Building air conditioner control method based on indoor and outdoor environment data

Abstract

The invention discloses a building air conditioner control method based on indoor and outdoor environment data. The method mainly solves the problems that control of current building air conditioners generally only pays attention to the influence of building indoor environment on energy consumption, and neglects the correlation degree of surrounding environment and indoor environment; the association degree between the building energy consumption and the energy consumption and the outdoor environment on the indoor thermal comfort level is small, and systematic linkage thinking is lacked. According to the building air conditioner control method based on the indoor and outdoor environment data, climate data can be accurately monitored by regularly monitoring outdoor environment data including temperature data, air pressure data, wind speed data and the like, and meanwhile energy consumption data of air conditioner equipment are associated; the energy consumption influence can be generated by the data of the related range of the outdoor environment and the indoor human body thermal comfort, when the outdoor environment is in the comfortable range, the starting of the air conditioning system is controlled, the numerical range limitation is effectively controlled, and the energy consumption is unnecessary as far as possible.

Description

Technical Field

[0001] The present invention relates to the field of green building intelligent control, and in particular to a building air conditioning control method based on indoor and outdoor environmental data. Background Art

[0002] The use of educational space runs through people's growth period, including the stage of vocational and technical further study, and its use time accounts for a large proportion. With the development of economy and the improvement of living standards, people have higher and higher requirements for the thermal comfort of indoor environment. Thermal comfort refers to the state that most people are satisfied with the objective thermal environment from physiological to psychological aspects. Since the factors and conditions that affect human thermal comfort are very complex, researchers have conducted a lot of research on the evaluation methods of indoor thermal comfort and proposed several indicators for evaluating thermal comfort, among which PMV (Predicted Mean Vote) indicator is the most widely used thermal comfort evaluation indicator.

[0003] Building operation energy consumption is the most important concern in building energy conservation tasks. At present, there are two main problems with building energy consumption control systems: 1. Usually only the impact of the building's indoor environment on energy consumption is focused on, ignoring the correlation between the surrounding environment and the indoor environment; 2. Building energy consumption has little correlation with energy consumption and outdoor environment at the level of indoor thermal comfort, and lacks systematic linkage thinking. Summary of the invention

[0004] In order to overcome the shortcomings of the background technology, the present invention provides a building air-conditioning control method based on indoor and outdoor environmental data, which mainly solves the problems that the current control of building air-conditioning usually only focuses on the impact of the building's indoor environment on energy consumption, and ignores the correlation between the surrounding environment and the indoor environment; the building energy consumption has little correlation with energy consumption and outdoor environment at the indoor thermal comfort level, and lacks systematic linkage thinking.

[0005] The technical solution of the present invention is:

[0006] A building air conditioning control method based on indoor and outdoor environmental data comprises the following steps:

[0007] Step 1: Collect data, including equipment energy consumption data, indoor data and outdoor data;

[0008] Step 2: Classify the building's outdoor environmental climate data, energy consumption classification metering data, and indoor environmental coefficients of rooms in the building, use the building's historical energy consumption data as energy-saving reference data, and obtain building energy consumption-related data standards; use the temperature, humidity, air pressure, and wind speed obtained by the outdoor environmental monitoring equipment as inputs to the algorithm, and use the optimization algorithm to optimize the error between the environmental parameters and the manually set parameters, thereby reducing power consumption.

[0009] In step 2, the following steps are specifically included:

[0010] The firefly algorithm is used in the initial stage, and the genetic algorithm is used in the middle stage to improve the optimization process. First, the parameters of the firefly algorithm and the genetic algorithm are initialized. Then, the population is randomly generated by the independent variables. After the population is generated, the fitness value of the optimization function is calculated using the values ​​of the independent variables. The combination of all independent variables constitutes the fireflies in the firefly algorithm, and the value associated with the objective function constitutes the light intensity associated with each firefly. The light intensity is used to find the best firefly from all the fireflies in the initially generated random population. The initially randomly generated solution search space is updated by finding the distance between each firefly and the best firefly. The value of the best firefly is an evaluation index composed of thermal comfort value and energy consumption data. According to this distance, the solution search space is updated and new values ​​are assigned to all fireflies.

