Air conditioning energy-saving optimization control system and method based on multi-parameter regulation

Abstract

The present application relates to the technical field of air conditioner energy saving optimization, and discloses an air conditioner energy saving optimization control system and method based on multi-parameter regulation and control, which comprises the following steps: obtaining environment data; the environment data comprises building information model data, indoor environment data, electricity price data and meteorological prediction data; based on the environment data, a three-dimensional game model for air conditioner energy saving optimization control is constructed; the three-dimensional game model is solved by a multi-objective equilibrium algorithm, and control instructions of the air conditioner system are generated and executed. The present application realizes regulation and control of multi-parameters of the air conditioner system, can significantly save energy, guarantee human comfort and reasonably control electricity cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of air conditioning energy saving optimization, and particularly relates to an air conditioning energy saving optimization control system and method based on multi-parameter regulation. BACKGROUND

[0002] Although there are certain achievements in energy saving technology research and development, the overall energy utilization efficiency of current air conditioning systems is still not ideal. In the actual operation process of many air conditioners, various influencing factors are not fully considered to dynamically adjust the operating parameters, resulting in a common phenomenon of energy waste. Taking commercial buildings as an example, due to the large differences in personnel density, equipment heating conditions, etc. of different areas at different time periods, the existing air conditioning control mode is difficult to carry out fine multi-parameter regulation for each area, resulting in high overall energy consumption.

[0003] Current air conditioning control systems are mostly single-function, and can only carry out simple start-stop control or limited adjustment according to a single parameter. In actual application, the comprehensive consideration and analysis capability of multiple environmental parameters is insufficient. It is difficult to establish a comprehensive and accurate environmental model, and it is also difficult to realize intelligent energy saving control of multi-parameter optimization, and it is difficult to provide users with the best operation scheme that is both energy saving and comfortable.

[0004] A terminal air conditioning energy saving optimization control system and method is disclosed in a Chinese patent with the authorization announcement number CN118856527B, which includes a pipeline sequentially connected by a fresh air filter, a chilled water valve configured with a chilled water valve opening degree controller, and a fan configured with a fan frequency converter. The pipeline has a fresh air inlet and an air outlet at both ends. The air outlet is connected with multiple air diffusers. Fresh air and return air enter the pipeline through the fresh air inlet and reach the corresponding working area through the air diffusers. Each working area is provided with a temperature sensor. The fan frequency converter and the temperature sensor are electrically connected with a first PID1 module. The chilled water valve opening degree controller and the temperature sensor are electrically connected with a second PID2 module. This technical solution overcomes the problem of relatively slow response speed of air conditioner fan and chilled water valve temperature regulation, large temperature fluctuation or untimely adjustment of working area temperature. It avoids the interference of controlling the chilled water valve opening degree and the fan, thereby affecting the temperature regulation of the working area.

[0005] A kind of air conditioner control method and device are disclosed in Chinese patent with authorization announcement No.CN104633857B, which method includes: according to preset period, the current operating parameter of the cold machine unit of air conditioning system, refrigerated water pump and cooling water pump is collected and stored;According to the current operating parameter and the operating parameter to be adjusted input by user, the energy consumption increment of air conditioning system under the operating state of operating parameter to be adjusted relative to current operating state is determined;When the energy consumption increment is less than zero, the operating state of air conditioning system is adjusted according to the operating parameter to be adjusted.The air conditioner control method and device provided by the application, when energy consumption increment is less than zero, adjust air conditioning system according to the operating parameter to be adjusted, realize energy saving, easy to realize.

[0006] The above patents all have the problems raised in the background art: it is difficult to realize intelligent energy-saving control of multi-parameter optimization, and it is impossible to provide users with the best operation scheme that is both energy-saving and comfortable.

[0007] The information disclosed in the background section is only intended to increase the understanding of the overall background of the application and should not be regarded as acknowledging or implying in any form that the information constitutes prior art known to those skilled in the art. SUMMARY

[0008] The technical problem to be solved by the present application is to overcome the defects of the prior art, provide an air conditioner energy-saving optimization control system and method based on multi-parameter regulation, and realize regulation of multiple parameters of air conditioning system, significantly save energy, ensure human comfort and reasonably control electricity cost.

[0009] To solve the above technical problems, the present application provides the following technical solutions:

[0010] On the one hand, the present application provides an air conditioner energy-saving optimization control method based on multi-parameter regulation, comprising the following steps: obtaining environmental data;The environmental data includes building information model data, indoor environmental data, electricity price data and weather forecast data;

[0011] Based on the environmental data, a three-dimensional game model for air conditioner energy-saving optimization control is constructed;Specifically, it includes:

[0012] Based on building information model data and indoor environmental data, calculate the heat buffer potential as the first game target of the three-dimensional game model;

[0013] Based on indoor environmental data and weather forecast data, calculate the comfort demand interval as the second game target of the three-dimensional game model;

[0014] Based on electricity price data and weather forecast data, calculate the electricity cost weight as the third game target of the three-dimensional game model;

[0015] The three-dimensional game model is solved by a multi-objective equilibrium algorithm to generate and execute a control instruction of the air conditioning system.

