process flow of a building carbon reduction method based on multi-objective optimization provided in Example 1;

[0056] Figure 2 A schematic diagram of the target building area division provided in Example 1;

[0057] Figure 3 A schematic diagram of the prediction accuracy of each prediction model provided in Example 1;

[0058] Figure 4 A block diagram of a building carbon reduction device based on multi-objective optimization provided in Example 2;

[0059] Figure 5 A block diagram of a computer device suitable for implementing a building carbon reduction method based on multi-objective optimization provided in Example 3. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0061] Embodiment 1

[0062] The embodiment of the present invention provides a building carbon reduction method based on multi-objective optimization, such as Figure 1 As shown, the method includes steps S1 to S4, wherein:

[0063] Step S1, obtaining the environmental parameter range for adjusting the carbon emissions and occupant comfort of the target building area.

[0064] The target building area may be the entire building, or one or more consecutive floors of the building, or a certain area on a certain floor of the building, which is not limited in this embodiment.

[0065] In this embodiment, the target building area is divided into a plurality of zones, wherein some zones need to be treated for carbon reduction, and each zone of these zones is referred to as a target zone; or, all zones need to be treated for carbon reduction, and each zone is referred to as a target zone.

[0066] The environmental parameter range includes: refrigeration equipment temperature range, natural ventilation temperature range and personnel density range; among them, the refrigeration equipment temperature range represents the operating temperature range of the refrigeration equipment, the natural ventilation temperature range represents the temperature range allowed for ventilation of the target partition; the personnel density range represents the range of personnel density carried by the target partition. There can be multiple environmental parameters within the environmental parameter range, and different environmental parameters have different values, among which the environmental parameters include the refrigeration equipment temperature value, the natural ventilation temperature value and the personnel density value.

[0067] For example, the temperature range of the refrigeration equipment is 22-28℃, the natural ventilation temperature range is 20-28℃, and the population density range is 0.1-0.3 person / square meter. One environmental parameter can be a refrigeration equipment temperature value of 28℃, a natural ventilation temperature value of 20℃, and a population density value of 0.1 person / square meter. Another environmental parameter can be a refrigeration equipment temperature value of 25℃, a natural ventilation temperature value of 20℃, and a population density value of 0.3 person / square meter.

[0068] Step S2, obtaining the carbon emission prediction model and the personnel comfort prediction model associated with each target partition of the target building area; wherein the carbon emission prediction model is used to predict the carbon emissions of the target partition based on the environmental parameters within the environmental parameter range; the personnel comfort prediction model is used to predict the personnel comfort of the target partition based on the environmental parameters within the environmental parameter range.

[0069] The number of carbon emission prediction models and occupant comfort prediction models associated with each target zone is the same.

[0070] When zoning the target building area, it can be divided according to the coverage of the electric well box. For example, the area within the coverage of one electric well box is divided into one target zone, and the area within the coverage of another electric well box is divided into another target zone.

[0071] Optionally, considering that different outside temperatures have an impact on building ventilation, the length of time carbon emission equipment is used in the building, etc., which ultimately affects the building's carbon emissions, this embodiment also takes into account the impact of weather temperature on building carbon emissions and personnel comfort. Specifically, this embodiment pre-divides the weather temperature into multiple weather temperature ranges, and different weather temperature ranges have different impacts on building carbon emissions and personnel comfort. When calculating the optimal solution for the building under each weather temperature range, steps S2 to S4 must be executed once, that is, the following description of steps S2 to S4 has been assumed to be executed under the limitation of a certain weather temperature range. Among them, the division of the weather temperature range can be divided according to the average daily temperature, or it can be divided according to the maximum daily temperature, and this embodiment does not limit this.

[0072] The method further includes: acquiring a plurality of preset weather temperature ranges.

[0073] Step S2 may be:

[0074] Obtain the carbon emission prediction model and the personnel comfort prediction model associated with each target partition in each weather temperature range. That is, for each weather temperature range, obtain the carbon emission prediction model and the personnel comfort prediction model associated with each target partition.

[0075] For example, taking the cooling season as an example, three weather temperature ranges are pre-set, namely 22-30℃, 30-35℃ and >35℃, and the target building area is divided into the west, east and south. Then, in the weather temperature range of 22-30℃, the carbon emission prediction model and personnel comfort prediction model associated with the west, the carbon emission prediction model and personnel comfort prediction model associated with the east, and the carbon emission prediction model and personnel comfort prediction model associated with the south are obtained; in the weather temperature range of 30-35℃, the carbon emission prediction model and personnel comfort prediction model associated with the west, the carbon emission prediction model and personnel comfort prediction model associated with the east, and the carbon emission prediction model and personnel comfort prediction model associated with the south are obtained; in the weather temperature range above 35℃, the carbon emission prediction model and personnel comfort prediction model associated with the west, the carbon emission prediction model and personnel comfort prediction model associated with the east, and the carbon emission prediction model and personnel comfort prediction model associated with the south are obtained. Among them, it is assumed that when the maximum temperature of the day is <22℃, the refrigeration equipment will not be turned on and the target building area will not need cooling throughout the day.

