A central air conditioning control strategy optimization method, system, computer device and storage medium

Abstract

The present application relates to a kind of central air conditioning control strategy optimization methods, specifically by multidimensional interpolation algorithm is used to fill the sparsity of control strategy library, the strategy simulation of central air conditioning system full working condition is realized, the dynamic optimization strategy of online dynamic simulation system operating condition is proposed, by the prediction of cooling load and the real-time measurement of outside temperature, relative humidity, online control strategy is provided, the defects that the current control strategy relies on the setting of expert experience operating mode to cause poor energy-saving effect, optimization strategy time is too long are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automatic control, and in particular to a central air conditioning control strategy optimization method and system, a computer device and a storage medium. BACKGROUND

[0002] In recent years, the central air conditioning system of large buildings is connected to the BAS for unified management, but the application of equipment rooms in the BAS is mostly simple logical control and data monitoring, with low automation and difficulty in realizing optimized operation. Since the central air conditioning system is in a partial load operation state for a long time in the actual operation process, and the operation condition is set according to the seasonal load change or working hours relying on expert experience, the data monitored by the BAS system in this stable operation state is a large amount of repeated actual operation data, causing the sparsity of operation data.

[0003] In actual application, the specific application environment of the central air conditioning system needs to be considered, including the influence of geographical location on temperature and humidity, system topology, the influence of the load and performance of each device on response, etc. The existing technology usually uses the operating parameters of the cold source system and environmental parameters as the control strategy of the working condition. For this control strategy optimization, there are two existing optimization strategy modes, one is offline optimization and the other is online optimization. For online optimization, due to the limitation of calculation speed (too long optimization time) and the time lag characteristics of the central air conditioning system, it is impossible to provide a strategy for the current working condition in real time, and frequent online strategy will reduce the service life of the equipment. For offline optimization, only a limited number of optimization control strategies under working conditions can be calculated in advance, and for the diversity of actual working conditions, the offline optimization strategy is sparse. Once the working condition changes slightly, the corresponding optimization control strategy cannot be found in the offline strategy library. SUMMARY

[0004] To solve the above technical problems, the present application provides a risk control method, system, server and storage medium.

[0005] A central air conditioning control strategy optimization method, the central air conditioning system includes a cold source system and a control system, the cold source system includes a plurality of chilled water pumps, a plurality of cooling water pumps, a plurality of cooling towers and a plurality of water chillers and a plurality of temperature sensors, humidity sensors and flow sensors, the control system includes a control strategy library, characterized in that the input of the control strategy library is the system cold load, the environmental temperature, the relative humidity, the chilled water supply temperature, the total flow of the chilled water system and the chilled water supply and return pressure difference, and the output of the control strategy library is the operating parameters of the cold source system, and the control strategy optimization method includes:

[0006] S10. Establish an expression model between the input and output of the control strategy, wherein the input is discretized according to its numerical range;

[0007] S20. Calculate the output of each interpolation by using the inverse distance weighted interpolation based on k-nearest neighbors for the discretized input parameters;

[0008] S30. Determine the optimal control strategy based on the output of each interpolation.

[0009] A central air conditioning control strategy optimization system, the central air conditioning comprising a cold source system and a control system, the cold source system comprising a plurality of chilled water pumps, a plurality of cooling water pumps, a plurality of cooling towers and a plurality of water chillers and a plurality of temperature sensors, humidity sensors and flow sensors, the control system comprising a control strategy library and a control strategy library optimization module, the input of the control strategy library being system cooling load, ambient temperature, ambient relative humidity, chilled water system supply water temperature, chilled water system total flow and chilled water system supply and return water pressure difference, the output of the control strategy library being the operating parameters of the cold source system, the control strategy library optimization module comprising:

[0010] A model establishment module for establishing an expression model between the input and output of the control strategy, wherein the input is discretized according to its numerical range;

[0011] An interpolation module for calculating the output of each interpolation by using the inverse distance weighted interpolation based on k-nearest neighbors for the discretized input parameters;

[0012] An optimization module for determining the optimal control strategy based on the output of each interpolation.

