Air conditioning system energy consumption simulation method and device based on data driving

Abstract

The invention provides an air conditioning system energy consumption simulation method and device based on data driving, and the method comprises the steps: firstly collecting the real-time data of a water chilling unit, a chilled water pump, a cooling water pump, a cooling tower and a tail end air conditioner in the operation process of an air conditioning system in parallel; the real-time data of the water chilling unit, the chilled water pump, the cooling water pump, the cooling tower and the tail end air conditioner are subjected to multiple regression fitting, and a water chilling unit energy consumption model, a cooling water pump energy consumption model, a chilled water pump energy consumption model, a cooling tower energy consumption model and a tail end air conditioner energy consumption model are obtained; fitting the fitting power in the energy consumption model again to obtain an air-conditioning system energy consumption model, and finally simulating the operation energy consumption of the air-conditioning system under the corresponding working condition by adopting the air-conditioning system energy consumption model under the given operation working condition of the air-conditioning system. According to the method, the problem that the simulation power result is inaccurate due to poor dynamic property and time-varying property of the existing simulation model is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy consumption simulation of subway air-conditioning systems, and in particular relates to a data-driven method and device for simulating energy consumption of air-conditioning systems. Background Art

[0002] In order to ensure the normal operation of the equipment in the subway and the comfort of subway passengers, air conditioning systems are generally installed in the subway. The total energy consumption of the air conditioning system accounts for more than 1 / 3 of the total energy consumption of subway operation, which is a system with extremely high energy consumption. The premise for optimizing the control of the air conditioning system is to conduct real-time evaluation or simulation of the energy consumption status during the operation of the system, so as to quickly identify the components or working conditions with high energy consumption in the subway system, so as to optimize the control of the air conditioning system in a targeted manner.

[0003] In the prior art, energy consumption assessment of air-conditioning systems is mainly based on energy consumption mechanism models to explain energy consumption patterns or based on experience summaries to explain energy consumption patterns. These two methods usually simplify boundary conditions such as structural parameters and physical parameters, and ignore the dynamics and time-varying nature of the air-conditioning system during operation. The energy consumption simulation results obtained are often inaccurate. Summary of the invention

[0004] The present invention provides a data-driven air conditioning system energy consumption simulation method and device, which are used to solve the problems existing in the prior art.

[0005] In a first aspect, to achieve the above-mentioned purpose, the present invention provides a data-driven air conditioning system energy consumption simulation method, which comprises:

[0006] S10: parallelly collect the real-time data of the chiller, the real-time data of the refrigeration water pump, the real-time data of the cooling water pump, the real-time data of the cooling tower and the real-time data of the terminal air conditioner during the operation of the air-conditioning system;

[0007] S20: performing multivariate regression fitting on the real-time data of the chiller, the real-time data of the refrigerated water pump, the real-time data of the cooling water pump, the real-time data of the cooling tower and the real-time data of the terminal air conditioner respectively, to obtain the energy consumption model of the chiller, the energy consumption model of the refrigerated water pump, the energy consumption model of the cooling water pump, the energy consumption model of the cooling tower and the energy consumption model of the terminal air conditioner;

[0008] S30: using a multivariate linear fitting method, refitting the fitted powers in the chiller energy consumption model, the cooling water pump energy consumption model, the refrigeration water pump energy consumption model, the cooling tower energy consumption model and the terminal air conditioner energy consumption model to obtain an air conditioning system energy consumption model;

[0009] S40: Under given operating conditions of the air-conditioning system, an air-conditioning system energy consumption model is used to simulate the operating energy consumption of the air-conditioning system under corresponding conditions.

[0010] Through the above technical solution, the method of the present invention fully considers the real-time data of each core device in the air-conditioning system, and performs multiple fittings on each real-time data to obtain the energy consumption model of the air-conditioning system and then simulates the energy consumption hour by hour. Compared with the prior art, the energy consumption model of the air-conditioning system of the present invention has higher integrity, dynamics and time-varying properties, provides data basis for the real-time optimization operation of the air-conditioning system, and the simulation results finally obtained are more accurate.

