Method, device and equipment for heating, ventilation and air conditioning control based on heat exchange amount prediction and medium

Abstract

The application discloses a heating, ventilation and air conditioning control method and device based on heat exchange amount prediction, equipment and medium, relates to the air conditioning control technical field, and the method comprises the following steps: according to historical time series data and weather forecast data in a future setting time period, a time series prediction model is used to predict the heat exchange amount in the future setting time period; the heat exchange amount in the future setting time period and the supply and return water temperature difference setting interval are used to calculate the circulating water amount in the future setting time period; the heat exchange amount in the future setting time period, the circulating water amount and the weather forecast data are used to predict the set water supply temperature in the future setting time period; based on the set water supply temperature in the future setting time period, an optimization algorithm is used to determine the air conditioning unit control scheme in the future setting time period with the minimum total energy consumption as the target; when the air conditioning host is controlled in real time, the current air conditioning unit control scheme is adjusted through real-time self-correction. The application improves the energy-saving efficiency and control accuracy.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of air conditioner control, in particular to an air conditioning control method and device based on heat exchange prediction, equipment and medium. BACKGROUND

[0002] Most related air conditioning systems are controlled based on fixed parameters, such as constant water flow or fixed temperature set point. This method has the following problems: 1. Energy waste: unable to dynamically adjust parameters according to actual demand, resulting in excessive heating or cooling; 2. Low running efficiency: equipment runs at high load for a long time, which easily causes component wear and tear and high energy consumption; 3. Poor adaptability: unable to meet flexible demands in different time periods and different scenarios. SUMMARY

[0003] The application aims to provide an air conditioning control method and device based on heat exchange prediction, which improves energy saving efficiency and control accuracy.

[0004] To achieve the above-mentioned purpose, the application provides the following solutions.

[0005] In a first aspect, the application provides an air conditioning control method based on heat exchange prediction, which comprises the following steps:

[0006] Collecting historical time series data of an air conditioner host and weather forecast data in a future set time period;

[0007] According to the historical time series data and weather forecast data in the future set time period, a time series prediction model is used to predict the heat exchange in the future set time period;

[0008] According to the relationship between the supply and return water temperature difference, the circulating water volume and the heat exchange, the heat exchange in the future set time period and the supply and return water temperature difference setting interval are used to calculate the circulating water volume in the future set time period;

[0009] The heat exchange, circulating water volume and weather forecast data in the future set time period are input into a set water supply temperature prediction model to obtain the set water supply temperature in the future set time period;

[0010] Based on the set water supply temperature in the future set time period, an optimization algorithm is used to minimize the total energy consumption as the target, and an air conditioning unit control scheme in the future set time period is output; the air conditioning unit control scheme includes air conditioning unit activation state and variable frequency compressor operating parameters;

[0011] When the air conditioning unit control scheme is used to control the air conditioning host, the circulating water volume, the set water supply temperature, the air conditioning unit activation state and the variable frequency compressor operation parameter of the air conditioning host are calculated in real time according to real-time return data and weather interface data of the current period, and the current air conditioning unit control scheme is adjusted according to the calculation result.

[0012] Optionally, the time series prediction model and the set water supply temperature prediction model are iteratively trained by using a reinforcement learning algorithm according to historical operation data of the air conditioning host, wherein the historical operation data includes predicted heat exchange, actual heat exchange, total energy consumption and operation parameters of the air conditioning unit and the heating and ventilation pump; the action in the training process includes the circulating water volume, the set return water temperature and the operation parameters of the air conditioning unit activation state and the variable frequency compressor; and the target of the reward function in the training process is to minimize the total energy consumption.

[0013] Optionally, the historical time series data of the air conditioning host are collected, specifically including:

[0014] The historical data of the supply and return water temperature and the circulating water volume of the air conditioning host are collected.

[0015] The heat exchange is calculated according to the product of the supply and return water temperature difference and the circulating water volume.

[0016] The calculated heat exchange and the historical weather data are statistically aligned according to a uniform interval time dimension, and the data are cleaned by using a data cleaning method to obtain the historical time series data marked in the time dimension; the time series features of the historical time series data include hour, week, month, quarter and holiday.

[0017] Optionally, the heat exchange in the future set period is a probability interval of the heat exchange in the future set period.