[0076] Optionally, before step S2, each carbon emission prediction model and each personnel comfort prediction model need to be trained. It should be noted that the training process of each carbon emission prediction model is similar, and the training process of each personnel comfort prediction model is also similar. This embodiment takes the training of a carbon emission prediction model and a personnel comfort prediction model as examples to elaborate on the model training process. The method also includes steps A1 to A4, wherein:

[0077] Step A1, constructing a plurality of target environmental parameter samples; wherein the target environmental parameter samples are environmental parameters within the environmental parameter range that meet preset constraint conditions;

[0078] Step A2, estimating the carbon emissions and personnel comfort of the target zone under each target environmental parameter sample;

[0079] Step A3, determining each target environmental parameter sample and the corresponding carbon emission as a carbon emission sample, counting all carbon emission samples as a carbon emission sample set, and training the first preset model based on the carbon emission sample set to obtain the carbon emission prediction model;

[0080] Step A4, determining each target environmental parameter sample and the corresponding personnel comfort as a personnel comfort sample, counting all personnel comfort samples as a personnel comfort sample set, and training the second preset model based on the personnel comfort sample set to obtain the personnel comfort prediction model.

[0081] The target environmental parameter samples include: refrigeration equipment temperature value, natural ventilation temperature value and human density value. Among them, each parameter in each target environmental parameter sample must meet the constraint conditions. The constraint conditions can be set according to actual needs, for example, the constraint condition is: the natural ventilation temperature value is less than or equal to the refrigeration equipment temperature value.

[0082] It should be noted that, for each weather temperature range, "estimating the carbon emissions and personnel comfort of the target partition under each target environmental parameter sample" can be: for each weather temperature range, estimating the carbon emissions and personnel comfort of the target partition under each target environmental parameter sample.

[0083] For example, if three weather temperature ranges are pre-set and the target building area includes three target partitions, a total of 18 prediction models need to be trained, of which 9 are carbon emission prediction models and 9 are occupant comfort prediction models.

[0084] Optionally, in this embodiment, a target building area simulation model is pre-established, and the target building area simulation model includes multiple target partition simulation models. By setting the outside weather temperature range of the target building area simulation model to a preset weather temperature range, and applying a certain target environmental parameter sample to a certain target partition simulation model of the target building area simulation model, the carbon emissions and personnel comfort of the target partition under a certain target environmental parameter sample can be obtained. Step A2 includes:

[0085] Applying the target environmental parameter sample to a pre-constructed target partition simulation model; wherein the target partition simulation model is located within a pre-constructed target building area simulation model, and the accuracy of predicting the carbon emissions of the target building area based on the target building area simulation model is greater than a preset accuracy threshold;

[0086] Calculating the carbon emissions of the target partition simulation model within a first time range as the carbon emissions of the target partition under the target environmental parameter sample;

[0087] The comfort level of personnel in the target partition simulation model within a first time range is calculated as the comfort level of personnel in the target partition under the target environmental parameter sample.

[0088] Before establishing a simulation model of the target building area, it is necessary to collect the required data. For example, obtain the hourly energy consumption data of the building during the cooling season, personnel distribution information, building floor plans, material information, equipment operation schedules, and hourly occupancy information of people in the building. Building energy consumption data mainly includes the hourly energy consumption of the cooling equipment terminal, such as chillers, air conditioners, etc. The hourly energy consumption of the air conditioner terminal is measured by a single partition meter on each floor. Due to meter tripping, failure, etc., the collected data is partially missing, and the collected data needs to be preprocessed as follows:

[0089]

[0090] CE elec =y l ×EF elec

[0091] Among them, t l is the time to be interpolated, t l-1 and t l+1 The time t l The moment before and the moment after y l-1 ,y l and l+1 Corresponding to time t l-1 ,t l and t l+1 Power consumption; EF elec is the carbon emission factor, CE elec It is the carbon emission corresponding to the electricity consumption.

[0092] A simulation model of the target building area is established based on the collected data. That is, a high-precision simulation model of the building is built based on the existing drawings and material information to simulate the carbon emissions and personnel comfort under the actual operation of the building. For example, a building model of the same scale can be built based on Revit software and CAD design drawings, with embedded building material information such as window-to-wall ratio, floor layout, etc., and exported to xml file format.

[0093] Verify the established simulation model of the target building area. First, import the constructed model into DB (DesignBuilder) in XML format, and then divide the area according to the coverage of the electric well. For example, Figure 2As shown in the figure, the target floor is divided into three areas: west, south and east. Further, the initial parameters are set, such as setting the initial air conditioning terminal setting temperature of the office area to 24°C, the corridor area setting temperature to 26°C, the cooling time to 8:00-20:00, and the partition personnel density to 0.2 (person / square meter). Through the above settings, the carbon emissions of the simulation model of the target building area are simulated and compared with the actual situation. When the error is large, the model carbon emissions are corrected by adjusting the indoor personnel, equipment schedule and refrigeration performance coefficient of the refrigeration equipment. When the accuracy of the carbon emissions of the target building area simulated by the simulation model of the target building area is greater than the preset accuracy threshold, it is considered that the simulation model of the target building area can accurately simulate the building carbon emissions in the real situation. For example, when the difference between the total carbon emissions in the simulated cooling season and the actual carbon emissions is less than the preset error value, and the monthly simulation value is highly consistent with the actual carbon emissions, it can be considered that the constructed model can accurately simulate the building carbon emissions in the real situation.

