Subway station air conditioner cooling regulation and control method, device and equipment and storage medium

Abstract

The invention discloses a subway station air conditioner cooling regulation and control method, device and equipment and a storage medium, and belongs to the technical field of energy optimization. The method comprises the following steps: predicting a cold load demand of a ground body station in a to-be-predicted time period based on a cold load prediction model to obtain cold load prediction data; based on a cooling load redistribution model, redistributing the cooling load prediction data in a time dimension to obtain a cooling load distribution result; and on the basis of an air conditioner water system optimization model, the cooling load distribution result, the air conditioner equipment constraint and the water circulation parameter fluctuation constraint, air conditioner unit parameters are solved, and an optimal parameter set is obtained. According to the invention, energy waste is reduced while the cold load demand of the demand side is ensured, so that efficient utilization of energy is realized.

Description

Technical Field

[0001] The present invention relates to the field of energy optimization technology, and in particular to a method, device, equipment and storage medium for regulating cooling supply of air conditioners in subway stations. Background Art

[0003] Since the air conditioning system equipment and demand-side air conditioning cooling load supply of subway stations are designed according to the long-term peak passenger flow, the cooling capacity is greater than the actual demand, resulting in a large amount of energy waste. However, the timetable mode control method used by related technologies for air conditioning cooling regulation has a low matching degree with the peak passenger flow, and the equipment supply side simply relies on manual experience to set parameters, and it is impossible to achieve real-time energy consumption regulation, which further leads to energy waste. Summary of the invention

[0004] The main purpose of the present invention is to provide a subway station air conditioning cooling control method, device, equipment and storage medium, aiming to solve the technical problem of unreasonable air conditioning cooling load supply on the demand side of the subway station in the related technology, thereby leading to energy waste.

[0005] To achieve the above object, the present invention provides a subway station air conditioning cooling control method, the subway station air conditioning cooling control method comprises the following steps:

[0006] S1, based on the cooling load prediction model, predict the cooling load demand of the ground station in the prediction period to obtain cooling load prediction data;

[0007] S2, based on the cooling load redistribution model, the cooling load prediction data is redistributed in the time dimension to obtain the cooling load distribution result;

[0008] S3, based on the air conditioning water system optimization model, cooling load distribution results, air conditioning equipment constraints and water cycle parameter fluctuation constraints, the air conditioning unit parameters are solved to obtain the optimal parameter group.

[0009] In addition, to achieve the above-mentioned purpose, the present invention also provides a subway station air conditioning cooling control device, the device comprising:

[0010] A cooling load prediction module is used to predict the cooling load demand of the ground station in the prediction period based on the cooling load prediction model and obtain cooling load prediction data;

[0011] A cooling load redistribution module is used to redistribute cooling load forecast data in the time dimension based on a cooling load redistribution model to obtain cooling load distribution results;

[0012] The parameter solving module is used to solve the air-conditioning unit parameters based on the air-conditioning water system optimization model, cooling load distribution results, air-conditioning equipment constraints and water cycle parameter fluctuation constraints to obtain the optimal parameter group.

[0013] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a subway station air conditioning and cooling control device, the device comprising: a memory, a processor, and a subway station air conditioning and cooling control program stored in the memory and executable on the processor, the subway station air conditioning and cooling control program being configured to implement the steps of the subway station air conditioning and cooling control method as described above.

[0014] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, on which a subway station air conditioning and cooling control program is stored. When the subway station air conditioning and cooling control program is executed by a processor, the steps of the subway station air conditioning and cooling control method as described above are implemented.

[0015] The present invention uses a cooling load prediction model to accurately predict the cooling load demand on the demand side within the prediction period and obtain cooling load prediction data. On this basis, the cooling load redistribution model is used to comprehensively consider factors such as passenger flow, electricity prices, and human comfort, and the cooling load prediction data is reasonably redistributed in the time dimension, thereby saving electricity costs while taking into account passenger comfort. Finally, the optimal air-conditioning unit parameters are solved by combining the air-conditioning water system optimization model, equipment constraints, and water cycle parameter fluctuation constraints to ensure that the air-conditioning equipment operates in the best state, thereby improving energy efficiency and reducing energy consumption. The present invention improves the operating efficiency of the air-conditioning system as a whole, saves energy costs, and reduces unnecessary energy consumption while ensuring the comfort level in the subway station and the long-term stable operation of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a structural schematic diagram of a subway station air conditioning cooling control device in a hardware operating environment involved in an embodiment of the present invention;

[0017] Figure 2 It is a flow chart of an embodiment of a method for controlling cooling supply of air conditioner in a subway station according to the present invention;

[0018] Figure 3 This is a schematic diagram of the training process of the cooling load prediction model;

[0019] Figure 4 This is a schematic diagram of the construction process of the cooling load redistribution model;

[0020] Figure 5 Schematic diagram of the process of solving the air-conditioning unit parameters.