[0018] Optionally, according to the relationship among the supply and return water temperature difference, the circulating water volume and the heat exchange, the circulating water volume in the future set period is calculated by using the heat exchange in the future set period and the set interval of the supply and return water temperature difference, specifically including:

[0019] According to the relationship among the supply and return water temperature difference, the circulating water volume and the heat exchange, the probability interval of the circulating water volume in each period in the future set period is obtained by using the probability interval of the heat exchange in the future set period and the set interval of the supply and return water temperature difference.

[0020] The circulating water volume probability curve is generated according to the probability interval of the circulating water volume in each period in the future set period.

[0021] According to the circulating water quantity probability curve, by a linear programming optimization algorithm, the circulating water quantity in the future setting time period is obtained by minimizing the heating and ventilation water pump energy consumption on the basis of meeting the set heat exchange demand and water supply temperature constraint.

[0022] Optionally, the time series prediction model is a long short-term memory network, a Prophet model or an autoregressive moving average model; and the set water supply temperature prediction model is a back propagation neural network.

[0023] Optionally, the optimization algorithm is a particle swarm optimization, a genetic annealing algorithm, a mixed integer programming or a decision tree algorithm.

[0024] In a second aspect, the application provides a heating and ventilation air conditioner control device based on heat exchange quantity prediction, which applies the heating and ventilation air conditioner control method based on heat exchange quantity prediction.

[0025] A data acquisition module is configured to acquire historical time series data of an air conditioner host and weather forecast data in a future setting time period;

[0026] A heat exchange quantity prediction module is configured to use a time series prediction model to predict the heat exchange quantity in the future setting time period based on the historical time series data and the weather forecast data in the future setting time period;

[0027] A circulating water quantity calculation module is configured to use the heat exchange quantity in the future setting time period and a set interval of supply and return water temperature difference to calculate the circulating water quantity in the future setting time period based on the relationship between the circulating water quantity and the heat exchange quantity and the supply and return water temperature difference;

[0028] A set water supply temperature prediction module is configured to input the heat exchange quantity, the circulating water quantity and the weather forecast data in the future setting time period into a set water supply temperature prediction model to obtain the set water supply temperature in the future setting time period;

[0029] An air conditioner unit control scheme optimization module is configured to use an optimization algorithm to output an air conditioner unit control scheme in the future setting time period based on the set water supply temperature in the future setting time period, with the minimum total energy consumption as the target; the air conditioner unit control scheme includes an air conditioner unit activation state and a variable frequency compressor operating parameter;

[0030] A deviation correction module is configured to perform real-time self-correction calculation on the circulating water quantity, the set water supply temperature, the air conditioner unit activation state and the variable frequency compressor operating parameter of the air conditioner host based on real-time return data and weather interface data when the air conditioner host is controlled by the air conditioner unit control scheme, and adjust the current air conditioner unit control scheme according to the calculation result.

[0031] In a third aspect, the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the heat exchange amount prediction based HVAC control method according to any one of the preceding aspects.

[0032] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, wherein the computer program is executable on a processor to implement the steps of the heat exchange amount prediction based HVAC control method according to any one of the preceding aspects.

[0033] According to the embodiments provided in the present application, the following technical effects are disclosed.

[0034] The present application provides a heat exchange amount prediction based HVAC control method, device, equipment and medium, according to the historical time series data and the weather forecast data in the future setting time period, using a time series prediction model, rolling prediction of the heat exchange amount in the future setting time period, predicting the setting water temperature based on the rolling prediction, taking the minimum total energy consumption as the target, using an optimization algorithm to output the air conditioning unit control scheme in the future setting time period, thereby reducing energy waste, improving energy efficiency, in addition, according to the real-time feedback data, the current running control scheme is calculated in real time, and the control strategy is adjusted in time, thereby improving the control precision. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0036] Figure 1 A flowchart of a heat exchange amount prediction based HVAC control method provided by an embodiment of the present application.

[0037] Figure 2 A structural schematic diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0039] The above objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings and specific embodiments.

[0040] The present application provides a heat exchange amount prediction-based HVAC control method, as shown in Figure 1 The heat exchange amount prediction-based HVAC control method comprises the following steps:

[0041] Step 101: Collecting historical time series data of an air conditioning host and weather forecast data in a future set time period.

[0042] Step 102: According to the historical time series data and the weather forecast data in the future set time period, using a time series prediction model to rollingly predict the heat exchange amount in the future set time period.