[0013] The present application has the following beneficial technical effects:

[0014] 1. The present application converts the online optimization which takes too long time into offline optimization by using the method of establishing offline strategy library, thereby improving the efficiency of seeking optimal strategy.

[0015] 2. The present application realizes the strategy simulation of the whole working condition of the central air conditioning system by using the multi-dimensional interpolation algorithm for the sparsity filling of the strategy library.

[0016] 3. The present application proposes a dynamic optimization strategy for simulating the running working condition of the online dynamic simulation system, and provides the control strategy online through the prediction of cooling load and the real-time measurement of outdoor dry bulb temperature and relative humidity.

[0017] 4. The present application proposes a strategy library comparison algorithm for selecting the best from the best, so as to select the most energy-saving strategy under the guarantee of the stability of actual operation.

[0018] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or recognized by practicing the application as described herein. BRIEF DESCRIPTION OF DRAWINGS

[0019] The above and / or additional aspects and advantages of the present application will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings in which:

[0020] Figure 1 A comparison chart of the to-be-inserted point and the grid node for the embodiment of the present application.

[0021] Figure 2 A chart for finding the upper and lower boundaries of the to-be-interpolated point for the embodiment of the present application.

[0022] Figure 3 A chart for dividing the grid node for the embodiment of the present application.

[0023] Figure 4 A flow chart for calculating and screening the optimal strategy for the embodiment of the present application.

[0024] Figure 5 A flow chart for optimizing the control strategy for the embodiment of the present application. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without any creative effort fall within the protection scope of the present application.

[0026] Generally, a central air conditioning system includes multiple chilled water pumps, multiple cooling water pumps, multiple cooling towers, and multiple water chillers, as well as multiple temperature sensors, humidity sensors, and flow sensors. The control strategy provided by a conventional central air conditioning cold source control system is generally static, and usually uses one or more combinations of the system cold load, the ambient temperature, the ambient relative humidity, the chilled water system supply water temperature, the chilled water system total flow, and the chilled water system supply and return water pressure difference as the input of the air conditioning system control strategy, and uses the on-off state and the corresponding operating frequency of each water chiller, chilled water pump, cooling water pump, and cooling tower as the output of the control strategy. Due to the limited experience of the operator, the equipment on-off mode is usually selected according to the seasonal load variation or the working time. In a certain period of time, the operation of the central air conditioning system is stable. Even if each device of the system is continuously monitored, the obtained data is a large amount of repeated actual operation data, causing the sparsity of the data.

[0027] In one embodiment of the present application, a central air conditioning control strategy optimization method is provided, the central air conditioning comprising a cold source system and a control system, the cold source system comprising a plurality of chilled water pumps, a plurality of cooling water pumps, a plurality of cooling towers and a plurality of water chillers and a plurality of temperature sensors, humidity sensors and flow sensors, the control system comprising a control strategy library, the input of the control strategy library being system cooling load, ambient temperature, ambient relative humidity, chilled water system supply water temperature, chilled water system total flow and chilled water system supply and return water pressure difference, the output of the control strategy library being the operating parameters of the cold source system, the control strategy optimization method comprising: S10. Establishing an expression model between the input and output of the control strategy, wherein the input is discretized according to its numerical range.

[0028] To explain, the foregoing control method is described in detail by way of example. Specifically, the input of the central air conditioning control strategy library is six external constraint variables: system cooling load, ambient temperature, ambient relative humidity, chilled water system supply water temperature, chilled water system total flow and chilled water system supply and return water pressure difference. The three external constraint variables not subject to human control are: system cooling load, ambient temperature and ambient relative humidity; the three external constraint variables determined according to the load distribution characteristics of the air conditioning system are: chilled water system supply water temperature, chilled water system total flow and chilled water system supply and return water pressure difference. The output of the central air conditioning control strategy library is the on-off state of the water chiller, chilled water pump, cooling water pump and cooling tower and the corresponding operating frequency. In the prior art, 5 different levels are usually taken for each of the six external constraint variables, and 15625 different combinations are formed by uniform arrangement. In detail, the six dimensions are cooling load X0, outdoor dry bulb temperature X1, outdoor ambient relative humidity X2 (independent variable); chilled water system supply water temperature X3, chilled water system total flow X4 and chilled water system pipe network supply and return water pressure difference X5 (non-independent variable). The distribution of the strategy library is 5x5x5x5x5x5=15625 working conditions.