[0011] In step 2, the crossover operator of the genetic algorithm is embedded into the firefly position transformation stage of the standard FA; the indoor thermal comfort index formula of the data collected in step 1 is calculated.

[0012] PMV=(0.303e -0.036M +0.028){(MW)-3.05×10 -3 ×[5733-6.99(MW)-p a ]-0.42×[(MW)-58.15]-1.7×10 -5 M(5867-p a )-0.0014M(34-t a )-3.96×10 -8 f cl ×[(t cl +273) 4 -(t mrt+273 ) 4 ]-f cl h c (t cl -t a )}

[0013]

[0014] Where Icl is the thermal resistance of clothing, in m2·K / W, corresponding to the clothing condition of the human body; tcl represents the outer surface temperature of clothing, in °C;

[0015]

[0016] Where, dT = tr-20;

[0017] tr is the mean radiation temperature, in °C; obtained by the black globe temperature value;

[0018] hc represents the convective heat transfer coefficient, and the unit of hc is W / m2·K;

[0019]

[0020] v is the wind speed in m / s; obtained through equipment monitoring

[0021] M is metabolic rate, unit is W / m 2 ;

[0022] fcl is the ratio of the body surface area of ​​a person when clothed to the body surface area of ​​a person when naked;

[0023] ta is the air temperature, in °C;

[0024] tt is the average radiation temperature, in °C;

[0025] Vat is the air velocity in m / s;

[0026] Pa is the partial pressure of water vapor, in Pa;

[0027] hc is the convective heat transfer coefficient, and its unit is W / (m2·℃).

[0028] Step 1 The collected outdoor data includes atmospheric pressure value, temperature value and humidity value

[0029] It also includes an evaluation step. The minimum energy consumption and the minimum thermal comfort deviation are taken as optimization goals in the form of mean square error. In order to ensure stability, the minimum oscillation degree is also taken as the optimization goal. The mean square error (MSE) is used to measure the deviation of each result from the target value (usually zero). The deviation part: The deviation is measured by the mean square error (MSE), and the formula is as follows:

[0030] MSE = (1 / n)*Σ(x_i^2).

[0031] The evaluation step also introduces an indicator to measure the degree of oscillation. The degree of oscillation can be measured by the difference between the results. The formula is

[0032] Oscillation=Σ(x_i-x_{i-1})^2;.

[0033] The beneficial effects of the present invention are as follows: the present invention provides a building air conditioning control method based on indoor and outdoor environmental data. By regularly monitoring outdoor environmental data, including temperature data, air pressure data, wind speed data, etc., climate data can be accurately monitored. At the same time, the energy consumption data of the air-conditioning equipment is associated, so that the energy consumption impact of the outdoor environment and the data within the range related to the thermal comfort of the indoor human body can be achieved. When the outdoor environment is within a comfortable range, the air-conditioning system is controlled to be turned on and the numerical range is effectively controlled to be limited, so as to avoid unnecessary energy consumption as much as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 The invention relates to a building air conditioning control system based on the method.

[0035] Figure 2 The following is a logic diagram based on this method.

[0036] Figure 3 This is the logic block diagram of the firefly algorithm and genetic algorithm. DETAILED DESCRIPTION

[0037] The present invention is further described below in conjunction with the accompanying drawings: As shown in the figure, a building air conditioning control method based on indoor and outdoor environmental data comprises the following steps:

[0038] Step 1: Collect data, including equipment energy consumption data, indoor data and outdoor data; Step 2: Classify the building's outdoor environmental climate data, energy consumption classification metering data and the indoor environmental coefficients of the rooms in the building, use the building's historical energy consumption data as energy-saving reference data, and obtain building energy consumption-related data standards; use the temperature, humidity, air pressure and wind speed obtained by the outdoor environmental monitoring equipment as the input of the algorithm, and use the optimization algorithm to optimize the error between the environmental parameters and the manually set parameters, thereby reducing power consumption. According to the reduced error value, the human thermal comfort value is calculated according to the comfort index calculation formula. This error value is the input of the fuzzy controller used in the system. According to the error value, the fuzzy controller calculates the value required to change the actuator state, and changes the actuator state accordingly, providing the actuator with the preference value of the corresponding room.