[0043] Step 103: According to the relationship among the supply and return water temperature difference, the circulating water amount and the heat exchange amount, using the heat exchange amount in the future set time period and the supply and return water temperature difference setting interval to calculate the circulating water amount in the future set time period.

[0044] Step 104: Inputting the heat exchange amount, the circulating water amount and the weather forecast data in the future set time period into a set supply water temperature prediction model to obtain the set supply water temperature in the future set time period.

[0045] Step 105: Based on the set supply water temperature in the future set time period, using an optimization algorithm to output an air conditioning unit control scheme in the future set time period with the minimum total energy consumption as the target; the air conditioning unit control scheme comprises an air conditioning unit enabling state and a variable frequency compressor operating parameter.

[0046] Step 106: When the air conditioning host is controlled by using the air conditioning unit control scheme, according to real-time return data and weather interface data in the current period, performing real-time self-correction calculation on the circulating water amount, the set supply water temperature, the air conditioning unit enabling state and the variable frequency compressor operating parameter of the air conditioning host, and adjusting the current air conditioning unit control scheme according to the calculation result.

[0047] The time series prediction model and the set water supply temperature prediction model are iteratively trained according to historical operation data of the air conditioner host by using a reinforcement learning algorithm, wherein the historical operation data includes predicted heat exchange, actual heat exchange, total energy consumption, and operation parameters of the air conditioning unit and the heating and water pump; the adjustment action of the control strategy in the training process includes circulating water quantity, set return water temperature, and operation parameters of the air conditioning unit and the variable frequency compressor; and the target of the reward function in the training process is to minimize the total energy consumption. The model is iteratively trained by the reinforcement learning algorithm, the energy consumption of the control scheme is evaluated, the circulating water quantity prediction and the control strategy of the air conditioning unit are optimized, and through continuous reinforcement learning, the regulation and control strategy is optimized, so that the energy efficiency of the air conditioning system is continuously optimized.

[0048] The target function of the total energy consumption is:

[0049] Wherein, c i is the comprehensive energy consumption of the i th heating and water pump, x i is the coefficient of the i th heating and water pump, the target function of the total energy consumption includes flow, water pressure, pump efficiency, pump starting energy consumption, pump starting time length, maintenance and other constraints. N is the number of pumps.

[0050] ①Flow constraint factor:

[0051] Wherein, Q i is the flow of the i th heating and water pump, Q pre is the predicted total water supply, Q max is the maximum allowable water quantity.

[0052] ②Water pressure constraint factor:

[0053] Wherein, P i is the water pressure of the i th heating and water pump, P pre is the predicted water pressure, P max is the maximum allowable water pressure.

[0054] ③Optimal efficiency factor:

[0055] Wherein, η i is the efficiency of the i th pump, η min is the expected minimum efficiency.

[0056] ④Pump starting energy consumption factor:

[0057] Wherein, E start_i is the pump starting energy consumption of the i th pump, E start_max is the maximum pump starting energy consumption limit.

[0058] ⑤Pump starting time length factor:

[0059] wherein T start_i is the on time of the i-th pump, T start_min is the minimum on time of a single cycle, T start_max is the maximum on time of a single cycle.

[0060] (6) Maintenance factor:

[0061] wherein F i is the running time of the i-th pump within a maintenance cycle, F max is the maximum maintenance cycle.

[0062] The minimum value of the sum of the pump comprehensive energy consumption needs to be calculated according to the above.

[0063] The application utilizes time series prediction algorithm, optimization algorithm, deep learning and reinforcement learning technology, and models and predicts and optimizes the control of the operation parameters of the heating and ventilation air conditioning unit and the heating and ventilation pump.

[0064] In an exemplary embodiment, the future setting time period is 24 hours in the future. The application first collects the air conditioning host supply and return water temperature, circulating water quantity and weather forecast data through sensors, uses a time series prediction algorithm to build a model to predict the heat exchange capacity in the next 24 hours. Then, according to the prediction result of the heat exchange capacity, the circulating water quantity of the heating and ventilation pump in the next 24 hours is dynamically planned to ensure that the system energy consumption is reduced while meeting the refrigeration / heat supply demand. In addition, because the heating and ventilation air conditioning system is a typical nonlinear time-varying system, in addition to the prediction result, the algorithm needs to combine the current data to adjust the circulating water quantity in real time, optimize the system operation parameters, realize dynamic correction and optimization control of the circulating water quantity of the heating and ventilation pump and the set return water temperature of the host, and provide further matching of the actual refrigeration / heat supply demand. The system supports multiple scene mode switching, and meets the different use scene demand through specific control strategy. At the same time, the reinforcement learning algorithm is used to continuously iterate the training model, optimize the control strategy, and realize higher energy efficiency.