[0029] Under the condition that the system cooling load, ambient temperature and ambient relative humidity are constant, the chilled water system supply water temperature, chilled water system total flow and chilled water system supply and return water pressure difference can have multiple combination modes at the corresponding time. The three constraint variables are strongly coupled and non-independent variables, and need to be determined according to building load prediction or experience. Generally, the cooperative relationship can be expressed according to the following rules:

[0030]

[0031] The chilled water system supply water temperatures are t_chiller_out 0 , t_chiller_out 1 , …, t_chiller_out nThe total flow rate range of the chilled water system corresponding to the supply water temperature of each chilled water system is [G_chiller]. 0 (0)~G_chiller 0 (n)]、[G_chiller 1 (0)~G_chiller 1 (n)]、

[0032] ..., [G_chiller] n (0)~G_chiller n (n)]; The range of chilled water system supply and return pressure difference corresponding to the total flow rate of each chilled water system is [ΔP]. 0_0 (0)~ΔP 0_0 (n)]、[ΔP 0_1 (0)~ΔP 0_1 (n)]、……、[ΔP n_n (0)~ΔP n_n (n)].

[0033] As can be seen from the above, a certain chilled water supply temperature must correspond to a certain chilled water flow rate range (which cannot be lower than the minimum flow rate requirement), and a certain chilled water flow rate must correspond to a certain supply and return water pressure difference range (which cannot be lower than the minimum supply and return water pressure difference). Such a correspondence is related to the load characteristics and requires load calculation analysis and prediction in advance. When the conditions are not met, the mutual constraint relationship can also be set based on experience.

[0034] This invention first considers the already determined chilled water system supply temperature range [t_chiller_out] 0 ~t_chiller_out n [t_chiller_out] can be discretized into 20 partitions, or it can be partitioned into any number of partitions greater than 5, i.e., [t_chiller_out] 0 t_chiller_out 1 , ..., t_chiller_out 20 Each chilled water system supply temperature corresponds to a [G_chiller] 0 (0), G_chiller 0 (1), ..., G_chiller 0 (20)], and each chilled water flow rate corresponds to a [ΔP] 0_0 (0), ΔP 0_0 (1), …ΔP 0_0 (20)], where G_chiller 0 (0) represents the minimum flow rate at the corresponding water supply temperature, ΔP 00(0) represents the minimum supply and return water pressure difference under the minimum flow rate. It can be seen that the flow rate range can be obtained based on the temperature, and then the pressure difference range can be obtained based on the flow rate. The combination method is: 21×21×21=9261.

[0035] Given a fixed setpoint for the differential pressure bypass regulating valve, a known chilled water supply temperature corresponds to a minimum chilled water flow rate, which in turn corresponds to a minimum supply-return pressure difference. Theoretically, to ensure that the flow rate and required supply-return pressure difference on the user's network side perfectly match the flow rate and effective pressure difference provided by the chilled water source, the setpoint of the differential pressure bypass regulating valve needs to be adjusted in real time to equal the effective pressure difference provided by the chilled water source. In this way, if the required chilled water flow rate is less than the chilled water flow rate provided by the chilled water source system, the excess chilled water returns to the chilled water source system through the bypass pipeline, while simultaneously maintaining the supply-return pressure difference in the network at the same level as the pressure difference provided by the chilled water source system (provided the differential pressure bypass regulating valve setpoint is dynamically adjusted). Only then can the offline optimization control strategy be maximized. However, in reality, it's impossible to accurately obtain the synergistic relationship between water supply temperature, flow rate, and differential pressure through prior load analysis, inevitably introducing a degree of uncertainty. Therefore, it's impossible to compare and analyze this with a strategy database. To resolve this contradiction, compromises must be made, sacrificing some energy savings in exchange for stable system operation. In actual engineering projects, the differential pressure bypass control valve setting is usually set to a certain value and rarely adjusted. In some scenarios, adjustments can be made according to the season, setting different values ​​for different seasons, but dynamic real-time adjustments are almost impossible unless the bypass control valve has remote communication capabilities and supports remote dynamic adjustment.