[0021] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0023] Analysis of relevant technologies revealed:

[0024] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of the subway station air conditioning cooling control equipment in the hardware operating environment involved in the embodiment of the present invention.

[0025] like Figure 1 As shown, the subway station air conditioning cooling control device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0026] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the air conditioning and cooling control equipment of the subway station, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0027] like Figure 1 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a data storage module, a network communication module, a user interface module, and a subway station air conditioning and cooling control program.

[0028] exist Figure 1 In the subway station air conditioning and cooling control device shown, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the subway station air conditioning and cooling control device of the present invention can be set in the subway station air conditioning and cooling control device, and the subway station air conditioning and cooling control device calls the subway station air conditioning and cooling control program stored in the memory 1005 through the processor 1001, and executes the subway station air conditioning and cooling control method provided by the embodiment of the present invention.

[0029] The embodiment of the present invention provides a method for controlling cooling supply of air conditioners in a subway station, referring to Figure 2 , Figure 2 The present invention is a flowchart of an embodiment of a method for controlling cooling supply of air conditioning in a subway station.

[0030] In this embodiment, the cooling control method of the subway station air conditioner includes:

[0031] Step S1, based on the cooling load prediction model, predict the cooling load demand of the ground station in the prediction period to obtain cooling load prediction data.

[0032] Step S1 specifically includes the following steps:

[0033] Step S11: extract and preprocess features based on the historical operation data of the subway station to obtain a second feature set.

[0034] like Figure 3 As shown, step S11 specifically includes the following steps:

[0035] Step S11-1: Acquire the meteorological data, passenger flow data, equipment energy consumption data and cooling load data of the subway station at all historical times as historical operation data; wherein the meteorological data includes but is not limited to indoor and outdoor temperature and humidity and outdoor wind speed; the passenger flow data includes but is not limited to the number of people entering and exiting the subway station; the equipment energy consumption data includes but is not limited to the real-time power value, real-time voltage value and real-time current value of various equipment in the air-conditioning system.

[0036] In this embodiment, a moment represents a shorter time interval, which can be set according to different prediction accuracy requirements.

[0037] Step S11-2: using the Pearson correlation calculation method, calculate the correlation between other different types of data in the historical operation data and the cooling load data, and use the multiple types of data with correlations greater than the first preset correlation as main features.

[0038] Assume that the historical operation data includes four types of data, namely data A, data B, data C and data D. The data value corresponding to data A at each historical moment constitutes a data set Ra. Similarly, data B corresponds to a data set Rb, data C corresponds to a data set Rc, data D corresponds to a data set Rd, and the cooling load data corresponds to a data set Re. Using the Pearson correlation calculation method, the correlation between data A and the cooling load data can be calculated based on the data set Ra and the data set Re. Similarly, the correlation between data B, data C and data D and the cooling load data can be calculated separately. If the correlation between data B, data C and data D and the cooling load data is greater than the first preset correlation, data B, data C and data D are used as the main features.

[0039] Step S11-3: using a time series prediction tool, performing time series feature mining on the cooling load data to obtain date features, performing feature expansion on the main features to obtain a first feature set; the date features include periodic features, seasonal features, and holiday features of the cooling load.

[0040] Step S11-4: Map the date features and convert them into numerical form so that the model can understand them; then label the holiday features of the cooling load so that the model can identify the holidays; in addition, fuzzy the temperature and humidity features of the cooling load through the membership function, and map the temperature and humidity values ​​to different fuzzy categories; finally, normalize all the data and construct the second feature set.

[0041] Step S12: training the TPA-TCN model based on the second feature set to obtain a cooling load prediction model;

[0042] Step S12 specifically includes:

[0043] Step S12-1: K-means clustering is performed based on the passenger flow data to divide a day into four different time periods; the four different time periods are the passenger flow peak period, the passenger flow from high to low peak period, the passenger flow low peak period and the passenger flow from low to peak period.

[0044] Step S12-2: Divide the daily feature data in the second feature set according to the corresponding four time periods to obtain four training subsets; normalize the four training subsets to obtain four feature vectors.

[0045] Step S12-3: input the four groups of feature vectors into the TPA-TCN model for training respectively, and obtain the cooling load prediction models corresponding to the four time periods.

[0046] Among them, the network structure of the TPA-TCN model includes a sequentially connected input layer, a DCC dilated causal convolution layer, a residual block, a TPA mechanism layer, and a fully connected layer. This network structure is used in model training in each period.

[0047] Taking the model training during peak passenger flow hours as an example, the input layer receives a normalized feature vector with a dimension of d=20, that is, the input feature for each time step consists of 20 values, each of which represents the normalized feature value of features of different dimensions in the training subset (for example, temperature, humidity, passenger flow, etc.).