[0065] In an exemplary embodiment, in step 101, the historical time series data of the air conditioning host is collected, specifically including:

[0066] The historical data of the supply and return water temperature and circulating water quantity of the air conditioning host is collected, specifically by collecting the supply and return water temperature and circulating water quantity of the air conditioning host through sensors. The supply and return water temperature includes the supply water temperature and the return water temperature.

[0067] The heat exchange capacity is calculated according to the product of the supply and return water temperature difference and the circulating water quantity. The supply and return water temperature difference is the temperature difference between the supply water temperature and the return water temperature.

[0068] The interface is used to crawl historical weather data, including weather phenomena, outdoor temperature, wind power, ultraviolet intensity, and relative humidity. Weather phenomena are represented by parameters such as cloud, sunny, rain, or snow. In fact, the textual description of each weather representation parameter is converted to one of a set of numbers, such as 1 for sunny, 20 for cloudy, and 106 for rain and snow.

[0069] The calculated heat exchange and historical weather data are aligned in a unified time dimension, and data cleaning methods are used to clean the data, obtaining time-dimensionally labeled historical time series data, i.e., a standard time series data set. The time series features of the historical time series data include hour, week, month, quarter, and holiday.

[0070] More specifically, step 101 includes: the central control system computer of the heating, ventilation and air conditioning system collects and stores key data required for system operation through sensors and network interfaces. The key data includes the supply water temperature T in and return water temperature T out of the air conditioning host, the heating pump circulating water volume Q l , the heating pump frequency F, the expansion valve opening degree L, the pump energy consumption Q w , the total energy consumption Q0, in addition to weather interface collected data such as outdoor temperature T w , weather phenomena W h , ultraviolet index grade UV, wind power W D , relative humidity f e , etc. The stored raw data is statistically processed according to different rules in the dimensions of minutes, hours, days, etc. The statistical rules include maximum value Max, minimum value Min, average value Avg, difference value Sub, etc. The statistical data is stored together with the raw data in the database of the central control system computer server.

[0071] The statistical multi-factor data is aligned in a continuous time sequence in order, and the actual heat exchange Q c (t) is calculated using the supply water temperature T s (t) and return water temperature T r (t) of the host at each time period t, and the heating pump circulating water volume Q l (t).

[0072] The calculation formula of the actual heat exchange is: Q c (t) = ΔT(t)·Q l (t)·ρ·c p = (T s (t) - T r (t))·Q l (t)·ρ·c p .

[0073] wherein, AT(t) is the supply and return water temperature difference, p is the density of the heat transfer fluid, c p is the specific heat capacity of the heat transfer fluid.

[0074] Then the abnormal noise data is cleaned by a data cleaning method, the data cleaning method includes data interpolation, data deduplication, and data conversion, the data interpolation method includes median interpolation, normal mean filling, Bezier interpolation, regression prediction filling, etc., the data deduplication method includes clustering deduplication, logical deduplication, and weighted average value merging deduplication, etc., and the data conversion method includes field standardization, merging of synonymous items, and data normalization, etc. After the data cleaning method, the time dimension of the time series data is marked, the marked time series features include hours, weeks, months, quarters, and whether it is a holiday, etc., to obtain a standard time series data sample set.

[0075] In an exemplary embodiment, the time series prediction model is a Long Short-Term Memory (LSTM) model, a Prophet model, or an Autoregressive Moving Average (ARMA) model. The time series prediction model predicts the heat exchange Q c (t) pred in the future 24 hours according to the time series feature information in the future 24 hours and the weather forecast data in the future 24 hours.

[0076] In an exemplary embodiment, step 102 specifically includes: according to the historical time series data and the weather forecast data in the future 24 hours, adopting a time series prediction model to predict the heat exchange in the future 24 hours, the heat exchange in the future setting time period is a probability interval of the heat exchange in the future setting time period, that is, the predicted heat exchange is a probability interval. The heat exchange in the future setting time period is time series data composed of heat exchanges in multiple time periods.