[0016] As a preferred scheme of the multi-parameter regulated air conditioning energy-saving optimization control method, the building information model data comprises wall thermal parameters and space geometric data, wherein the wall thermal parameters comprise thermal conductivity, specific heat capacity and density, and the space geometric data comprises volume, wall surface area, wall thickness and connectivity of adjacent control areas of each control area.

[0017] The indoor environment data comprises historical temperature, air supply and historical heat load of each control area, and the heat buffer potential is represented by a heat buffer time window, wherein the heat buffer time window represents a maximum duration for maintaining the current temperature of each control area in the case of air conditioning being turned off.

[0018] As a preferred scheme of the multi-parameter regulated air conditioning energy-saving optimization control method, the heat buffer potential is calculated based on the building information model data and the indoor environment data, and specifically comprises:

[0019] The wall thermal parameters and the space geometric data are mapped to the basic heat buffer potential of each control area based on the pre-trained buffer time prediction model, wherein the input of the buffer time prediction model is a feature vector composed of the wall thermal parameters and the space geometric data, the output is the basic heat buffer potential of the corresponding control area, and the basic heat buffer potential is a reference value of the heat buffer time window.

[0020] The basic buffer potential is corrected based on the historical temperature and the historical heat load to obtain a corrected heat buffer potential, and specifically comprises: calculating a temperature change rate of the control area based on the historical temperature; and correcting the basic buffer potential of the control area based on the temperature change rate to obtain the corrected heat buffer potential.

[0021] The corrected heat buffer potential is further adjusted based on the air supply to obtain the heat buffer time window of each control area, and specifically comprises: adjusting the corrected heat buffer potential based on a preset adjustment rule to obtain the heat buffer time window, wherein the heat buffer time window is negatively correlated with the air supply.

[0022] As a preferred scheme of the multi-parameter regulated air conditioning energy-saving optimization control method, the indoor environment data further comprises carbon dioxide concentration, thermal imaging data, real-time temperature and real-time humidity of each control area, and the weather prediction data comprises outdoor temperature, outdoor humidity and light intensity.

[0023] The comfort interval includes a temperature threshold interval, a humidity fluctuation interval, and a carbon dioxide concentration limit value; wherein the temperature threshold interval represents a temperature variation range of each control area; the humidity fluctuation interval represents a humidity variation value range of each control area; and the carbon dioxide concentration limit value represents a maximum threshold value of carbon dioxide concentration of each control area.

[0024] As a preferred scheme of the multi-parameter regulated air conditioning energy-saving optimization control method, the comfort demand interval is calculated based on indoor environment data and meteorological prediction data, and specifically includes:

[0025] The personnel density level of each control area is determined based on the carbon dioxide concentration and thermal imaging data; and the temperature variation and humidity variation of each control area are predicted based on the real-time temperature, real-time humidity, outdoor temperature, outdoor humidity, and light intensity.

[0026] A reference comfort demand interval is set for each control area.

[0027] The reference comfort demand interval is adjusted based on the temperature variation, humidity variation, and personnel density level of the control area, to obtain the comfort demand interval of each control area.

[0028] As a preferred scheme of the multi-parameter regulated air conditioning energy-saving optimization control method, the personnel density level of each control area is determined based on the carbon dioxide concentration and thermal imaging data, and specifically includes: setting a carbon dioxide concentration threshold value and a number threshold value; detecting the number of people in each control area based on thermal imaging data; if the carbon dioxide concentration of any control area is greater than the carbon dioxide concentration threshold value and the number of people is greater than the number threshold value, the personnel density level of the corresponding control area is high density; if the carbon dioxide concentration of any control area is not greater than the carbon dioxide concentration threshold value or the number of people is not greater than the number threshold value, the personnel density level of the corresponding control area is medium density; and if the carbon dioxide concentration of any control area is less than a preset minimum threshold value or the number of people is 0, the personnel density level of the corresponding control area is low density.

[0029] As a preferred scheme of the multi-parameter regulated air conditioning energy-saving optimization control method, the meteorological prediction data further includes extreme weather warning information; the electricity cost weight includes a time-of-use electricity price and a peak-shaving power range; the time-of-use electricity price includes an electricity price of each time period; and the peak-shaving power range represents an operating power range of the air conditioning system.

[0030] The electricity cost weight is calculated based on the electricity price data and the meteorological prediction data, and specifically includes:

[0031] Based on the electricity price data, the next 24 hours are divided into different time periods, and the electricity price of each time period is recorded to obtain the time-of-use electricity price.

[0032] Map the extreme weather warning information to a peak shaving power range based on a preset peak shaving power strategy.