[0011] Preferably, the real-time data of the chiller includes the power of the chiller, the inlet temperature of the cooling water, the outlet temperature of the chilled water and the load of the chiller. The energy consumption model of the chiller is expressed as:

[0012] P chiller =A0+A1(T cdw,in -T chw,out )+A2(T cdw,in -T chw,out ) 2 +A3Q+A4Q 2 +A5(T cdw,in -T chw,out )Q(1)

[0013] Among them, P chiller is the power of the chiller, T cdw,in is the cooling water inlet temperature, T cdw,out is the outlet temperature of chilled water, Q is the load of the chiller, and A0~A5 are fitting coefficients.

[0014] Preferably, the real-time data of the cooling water pump includes the power of the cooling water pump, the flow rate of the cooling water pump and the frequency of the cooling water pump, and the expression of the cooling water pump energy consumption model is:

[0015]

[0016] q pump_cw =C0+C1f pump_cw (3)

[0017] Among them, P pump_cw is the power of the cooling water pump, q pump_cw is the cooling water pump flow rate, f pump_cw is the cooling water pump frequency, B0~B3 and C0~C1 are fitting coefficients; if the cooling water pump flow is missing in a certain period of time, the cooling water pump frequency and the cooling water pump power are placed in formulas (2)-(3) to obtain B0~B3 and C0~C1 by fitting; when the cooling water pump flow exists, the cooling water pump flow and the cooling water pump power are placed in formula (2) to obtain B0~B3 by fitting.

[0018] Preferably, the real-time data of the chilled water pump includes the power of the chilled water pump, the flow rate of the chilled water pump and the frequency of the chilled water pump, and the expression of the energy consumption model of the chilled water pump is:

[0019]

[0020] q pump_chw =c0+c1f pump_chw (5)

[0021] Among them, P pump_chw is the power of the chilled water pump, q pump_chw is the chilled water pump flow rate, f pump_chw is the chilled water pump frequency, b0~b3 and c0~c1 are fitting coefficients; if the chilled water pump flow is missing in a certain period of time, the chilled water pump frequency and the chilled water pump power are placed in formulas (4)-(5) to obtain b0~b3 and c0~c1 by fitting; when the chilled water pump flow exists, the chilled water pump flow and the chilled water pump power are placed in formula (4) to obtain b0~b3 by fitting.

[0022] Preferably, the real-time data of the cooling tower includes the power of the cooling tower fan, the flow rate of the cooling tower fan and the frequency of the cooling tower water pump, and the expression of the cooling tower energy consumption model is:

[0023]

[0024] q tw =E0+E1f tw (7)

[0025] Among them, P tw is the cooling tower fan power, q tw is the cooling tower fan flow rate, f tw is the cooling tower water pump frequency, D0~D3 and E0~E1 are fitting coefficients; if the cooling tower fan flow is missing in a certain period of time, the cooling tower water pump frequency and the cooling tower fan power are placed in formulas (6)-(7) to fit D0~D3 and E0~E1; when the cooling tower fan flow exists, the cooling tower fan flow and the cooling tower fan power are placed in formula (6) to fit D0~D3.

[0026] Preferably, the real-time data of the terminal air conditioner includes the power of the terminal air conditioner, the fan flow of the terminal air conditioner and the frequency of the terminal air conditioner, and the expression of the energy consumption model of the terminal air conditioner is:

[0027]

[0028] q fan =G0+G1f fan (9)

[0029] Among them, P fanis the terminal air conditioner power, q fan is the fan flow rate of the terminal air conditioner, f fan is the frequency of the terminal air conditioner, F0~F3 and G0~G1 are fitting coefficients; if the fan flow of the terminal air conditioner is missing in a certain period of time, the terminal air conditioner frequency and the terminal air conditioner power are placed in formulas (8)-(9) to fit F0~F3 and G0~G1; when the fan flow of the terminal air conditioner exists, the fan flow of the terminal air conditioner and the terminal air conditioner power are placed in formula (8) to fit F0~F3.