[0077] In an exemplary embodiment, step 103 specifically includes:

[0078] According to the relationship between the supply and return water temperature difference, the circulating water volume, and the heat exchange, the probability interval of the circulating water volume in each time period in the future setting time period is obtained by adopting the probability interval of the heat exchange in the future setting time period and the supply and return water temperature difference setting interval.

[0079] The circulating water volume probability curve is generated according to the probability interval of the circulating water volume in each time period in the future setting time period.

[0080] According to the circulating water quantity probability curve, by using a linear programming optimization algorithm, the circulating water quantity in the future setting time period is obtained by minimizing the heating and ventilation water pump energy consumption on the basis of meeting the set heat exchange demand and water supply temperature constraint, unnecessary circulating water quantity demand is reduced, and system energy consumption is reduced. The water supply temperature constraint is that the circulating water quantity is not lower than the minimum limit value.

[0081] More specifically, according to the heat exchange quantity prediction data of the future 24 hours, the median value 95% confidence interval is the minimum value of the confidence interval, is the maximum value of the confidence interval, and the set interval of the supply and return water temperature difference is designed as a typical experience interval, usually 5-10℃. According to the theoretical formula of the supply and return water temperature difference, circulating water quantity and heat exchange quantity, the circulating water quantity Q l (t) pred of each time period t in the future 24 hours is calculated. p The prediction probability interval is generated, and the future 24-hour heating and ventilation pump circulating water quantity probability curve is generated. By using a linear programming optimization algorithm, the heating and ventilation water pump energy consumption Q p (t) is minimized on the basis of meeting the heat exchange quantity demand and ensuring that the water supply temperature is not lower than the minimum limit value, so that unnecessary circulating water quantity demand is reduced, and system energy consumption is reduced. k is a constant.

[0082] In an exemplary embodiment, a neural network black box model, i.e., a set water supply temperature prediction model, is established by taking heat exchange quantity, circulating water quantity and weather factors as inputs and taking set water supply temperature as output. According to the predicted heat exchange quantity and circulating water quantity data in the future 24 hours and the future 24-hour weather forecast data, the set water supply temperature of the air conditioning unit in the future 24 hours is obtained. The neural network black box model is a back propagation (BP) neural network.

[0083] In an exemplary embodiment, step 105 specifically includes summarizing historical operation data of the air conditioning units, analyzing which units have higher operating efficiency and which units have lower operating efficiency under the same working condition by using unit operating power and unit energy consumption, and setting the activation priority of each machine according to the operating efficiency of the air conditioning units.

[0084] Based on the set water supply temperature in the future setting time period, an optimization algorithm is used to output the air conditioning unit control scheme in the future setting time period with the minimum total energy consumption as the target; the air conditioning unit control scheme includes the activation state of the air conditioning unit and the operating parameter of the variable frequency compressor. The operating parameter of the variable frequency compressor is the frequency or speed of the variable frequency compressor.

[0085] The air conditioning unit control scheme in the future setting time period is determined, i.e., which units should be enabled, which units should be kept in a closed state, and how the frequency or speed of the variable frequency compressor should be adjusted in the future setting time period, so as to achieve the goal of the lowest overall energy consumption, and realize the coordinated energy saving between the heating and ventilation water pump and the air conditioning unit.

[0086] In an exemplary embodiment, the optimization algorithm is a particle swarm optimization, a genetic annealing algorithm, a mixed integer programming, or a decision tree algorithm.

[0087] The present application uses historical operation data and corresponding energy consumption records, and through an optimization algorithm, the data is deeply learned and analyzed, and the relationship between system energy consumption and set water supply temperature, air conditioning unit enabling state, and variable frequency compressor frequency is summarized. The optimization model is based on future 24-hour set water supply temperature prediction data, pump group energy consumption performance, and weather factors (weather, outdoor temperature, wind, ultraviolet intensity, relative humidity, etc.), and automatically selects the optimal control decision of the air conditioning unit. The output result is how to adjust the air conditioning unit enabling state, running time, and variable frequency compressor frequency or speed in the future 24 hours, to generate a set of optimal control scheme of the air conditioning unit in the future 24 hours, so as to achieve the goal of the lowest overall energy consumption, and realize the coordinated energy saving between the circulating water pump and the unit. For example, in the case of low night usage, the system scheme will reduce the running frequency of the circulating water pump, and shut down part of the air conditioning host, and only maintain the minimum load demand of the core area, so as to greatly reduce the energy consumption.