[0094] After the simulation model meets the requirements, the training set can be constructed. Among them, the environmental parameter range can be input into the JMP (John's Macintosh Program) experimental design software, and JMP generates multiple groups of representative environmental parameter samples, and then multiple target environmental parameter samples that meet the constraints are screened out from these environmental parameter samples. Further, each target environmental parameter sample is input into the value DB, and the weather temperature parameter is limited to a certain pre-set weather temperature range. The carbon emissions and personnel comfort of each target partition under each target environmental parameter sample are counted in DB. The target environmental parameter sample and carbon emissions are used as carbon emission samples, and the target environmental parameter sample and personnel comfort are used as personnel comfort samples, and then a carbon emission sample set containing multiple carbon emission samples and a personnel comfort sample set containing multiple personnel comfort samples are constructed.

[0095] This embodiment builds a high-precision three-dimensional simulation model of building operation and maintenance, which can efficiently obtain the building carbon emissions and indoor occupant comfort data of the target building area under various weather conditions and different operation and maintenance modes, solving the problem of insufficient data in traditional building carbon reduction optimization research, and can lay the model foundation for subsequent building layout transformation and related carbon emission simulation.

[0096] The first preset model and the second preset model can be the same model or different models. This embodiment does not limit this. It is sufficient as long as a carbon emission prediction model and a personnel comfort prediction model that meet the requirements can be trained based on the first preset model and the second preset model.

[0097] For example, the first preset model and the second preset model are both GWO-XGBoost models, wherein GWO (Grey Wolf Optimizer) is the grey wolf optimized algorithm, XGBoost (Extreme Gradient Boosting) is the extreme gradient boosting tree, and GWO-XGBoost is the extreme gradient boosting tree after grey wolf optimization.

[0098] For the carbon emission prediction model and personnel comfort prediction model trained based on the GWO-XGBoost model, under different weather temperature ranges, the hyperparameters of the carbon emission prediction model are different for different target partitions, and the hyperparameters of the personnel comfort prediction model are also different.

[0099] Combining the above examples, Figure 3 As shown in the figure, under the three weather temperature ranges of 22-30℃, 30-35℃ and >35℃, the GWO-XGBoost hybrid model performs well in carbon emission and comfort prediction in the three west, south and east regions, with prediction accuracies higher than 0.912. 2 Describes the degree of match between the model prediction results and the actual results, that is, the prediction accuracy. As mentioned above, three weather temperatures, three zones, and two prediction targets can be obtained by permutation and combination. The two hyperparameters n_estimator and learning rate in the GWO-XGBoost model are used to improve the prediction accuracy of the model. The optimal model parameters searched by the optimization algorithm are shown in Table 1. Among them, it can be seen from Table 1 that: in the same scenario, the hyperparameters of the carbon emission prediction model and the personnel comfort prediction model are different; in different scenarios, the hyperparameters of each carbon emission prediction model are different; and in different scenarios, the hyperparameters of each personnel comfort prediction model are also different.

[0100] Table 1 Hyperparameters of GWO-XGBoost model

[0101]

[0102]

[0103] Step S3, setting the carbon emissions and occupant comfort of the target building area as optimization targets.

[0104] The carbon emissions of the target building area are the sum of the carbon emissions of each target zone, and the occupant comfort of the target building area is the average of the occupant comfort of each target zone.

[0105] When multiple weather temperature ranges are set, step S3 includes: in each weather temperature range, setting the carbon emissions and occupant comfort of the target building area as optimization targets.

[0106] Step S4, using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, calculate the optimal solution of the optimization objective within the range of the environmental parameters, so that each target partition operates under the optimal solution; wherein the optimal solution includes the optimal environmental parameters of each target partition.

[0107] Based on the multi-objective optimization algorithm, multiple solutions can be calculated, each of which contains the environmental parameters of each target partition, and each solution corresponds to carbon emissions and personnel comfort. The carbon emissions of each target partition in each solution are predicted based on the carbon emissions prediction model, and the personnel comfort of each target partition in each solution is predicted based on the personnel comfort prediction model; and the carbon emissions and personnel comfort of the target building area under each solution are calculated. According to the actual application scenario, the ideal carbon emissions and ideal personnel comfort of the target building area are pre-established. By calculating the Euclidean distance between the carbon emissions and personnel comfort of the target building area under each solution and the ideal carbon emissions and ideal personnel comfort, the maximum Euclidean distance can be obtained, and the solution corresponding to the maximum Euclidean distance is determined as the optimal solution.

[0108] When multiple weather temperature ranges are preset, step S4 may be: using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition in each weather temperature range, the optimal solution of the optimization target in each weather temperature range is calculated within the environmental parameter range, so that each target partition operates based on the optimal solution in each weather temperature range. That is, for each weather temperature range, using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, the optimal solution of the optimization target is calculated within the environmental parameter range, so that each target partition operates under the optimal solution.

[0109] There are many existing multi-objective optimization algorithms. In this embodiment, a suitable multi-objective optimization algorithm can be selected according to actual needs. The following takes the NSGA-II optimization algorithm as an example to explain the specific steps of the optimization.