[0030] Preferably, the expression of the air conditioning system energy consumption model is:

[0031] P sys =a1P chiller ′+a2P pump_cw ′+a3P pump_chw ′+a4P tw ′+a5P fan ′(10)

[0032] Among them, a1~a5 are fitting coefficients, P chiller ′ is the fitted power of the chiller, P pump_cw ′ is the fitting power of the cooling water pump, P pump_chw ′ is the fitted power of the chilled water pump, P tw ′ is the fitted power of the cooling tower fan, P fan ′ is the fitting power of the terminal air conditioner, P sys is the power simulation value of the air conditioning system energy consumption model.

[0033] Preferably, after step S40, the method further comprises:

[0034] The index R-Squared of the air-conditioning system energy consumption model is introduced to calculate the simulation accuracy of the air-conditioning system energy consumption model.

[0035] Preferably, the specific formula for calculating the simulation accuracy of the air conditioning system energy consumption model is:

[0036]

[0037] in, represents the actual power of the air conditioning system at the i-th time point under the corresponding working conditions, P sys (i) represents the power simulation value of the air conditioning system energy consumption model at the i-th time point under the corresponding working conditions, represents the average power of the air conditioning system at time point i under the corresponding working conditions, R 2 The closer the value is to 1, the higher the accuracy of the model is, and 0 means the worst accuracy of the model.

[0038] In a second aspect, in order to achieve the above-mentioned purpose, the present invention further provides an air conditioning system energy consumption simulation device based on data drive, which comprises:

[0039] The data acquisition module is used to collect the real-time data of the chiller, the refrigeration water pump, the cooling water pump, the cooling tower and the terminal air conditioner during the operation of the air-conditioning system in parallel;

[0040] The equipment energy consumption fitting module is used to perform multivariate regression fitting on the real-time data of the chiller, the real-time data of the refrigerated water pump, the real-time data of the cooling water pump, the real-time data of the cooling tower and the real-time data of the terminal air conditioner, and obtain the energy consumption model of the chiller, the energy consumption model of the cooling water pump, the energy consumption model of the refrigerated water pump, the energy consumption model of the cooling tower and the energy consumption model of the terminal air conditioner respectively;

[0041] The system energy consumption fitting module is used to refit the fitting power in the chiller energy consumption model, cooling water pump energy consumption model, refrigeration water pump energy consumption model, cooling tower energy consumption model and terminal air conditioner energy consumption model by using the multivariate linear fitting method to obtain the air conditioning system energy consumption model;

[0042] The system energy consumption simulation module is used to evaluate the operating energy consumption of the air-conditioning system under the given operating conditions of the air-conditioning system by adopting the air-conditioning system energy consumption model.

[0043] The present invention has the following advantages:

[0044] Compared with the prior art, the method of the present invention collects real-time operating data of each core equipment of the air-conditioning system, adopts a multivariate fitting regression method, and constructs energy consumption models of the chiller, cooling tower, cooling water pump, refrigeration water pump and terminal air conditioner respectively, and performs multivariate regression fitting again based on the above energy consumption model to establish an energy consumption model of the entire air-conditioning system. The model couples the main energy-consuming equipment of the air-conditioning system, has higher integrity and accuracy, and has good universality, dynamics and time-varying properties, which provides a data basis for the real-time optimization operation of the air-conditioning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 is a flow chart of a data-driven air conditioning system energy consumption simulation method in Embodiment 1 of the present invention;

[0047] Figure 2Schematic diagram of the structure of the data-driven air conditioning system energy consumption simulation device in the second embodiment of the present invention. DETAILED DESCRIPTION

[0048] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] In the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they cannot be understood as limitations on the present invention.

[0050] Embodiment 1

[0051] like Figure 1 As shown, this embodiment discloses a data-driven air conditioning system energy consumption simulation method, including:

[0052] S10: collect the real-time data of the chiller, the real-time data of the refrigeration water pump, the real-time data of the cooling water pump, the real-time data of the cooling tower and the real-time data of the terminal air conditioner in parallel during the operation of the air-conditioning system.