[0036] Based on the above considerations, in practical applications, the existence of bypass loops in chilled water systems is inevitable, and it is impossible to dynamically adjust the setpoint of the differential pressure bypass regulating valve in real time. Therefore, the relationship between chilled water outlet temperature, flow rate, and differential pressure under different cooling and wet load couplings can be calculated and analyzed (or empirically) in advance, and a collaborative database of their corresponding relationships can be built in advance. During actual operation, the selection can be made based on system cooling load, ambient temperature and humidity, and time. If the collaborative database is not available, the range can be roughly determined based on engineering experience. If a certain collaborative relationship is selected, it can be discretized as follows:

[0037]

[0038] The chilled water system supply temperatures are t_chiller_out 0 t_chiller_out 1 ... t_chiller_out 20The total flow rate range of the chilled water system corresponding to the supply water temperature of each chilled water system is [G_chiller]. 0 (0)~G_chiller 0 (20)]、[G_chiller 1 (0)~G_chiller 1 (20)]、….、[G_chiller 20 (0)~G_chiller 20 (20)]; The corresponding chilled water system supply and return water pressure difference range is [ΔP] 0 (0)~ΔP 0 (20)]、[ΔP 1 (0)~ΔP 1 (20)]、….、[ΔP 20 (0)~ΔP 20 (20)].

[0039] S20. Apply inverse distance weighted interpolation based on k-nearest neighbors to the discretized input parameters and calculate the output of each interpolation.

[0040] Specifically, after discretizing the chilled water supply temperature, chilled water flow rate, and chilled water supply and return pressure difference according to the above rules, the following combination method can be adopted under the condition of known actual operating data of cooling load, outdoor ambient temperature, and relative humidity:

[0041]

[0042] Where Q is the cooling load, t 环境 The dry-bulb temperature of the external environment. For the relative humidity of the external environment, G_chiller n (0) and ΔP n (0) represents the minimum chilled water flow rate and the supply and return water pressure difference in the pipe network at the corresponding supply water temperature, which changes with the supply water temperature; G_chiller n (20) The maximum possible chilled water flow rate of the location system can be set (which can be set to a constant value), ΔP n (20) is the manual setting value for the differential pressure bypass regulating valve (it is not frequently adjusted and can be considered a fixed value for a period of time). Therefore, there are a total of (20+21)×21=861 combinations under a certain state. That is, under a certain operating state, 861 inverse distance weight interpolation calculations need to be performed, and the best operating strategy is selected from the 861 interpolation results.

[0043] For multidimensional interpolation, there are 861 possible input combinations, and an interpolation calculation is performed for each input. The interpolation calculation uses inverse distance weighted interpolation based on k-nearest neighbors. The basic idea is that the closer a discrete point is to the estimated point, the greater its influence on the estimated point, and the larger its weight; conversely, the farther a discrete point is from the estimated point, the smaller its influence.

[0044] The independent variables are handled by dividing the 3D grid nodes into 20 equal parts;

[0045]

[0046] Determine which of the 20 equal intervals the input cooling loads X0_input, X1_input, and X2_input fall into, and take the median as the input value for calculation.

[0047] The handling of independent variables involves finding the corresponding coupling patterns of independent variables, i.e., external environmental parameters. There are 41 possible combinations for a single chilled water supply temperature (t_chiller_out); that is, 861 possible combinations for 21 chilled water supply temperatures. That is, the corresponding value for each of the above combinations.