[0033] As a preferred scheme of the multi-parameter regulation and energy-saving optimization control method of the air conditioner, the adjustment object of the control instruction of the air conditioning system includes the air conditioning temperature set value, the air supply amount, the compressor start-stop timing, the compressor power, and the fresh air system ventilation frequency of each control area.

[0034] The three-dimensional game model is solved by a multi-objective balancing algorithm, and specifically includes:

[0035] An optimization target and a constraint condition are generated based on the first game target, the second game target, and the third game target.

[0036] An optimal solution set of the adjustment object of the control instruction is generated by a multi-objective balancing algorithm.

[0037] A final execution solution is selected from the optimal solution set based on a preset game target priority.

[0038] The control instruction of the air conditioning system corresponding to the final execution solution is analyzed.

[0039] As a preferred scheme of the multi-parameter regulation and energy-saving optimization control method of the air conditioner, the optimization target includes: maximizing the heat buffer time window; minimizing the humidity offset; and minimizing the total power cost, wherein the humidity offset is the offset of the humidity of the control area from the humidity fluctuation interval.

[0040] The specific constraint term of the constraint condition includes: the temperature of the control area is within the temperature threshold interval; the carbon dioxide concentration is less than the carbon dioxide concentration limit value; and the operating power of the air conditioning system is within the peak shaving power range.

[0041] In a second aspect, the present application provides a multi-parameter regulation and energy-saving optimization control system of an air conditioner, which comprises a data acquisition module, a model construction module, a game calculation module, an algorithm solving module, and an instruction execution module.

[0042] The data acquisition module is used to acquire environmental data, including building information model data, indoor environmental data, electricity price data, and meteorological prediction data.

[0043] The model construction module constructs a three-dimensional game model for air conditioning energy-saving optimization control based on the environmental data.

[0044] The game calculation module is used to calculate the first game target, the second game target, and the third game target of the three-dimensional game model.

[0045] The algorithm solving module is configured to solve the three-dimensional game model, and generate a final execution solution of the control instruction of the air conditioning system.

[0046] The instruction execution module is configured to parse the final execution solution, and obtain and execute the control instruction of the air conditioning system.

[0047] Compared with the prior art, the present application has the following beneficial effects:

[0048] The present application can reduce the number of air conditioning start-stop times, thereby reducing power consumption, and can guarantee personnel comfort by taking the comfort requirement interval as one of the game targets, comprehensively considering indoor environment data and meteorological prediction data. The power consumption cost weight is calculated based on the electricity price data and the meteorological prediction data, the total power consumption cost is minimized, and the operation pressure of the power grid is reduced.

[0049] The three-dimensional game model is solved by a multi-objective equilibrium algorithm, and the control instruction of the air conditioning system is generated and executed, so as to adjust multiple parameters such as air conditioning temperature setting value and air supply quantity, realize multi-parameter regulation and control of air conditioning energy-saving optimization control, and improve the accuracy and intelligent degree of air conditioning system operation. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor. Among them:

[0051] Figure 1 The flow chart of the multi-parameter regulation and control air conditioning energy-saving optimization control method provided by the present application;

[0052] Figure 2 The structural schematic diagram of the multi-parameter regulation and control air conditioning energy-saving optimization control system provided by the present application. DETAILED DESCRIPTION

[0053] The technical solutions of the present application will be described in detail below by means of the drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application. In the case of no conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0054] Embodiment 1

[0055] This embodiment introduces a multi-parameter regulation and control air conditioning energy-saving optimization control method, which refers to Figure 1 The method comprises the following steps:

[0056] acquire environment data; the environment data includes building information model data, indoor environment data, electricity price data, and weather forecast data;

[0057] construct a three-dimensional game model for air conditioning energy-saving optimization control based on the environment data; specifically including:

[0058] calculate a heat buffer potential based on the building information model data and the indoor environment data as a first game target of the three-dimensional game model;

[0059] The building information model data includes wall thermal parameters and space geometry data; wherein the wall thermal parameters include thermal conductivity, specific heat capacity, and density; the wall thermal parameters are extracted based on Autodesk Revit, ArchiCAD, and other BIM software; the wall thermal parameters can be used to calculate the thermal inertia time parameter of the wall. The space geometry data includes the volume, wall surface area, wall thickness, and connectivity of adjacent control areas of each control area; the space geometry data can be used to determine the heat exchange path of each control area.

[0060] The object of the air conditioning energy-saving optimization control of the present application is the control area divided in the building, such as an office area, a warehouse area, etc. The thermal inertia time parameter is calculated through the wall thermal parameters, and the heat exchange path of each control area is determined through the space geometry data, which can provide a data basis for subsequent air conditioning energy-saving optimization control.

[0061] The indoor environment data includes the historical temperature, air supply, and historical heat load of each control area; the historical temperature is the average temperature of the control area in each hour within the past M hours; the air supply is the air flow rate of the air conditioning air outlet corresponding to the control area, which is measured based on the air speed sensor; the historical heat load is the working power of the air conditioner in each hour within the past M hours. M is a positive integer.