[0039] like Figure 1 As shown, the present application can obtain energy consumption data within the same time range through energy consumption monitoring equipment and indoor and outdoor environment data acquisition equipment, indoor thermal comfort-related temperature, humidity, wind speed, thermal radiation, thermal resistance, metabolic rate, etc., and outdoor environment values ​​including temperature, air pressure, wind pressure, etc., and collect and organize data.

[0040] Indoor data, through indoor environment monitoring equipment, obtain temperature, humidity, thermal radiation, wind speed values, and obtain clothing thermal resistance and human metabolic rate based on the current date

[0041] Classification of building energy consumption data: Classify and organize building energy consumption data, external environmental variables, internal environmental parameters, etc. according to the latest specifications, and then conduct cooling capacity prediction, cluster analysis, classification identification and parameter estimation on the big data, formulate white-box models of building energy consumption data, and apply PENN (Probabilistic Entropy-based Neutral Network) to establish a cooling capacity prediction model.

[0042] Set up an energy consumption metering system: In accordance with energy-saving regulations, independently measure the energy consumption of each part, such as cold and heat sources, transmission and distribution systems, etc., and automatically collect metering data through custom metering ranges and monitoring areas to achieve online dynamic monitoring of each metering point and regional energy, energy summary analysis, comprehensive evaluation of energy consumption indicators, automatic fault alarm, historical data recording, etc.

[0043] Energy consumption data collection preprocessing and quality control: Regularly preprocess building energy consumption data to remove sample quality, data anomalies, range anomalies and error anomalies to ensure that the data covers the effective range. Energy consumption and environmental data samples and control samples should exceed 10,000. If the data range, typicality and effectiveness are insufficient, additional testing is required.

[0044] In step 2, the following steps are specifically included:

[0045] The firefly algorithm is used in the initial stage, and the genetic algorithm is used in the intermediate stage to improve the optimization process; first, the parameters of the firefly algorithm and the genetic algorithm are initialized; the firefly values ​​at this time include the state control parameters of all air-conditioning equipment including wind speed, temperature, hot and cold modes, fan mode, etc., and then, the population is randomly generated by the independent variables; in this case, the independent variables are wind speed, temperature, wind pressure, humidity, etc. from the outdoor environment; after the population is generated, the fitness value of the optimization function is calculated using the values ​​of the independent variables. The combination of all independent variables constitutes the fireflies in the firefly algorithm, and the value associated with the objective function constitutes the light intensity associated with each firefly. The light intensity is used to find the best firefly from all the fireflies in the initially generated random population, and the initially randomly generated solution search space is updated by finding the distance between each firefly and the best firefly. The value of the best firefly is an evaluation index composed of thermal comfort value and energy consumption data. According to this distance, the solution search space is updated and new values ​​are assigned to all fireflies.

[0046] Hybrid technology of two algorithms, genetic algorithm and firefly algorithm. In the hybrid optimization model proposed in this paper, the firefly algorithm is used in the initial stage, and the genetic algorithm is used in the intermediate stage to improve the optimization process. First, the parameters of the firefly algorithm and the genetic algorithm are initialized. The firefly values ​​at this time include the state control parameters of all air-conditioning equipment including wind speed, temperature, hot and cold mode, fan mode, etc. Then, the population is randomly generated by the independent variables. In this case, the independent variables are wind speed, temperature, wind pressure, humidity, etc. from the outdoor environment. After the population is generated, the fitness value of the optimization function is calculated using the values ​​of the independent variables. The combination of all independent variables constitutes the fireflies in the firefly algorithm, and the value associated with the objective function constitutes the light intensity associated with each firefly. The light intensity is used to find the best firefly from all the fireflies in the initially generated random population. The solution search space generated initially randomly is updated by finding the distance between each firefly and the best firefly. The value of the best firefly is an evaluation index composed of thermal comfort value and energy consumption data. Based on this distance, the solution search space is updated and new values ​​are assigned to all fireflies.