[0053] In this embodiment, the real-time data of the chiller includes the power of the chiller, the inlet temperature of the cooling water, the outlet temperature of the chilled water, and the load of the chiller. The real-time data of the chilled water pump includes the power of the chilled water pump, the flow rate of the chilled water pump, and the frequency of the chilled water pump. The real-time data of the cooling water pump includes the power of the cooling water pump, the flow rate of the cooling water pump, and the frequency of the cooling water pump. The real-time data of the cooling tower includes the power of the cooling tower fan, the flow rate of the cooling tower fan, and the frequency of the cooling tower water pump. The real-time data of the terminal air conditioner includes the power of the terminal air conditioner, the flow rate of the terminal air conditioner fan, and the frequency of the terminal air conditioner.

[0054] Specifically, the above data are core energy consumption devices in the air-conditioning system. The above real-time data can be collected in parallel through corresponding sensors and aggregated to a preset processing terminal for unified processing.

[0055] S20: Perform multivariate regression fitting on the real-time data of the chiller, the real-time data of the refrigeration water pump, the real-time data of the cooling water pump, the real-time data of the cooling tower and the real-time data of the terminal air conditioner respectively to obtain the energy consumption model of the chiller, the energy consumption model of the refrigeration water pump, the energy consumption model of the cooling water pump, the energy consumption model of the cooling tower and the energy consumption model of the terminal air conditioner.

[0056] In this embodiment, the above energy consumption models can be fitted in parallel using a multi-threaded processing terminal.

[0057] Specifically, the expression of the chiller energy consumption model is:

[0058] P chiller =A0+A1(T cdw,in -T chw,out )+A2(T cdw,in -T chw,out ) 2 +A3Q+A4Q 2 +A5(T cdw,in -T chw,out )Q(1)

[0059] Among them, P chiller is the power of the chiller, T cdw,in is the cooling water inlet temperature, T cdw,out is the outlet temperature of chilled water, Q is the load of the chiller, and A0~A5 are fitting coefficients. By inserting the real-time data of the chiller at multiple time points into formula (1) for fitting, the five fitting coefficients A0~A5 can be obtained. After the above fitting coefficients are determined, if only the inlet temperature of the cooling water, the outlet temperature of the chilled water and the load of the chiller at the new time point are substituted, the power fitting value corresponding to the output of the model is P chiller '.

[0060] Specifically, the expression of the cooling water pump energy consumption model is:

[0061]

[0062] q pump_cw =C0+C1f pump_cw (3)

[0063] Among them, P pump_cw is the power of the cooling water pump, q pump_cw is the cooling water pump flow rate, f pump_cw is the cooling water pump frequency, B0~B3 and C0~C1 are fitting coefficients. By placing the real-time data of the cooling water pump at multiple time points into formula (2) and formula (3) for fitting, the five fitting coefficients B0~B3 and C0~C1 can be obtained. After the above fitting coefficients are determined, only the cooling water pump flow rate or cooling water pump frequency at the new time point is substituted, and the model can output the corresponding power fitting value P pump_cw '.

[0064] Furthermore, if the cooling water pump flow is missing in a certain period of time, the cooling water pump frequency and the cooling water pump power are placed in formulas (2)-(3) to fit B0~B3 and C0~C1; when the cooling water pump flow exists, the cooling water pump flow and the cooling water pump power are placed in formula (2) to fit B0~B3.

[0065] Specifically, the expression of the chilled water pump energy consumption model is:

[0066]

[0067] q pump_chw =c0+c1f pump_chw (5)

[0068] Among them, P pump_chw is the power of the chilled water pump, q pump_chw is the chilled water pump flow rate, f pump_chw is the chilled water pump frequency, b0~b3 and c0~c1 are fitting coefficients. By placing the real-time data of the chilled water pump at multiple time points into formula (4) and formula (5) for fitting, the five fitting coefficients b0~b3 and c0~c1 can be obtained. After the above fitting coefficients are determined, only the chilled water pump flow or chilled water pump frequency at the new time point is substituted, and the model can output the corresponding power fitting value as P tw '.