[0062] The heat buffer potential is represented by a heat buffer time window; the heat buffer time window represents the maximum duration that each control area maintains the current temperature in the case of air conditioning being turned off.

[0063] The heat buffer potential is calculated based on the building information model data and the indoor environment data, specifically including:

[0064] Map the wall thermal parameters and the space geometry data to the basic heat buffer potential of each control area based on the pre-trained buffer time prediction model;

[0065] The buffer time prediction model is any one of a polynomial regression model, a support vector regression model, and a multilayer perception; an input of the buffer time prediction model is a feature vector composed of wall thermal parameters and space geometry data, and an output of the buffer time prediction model is a basic thermal buffer potential of a corresponding control area; the basic thermal buffer potential is a reference value of a thermal buffer time window. For a control area including a wall with high specific heat capacity and high density, the heat storage capacity thereof is superior to that of a lightweight partition wall, and the buffer time prediction model maps a larger basic thermal buffer potential for the control area. For an open control area with good connectivity, heat can be diffused through air convection, and the buffer time prediction model maps a smaller basic thermal buffer potential for the control area than that for a closed control area.

[0066] The basic buffer potential is corrected based on the historical temperature and the historical heat load to obtain a corrected thermal buffer potential; specifically, a temperature change rate of the control area is calculated based on the historical temperature, and the basic buffer potential of the control area is corrected based on the temperature change rate to obtain the corrected thermal buffer potential.

[0067] The method for correcting the basic buffer potential of the control area based on the temperature change rate preferably includes setting a temperature change threshold, and if the temperature change rate is higher than the temperature change threshold, the basic buffer potential of the corresponding control area is reduced; for example, if it is detected that the temperature of a control area rises by 2 ℃ per hour, and the temperature change threshold is 1 ℃ per hour, the actual heat storage capacity of the control area is lower than the theoretical value, and the basic buffer potential needs to be reduced.

[0068] The corrected thermal buffer potential is further adjusted based on the air supply amount to obtain a thermal buffer time window of each control area.

[0069] The manner for further adjusting the corrected thermal buffer potential based on the air supply amount includes adjusting the corrected thermal buffer potential based on a preset adjustment rule to obtain the thermal buffer time window, wherein the thermal buffer time window is negatively correlated with the air supply amount.

[0070] The preferred adjustment rule is as follows: when it is detected that the air supply amount is greater than 3 m / s, the corrected thermal buffer potential is reduced by 15% to obtain the thermal buffer time window. High-speed air supply can accelerate indoor air convection, causing heat to be lost faster, and therefore, a large air supply amount affects the ability of the control area to maintain the current temperature.

[0071] A comfort demand interval is calculated based on indoor environment data and meteorological prediction data, as a second game target of the three-dimensional game model;

[0072] The indoor environment data further comprises carbon dioxide concentration, thermal imaging data, real-time temperature, and real-time humidity of each control area; wherein the carbon dioxide concentration is detected based on a gas sensor and is used to deduce the personnel density; the thermal imaging data is detected by an infrared sensor and is used to determine the personnel density together with the carbon dioxide concentration.

[0073] The weather forecast data comprises outdoor temperature, outdoor humidity, and light intensity; and the outdoor temperature, humidity, and light intensity are predicted for several hours in the future based on the data provided by a weather API, which are used to predict the indoor temperature and humidity changes.

[0074] The comfort requirement interval is used to represent the dynamic allowable range of the temperature, humidity, and air quality acceptable to the human body. By setting the comfort requirement interval as one of the game objectives of the three-dimensional game model, the energy saving target and the human body perception comfort can be balanced.

[0075] The comfort interval comprises a temperature threshold interval, a humidity fluctuation interval, and a carbon dioxide concentration limit value; wherein the temperature threshold interval represents the temperature change range of each control area; the humidity fluctuation interval represents the humidity change value range of each control area; and the carbon dioxide concentration limit value represents the maximum threshold value of the carbon dioxide concentration of each control area.

[0076] The comfort requirement interval is calculated based on the indoor environment data and the weather forecast data, and specifically comprises:

[0077] The personnel density level of each control area is determined based on the carbon dioxide concentration and the thermal imaging data, and specifically comprises: setting a carbon dioxide concentration threshold and a number threshold; detecting the number of people in each control area based on the thermal imaging data; if the carbon dioxide concentration of any control area is greater than the carbon dioxide concentration threshold and the number of people is greater than the number threshold, the personnel density level of the corresponding control area is high density; if the carbon dioxide concentration of any control area is not greater than the carbon dioxide concentration threshold or the number of people is not greater than the number threshold, the personnel density level of the corresponding control area is medium density; and if the carbon dioxide concentration of any control area is less than a preset minimum threshold or the number of people is 0, the personnel density level of the corresponding control area is low density.