[0048] The DCC dilated causal convolution layer performs convolution on the feature vector received by the input layer to obtain the convolution result Conv(x). During the convolution process, the convolution kernel size is set to 25 and the dilation coefficient is set to 2. nExponential growth. When a convolution kernel of size 25 slides one time step, it will perform convolution processing on the data points of 25 consecutive time steps in the feature vector. At the same time, according to 2 n The interval (expansion coefficient) in the convolution kernel is increased by multiple times to expand the receptive field and extract the long-term temporal dependency of the cold load.

[0049] The residual block activates the convolution result Conv(x) of the DCC dilated causal convolution layer through the RELU activation function, setting negative values ​​to zero and retaining positive values. On this basis, the input feature vector x itself is superimposed to avoid the problem of gradient vanishing or gradient exploding. Then, the output of the residual block is:

[0050] ;

[0051] in, is the output of the residual block, is the input feature vector, Represents the feature vector The convolution result obtained by performing the convolution operation is Indicates an activation operation.

[0052] Output results of the TPA mechanism layer for the residual block , 10 one-dimensional convolution kernels are used to perform convolution operations on the time series, extract the time series features, and output the convolution results. Then the convolution results are normalized using the Softmax activation function to obtain the time series attention weight matrix:

[0053] ;

[0054] in, represents a one-dimensional convolution operation, Represents a normalization operation.

[0055] Use the obtained time attention weight matrix W to input features Perform weighting to generate weighted features:

[0056] ;

[0057] in, Represents a weighted feature. The original input features are calculated based on the time attention weight matrix W. Weighting is performed to emphasize important time step features and weaken unimportant time step features, so that the model can better focus on the key moments in the time series, thereby improving the performance of the model.

[0058] The fully connected layer outputs the normalized cooling load prediction value at each moment in the corresponding prediction period.

[0059] During the model training process, the HuberLoss (δ=1.0) function is used as the loss function of the TPA-TCN model, which can combine the advantages of the mean square error (MSE, MeanSquaredError) and the mean absolute error (MAE, MeanAbsoluteError). Specifically, when the error is small, the HuberLoss loss function will use MSE to measure the prediction error, so that the hyperparameters of the cold load prediction model (such as learning rate, optimizer parameters, batch size, and δ value of the HuberLoss loss function) can be adjusted more finely; when the error is large, MAE is used to measure the prediction error to avoid excessive influence from outliers. The Adam optimizer is used to calculate the adaptive learning rate of each weight parameter in the model, and the weight parameters are updated based on the first-order moment estimate (the average value of the gradient) and the second-order moment estimate (the average value of the square of the gradient). Among them, the initial learning rate , controls the decay rate of the first-order moment estimate Set to 0.9 to control the decay rate of the second-order moment estimate Set to 0.999. Use R 2 (variance), MAPE (mean absolute percentage error), and MAE (mean absolute error) are used as evaluation indicators for the prediction results of the cold load prediction model. The early stopping method is used to prevent the model from overfitting. When the validation loss does not decrease for 10 consecutive rounds, the training is terminated to obtain the optimal cold load prediction model.

[0060] Step S13: inputting the real-time value of the feature corresponding to the second feature set within the prediction period into the cooling load prediction model to obtain the cooling load prediction data.

[0061] Specifically, the cooling load prediction model is used to analyze and calculate the cooling load value corresponding to each moment in the prediction period according to the input characteristic real-time value. After all calculations are completed, the cooling load prediction data corresponding to the prediction period is obtained.

[0062] Step S2: Based on the cooling load redistribution model, the cooling load prediction data is redistributed in the time dimension to obtain the cooling load distribution result.

[0063] like Figure 4 As shown, step S2 specifically includes the following steps:

[0064] Step S2-1: Obtain time-of-use electricity price characteristics and passenger flow characteristics, and design adaptive load regulation factors.

[0065] Based on the trend of time-of-use electricity prices, feature extraction is performed to obtain time-of-use electricity price features. Feature extraction is performed on the passenger flow data of subway stations to obtain passenger flow features. Based on the time-of-use electricity price features and passenger flow features, an adaptive load control factor is designed so that the cold load redistribution model can dynamically adjust the cold load shift value according to the passenger flow and time-of-use electricity price trends, thereby realizing the dynamic redistribution of cold load forecast data.

[0066] First, based on passenger flow characteristics, construct passenger flow control factors :

[0067] ;

[0068] in, It represents the normalized time distance from the peak passenger flow at time t, between 0 and 1. When it is equal to 0, it means that time t is the peak time of passenger flow. When it is equal to 1, it means that time t is the valley moment of passenger flow; is the distance threshold, set to 0.4, indicating a critical value. Less than It is considered as the “passenger flow peak period”. Greater than When the passenger flow is less than 100 km / h, it is regarded as the “non-peak passenger flow stage”; k is the curve steepness coefficient, ranging from 2 to 3, which is used to adjust the slope of the passenger flow control factor and determines the speed at which the passenger flow control factor changes over time. A higher k value will lead to more drastic changes in the control factor; Represents power function calculation.