[0048] In summary, there are 861 possible combinations under a single external operating condition.

[0049] For the point to be interpolated ,

[0050] The points after normalization are

[0051]

[0052] Find the upper and lower boundary points of each dimension of the point to be interpolated.

[0053] By combining the upper and lower boundary nodes of each dimension one by one, we obtain the 2^n nodes near the point to be interpolated. 6 =64 neighboring points.

[0054] The distribution intervals of the six-dimensional grid nodes in the policy library are 3125, 625, 125, 25, 5, and 1, respectively.

[0055] For each combination of upper and lower boundaries, the distribution row label in the strategy library is as follows:

[0056]

[0057] Using 64 labels, 64 neighboring points (X0(j),X1(j),X2(j),X3(j),X4(j),X5(j)) were extracted.

[0058] The interpolation calculation uses inverse distance weighted interpolation based on k-nearest neighbors. The basic idea is that the closer a discrete point is to the estimated point, the greater its influence on the estimated point, and the larger its weight; conversely, the farther a discrete point is from the estimated point, the smaller its influence.

[0059] Define d t The distance between the point to be interpolated and its neighboring points (t = 1, 2, ..., 64)

[0060]

[0061] Define ω t Let be the weight corresponding to the t-th neighboring point (t = 1, 2, ..., 64).

[0062]

[0063] The result of multidimensional inverse distance weighted interpolation is:

[0064]

[0065] Special handling of attribute values: Since the start-up status of chilled water pumps, cooling water pumps, and cooling towers is equivalently handled by their operating frequency range settings, such as the operating frequency range of chilled water pumps [30Hz, 50Hz], the operating frequency range of cooling water pumps [30Hz, 50Hz], and the operating frequency range of cooling tower fans [25Hz, 50Hz], in order to avoid interpolation errors, we first determine whether the corresponding power equipment is in operation. If the operating frequency is zero, then the minimum frequency is assigned during interpolation calculation. For example, if the operating frequency of a certain chilled water pump corresponding to an optimization strategy is 0, then 30Hz is assigned during interpolation to facilitate interpolation.

[0066] S30. Based on the output of each interpolation, determine the optimal control strategy.

[0067] Specifically, for the interpolation results, the 861 interpolation results are sorted by Energy Efficiency Ratio (EER), and strategies are selected from high to low. The reasonable operating strategy of the interpolation result is output as the interpolation result. If the interpolation result is still unreasonable, the closest optimized control strategy can be selected from the existing strategy library.

[0068] The screening rules include ensuring that the number of operating chilled water pumps, cooling water pumps, and cooling towers is greater than or equal to the number of operating chiller units, and that none of them are in a blind zone. This rule should be modified before the final output control strategy.

[0069] When performing interpolation calculations for the operating status of the tower pump, the interpolation is performed within the range of [0-1]. If the interpolation result is greater than or equal to 0.5, the equipment is considered to be on; otherwise, it is considered off. However, since the interpolation results around 0.5 are ambiguous in terms of whether they are 0 or 1, a blind zone is set for the interpolation results. Results in which the on / off status of the main unit, chilled water pump, cooling water pump, and cooling tower falls within the blind zone are filtered and discarded, thus avoiding ambiguous results for the on / off status. The filtered result is the strategy with the highest EER among the reasonable results. Although it is not the most energy-efficient strategy, it ensures its stability and rationality.

[0070] One embodiment of the present invention provides a central air conditioning control strategy optimization system. The central air conditioning system includes a cold source system and a control system. The cold source system includes multiple chilled water pumps, multiple cooling water pumps, multiple cooling towers, multiple chiller units, and multiple temperature sensors, humidity sensors, and flow sensors. The control system includes a control strategy library and a control strategy library optimization module. The inputs to the control strategy library are system cooling load, ambient temperature, ambient relative humidity, chilled water system supply temperature, chilled water system total flow rate, and chilled water system supply and return pressure difference. The output of the control strategy library is the operating parameters of the cold source system. The control strategy library optimization module includes:

[0071] The model building module establishes an expression model between the input and output of the control strategy, wherein the input is discretized according to its numerical range.