[0110] Optionally, step S4 includes:

[0111] The environmental parameter range and the carbon emission prediction model and the personnel comfort prediction model associated with each target partition are used as inputs of the multi-objective optimization algorithm, so that the multi-objective optimization algorithm outputs a Pareto optimal solution set and a Pareto frontier of the optimization target; wherein the Pareto optimal solution set includes multiple target solutions, each target solution includes the environmental parameters of each target partition; the Pareto front includes target frontiers corresponding to each target solution, each target front includes the carbon emission and personnel comfort of each target partition;

[0112] Obtaining an ideal optimization plan; wherein the ideal plan includes the ideal carbon emissions and ideal personnel comfort of the target building area;

[0113] Calculating the Euclidean distance between each target front and the ideal optimization solution;

[0114] Selecting a target solution corresponding to a target frontier with a maximum Euclidean distance from the Pareto optimal solution set;

[0115] The screened target solution is determined as the optimal solution.

[0116] Each target solution includes the environmental parameters of each target zone in the multiple target zones, and the environmental parameters of each target zone include: the temperature value of the refrigeration equipment, the natural ventilation temperature value and the personnel density value acting on the target zone. In the same target solution, the environmental parameters of different target zones may be different.

[0117] Optionally, calculating the Euclidean distance between each target frontier and the ideal optimization solution includes:

[0118] Calculating the carbon emissions of the target building area under the target solution;

[0119] Calculating the comfort level of personnel in the target building area under the target solution;

[0120] Based on the carbon emissions and occupant comfort of the target building area under the target solution and the ideal carbon emissions and ideal occupant comfort of the target building area, the Euclidean distance between the target frontier and the ideal optimization solution is calculated.

[0121] The carbon emissions of the target building area under the target solution are actually the overall carbon emissions of the target front. The calculating the carbon emissions of the target building area under the target solution includes: calculating the sum of all carbon emissions in the target front as the carbon emissions of the target building area under the target solution.

[0122] The occupant comfort of the target building area under the target solution is actually the entire occupant comfort of the target front. The step of calculating the occupant comfort of the target building area under the target solution includes: calculating the average of all occupant comforts in the target front as the occupant comfort of the target building area under the target solution.

[0123] The calculation method of Euclidean distance is:

[0124]

[0125] Among them, Ed is the Euclidean distance between a certain target frontier and the ideal optimization solution, c is the carbon emissions of the target building area under the target solution corresponding to the target frontier, p is the occupant comfort of the target building area under the target solution corresponding to the target frontier, c′ is the ideal carbon emissions of the target building area, and p′ is the ideal occupant comfort of the target building area.

[0126] Combined with the above examples, the optimized strategy can significantly optimize building performance and reduce carbon emissions. Based on the high-precision GWO-XGBoost prediction model constructed above, the operation and maintenance status of the three target partitions in the real situation are input (the cooling setting temperature value of the three partitions is 24℃, the natural ventilation temperature value is 20℃, and the personnel density value is 0.2). The initial carbon emissions in the three temperature scenarios of 22-30℃, 30-35℃ and >35℃ can be accurately predicted as 4134.34, 10027.52, and 15001.11 kg respectively. In addition, the environmental parameters of each partition in the three target partitions and the constructed prediction model are input into the NSGA-II optimization algorithm. The optimization algorithm searches for 150 groups of Pareto fronts under different weather temperature ranges, and selects the optimal operation and maintenance parameter combination strategy based on the Euclidean distance. As shown in Table 2, after adopting the optimization strategy, carbon emissions are reduced by 50.29%, 25.99%, and 10.13%, and the building optimization rates are 48.6%, 44%, and 59.2%, respectively. Among them, X1-X3 are the refrigeration equipment temperature values ​​of each target zone, X4-X6 are the natural ventilation temperature values ​​of each target zone, and X7-X9 are the personnel density values ​​of each target zone.

[0127] Table 2 Optimal operation and maintenance strategies under three weather temperature ranges

[0128]

[0129] In addition, considering that the core of refined carbon reduction management of buildings is to deliver energy to target areas according to demand, refined management of building zoning can effectively improve the performance of building operation and maintenance. However, the uncertainty caused by the interaction between zoning is inevitable. By considering the decarbonization of buildings with personnel uncertainty, we can obtain more efficient and practical strategies through optimization. However, the number of indoor personnel changes dynamically, and their behavior is affected by many deterministic and uncertain factors, which makes it impossible to accurately capture the pattern. The existing technology has not solved the uncertainty caused by the flow of personnel in the optimization of building zoning. Based on Latin hypercube sampling, this application fully considers the impact of the uncertainty of internal personnel flow on building carbon emissions, and proposes a personnel uncertainty measurement method. By determining the personnel distribution characteristics of each area, it seeks building carbon reduction strategies from the perspective of uncertainty, and avoids the impact of personnel uncertainty on this study. Among them, Latin Hypercube Sampling (LHS) is a sampling method that generates a set of samples according to a probability distribution, which can improve computational efficiency more than Monte Carlo simulation.