[0069] Furthermore, if the chilled water pump flow is missing in a certain period of time, the chilled water pump frequency and the chilled water pump power are placed in formulas (4)-(5) to fit b0~b3 and c0~c1; when the chilled water pump flow exists, the chilled water pump flow and the chilled water pump power are placed in formula (4) to fit b0~b3.

[0070] Specifically, the expression of the cooling tower energy consumption model is:

[0071]

[0072] q tw =E0+E1f tw (7)

[0073] Among them, P tw is the cooling tower fan power, q tw is the cooling tower fan flow rate, f twis the cooling tower water pump frequency, D0~D3 and E0~E1 are fitting coefficients. By placing the real-time data of the cooling tower at multiple time points into formula (6) and formula (7) for fitting, the five fitting coefficients D0~D3 and E0~E1 can be solved. After the above fitting coefficients are determined, only the cooling tower fan flow or cooling tower water pump frequency at the new time point is substituted, and the model can output the corresponding power fitting value as P pump_chw '.

[0074] Furthermore, if the cooling tower fan flow is missing in a certain period of time, the cooling tower water pump frequency and the cooling tower fan power are placed in formulas (6)-(7) to fit D0~D3 and E0~E1; when the cooling tower fan flow exists, the cooling tower fan flow and the cooling tower fan power are placed in formula (6) to fit D0~D3.

[0075] Specifically, the expression of the terminal air conditioner energy consumption model is:

[0076]

[0077] q fan =G0+G1f fan (9)

[0078] Among them, P fan is the terminal air conditioner power, q fan is the fan flow rate of the terminal air conditioner, f fan is the frequency of the terminal air conditioner, and F0~F3 and G0~G1 are fitting coefficients. By placing the real-time data of the terminal air conditioner at multiple time points into formulas (8) and (9) for fitting, the five fitting coefficients of F0~F3 and G0~G1 can be obtained. After the above fitting coefficients are determined, if only the fan flow rate or the frequency of the terminal air conditioner at the new time point is substituted, the model can output the corresponding power fitting value as P fan '.

[0079] Furthermore, if the fan flow of the terminal air conditioner is missing in a certain period of time, the terminal air conditioner frequency and the terminal air conditioner power are placed in formulas (8)-(9) to fit F0~F3 and G0~G1; when the fan flow of the terminal air conditioner exists, the fan flow of the terminal air conditioner and the terminal air conditioner power are placed in formula (8) to fit F0~F3.

[0080] It should be noted that the above energy consumption models can be used to simulate the energy consumption of some core equipment in the air-conditioning system under different working conditions. It should be emphasized that after solving the fitting coefficients, if new real-time data is substituted again, the corresponding model output value is the power fitting value.

[0081] It needs to be further explained that when actually acquiring data, there may be situations where there is only frequency or only flow. In order to enhance the robustness and applicability of the model and enable the model to establish a corresponding energy consumption model when data is missing, the flow fitting model and the frequency fitting model are fitted to obtain the above-mentioned energy consumption models.

[0082] After the above step S20, the method of the present invention further comprises:

[0083] S30: Using a multivariate linear fitting method, the fitted powers in the chiller energy consumption model, the cooling water pump energy consumption model, the refrigeration water pump energy consumption model, the cooling tower energy consumption model and the terminal air conditioner energy consumption model are refitted to obtain an air conditioning system energy consumption model.

[0084] Specifically, the expression of the air conditioning system energy consumption model is:

[0085] P sys =a1P chiller ′+a2P pump_cw ′+a3P pump_chw ′+a4P tw ′+a5P fan ′(10)

[0086] Among them, a1~a5 are fitting coefficients, P chiller ′ is the fitted power of the chiller, P pump_cw ′ is the fitting power of the cooling water pump, P pump_chw ′ is the fitted power of the chilled water pump, P tw ′ is the fitted power of the cooling tower fan, P fan ′ is the fitting power of the terminal air conditioner, P sys is the power simulation value of the air conditioning system energy consumption model.

[0087] S40: Under given operating conditions of the air-conditioning system, an air-conditioning system energy consumption model is used to simulate the operating energy consumption of the air-conditioning system under corresponding conditions.