[0072] The interpolation module uses inverse distance weighting based on k-nearest neighbors to interpolate the discretized input parameters and calculates the output of each interpolation.

[0073] The optimization module determines the optimal control strategy based on the output of each interpolation.

[0074] The control strategy library optimization module adopts the central air conditioning control strategy optimization method of the aforementioned embodiment.

[0075] Additionally, one embodiment of the present invention provides a computer device comprising: a memory, a processor, and a computer program stored on the memory and capable of running the aforementioned central air conditioning control strategy optimization method on the processor. The processor and the memory can be connected via a bus or other means. The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0076] Furthermore, one embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions that are executed by a processor or controller using the aforementioned central air conditioning control strategy optimization method.

[0077] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0078] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0079] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformations made using the present specification under the concept of the present invention, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A method for optimizing a central air conditioning control strategy, wherein the central air conditioning system includes a cold source system and a control system, the cold source system includes multiple chilled water pumps, multiple cooling water pumps, multiple cooling towers, and multiple chiller units, as well as multiple temperature sensors, humidity sensors, and flow sensors, and the control system includes a control strategy library, characterized in that, The inputs to the control strategy library are system cooling load, ambient temperature, ambient relative humidity, chilled water system supply water temperature, total chilled water system flow rate, and chilled water system supply and return water pressure difference. The outputs of the control strategy library are the operating parameters of the cold source system, including the on / off status and corresponding operating frequency of the chiller unit, chilled water pump, cooling water pump, and cooling tower. The control strategy optimization method includes: S10. Establish an expression model between the input and output of the control strategy, wherein the input is discretized according to its numerical range; S20. Apply inverse distance weighted interpolation based on k nearest neighbors to the discretized input parameters and calculate the output of each interpolation. S30. Based on the output of each interpolation, determine the optimal control strategy.

2. The central air conditioning control strategy optimization method according to claim 1, characterized in that, The input is discretized according to its numerical range by being discretized into multiples of 5 level values ​​according to its numerical range.

3. The central air conditioning control strategy optimization method according to claim 1, characterized in that, The step of determining the optimal control strategy based on the output of each interpolation includes: sorting the output of each interpolation by energy efficiency ratio (EER), filtering strategies from high to low, and taking the operating strategy with reasonable interpolation results as the optimal control strategy.

4. A central air conditioning control strategy optimization system, wherein the central air conditioning system includes a cold source system and a control system, the cold source system includes multiple chilled water pumps, multiple cooling water pumps, multiple cooling towers, and multiple chiller units, as well as multiple temperature sensors, humidity sensors, and flow sensors, the control system includes a control strategy library and a control strategy library optimization module, the inputs of the control strategy library are system cooling load, ambient temperature, ambient relative humidity, chilled water system supply water temperature, chilled water system total flow rate, and chilled water system supply and return water pressure difference, the output of the control strategy library is the operating parameters of the cold source system, the operating parameters of the cold source system include the on / off status of the chiller units, chilled water pumps, cooling water pumps, and cooling towers, and their corresponding operating frequencies, the control strategy library optimization module includes: The model building module establishes an expression model between the input and output of the control strategy, wherein the input is discretized according to its numerical range. The interpolation module uses inverse distance weighting based on k-nearest neighbors to interpolate the discretized input parameters and calculates the output of each interpolation. The optimization module determines the optimal control strategy based on the output of each interpolation.

5. The central air conditioning control strategy optimization system according to claim 4, characterized in that, The input is discretized according to its numerical range by being discretized into multiples of 5 level values ​​according to its numerical range.

6. The central air conditioning control strategy optimization system according to claim 4, characterized in that, The step of determining the optimal control strategy based on the output of each interpolation includes: sorting the output of each interpolation by energy efficiency ratio (EER), filtering strategies from high to low, and taking the operating strategy with reasonable interpolation results as the optimal control strategy.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 3.

Images