[0078] predict the temperature change and humidity change of each control area based on the real-time temperature, real-time humidity, outdoor temperature, outdoor humidity, and light intensity; predict the temperature change and humidity change of each control area based on a pre-trained temperature and humidity prediction model; the temperature and humidity prediction model is any one of a long short-term memory network, a self-attention model, and a gradient boosting tree; the input of the temperature and humidity prediction model includes the real-time temperature, real-time humidity, outdoor temperature, outdoor humidity, and light intensity, and the wall thermal parameter and space geometry data; the output of the temperature and humidity prediction model includes the temperature prediction value and humidity prediction value of each control area in the next N hours; and the temperature and humidity prediction model can output the change curve of temperature and humidity according to a prediction step (for example, one prediction value every 15 minutes).

[0079] set a reference comfort requirement interval for each control area; the reference comfort requirement interval includes a reference temperature threshold interval, a reference humidity fluctuation interval, and a reference carbon dioxide concentration limit value.

[0080] The reference temperature threshold interval is preferably set by a PMV model; the value range of a preset PMV value is determined, the PMV value is calculated, and the value range of the PMV value is mapped to the reference temperature threshold interval. For example, the value range of the preset PMV value is -0.5 to 0.5.

[0081] The reference carbon dioxide concentration limit value and the value range of humidity are also preferably set based on the ASHRAE standard; for example, the reference carbon dioxide concentration limit value is 1000 ppm, and the value range of humidity is 30% to 60%; further, the reference humidity fluctuation interval is determined based on a comparison between the real-time humidity and the value range of humidity.

[0082] adjust the reference comfort requirement interval based on the temperature change, humidity change, and personnel density level of the control area, to obtain a comfort requirement interval of each control area. Specifically, the adjustment includes:

[0083] calculate the temperature change rate and humidity change rate of the control area; and adjust each comfort requirement interval based on the temperature change rate, humidity change rate, and personnel density level, to obtain the temperature threshold interval, humidity fluctuation interval, and carbon dioxide concentration limit value of each control area.

[0084] The strategy for adjusting each comfort requirement interval is preferably as follows:

[0085] If the temperature change rate is higher than a preset temperature change threshold, the reference temperature threshold interval is reduced, and the higher the personnel density level, the smaller the reference temperature threshold interval, to compensate for the influence of human body heat dissipation on the temperature of the control area.

[0086] When the personnel density level is high density, and the real-time humidity is within the humidity value range, the reference humidity fluctuation range is increased, so as to avoid frequent triggering of humidity regulation due to personnel activities. If the real-time humidity is outside the humidity value range, the reference humidity fluctuation range is kept unchanged, so as to preferentially trigger the humidity adjustment instruction and ensure priority of comfort.

[0087] If the personnel density level is high, and if the temperature change rate is higher than the preset temperature change threshold or the humidity change rate is higher than the preset humidity change threshold, the reference carbon dioxide concentration limit value is increased to preferentially ensure temperature and humidity control.

[0088] The electricity cost weight is calculated based on the electricity price data and the weather forecast data, and is used as a third game target of the three-dimensional game model.

[0089] The weather forecast data further includes extreme weather warning information, such as high temperature red warning, heavy rain warning, etc., for measuring the peak regulation pressure of the power grid, so as to determine the adjustable power range of the air conditioning system.

[0090] The electricity cost weight is used to represent the influence degree of air conditioning load on the economy and stability of the power grid at different time periods, including the cost weight reflecting the price sensitivity and power grid load demand.

[0091] The electricity cost weight includes time-of-use electricity price and peak regulation power range; the time-of-use electricity price includes the electricity price of each time period; and the peak regulation power range represents the operation power range of the air conditioning system.

[0092] The electricity cost weight is calculated based on the electricity price data and the weather forecast data, and specifically includes:

[0093] Based on the electricity price data, different time periods are divided in the future 24 hours, and the electricity price of each time period is recorded to obtain the time-of-use electricity price.

[0094] Based on the preset peak regulation power strategy, the extreme weather warning information is mapped to the peak regulation power range.

[0095] The peak regulation power strategy is as follows: based on the extreme weather warning information, the peak regulation emergency level is determined; for example, the peak regulation emergency level corresponding to the red warning is high emergency, and the peak regulation emergency level corresponding to the yellow warning is low emergency; based on the preset peak regulation power rule, the peak regulation emergency level is mapped to the peak regulation power range. For example, the peak regulation power range corresponding to the high emergency is not more than 70% of the rated power, indicating that under the weather condition of high emergency, the maximum operation power of the air conditioning system is 70% of the rated power.

[0096] The three-dimensional game model is solved by a multi-objective equilibrium algorithm to generate and execute the control instruction of the air conditioning system.

[0097] The adjustment object of the control instruction of the air conditioning system includes an air conditioning temperature set value, an air supply amount, a compressor start-stop timing, a compressor power, and a fresh air system ventilation frequency of each control area.