[0088] It should be explained that the above given operating condition setting values ​​include factors such as cooling water inlet temperature, chilled water outlet temperature, water pump frequency, cooling tower fan frequency, etc. In the air-conditioning system, different operating conditions, i.e., cooling, cold storage, cooling and cold storage in parallel, or cooling peak period, have different cooling water inlet temperature, chilled water outlet temperature, water pump frequency, and fan frequency.

[0089] Through the above steps S10-S40, the method of the present invention fully considers the real-time data of each core device in the air-conditioning system, and performs multiple fittings on each real-time data, and finally obtains the energy consumption model of the air-conditioning system and then performs energy consumption simulation of other working conditions. Compared with the prior art, the energy consumption model of the air-conditioning system obtained by the method of the present invention has higher integrity, accuracy, dynamics and time-varying properties, and provides a data basis for the real-time optimization operation of the air-conditioning system.

[0090] On the basis of the above steps S10-S40, in order to verify the accuracy of the method of the present invention, after step S40, the method of the present invention further includes:

[0091] The index R-Squared of the air-conditioning system energy consumption model is introduced to calculate the simulation accuracy of the air-conditioning system energy consumption model.

[0092] Specifically, the specific formula for the simulation accuracy of the above air conditioning system energy consumption model is:

[0093]

[0094] in, represents the actual power of the air conditioning system at the i-th time point under the corresponding working conditions, P sys (i) represents the power simulation value of the air conditioning system energy consumption model at the i-th time point under the corresponding working conditions, represents the average power of the air conditioning system at time point i under the corresponding working conditions, R 2 The closer the value is to 1, the higher the accuracy of the model is, and 0 means the worst accuracy of the model.

[0095] The air-conditioning system energy consumption assessment accuracy obtained by the method of the present invention can reach above 0.9. Compared with the prior art, the air-conditioning system energy consumption model simulation accuracy in the method of the present invention is higher.

[0096] Embodiment 2

[0097] On the basis of the first embodiment, the present invention further provides an air conditioning system energy consumption simulation device based on data drive, which comprises:

[0098] The data acquisition module is used to collect the real-time data of the chiller, the refrigeration water pump, the cooling water pump, the cooling tower and the terminal air conditioner during the operation of the air-conditioning system in parallel;

[0099] The equipment energy consumption fitting module is used to perform multivariate regression fitting on the real-time data of the chiller, the real-time data of the refrigerated water pump, the real-time data of the cooling water pump, the real-time data of the cooling tower and the real-time data of the terminal air conditioner to obtain the energy consumption model of the chiller, the energy consumption model of the refrigerated water pump, the energy consumption model of the cooling water pump, the energy consumption model of the cooling tower and the energy consumption model of the terminal air conditioner;

[0100] The system energy consumption fitting module is used to refit the fitting power in the chiller energy consumption model, cooling water pump energy consumption model, refrigeration water pump energy consumption model, cooling tower energy consumption model and terminal air conditioner energy consumption model by using the multivariate linear fitting method to obtain the air conditioning system energy consumption model;

[0101] The system energy consumption simulation module is used to evaluate the operating energy consumption of the air-conditioning system under the given operating conditions of the air-conditioning system by adopting the air-conditioning system energy consumption model.

[0102] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc. Various media that can store program codes.

[0103] For those skilled in the art, various other corresponding changes and deformations can be made according to the technical solutions and concepts described above, and all of these changes and deformations should fall within the protection scope of the claims of the present invention.

Claims

1. A data-driven air conditioning system energy consumption simulation method, characterized in that: include: S10: parallelly collect the real-time data of the chiller, the real-time data of the refrigeration water pump, the real-time data of the cooling water pump, the real-time data of the cooling tower and the real-time data of the terminal air conditioner during the operation of the air-conditioning system; S20: performing multivariate regression fitting on the real-time data of the chiller, the real-time data of the refrigerated water pump, the real-time data of the cooling water pump, the real-time data of the cooling tower and the real-time data of the terminal air conditioner respectively, to obtain an energy consumption model of the chiller, an energy consumption model of the refrigerated water pump, an energy consumption model of the cooling water pump, an energy consumption model of the cooling tower and an energy consumption model of the terminal air conditioner; S30: using a multivariate linear fitting method, refitting the fitted powers in the chiller energy consumption model, the cooling water pump energy consumption model, the freezing water pump energy consumption model, the cooling tower energy consumption model and the terminal air conditioner energy consumption model to obtain an air conditioning system energy consumption model; S40: Under a given operating condition of the air-conditioning system, the air-conditioning system energy consumption model is used to simulate the operating energy consumption of the air-conditioning system under the corresponding operating condition.