[0130] Optionally, the method further comprises steps B1 to B4:

[0131] Step B1, using the Latin hypercube sampling algorithm to sample the population density within the second time range of each target partition to obtain a population density variable parameter value of each target partition;

[0132] Step B2, determining an optimal population density value from each optimal environmental parameter of the optimal solution, and respectively correcting the corresponding optimal population density value based on each population density variable parameter value to obtain an updated optimal population density value of each target partition;

[0133] Step B3, replacing the population density range in the environmental parameter range with all the obtained updated optimal population density values ​​to obtain a new environmental parameter range;

[0134] Step B4, using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, a new optimal solution of the optimization objective is calculated within the new environmental parameter range, so that each target partition operates under the new optimal solution;

[0135] The new optimal solution includes new optimal environmental parameters of each target partition, and each new optimal environmental parameter includes an updated personnel density value of the corresponding target partition.

[0136] It should be noted that this embodiment actually replaces the variable population density range in the environmental parameter range with a fixed updated population density value, and then finds other parameters (such as refrigeration equipment temperature value and natural ventilation temperature value) that optimize the optimization target based on the optimization algorithm, so that each target partition operates under the new optimal solution. This embodiment uses the Latin hypercube sampling method to measure the distribution of people in each partition, solving the impact of indoor personnel distribution uncertainty on the building carbon reduction strategy.

[0137] In view of the low degree of digitization and extensive management in the traditional construction industry, this embodiment provides a theoretical framework for carbon emission tracking and energy conservation and carbon reduction optimization of operation and maintenance buildings that integrates three-dimensional digital modeling, deep learning, and natural bionic algorithms. The target building area is divided into multiple target zones. According to multiple weather temperature ranges, the uncertainty of indoor personnel distribution is considered to calculate the combination strategy that optimizes the building's carbon emissions and personnel comfort under different weather temperature ranges. The current research focuses on the carbon reduction optimization of the entire building, mainly from the parameters such as the building's envelope structure, spatial layout, equipment control strategy, etc., and optimizes the overall cost, comfort, and carbon emissions of the building, providing a basis for the optimization of the building design scheme.

[0138] This application has the following advantages:

[0139] (1) Using 3D digital modeling technology, a 3D simulation model of the building is constructed to solve the problem of difficulty in obtaining building operation and maintenance data in different scenarios. At the same time, a systematic theoretical framework for multi-scenario carbon emissions and comfort prediction and multi-objective building carbon reduction optimization is proposed to achieve significant carbon reduction of the entire building.

[0140] (2) By dividing the target building area into multiple sub-areas and the weather into multiple weather temperature ranges, refined building management under multiple weather temperature ranges can be achieved. The carbon emissions and personnel comfort targets of each sub-area are optimized to solve the problems of insufficient refinement of current building carbon reduction optimization and a small number of optimization targets. That is, based on the target zoning-personnel-equipment collaborative optimization technology, the carbon emission intensity of building operation and maintenance can be minimized while ensuring the comfort of indoor personnel.

[0141] (3) Taking into full consideration the impact of external environmental changes and internal personnel flow on building carbon emissions, a personnel uncertainty measurement method is proposed to address the impact of indoor personnel distribution uncertainty on this study.

[0142] Embodiment 2

[0143] The embodiment of the present invention provides a building carbon reduction device based on multi-objective optimization, such as Figure 4 As shown, the building carbon reduction device 40 based on multi-objective optimization specifically includes the following components:

[0144] The first acquisition module 401 is used to acquire the environmental parameter range for adjusting the carbon emission and occupant comfort of the target building area;

[0145] The second acquisition module 402 is used to acquire the carbon emission prediction model and the personnel comfort prediction model associated with each target partition of the target building area; wherein the carbon emission prediction model and the personnel comfort prediction model are used to predict the carbon emission and the personnel comfort of the target partition based on the environmental parameters within the environmental parameter range, respectively;

[0146] A setting module 403 is used to set the carbon emissions and occupant comfort of the target building area as optimization targets;

[0147] The calculation module 404 is used to calculate the optimal solution of the optimization objective within the range of the environmental parameters by using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, so that each target partition can operate under the optimal solution; wherein the optimal solution includes the optimal environmental parameters of each target partition.

[0148] Optionally, the device further comprises:

[0149] A construction module, used for constructing a plurality of target environmental parameter samples before obtaining the carbon emission prediction model and the personnel comfort prediction model associated with each target partition of the target building area; wherein the target environmental parameter samples are environmental parameters within the environmental parameter range that meet the preset constraint conditions;

[0150] An estimation module, used to estimate the carbon emissions and personnel comfort of the target partition under each target environmental parameter sample;

[0151] A first training module is used to determine each target environmental parameter sample and the corresponding carbon emission as a carbon emission sample, count all carbon emission samples as a carbon emission sample set, and train a first preset model based on the carbon emission sample set to obtain the carbon emission prediction model;

[0152] The second training module is used to determine each target environmental parameter sample and the corresponding personnel comfort as a personnel comfort sample, count all personnel comfort samples as a personnel comfort sample set, and train the second preset model based on the personnel comfort sample set to obtain the personnel comfort prediction model.

[0153] Optionally, the estimation module is specifically used for:

[0154] Applying the target environmental parameter sample to a pre-constructed target partition simulation model; wherein the target partition simulation model is located within a pre-constructed target building area simulation model, and the accuracy of predicting the carbon emissions of the target building area based on the target building area simulation model is greater than a preset accuracy threshold;

[0155] Calculating the carbon emissions of the target partition simulation model within a first time range as the carbon emissions of the target partition under the target environmental parameter sample;

[0156] The comfort level of personnel in the target partition simulation model within a first time range is calculated as the comfort level of personnel in the target partition under the target environmental parameter sample.