[0047] The step-by-step working mechanism of the method. Accordingly, the positions of the fireflies are updated according to the calculated fitness values. At the current stage, if the recently calculated fitness value appears to have a better optimized value, another iteration will be initiated, and further processing is required to improve the performance of FA. The firefly position change stage of the standard FA depends on the value of the random factor used in the standard FA. If this factor is taken very small, the utilization of the solution search space will be poor, thereby reducing the solution quality of the algorithm. In order to solve this problem, the genetic crossover operator is embedded in the firefly position transformation stage to enhance the availability of the solution search space and improve the optimization mechanism.

[0048] Embedding the crossover operator of the genetic algorithm into the firefly position transformation stage of the standard FA involves fewer technical operations. The standard FA has the concept of fireflies and their light intensity, while the standard GA has the concept of genes and chromosomes. When the GA is embedded into the FA, the fireflies consisting of the independent variables are replaced by the GA chromosomes consisting of the genes representing the independent variables. The light intensity of the fireflies is related to the value of the chromosome, and the value of the chromosome represents the value of the optimization function. In this case, the optimization function is the function outlined in Equation 1. The processing is then processed using the crossover operator of the genetic algorithm.

[0049] In FA, the opposite process occurs, i.e., the chromosomes are replaced by fireflies and the value of the chromosomes is replaced by the light intensity of the fireflies.

[0050] At the beginning, the population is randomly initialized, and all fireflies are evaluated according to their fitness values.

[0051] i=0;

[0052] {

[0053] Calculate the distance of all fireflies to the best firefly

[0054] Update the positions of all fireflies

[0055] Fitness function evaluation

[0056] Sort fireflies based on fitness function values

[0057] Replace all the fireflies in FA with GA chromosomes. Apply GA operator to replace all the chromosomes in GA with the fireflies in FA. Evaluation of fitness function value

[0058] }

[0059] i=i+1;

[0060] }

[0061] While (stop condition not met) prints the result.

[0062] In step two, the crossover operator of the genetic algorithm is embedded into the firefly position transformation stage of the standard FA, which involves fewer technical operations. The standard FA has the concept of fireflies and their light intensity, while the standard GA has the concept of genes and chromosomes. When the GA is embedded into the FA, the fireflies consisting of the independent variables are replaced by the GA chromosomes consisting of the genes representing the independent variables. The light intensity of the fireflies is related to the value of the chromosome, and the value of the chromosome represents the value of the optimization function. In this case, the optimization function is the function outlined in Equation 1. The crossover operator of the genetic algorithm is used after processing

[0063] The data collected in step 1 is calculated using the indoor thermal comfort index formula.

[0064] PMV=(0.303e -0.036M +0.028){(MW)-3.05×10 -3 ×[5733-6.99(MW)-p a ]-0.42×[(MW)-58.15]-1.7×10 -5 M(5867-p a )-0.0014M(34-t a )-3.96×10 -8 f cl ×[(t cl +273) 4 -(t mrt+273 ) 4 ]-f cl h c (t cl -t a )}

[0065]

[0066] Where Icl is the thermal resistance of clothing, in m2·K / W, corresponding to the clothing condition of the human body; tcl represents the outer surface temperature of clothing, in °C;

[0067]

[0068] Where, dT = tr-20;

[0069] tr is the mean radiation temperature, in °C; obtained by the black globe temperature value;

[0070] hc represents the convective heat transfer coefficient, and the unit of hc is W / m2·K;