[0088] In an exemplary embodiment, in step 106, the real-time feedback data includes the circulating water volume of the heating and ventilation water pump, the supply and return water temperature difference, the terminal panel set temperature, and the air conditioning unit energy consumption. The weather interface data includes weather phenomena, outdoor temperature, wind, ultraviolet intensity, and relative humidity. The current and future 24-hour operation scheme is automatically adjusted in real time, and the operation parameters of the entire system are re-controlled according to the calculation result, so as to realize the dynamic matching and optimization of the heat exchange capacity of the heating and ventilation air conditioning system, optimize the system performance, and reduce the system energy consumption.

[0089] The technical effects of the present application are as follows:

[0090] 1、The application significantly improves the energy efficiency of the heating, ventilation and air conditioning system through circulating water quantity adjustment and unit optimization. Traditional systems usually run at a constant refrigeration or heating capacity, which cannot be flexibly adjusted according to actual demand, easily leading to energy waste. The application combines time series prediction model, uses historical operation data and real-time weather information to accurately predict the heat exchange demand in the next 24 hours, dynamically adjusts the circulating water quantity of the heating pump and other operating parameters. For example, at the demand trough, the system will automatically reduce the circulating water quantity and heat exchange capacity, thereby avoiding excessive refrigeration or heating; at the demand peak, the system will optimize the operation strategy in advance to ensure efficient heating or cooling. By adjusting the circulating water quantity and unit power, unnecessary energy loss is reduced. This demand-driven control method makes the system meet the demand while minimizing energy waste, with energy efficiency improved by more than 20% compared with traditional systems.

[0091] 2、The application realizes a significant improvement in control accuracy through real-time self-correction adjustment and reinforcement learning. The real-time self-correction adjustment module is based on real-time operation data of the heating pump, combined with weather phenomena, outdoor temperature and other variables, to dynamically control the circulating water quantity of the heating pump. This closed-loop control mechanism can quickly respond to environmental and load changes, ensuring that the operating parameters are always highly matched with actual demand. In addition, the reinforcement learning model optimizes the control strategy of the air conditioning host through continuous training and learning of historical operation data, enabling the system to adapt to complex operating scenarios and find the optimal regulation scheme. Compared with traditional fixed rule control methods, the application not only improves control accuracy, but also effectively reduces energy consumption, enhancing the reliability and stability of the system.

[0092] 3、The application adds weather and holiday information heat exchange prediction. Traditional heating, ventilation and air conditioning systems often use a single operating mode, making it difficult to flexibly respond to demand changes in different time periods or special scenarios. The application can adapt to multiple scenarios, including weekdays, holidays, night, rainy and snowy days, and provides different scenario control strategies. For example, during holidays, the system preferentially reduces the load of non-essential areas and only maintains basic operating requirements; during peak demand periods, the system quickly increases circulating water quantity and heat exchange capacity to meet large-scale centralized refrigeration / heating demand. Ensuring that the air conditioning system can adjust operating parameters according to actual usage scenarios, thereby more efficiently and flexibly meeting demand and improving user experience.

[0093] 4、The application effectively reduces the excess energy consumption through accurate prediction and dynamic regulation under the premise of meeting the heat exchange demand. For example, the system continuously learns and evaluates the energy consumption of the control scheme. In the case of low usage at night, the system reduces the operating frequency of the circulating water pump and turns off part of the air conditioning host, and only maintains the minimum load demand of the core area, thereby greatly reducing the energy consumption. At the same time, the reinforcement learning module continuously optimizes the system operating parameters, reduces the unnecessary running time of the equipment, reduces the wear and tear of mechanical parts, and prolongs the service life of the equipment. Compared with the traditional system, the application not only significantly reduces the operating cost, but also reduces the maintenance cost, thereby bringing higher economic benefits to the user.

[0094] Based on the same inventive concept, the application also provides a heat exchange amount prediction-based HVAC control device for implementing the heat exchange amount prediction-based HVAC control method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more heat exchange amount prediction-based HVAC control device embodiments provided below can refer to the limitations of the heat exchange amount prediction-based HVAC control method described above, which will not be repeated here.