[0157] Optionally, the calculation module is specifically used for:

[0158] The environmental parameter range and the carbon emission prediction model and the personnel comfort prediction model associated with each target partition are used as inputs of the multi-objective optimization algorithm, so that the multi-objective optimization algorithm outputs a Pareto optimal solution set and a Pareto frontier of the optimization target; wherein the Pareto optimal solution set includes multiple target solutions, each target solution includes the environmental parameters of each target partition; the Pareto front includes target frontiers corresponding to each target solution, each target front includes the carbon emission and personnel comfort of each target partition;

[0159] Obtaining an ideal optimization plan; wherein the ideal plan includes the ideal carbon emissions and ideal personnel comfort of the target building area;

[0160] Calculating the Euclidean distance between each target front and the ideal optimization solution;

[0161] Selecting a target solution corresponding to a target frontier with a maximum Euclidean distance from the Pareto optimal solution set;

[0162] The screened target solution is determined as the optimal solution.

[0163] Optionally, when executing the step of calculating the Euclidean distance between each target frontier and the ideal optimization solution, the calculation module is specifically used to:

[0164] Calculating the carbon emissions of the target building area under the target solution;

[0165] Calculating the comfort level of personnel in the target building area under the target solution;

[0166] Based on the carbon emissions and occupant comfort of the target building area under the target solution and the ideal carbon emissions and ideal occupant comfort of the target building area, the Euclidean distance between the target frontier and the ideal optimization solution is calculated.

[0167] Optionally, when executing the step of calculating the carbon emissions of the target building area under the target solution, the calculation module is specifically used to: calculate the sum of all carbon emissions in the target front as the carbon emissions of the target building area under the target solution; when executing the step of calculating the occupant comfort of the target building area under the target solution, the calculation module is specifically used to: calculate the mean of all occupant comfort in the target front as the occupant comfort of the target building area under the target solution.

[0168] Optionally, the device further comprises:

[0169] A sampling module, used to sample the personnel density within the second time range of each target partition using a Latin hypercube sampling algorithm to obtain a variable parameter value of the personnel density of each target partition;

[0170] A correction module, used to determine the optimal population density value from each optimal environmental parameter of the optimal solution, and to correct the corresponding optimal population density value based on each population density variable parameter value, so as to obtain an updated optimal population density value of each target partition;

[0171] A replacement module, used for replacing the population density range in the environmental parameter range with all the obtained updated optimal population density values ​​to obtain a new environmental parameter range;

[0172] An updating module, for calculating a new optimal solution of the optimization objective within a new environmental parameter range by using a multi-objective optimization algorithm and based on a carbon emission prediction model and a personnel comfort prediction model associated with each target partition, so that each target partition operates under the new optimal solution;

[0173] The new optimal solution includes new optimal environmental parameters of each target partition, and each new optimal environmental parameter includes an updated personnel density value of the corresponding target partition.

[0174] Optionally, the device further comprises:

[0175] A third acquisition module is used to acquire a plurality of preset weather temperature ranges;

[0176] The second acquisition module is specifically used to: acquire the carbon emission prediction model and the personnel comfort prediction model associated with each target partition under each weather temperature range;

[0177] The calculation module is specifically used to: utilize a multi-objective optimization algorithm and based on the carbon emission prediction model and personnel comfort prediction model associated with each target partition in each weather temperature range, calculate the optimal solution of the optimization objective in each weather temperature range within the environmental parameter range, so that each target partition can operate based on the optimal solution in each weather temperature range.

[0178] Optionally, the environmental parameter range includes: a refrigeration equipment temperature range, a natural ventilation temperature range and a personnel density range; wherein the refrigeration equipment temperature range represents the operating temperature range of the refrigeration equipment, and the natural ventilation temperature range represents the temperature range allowed for ventilation of the target partition; the personnel density range represents the range of personnel density allowed for the target partition, and the environmental parameters include the refrigeration equipment temperature value, the natural ventilation temperature value and the personnel density value.

[0179] Embodiment 3

[0180] This embodiment also provides a computer device, such as a smart phone, tablet computer, laptop computer, desktop computer, rack server, blade server, tower server or cabinet server (including an independent server or a server cluster composed of multiple servers) that can execute programs. Figure 5 As shown, the computer device 50 of this embodiment includes at least but not limited to: a memory 501 and a processor 502 that can communicate with each other via a system bus. It should be noted that Figure 5 Only computer device 50 is shown with components 501 - 502 , but it should be understood that implementing all of the components shown is not a requirement, and more or fewer components may alternatively be implemented.

[0181] In this embodiment, the memory 501 (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 501 may be an internal storage unit of the computer device 50, such as a hard disk or a memory of the computer device 50. In other embodiments, the memory 501 may also be an external storage device of the computer device 50, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. equipped on the computer device 50. Of course, the memory 501 may also include both the internal storage unit and the external storage device of the computer device 50. In this embodiment, the memory 501 is generally used to store the operating system and various application software installed on the computer device 50. In addition, the memory 501 may also be used to temporarily store various data that have been output or are to be output.

[0182] In some embodiments, the processor 502 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 502 is generally used to control the overall operation of the computer device 50 .