[0098] The three-dimensional game model is solved by a multi-objective balancing algorithm, specifically including:

[0099] Based on the first game target, the second game target, and the third game target, an optimization target and a constraint condition are generated; the optimization target includes: maximizing the heat buffer time window; minimizing the humidity offset; minimizing the total power consumption; wherein the humidity offset is an offset of the humidity of the control area from the humidity fluctuation interval. Maximizing the heat buffer time window can reduce the number of air conditioner start-stop times, thereby reducing power consumption. The humidity offset as a soft constraint participates in constructing the optimization target, allowing the humidity to deviate from the humidity fluctuation interval to a certain extent, but the offset needs to be controlled; minimizing the total power consumption can reduce energy consumption while reducing the operation pressure of the power grid.

[0100] The specific constraint term of the constraint condition includes: the temperature of the control area is within the temperature threshold interval; the carbon dioxide concentration is less than the carbon dioxide concentration limit value; and the operation power of the air conditioning system is within the peak regulation power range. The temperature needs to be strictly controlled within the temperature threshold interval to meet the comfort requirement; the carbon dioxide concentration needs to be less than the limit value, otherwise the fresh air system needs to be triggered for ventilation; and the operation power of the air conditioning system is limited according to the peak regulation power range to prevent excessive regulation.

[0101] An optimal solution set of the adjustment object of the control instruction is generated by a multi-objective balancing algorithm;

[0102] The application preferably generates an optimal solution set of the adjustment object of the control instruction by the NSGA-II algorithm, specifically including:

[0103] The adjustment objects of multiple groups of control instructions are encoded as decision variables; any group of adjustment objects constitutes a group of solutions;

[0104] Based on each group of adjustment objects, variables corresponding to each optimization target and each constraint term are calculated; wherein,

[0105] The heat buffering time window is calculated based on the air supply volume; the air supply volume, the fresh air system air exchange frequency, and the outdoor humidity are combined to calculate the humidity of the control area, and then the humidity offset is calculated; the higher the air supply volume, the higher the dehumidification efficiency; the fresh air system air exchange frequency introduces outdoor air, and the outdoor humidity is combined to calculate the humidity of the control area. The air conditioning system running power is calculated based on the compressor power, the air supply volume, and the fresh air system air exchange frequency, and the total electricity cost can be calculated based on the time-of-use electricity price. The variables corresponding to the constraint terms include the temperature of the control area, the carbon dioxide concentration, and the running power of the air conditioning system; the temperature of the control area is calculated based on the air conditioning temperature set value, the air supply volume, and the heat balance equation. The carbon dioxide concentration is calculated based on the fresh air system air exchange frequency and the air supply volume, and a carbon dioxide diffusion model can be constructed based on the Fick law. The running power of the air conditioning system is calculated based on the compressor power, the air supply volume, and the fresh air system air exchange frequency, and the energy consumption curve of each device is combined to calculate the running power.

[0106] Preferably, the calculation of each optimization objective and the variable corresponding to each constraint term is simulated and verified by a simulation tool, for example, the relationship between the air supply volume and the temperature and humidity of the control area is calibrated by CFD simulation.

[0107] Each set of solutions is screened based on the optimization objectives and the constraints to generate a non-dominated solution set as the optimal solution set. The quality of the solutions is evaluated according to the optimization objectives, and solutions that do not satisfy all the constraint terms are removed based on the variables of the constraint terms, for example, if the temperature of the control area is not within the temperature threshold interval, the constraint term is not satisfied. The non-dominated solution set is a Pareto optimal solution set, and each set of solutions in the Pareto optimal solution set represents a different trade-off scheme for the three optimization objectives of the heat buffering time window, the humidity offset, and the total electricity cost, and the solutions are not dominated by each other (i.e., cannot be better in one optimization objective without sacrificing other optimization objectives).

[0108] Based on the preset game target priority, a final execution solution is screened from the optimal solution set;

[0109] The preferred part of the game target priority in this embodiment is as follows: different game target priorities are triggered according to the current scene, for example, if the personnel density level of the current control area is high density, the priority of minimizing the humidity offset is the highest, the priority of maximizing the heat buffering time window is the second, and the priority of minimizing the total electricity cost is the lowest, so as to ensure the comfort of the personnel as much as possible. The final execution solution that best meets the game target priority is screened from the optimal solution set.

[0110] The control instructions of the air conditioning system corresponding to the final execution solution are analyzed. The final execution solution is converted into the air conditioning temperature set value, the air supply volume, the compressor start-stop sequence, the compressor power, the fresh air system air exchange frequency, and the control instructions of the air conditioning system are generated to realize the multi-parameter regulation and control of the air conditioning energy-saving optimization control.