[0095] In one exemplary embodiment, the application provides a heat exchange amount prediction-based HVAC control device that applies the heat exchange amount prediction-based HVAC control method described above. The heat exchange amount prediction-based HVAC control device comprises:

[0096] A data acquisition module is configured to acquire historical time series data of the air conditioning host and weather forecast data in a future set time period.

[0097] A heat exchange amount prediction module is configured to use a time series prediction model to predict the heat exchange amount in the future set time period based on the historical time series data and the weather forecast data in the future set time period.

[0098] A circulating water amount calculation module is configured to calculate the circulating water amount in the future set time period based on the relationship between the circulating water amount, the heat exchange amount, and the supply and return water temperature difference, the heat exchange amount in the future set time period, and the supply and return water temperature difference setting interval.

[0099] A set supply water temperature prediction module is configured to input the heat exchange amount, the circulating water amount, and the weather forecast data in the future set time period into a set supply water temperature prediction model to obtain the set supply water temperature in the future set time period.

[0100] The air conditioning unit control scheme optimization module is configured to adopt an optimization algorithm to output an air conditioning unit control scheme in a future setting time period based on a setting water supply temperature in the future setting time period, with the goal of minimizing total energy consumption; the air conditioning unit control scheme includes an air conditioning unit activation state and a variable frequency compressor operating parameter.

[0101] The deviation correction module is configured to perform real-time self-correction calculation on the circulating water volume, the setting water supply temperature, the air conditioning unit activation state, and the variable frequency compressor operating parameter of the air conditioning host based on real-time return data and weather interface data of the current time period when the air conditioning host is controlled based on the air conditioning unit control scheme, and adjust the current air conditioning unit control scheme based on the calculation result.

[0102] In an exemplary embodiment, a computer device, which can be a server or a terminal, is provided, and an internal structure diagram of the computer device can be as shown in Figure 2 The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store heating, ventilation, and air conditioning control data based on heat exchange prediction. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through a network connection. The computer program is executed by the processor to implement a heating, ventilation, and air conditioning control method based on heat exchange prediction.

[0103] Those skilled in the art can understand that Figure 2 The structure shown in the above is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. Specifically, the computer device can include more or fewer components than those shown in the diagram, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, and the memory stores a computer program. The processor executes the computer program to implement the steps in the above method embodiments.

[0104] In an exemplary embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0105] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0106] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to a memory, database or other medium used in the embodiments provided by the present application can include at least one of a non-volatile and volatile memory. The non-volatile memory can include a read-only memory (ROM), a magnetic tape, a floppy disk, a flash memory, an optical storage, a high-density embedded non-volatile memory, a resistive memory (ReRAM), a magnetoresistive random access memory (MRAM), a ferroelectric memory (FRAM), a phase change memory (PCM), a graphene memory, etc. The volatile memory can include a random access memory (RAM) or an external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), etc.

[0107] The database involved in the embodiments provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in the embodiments provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a data processing logic of a programmable logic device, etc., without being limited thereto.

[0108] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0109] The principles and implementations of the present application are described in the specific examples used herein, and the above examples are only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation and application range will be changed. Therefore, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A heating, ventilation, and air conditioning control method based on heat exchange amount prediction, characterized by, The HVAC control method based on heat exchange amount prediction comprises: collecting historical time series data of an air conditioning host and weather forecast data in a future set time period; using a time series prediction model to predict the heat exchange amount in the future set time period according to the historical time series data and the weather forecast data in the future set time period; calculating the circulating water amount in the future set time period according to the relationship among the supply-return water temperature difference, the circulating water amount and the heat exchange amount, the heat exchange amount in the future set time period and the supply-return water temperature difference set interval; inputting the heat exchange amount, the circulating water amount and the weather forecast data in the future set time period into a set supply water temperature prediction model to obtain the set supply water temperature in the future set time period; using an optimization algorithm to output an air conditioning unit control scheme in the future set time period based on the set supply water temperature in the future set time period, with the minimum total energy consumption as the target; the air conditioning unit control scheme comprises an air conditioning unit enabling state and a variable frequency compressor operating parameter; when the air conditioning unit control scheme is used to control the air conditioning host, real-time self-correction calculation is performed on the circulating water amount, the set supply water temperature, the air conditioning unit enabling state and the variable frequency compressor operating parameter of the air conditioning host according to real-time return data and weather interface data in the current period, and the current air conditioning unit control scheme is adjusted according to the calculation result; the heat exchange amount in the future set time period is a probability interval of the heat exchange amount in the future set time period; calculating the circulating water amount in the future set time period according to the relationship among the supply-return water temperature difference, the circulating water amount and the heat exchange amount, the heat exchange amount in the future set time period and the supply-return water temperature difference set interval, specifically comprising: obtaining the probability interval of the circulating water amount in each period in the future set time period according to the relationship among the supply-return water temperature difference, the circulating water amount and the heat exchange amount, the probability interval of the heat exchange amount in the future set time period and the supply-return water temperature difference set interval; generating a circulating water amount probability curve according to the probability interval of the circulating water amount in each period in the future set time period; obtaining the circulating water amount in the future set time period by linear programming optimization algorithm on the basis of meeting the set heat exchange demand and the supply water temperature constraint, wherein the supply water temperature constraint is that the circulating water amount is not lower than the minimum limit value.