[0183] Specifically, in this embodiment, the processor 502 is used to execute the program of the building carbon reduction method based on multi-objective optimization stored in the memory 501. When the program of the building carbon reduction method based on multi-objective optimization is executed, the following steps are implemented:

[0184] Obtain the environmental parameter range for adjusting the carbon emissions and occupant comfort of the target building area;

[0185] Obtaining a carbon emission prediction model and a personnel comfort prediction model associated with each target partition of the target building area; wherein the carbon emission prediction model and the personnel comfort prediction model are respectively used to predict the carbon emission and personnel comfort of the target partition based on the environmental parameters within the environmental parameter range;

[0186] Setting the carbon emissions and occupant comfort of the target building area as optimization targets;

[0187] By using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, the optimal solution of the optimization objective is calculated within the range of the environmental parameters so that each target partition can operate under the optimal solution; wherein the optimal solution includes the optimal environmental parameters of each target partition.

[0188] The specific implementation process of the above method steps can be found in Example 1, and this embodiment will not be repeated here.

[0189] Embodiment 4

[0190] This embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, a server, an App application store, etc., on which a computer program is stored. When the computer program is executed by a processor, the steps of a building carbon reduction method based on multi-objective optimization are implemented. The method specifically includes:

[0191] Obtain the environmental parameter range for adjusting the carbon emissions and occupant comfort of the target building area;

[0192] Obtaining a carbon emission prediction model and a personnel comfort prediction model associated with each target partition of the target building area; wherein the carbon emission prediction model and the personnel comfort prediction model are respectively used to predict the carbon emission and personnel comfort of the target partition based on the environmental parameters within the environmental parameter range;

[0193] Setting the carbon emissions and occupant comfort of the target building area as optimization targets;

[0194] By using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, the optimal solution of the optimization objective is calculated within the range of the environmental parameters so that each target partition can operate under the optimal solution; wherein the optimal solution includes the optimal environmental parameters of each target partition.

[0195] The specific implementation process of the above method steps can be found in Example 1, and this embodiment will not be repeated here.

[0196] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0197] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0198] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method.

[0199] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A building carbon reduction method based on multi-objective optimization, characterized in that: The method comprises: Obtain the environmental parameter range for adjusting the carbon emissions and occupant comfort of the target building area; Obtaining a carbon emission prediction model and a personnel comfort prediction model associated with each target partition of the target building area; wherein the carbon emission prediction model and the personnel comfort prediction model are respectively used to predict the carbon emission and personnel comfort of the target partition based on the environmental parameters within the environmental parameter range; Setting the carbon emissions and occupant comfort of the target building area as optimization targets; Using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, the optimal solution of the optimization objective is calculated within the range of the environmental parameters, so that each target partition operates under the optimal solution; wherein the optimal solution includes the optimal environmental parameters of each target partition; The environmental parameter range includes: a refrigeration equipment temperature range, a natural ventilation temperature range and a personnel density range; the refrigeration equipment temperature range represents the operating temperature range of the refrigeration equipment, the natural ventilation temperature range represents the temperature range allowed for ventilation of the target partition, and the personnel density range represents the range of personnel density allowed for the target partition; there are multiple environmental parameters within the environmental parameter range, and the environmental parameters include a refrigeration equipment temperature value, a natural ventilation temperature value and a personnel density value; The method of using a multi-objective optimization algorithm and calculating the optimal solution of the optimization objective within the range of the environmental parameters based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, so that each target partition operates under the optimal solution, includes: The environmental parameter range and the carbon emission prediction model and the personnel comfort prediction model associated with each target partition are used as inputs of the multi-objective optimization algorithm, so that the multi-objective optimization algorithm outputs a Pareto optimal solution set and a Pareto frontier of the optimization target; wherein the Pareto optimal solution set includes multiple target solutions, each target solution includes the environmental parameters of each target partition; the Pareto front includes target frontiers corresponding to each target solution, each target front includes the carbon emission and personnel comfort of each target partition; Obtaining an ideal optimization plan; wherein the ideal optimization plan includes an ideal carbon emission and an ideal personnel comfort level in the target building area; Calculating the Euclidean distance between each target front and the ideal optimization solution; Selecting a target solution corresponding to a target frontier with a maximum Euclidean distance from the Pareto optimal solution set; The screened target solution is determined as the optimal solution.

2. The method according to claim 1, characterized in that Before obtaining the carbon emission prediction model and the occupant comfort prediction model associated with each target partition of the target building area, the method further includes: Constructing a plurality of target environmental parameter samples; wherein the target environmental parameter samples are environmental parameters within the environmental parameter range that meet preset constraint conditions; Estimate the carbon emissions and personnel comfort of the target zone under each target environmental parameter sample; Determine each target environmental parameter sample and the corresponding carbon emission as a carbon emission sample, count all carbon emission samples as a carbon emission sample set, and train the first preset model based on the carbon emission sample set to obtain the carbon emission prediction model; Each target environmental parameter sample and the corresponding personnel comfort are determined as a personnel comfort sample, all personnel comfort samples are counted as a personnel comfort sample set, and the second preset model is trained based on the personnel comfort sample set to obtain the personnel comfort prediction model.