[0111] Embodiment 2

[0112] This embodiment is the second embodiment of the present application; based on the same inventive concept as Embodiment 1, refer to Figure 2 , this embodiment introduces a multi-parameter regulated air conditioning energy-saving optimization control system, which is composed of a data acquisition module, a model construction module, a game calculation module, an algorithm solving module, and an instruction execution module; wherein:

[0113] The data acquisition module is used to acquire environmental data, including acquiring building information model data, indoor environmental data, electricity price data, and meteorological prediction data; this module extracts wall thermal parameters and spatial geometric data from BIM software; measures historical temperature, air supply, historical heat load, carbon dioxide concentration, thermal imaging data, real-time temperature, and real-time humidity of each control area; obtains meteorological prediction data through meteorological API and records electricity price data, providing a basis for subsequent analysis and decision-making.

[0114] The model construction module constructs a three-dimensional game model for air conditioning energy-saving optimization control based on the environmental data. This module determines the three game objectives of the three-dimensional game model by calculating the heat buffer potential, comfort demand interval, and electricity cost weight, providing a model framework for realizing air conditioning energy-saving optimization control.

[0115] The game calculation module is used to calculate the first game objective, the second game objective, and the third game objective of the three-dimensional game model; this module uses the buffer time prediction model to calculate the basic heat buffer potential, and combines historical temperature, historical heat load, and air supply to correct and adjust it to obtain the heat buffer time window of each control area; determines the personnel density level according to the carbon dioxide concentration and thermal imaging data, predicts the temperature and humidity changes with the help of the temperature and humidity prediction model, combines the reference comfort demand interval, and adjusts the actual comfort demand interval according to the personnel density level and temperature and humidity change rate; determines the time-of-use electricity price according to the electricity price data, and determines the peak shaving power range according to the extreme weather warning information and peak shaving power strategy, thereby obtaining the electricity cost weight.

[0116] The algorithm solving module is used to solve the three-dimensional game model and generate the final execution solution of the air conditioning system control instruction; this module takes maximizing the heat buffer time window, minimizing the humidity deviation, and minimizing the total electricity cost as the optimization objective, takes the temperature, carbon dioxide concentration, and air conditioning system running power limit of the control area as the constraint condition, and generates the final execution solution that best meets the current scene demand through the multi-objective equilibrium algorithm and the preset game objective priority.

[0117] The instruction execution module is configured to parse the final execution solution, acquire and execute the control instruction of the air conditioning system. The control instruction is used to adjust the air conditioning temperature setting value, air supply volume, compressor start-stop timing, compressor power, fresh air system ventilation frequency, and realize multi-parameter regulation and control of the air conditioning energy-saving optimization control.

[0118] The specific function implementation of each module is described in the multi-parameter regulation and control of the air conditioning energy-saving optimization control method of the embodiment 1, and is not described herein.

[0119] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer usable program code.

[0120] The embodiments of the present application are described above in combination with the drawings, but the present application is not limited to the above specific embodiments, and the above specific embodiments are only illustrative but not restrictive. Those skilled in the art can make many forms under the inspiration of the present application without departing from the purpose and the protected scope of the present application, and these are all within the protection of the present application.

Claims

1. An air conditioning energy-saving optimization control method based on multi-parameter regulation, characterized in that: The method comprises the following steps: obtaining environment data; the environment data comprises building information model data, indoor environment data, electricity price data, and meteorological prediction data; based on the environment data, constructing a three-dimensional game model for air conditioning energy-saving optimization control; specifically comprising: calculating heat buffer potential based on the building information model data and the indoor environment data as the first game target of the three-dimensional game model; calculating heat buffer potential based on the building information model data and the indoor environment data, specifically comprising: mapping wall thermal parameters and space geometry data to basic heat buffer potential of each control area based on a pre-trained buffer time prediction model; the input of the buffer time prediction model is a feature vector composed of wall thermal parameters and space geometry data, and the output is the basic heat buffer potential of the corresponding control area; the basic heat buffer potential is a reference value of the heat buffer time window; correcting the basic buffer potential based on historical temperature and historical heat load to obtain corrected heat buffer potential; specifically comprising: calculating the temperature change rate of the control area based on the historical temperature; correcting the basic buffer potential of the control area based on the temperature change rate to obtain the corrected heat buffer potential; further adjusting the corrected heat buffer potential based on the air supply volume to obtain the heat buffer time window of each control area; specifically comprising: adjusting the corrected heat buffer potential based on a preset adjustment rule to obtain the heat buffer time window, wherein the heat buffer time window is negatively correlated with the air supply volume; calculating the comfort requirement interval based on the indoor environment data and the meteorological prediction data as the second game target of the three-dimensional game model; the indoor environment data comprises carbon dioxide concentration, thermal imaging data, real-time temperature, and real-time humidity of each control area; the meteorological prediction data comprises outdoor temperature, outdoor humidity, and light intensity; the comfort interval comprises a temperature threshold interval, a humidity fluctuation interval, and a carbon dioxide concentration limit value; wherein the temperature threshold interval represents the temperature change range of each control area; the humidity fluctuation interval represents the humidity change value range of each control area; the carbon dioxide concentration limit value represents the maximum threshold value of the carbon dioxide concentration of each control area; calculating the comfort requirement interval based on the indoor environment data and the meteorological prediction data, specifically comprising: determining the personnel density level of each control area based on the carbon dioxide concentration and the thermal imaging data; predicting the temperature change and humidity change of each control area based on the real-time temperature, real-time humidity, outdoor temperature, outdoor humidity, and light intensity; setting a reference comfort requirement interval for each control area; adjusting the reference comfort requirement interval based on the temperature change, humidity change, and personnel density level of the control area to obtain the comfort requirement interval of each control area; calculating the electricity cost weight based on the electricity price data and the meteorological prediction data as the third game target of the three-dimensional game model; solving the three-dimensional game model through a multi-objective equilibrium algorithm to generate and execute control instructions of the air conditioning system.