[0071]

[0072] v is the wind speed in m / s; obtained through equipment monitoring

[0073] M is metabolic rate, unit is W / m 2 ;

[0074] fcl is the ratio of the body surface area of ​​a person when clothed to the body surface area of ​​a person when naked;

[0075] ta is the air temperature, in °C;

[0076] tt is the average radiation temperature, in °C;

[0077] Vat is the air velocity in m / s;

[0078] Pa is the partial pressure of water vapor, in Pa;

[0079] hc is the convection heat transfer coefficient, unit is W / (m2·℃)

[0080] W is the heat consumed by external work (negligible for most activities), and its unit is W / m2.

[0081] The outdoor data collected in step one include atmospheric pressure values, temperature values ​​and humidity values. Through the integration of outdoor environmental data, the stereotyped deviations caused by the thermal resistance value of clothing, metabolic rate and other data based on fixed date and season as the evaluation criteria can be corrected. The server reads the data through the communication equipment of the outdoor monitoring equipment. In addition, the climate information is obtained through the climate platform to obtain more accurate classification basis, including weather, wind direction, wind speed, etc.

[0082] It also includes an evaluation step. The minimum energy consumption and the minimum thermal comfort deviation are taken as optimization goals in the form of mean square error. In order to ensure stability, the minimum oscillation degree is also taken as the optimization goal. The mean square error (MSE) is used to measure the deviation of each result from the target value (usually zero). The deviation part: The deviation is measured by the mean square error (MSE), and the formula is as follows:

[0083] MSE = (1 / n) * Σ(x_i^2). The closer the result is to zero, the smaller the MSE value. The target value here is (thermal comfort value deviation^2 + energy consumption deviation value^2), where the thermal comfort value deviation is the absolute value of the thermal comfort value, and the energy consumption value deviation is the value obtained by dividing the energy consumption value reduction by the conventional energy consumption value based on the green building evaluation standard.

[0084] The evaluation step also introduces an indicator to measure the degree of oscillation. The degree of oscillation can be measured by the difference between the results. The formula is

[0085] Oscillation = Σ(x_i-x_{i-1})^2. This formula represents the sum of the squares of the differences between every two adjacent results. The smaller the oscillation, the smaller the difference between adjacent results and the smaller the total change.

[0086] Comprehensive cost function: The comprehensive cost function combines the deviation and the degree of oscillation, which can be expressed as: Cost = α*MSE + β*Oscillation; where α and β are weight parameters used to adjust the relative importance of the deviation and the degree of oscillation in the cost function. Substituting MSE and the degree of oscillation into the comprehensive cost function, we can get: Cost = α*(1 / n)*Σ(x_i^2)+β*Σ(x_i-x_{i-1})^2.

[0087] The control method of the present invention takes into account six indoor environmental parameters of human thermal comfort (air temperature, relative humidity, average radiant temperature, wind speed, human metabolic rate and clothing thermal resistance), and can accurately control thermal comfort; outdoor environmental parameters are used as input parameters, and the control method of the present invention is thermal comfort control for the purpose of energy saving. The most effective control parameters based on historical data are obtained through an optimization algorithm, and the control parameters are continuously approached to the optimal point through the continuous gain of data volume, so that the air-conditioning system always operates close to the optimal point, and the air-conditioning energy consumption can be effectively reduced while ensuring thermal comfort; in educational buildings themselves, the target range is clear and the effectiveness is strong, and because it is based on the amount of data, it is real-time and targeted.

[0088] The embodiments described with reference to the accompanying drawings are exemplary and intended to be used to explain the present invention, but should not be understood as limiting the present invention. The embodiments should not be regarded as limiting the present invention, but any improvements made based on the spirit of the present invention should be within the scope of protection of the present invention.