2. The data-driven air conditioning system energy consumption simulation method according to claim 1, characterized in that: The real-time data of the chiller includes the power of the chiller, the inlet temperature of the cooling water, the outlet temperature of the chilled water and the load of the chiller. The expression of the energy consumption model of the chiller is: P chiller =A0+A1(T cdw,in -T chw,out )+A2(T cdw,in -T chw,out ) 2 +A3Q+A4Q 2 +A5(T cdw,in -T chw,out )Q (1) Among them, p chiller is the power of the chiller, T cdw,in is the cooling water inlet temperature, T cdw,out is the outlet temperature of chilled water, Q is the load of the chiller, and A0~A5 are fitting coefficients.

3. The data-driven air conditioning system energy consumption simulation method according to claim 1, characterized in that: The real-time data of the cooling water pump includes the power, flow rate and frequency of the cooling water pump. The expression of the cooling water pump energy consumption model is: what pump_cw =C0+C1f pump_cw (3) Among them, P pump_cw is the power of the cooling water pump, q pump_cw is the cooling water pump flow rate, f pump_cw is the cooling water pump frequency, B0~B3 and C0~C1 are fitting coefficients; if the cooling water pump flow is missing in a certain period of time, the cooling water pump frequency and the cooling water pump power are placed in formulas (2)-(3) to obtain B0~B3 and C0~C1 by fitting; when the cooling water pump flow exists, the cooling water pump flow and the cooling water pump power are placed in formula (2) to obtain B0~B3 by fitting.

4. The data-driven air conditioning system energy consumption simulation method according to claim 1, characterized in that: The real-time data of the chilled water pump includes the power, flow rate and frequency of the chilled water pump. The expression of the energy consumption model of the chilled water pump is: what pump_chw =c0+c1f pump_chw (5) Among them, P pumo_chw is the power of the chilled water pump, q pump_chw is the chilled water pump flow rate, f pump_chw is the chilled water pump frequency, b0~b3 and c0~c1 are fitting coefficients; if the chilled water pump flow is missing in a certain period of time, the chilled water pump frequency and the chilled water pump power are placed in formulas (4)-(5) to obtain b0~b3 and c0~c1 by fitting; when the chilled water pump flow exists, the chilled water pump flow and the chilled water pump power are placed in formula (4) to obtain b0~b3 by fitting.

5. The data-driven air conditioning system energy consumption simulation method according to claim 1, characterized in that: The real-time data of the cooling tower includes the power of the cooling tower fan, the flow rate of the cooling tower fan and the frequency of the cooling tower water pump. The expression of the cooling tower energy consumption model is: q tw =E0+E1f tw (7) Among them, P tw is the cooling tower fan power, q tw is the cooling tower fan flow rate, f tw is the cooling tower water pump frequency, D0~D3 and E0~E1 are fitting coefficients; if the cooling tower fan flow is missing in a certain period of time, the cooling tower water pump frequency and the cooling tower fan power are placed in formulas (6)-(7) to obtain D0~D3 and E0~E1 by fitting; when the cooling tower fan flow exists, the cooling tower fan flow and the cooling tower fan power are placed in formula (6) to obtain D0~D3 by fitting.