2. The heat-exchange amount prediction-based HVAC control method according to claim 1, characterized by, The time series prediction model and the set supply water temperature prediction model are iteratively trained by using a reinforcement learning algorithm according to historical operation data of the air conditioning host, wherein the historical operation data comprises predicted heat exchange amount, actual heat exchange amount, total energy consumption and operating parameters of the air conditioning unit and the HVAC water pump; the actions in the training process comprise circulating water amount, set return water temperature and operating parameters of the air conditioning unit enabling state and the variable frequency compressor; and the target of the reward function in the training process is to minimize the total energy consumption.

3. The heat-exchange amount prediction-based HVAC control method according to claim 1, characterized by, The historical time series data of the air conditioning host is collected, specifically comprising: collecting historical data of the supply-return water temperature and the circulating water amount of the air conditioning host; calculating the heat exchange amount according to the product of the supply-return water temperature difference and the circulating water amount; The calculated heat exchange amount and historical weather data are statistically aligned according to a uniform interval time dimension, and data cleaning methods are used to clean the data, to obtain the time dimension marked historical time series data; the time series characteristics of the historical time series data include hours, weeks, months, quarters, and whether it is a holiday.

4. The heat-exchange amount prediction-based HVAC control method according to claim 1, characterized by, The time series prediction model is a long short-term memory network, a Prophet model, or an autoregressive moving average model; and the set water supply temperature prediction model is a back propagation neural network.

5. The heat-exchange amount prediction-based HVAC control method according to claim 1, characterized by, The optimization algorithm is a particle swarm optimization, a genetic annealing algorithm, a mixed integer programming, or a decision tree algorithm.

6. A heating, ventilation, and air conditioning control device based on heat exchange amount prediction, characterized by, The HVAC control device based on heat exchange amount prediction applies the HVAC control method based on heat exchange amount prediction in any one of claims 1-5, and comprises: a data acquisition module configured to acquire historical time series data of an air conditioning host and weather forecast data in a future set time period; a heat exchange amount prediction module configured to use a time series prediction model to predict the heat exchange amount in the future set time period based on the historical time series data and the weather forecast data in the future set time period; a circulating water amount calculation module configured to calculate the circulating water amount in the future set time period based on the relationship between the supply and return water temperature difference, the circulating water amount, and the heat exchange amount, and using the heat exchange amount in the future set time period and the supply and return water temperature difference setting interval; a set water supply temperature prediction module configured to input the heat exchange amount, the circulating water amount, and the weather forecast data in the future set time period into a set water supply temperature prediction model to obtain the set water supply temperature in the future set time period; an air conditioning unit control scheme optimization module configured to use an optimization algorithm to output an air conditioning unit control scheme in the future set time period based on the set water supply temperature in the future set time period, with the objective of minimizing total energy consumption; the air conditioning unit control scheme includes an air conditioning unit activation state and a variable frequency compressor operating parameter; a correction module configured to perform real-time self-correction calculation on the circulating water amount, the set water supply temperature, the air conditioning unit activation state, and the variable frequency compressor operating parameter of the air conditioning host based on real-time return data and weather interface data when the air conditioning host is controlled using the air conditioning unit control scheme, and adjust the current air conditioning unit control scheme according to the calculation result.

7. A computer device comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that the processor executes the computer program to implement the HVAC control method based on heat exchange amount prediction in any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the HVAC control method based on heat exchange amount prediction in any one of claims 1-5.

Images