2. The multi-parameter regulation based air conditioning energy-saving optimization control method according to claim 1, characterized in that: The building information model data comprises wall thermal parameters and space geometry data; the wall thermal parameters comprise thermal conductivity, specific heat capacity and density; the space geometry data comprises volume, wall surface area, wall thickness and connectivity of adjacent control areas of each control area; The indoor environment data comprises historical temperature, air supply volume and historical heat load of each control area; the heat buffer potential is represented by a heat buffer time window; the heat buffer time window represents the maximum duration for each control area to maintain the current temperature in the case of air conditioner shutdown.

3. The multi-parameter regulation based air conditioning energy-saving optimization control method according to claim 2, characterized in that: The personnel density level of each control area is determined based on the carbon dioxide concentration and thermal imaging data, specifically comprising: setting a carbon dioxide concentration threshold and a number threshold; detecting the number of people in each control area based on the thermal imaging data; if the carbon dioxide concentration of any control area is greater than the carbon dioxide concentration threshold and the number of people is greater than the number threshold, the personnel density level of the corresponding control area is high density; if the carbon dioxide concentration of any control area is not greater than the carbon dioxide concentration threshold, or the number of people is not greater than the number threshold, the personnel density level of the corresponding control area is medium density; if the carbon dioxide concentration of any control area is less than a preset minimum threshold or the number of people is 0, the personnel density level of the corresponding control area is low density.

4. The multi-parameter regulation based air conditioning energy-saving optimization control method of claim 3, wherein: The weather forecast data further comprises extreme weather warning information; the electricity cost weight comprises time-of-use electricity price and peak shaving power range; the time-of-use electricity price comprises electricity price of each time period; the peak shaving power range represents the operating power range of the air conditioning system; The electricity cost weight is calculated based on the electricity price data and weather forecast data, specifically comprising: Based on the electricity price data, the next 24 hours are divided into different time periods, and the electricity price of each time period is recorded to obtain the time-of-use electricity price; Based on a preset peak shaving power strategy, the extreme weather warning information is mapped to the peak shaving power range.

5. The multi-parameter regulation based air conditioning energy-saving optimization control method of claim 4, wherein: The adjustment object of the control instruction of the air conditioning system comprises air conditioning temperature set value, air supply volume, compressor start-stop time sequence, compressor power and fresh air system ventilation frequency of each control area; The three-dimensional game model is solved by a multi-objective balancing algorithm, specifically comprising: Based on the first game target, the second game target and the third game target, an optimization target and a constraint condition are generated; An optimal solution set of the control instruction adjustment object is generated by a multi-objective balancing algorithm; Based on a preset game target priority, a final execution solution is selected from the optimal solution set; The control instruction of the air conditioning system corresponding to the final execution solution is analyzed.

6. The multi-parameter regulation based air conditioning energy-saving optimization control method of claim 5, wherein: The optimization target comprises: maximizing the heat buffer time window; minimizing the humidity offset; minimizing the total electricity cost; wherein the humidity offset is the offset of the humidity of the control area from the humidity fluctuation interval; The specific constraint term of the constraint condition comprises: the temperature of the control area is within the temperature threshold interval; the carbon dioxide concentration is less than the carbon dioxide concentration limit value; the operating power of the air conditioning system is within the peak shaving power range.

7. The air conditioning energy-saving optimization control system based on multi-parameter regulation, which is used for realizing the air conditioning energy-saving optimization control method based on multi-parameter regulation as claimed in any one of claims 1-6, characterized in that: It comprises a data acquisition module, a model construction module, a game calculation module, an algorithm solving module and an instruction execution module; wherein: The data acquisition module is configured to acquire environment data, including acquiring building information model data, indoor environment data, electricity price data, and meteorological prediction data; The model construction module is configured to construct a three-dimensional game model for air conditioning energy-saving optimization control based on the environment data; The game calculation module is configured to calculate a first game target, a second game target, and a third game target of the three-dimensional game model; The algorithm solving module is configured to solve the three-dimensional game model to generate a final execution solution of the air conditioning system control instruction; The instruction execution module is configured to parse the final execution solution to acquire and execute the control instruction of the air conditioning system.

Images