6. The data-driven air conditioning system energy consumption simulation method according to claim 1, characterized in that: The real-time data of the terminal air conditioner includes the power of the terminal air conditioner, the fan flow of the terminal air conditioner and the frequency of the terminal air conditioner. The expression of the energy consumption model of the terminal air conditioner is: q fan =G0+G1f fan (9) Among them, P fan is the terminal air conditioner power, q fan is the fan flow rate of the terminal air conditioner, f fan is the frequency of the terminal air conditioner, F0~F3 and G0~G1 are fitting coefficients; if the fan flow of the terminal air conditioner is missing in a certain period of time, the terminal air conditioner frequency and the terminal air conditioner power are placed in formulas (8)-(9) to fit F0~F3 and G0~G1; when the fan flow of the terminal air conditioner exists, the fan flow of the terminal air conditioner and the terminal air conditioner power are placed in formula (8) to fit F0~F3.

7. The data-driven air conditioning system energy consumption simulation method according to claim 1, characterized in that: The expression of the energy consumption model of the air conditioning system is: <h2 style=";text-align:left;direction:ltr">P<h2 style=";text-align:left;direction:ltr"> sys <h2 style=";text-align:left;direction:ltr"> =a1P<h2 style=";text-align:left;direction:ltr"> chiller <h2 style=";text-align:left;direction:ltr"> ′+a2P<h2 style=";text-align:left;direction:ltr"> pump_cw <h2 style=";text-align:left;direction:ltr"> ′+a3P<h2 style=";text-align:left;direction:ltr"> pump_chw <h2 style=";text-align:left;direction:ltr"> ′+a4P<h2 style=";text-align:left;direction:ltr"> tw <h2 style=";text-align:left;direction:ltr"> ′+a5P<h2 style=";text-align:left;direction:ltr"> fan <h2 style=";text-align:left;direction:ltr"> (10) Among them, a1~a5 are fitting coefficients, P chiller ′ is the fitted power of the chiller, P pump_cw ′ is the fitting power of the cooling water pump, P pump_chw ′ is the fitted power of the chilled water pump, P tw ′ is the fitted power of the cooling tower fan, P fan ′ is the fitting power of the terminal air conditioner, P sys is the power simulation value of the air conditioning system energy consumption model.

8. The data-driven air conditioning system energy consumption simulation method according to claim 1, characterized in that: After step S40, the method further includes: The index R-Squared of the energy consumption model of the air-conditioning system is introduced to calculate the simulation accuracy of the energy consumption model of the air-conditioning system.

9. The data-driven air conditioning system energy consumption simulation method according to claim 8, characterized in that: The calculation of the simulation accuracy of the air conditioning system energy consumption model includes: in, represents the actual power of the air conditioning system at the i-th time point under the corresponding working conditions, P sys (i) represents the power simulation value of the air-conditioning system energy consumption model at the i-th time point under the corresponding working conditions, represents the average power of the air conditioning system at time point i under the corresponding working conditions, R 2 The closer the value is to 1, the higher the accuracy of the model is, and 0 means the worst accuracy of the model.

10. A data-driven air conditioning system energy consumption simulation device, characterized in that: The device is used to implement the data-driven air conditioning system energy consumption simulation method according to any one of claims 1 to 9, the device comprising: The data acquisition module is used to collect the real-time data of the chiller, the refrigeration water pump, the cooling water pump, the cooling tower and the terminal air conditioner during the operation of the air-conditioning system in parallel; An equipment energy consumption fitting module is used to perform multivariate regression fitting on the real-time data of the chiller, the real-time data of the refrigerated water pump, the real-time data of the cooling water pump, the real-time data of the cooling tower and the real-time data of the terminal air conditioner, respectively, to obtain an energy consumption model of the chiller, an energy consumption model of the refrigerated water pump, an energy consumption model of the cooling water pump, an energy consumption model of the cooling tower and an energy consumption model of the terminal air conditioner; A system energy consumption fitting module is used to refit the fitting power in the chiller energy consumption model, the cooling water pump energy consumption model, the freezing water pump energy consumption model, the cooling tower energy consumption model and the terminal air conditioner energy consumption model by using a multivariate linear fitting method to obtain an air conditioning system energy consumption model; The system energy consumption simulation module is used to evaluate the operating energy consumption of the air-conditioning system under the given operating conditions of the air-conditioning system by using the air-conditioning system energy consumption model.

Images