Claims

1. A building air conditioning control method based on indoor and outdoor environmental data, characterized in that: The following steps are included: Step 1: Collect data, including equipment energy consumption data, indoor data and outdoor data; Step 2: Classify the building's outdoor environmental climate data, energy consumption classification metering data, and indoor environmental coefficients of rooms in the building, use the building's historical energy consumption data as energy-saving reference data, and obtain building energy consumption-related data standards; use the temperature, humidity, air pressure, and wind speed obtained by the outdoor environmental monitoring equipment as inputs to the algorithm, and use the optimization algorithm to optimize the error between the environmental parameters and the manually set parameters, thereby reducing power consumption.

2. A building air conditioning control method based on indoor and outdoor environmental data according to claim 1, characterized in that: In step 2, the following steps are specifically included: The firefly algorithm is used in the initial stage, and the genetic algorithm is used in the middle stage to improve the optimization process. First, the parameters of the firefly algorithm and the genetic algorithm are initialized. Then, the population is randomly generated by the independent variables. After the population is generated, the fitness value of the optimization function is calculated using the values ​​of the independent variables. The combination of all independent variables constitutes the fireflies in the firefly algorithm, and the value associated with the objective function constitutes the light intensity associated with each firefly. The light intensity is used to find the best firefly from all the fireflies in the initially generated random population. The initially randomly generated solution search space is updated by finding the distance between each firefly and the best firefly. The value of the best firefly is an evaluation index composed of thermal comfort value and energy consumption data. According to this distance, the solution search space is updated and new values ​​are assigned to all fireflies.

3. A building air conditioning control method based on indoor and outdoor environmental data according to claim 2, characterized in that: In step 2, the crossover operator of the genetic algorithm is embedded into the firefly position transformation stage of the standard FA.

4. A building air conditioning control method based on indoor and outdoor environmental data according to claim 3, characterized in that: The data collected in step 1 is calculated using the indoor thermal comfort index formula. PMV=(0.303e -0.036M +0.028){(M-W)-3.05×10 -3 ×[5733-6.99(M-W)-p a ]-0.42×[(M-W)-58.15]-1.7×10 -5 M(5867-p a )-0.0014M(34-t a )-3.96×10 -8 f cl ×[(t cl +273) 4 -(t mrt+273 ) 4 ]-f cl h c (t cl -t a )}; Among them, Icl is the thermal resistance of clothing, in m2·K / W, corresponding to the clothing condition of the human body; tcl represents the outer surface temperature of the clothes, in °C; its formula is Where, dT = tr-20; tr is the mean radiation temperature, in °C; obtained by the black globe temperature value; hc represents the convective heat transfer coefficient, and the unit of hc is W / m2·K; its formula is: v is the wind speed in m / s; obtained through equipment monitoring M is metabolic rate, unit is W / m 2 ; fcl is the ratio of the body surface area of ​​a person when clothed to the body surface area of ​​a person when naked; ta is the air temperature, in °C; tt is the average radiation temperature, in °C; Vat is the air velocity in m / s; Pa is the partial pressure of water vapor, in Pa; hc is the convective heat transfer coefficient, and its unit is W / (m2·℃).

5. A building air conditioning control method based on indoor and outdoor environmental data according to claim 4, characterized in that: The outdoor data collected in step 1 include atmospheric pressure value, temperature value and humidity value.

6. A building air conditioning control method based on indoor and outdoor environmental data according to claim 5, characterized in that: It also includes an evaluation step. The minimum energy consumption and the minimum thermal comfort deviation are taken as optimization goals in the form of mean square error. In order to ensure stability, the minimum oscillation degree is also taken as the optimization goal. The mean square error (MSE) is used to measure the deviation of each result from the target value (usually zero). The deviation part: The deviation is measured by the mean square error (MSE), and the formula is as follows: MSE = (1 / n)*Σ(x_i^2).

7. A building air conditioning control method based on indoor and outdoor environmental data according to claim 6, characterized in that: The evaluation step also introduces an indicator to measure the degree of oscillation. The degree of oscillation can be measured by the difference between the results. The formula is Oscillation=Σ(x_i-x_{i-1})^2.

Images