3. The method according to claim 2, characterized in that The estimated carbon emissions and personnel comfort of the target zone under each target environmental parameter sample include: Applying the target environmental parameter sample to a pre-constructed target partition simulation model; wherein the target partition simulation model is located within a pre-constructed target building area simulation model, and the accuracy of predicting the carbon emissions of the target building area based on the target building area simulation model is greater than a preset accuracy threshold; Calculating the carbon emissions of the target partition simulation model within a first time range as the carbon emissions of the target partition under the target environmental parameter sample; The comfort level of personnel in the target partition simulation model within a first time range is calculated as the comfort level of personnel in the target partition under the target environmental parameter sample.

4. The method according to claim 1, characterized in that The calculating of the Euclidean distance between each target frontier and the ideal optimization solution comprises: Calculating the carbon emissions of the target building area under the target solution; Calculating the comfort level of personnel in the target building area under the target solution; Based on the carbon emissions and occupant comfort of the target building area under the target solution and the ideal carbon emissions and ideal occupant comfort of the target building area, the Euclidean distance between the target frontier and the ideal optimization solution is calculated.

5. The method according to claim 4, characterized in that The calculating the carbon emissions of the target building area under the target solution includes: Calculate the sum of all carbon emissions in the target frontier as the carbon emissions of the target building area under the target solution; The calculating the comfort level of personnel in the target building area under the target solution comprises: The average of the comfort levels of all personnel in the target front is calculated as the comfort level of personnel in the target building area under the target solution.

6. The method according to claim 1, characterized in that The method further comprises: The Latin hypercube sampling algorithm is used to sample the population density within the second time range of each target partition to obtain the population density variable parameter value of each target partition; Determine an optimal population density value from each optimal environmental parameter of the optimal solution, and modify the corresponding optimal population density value based on each population density variable parameter value to obtain an updated optimal population density value for each target partition; Replacing the population density range in the environmental parameter range with all the obtained updated optimal population density values ​​to obtain a new environmental parameter range; Using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, a new optimal solution of the optimization objective is calculated within a new environmental parameter range, so that each target partition operates under the new optimal solution; The new optimal solution includes new optimal environmental parameters of each target partition, and each new optimal environmental parameter includes an updated optimal personnel density value of the corresponding target partition.

7. The method according to claim 1, characterized in that The method further comprises: Get multiple preset weather temperature ranges; The step of obtaining the carbon emission prediction model and the occupant comfort prediction model associated with each target partition of the target building area includes: Obtain the carbon emission prediction model and personnel comfort prediction model associated with each target zone under each weather temperature range; The method of using a multi-objective optimization algorithm and calculating the optimal solution of the optimization objective within the range of the environmental parameters based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, so that each target partition operates under the optimal solution, includes: By utilizing a multi-objective optimization algorithm and based on the carbon emission prediction model and personnel comfort prediction model associated with each target partition in each weather temperature range, the optimal solution of the optimization objective in each weather temperature range is calculated within the range of environmental parameters, so that each target partition can operate based on the optimal solution in each weather temperature range.

8. A building carbon reduction device based on multi-objective optimization, characterized in that: The device comprises: A first acquisition module is used to acquire the environmental parameter range for adjusting the carbon emission and occupant comfort of the target building area; A second acquisition module is used to acquire a carbon emission prediction model and a personnel comfort prediction model associated with each target partition of the target building area; wherein the carbon emission prediction model and the personnel comfort prediction model are used to predict the carbon emission and personnel comfort of the target partition based on the environmental parameters within the environmental parameter range, respectively; A setting module, used to set the carbon emissions and occupant comfort of the target building area as optimization targets; A calculation module, used to calculate the optimal solution of the optimization target within the range of the environmental parameters by using a multi-objective optimization algorithm and based on the carbon emission prediction model and the personnel comfort prediction model associated with each target partition, so that each target partition can operate under the optimal solution; wherein the optimal solution includes the optimal environmental parameters of each target partition; The environmental parameter range includes: a refrigeration equipment temperature range, a natural ventilation temperature range and a personnel density range; the refrigeration equipment temperature range represents the operating temperature range of the refrigeration equipment, the natural ventilation temperature range represents the temperature range allowed for ventilation of the target partition, and the personnel density range represents the range of personnel density allowed for the target partition; there are multiple environmental parameters within the environmental parameter range, and the environmental parameters include a refrigeration equipment temperature value, a natural ventilation temperature value and a personnel density value; The calculation module is specifically used for: The environmental parameter range and the carbon emission prediction model and the personnel comfort prediction model associated with each target partition are used as inputs of the multi-objective optimization algorithm, so that the multi-objective optimization algorithm outputs a Pareto optimal solution set and a Pareto frontier of the optimization target; wherein the Pareto optimal solution set includes multiple target solutions, each target solution includes the environmental parameters of each target partition; the Pareto front includes target frontiers corresponding to each target solution, each target front includes the carbon emission and personnel comfort of each target partition; Obtaining an ideal optimization plan; wherein the ideal optimization plan includes an ideal carbon emission and an ideal personnel comfort level in the target building area; Calculating the Euclidean distance between each target front and the ideal optimization solution; Selecting a target solution corresponding to a target frontier with a maximum Euclidean distance from the Pareto optimal solution set; The screened target solution is determined as the optimal solution.

Images