[0069] Then, based on the characteristics of time-of-use electricity prices, the time-of-use electricity price regulation factor is constructed. :

[0070] ;

[0071] in, is the countdown time to the peak electricity price. is the time attenuation coefficient, It is the electricity price benchmark factor (that is, the normal benchmark electricity price).

[0072] The time-of-use electricity price control factor can adjust the cooling load value at each moment in the forecast period according to the change of electricity price. Specifically, at the moment of high electricity price, the time-of-use electricity price control factor suppresses the increase of the cooling load value at that moment, and at the moment of low electricity price, the time-of-use electricity price control factor allows the cooling load value at that moment to increase.

[0073] Finally, based on the passenger flow control factor and time-of-use electricity price control factors Establishing adaptive load regulation factors :

[0074] ;

[0075] in, To adjust the willingness factor (fine-tuned by the operator according to actual conditions and needs); is the dynamic weight factor, that is, the synchronization degree between the peak and valley state of time-of-use electricity price and the peak and valley state of passenger flow. The calculation formula is:

[0076] ;

[0077] in, is the time difference between the current time and the nearest cooling load peak, It is the time difference between the current time and the nearest electricity price peak.

[0078] It can be seen that the dynamic weight factor The degree of misalignment between the peak and valley states of time-of-use electricity prices and the peak and valley states of passenger flows can be measured. The closer it is to 0.5, the more significant the misalignment is, which means that the cooling load regulation will remain at a moderate level. The closer it is to 1, the closer the peaks and valleys of electricity prices and passenger flow are to synchronization, and the more effective the cooling load regulation is. It can allocate more cooling load during low electricity price periods and suppress the increase of cooling load during high electricity price periods. It can adjust the cooling load more flexibly according to the specific operating conditions, thereby realizing the dynamic redistribution of cooling load forecast data, making the regulation process more in line with the actual needs of the subway station.

[0079] Step S2-2: Based on the adaptive load control factor, human comfort constraints, cooling load movement constraints and equipment constraints are established, and an objective function is constructed with the goal of minimizing electricity costs, thereby constructing a cooling load redistribution model.

[0080] (1) Establish human comfort constraints:

[0081] First, construct the human comfort constraint index:

[0082] ;

[0083] in, represents the human comfort constraint index, is the partial pressure of water vapor (unit: Pa), M is the metabolic rate of the human body (unit: W / ㎡), is the ambient dry-bulb temperature at time t (in °C), is the thermal resistance of the clothing after sweat immersion, is the thermal resistance of the air boundary outside the clothing, and R is the average heat energy radiated per unit skin area (in W / ㎡). The indoor temperature at the corresponding time and outdoor temperature When calculating indoor human comfort, the ambient dry bulb temperature The indoor temperature is taken When calculating outdoor human comfort, the ambient dry bulb temperature The outdoor temperature is taken .

[0084] Then, according to the principle of dynamic heat balance, the relationship between indoor and outdoor temperature and cooling load is established to constrain the human comfort index. and cooling load The relationship between:

[0085] ;

[0086] in, represents the heat transfer coefficient of the furnace structure (in W / ℃), C represents the air heat capacity of the subway station hall (in J / ℃), Indicates the indoor heat source. Indicates cooling load.

[0087] The human comfort constraints constructed include two aspects: absolute constraints and relative constraints:

[0088] Absolute constraints: , ;

[0089] , ;

[0090] Relative constraints: , ;

[0091] , ;

[0092] in, Indicates the start time, Indicates the end time. represents the indoor target temperature at time t, represents the human comfort constraint index at time t, represents the human comfort constraint index at time t+1, represents the outdoor human comfort constraint index at time t, Represents the indoor human comfort constraint index at time t.

[0093] (2) Establish cooling load transfer constraints:

[0094] Total cooling load constraint: ;

[0095] Constraints on the range of movement at a single moment: ;

[0096] in, represents the cooling load value at time t before redistribution, Represents the cooling load value at time t after redistribution.

[0097] (3) Establish equipment constraints:

[0098] ;

[0099] in, represents the target cooling capacity, Indicates the minimum cooling capacity allowed by the air-conditioning equipment. Indicates the maximum cooling capacity allowed by the air conditioning equipment.

[0100] Next, based on the above constraints, the objective function of the cooling load redistribution model is established with the minimum electricity cost as the goal:

[0101] ;

[0102] in, is the electricity price at time t (in yuan / kWh), is the RWI comfort penalty coefficient.

[0103] Step S2-3: Input the cooling load prediction data into the cooling load redistribution model, and use the improved Black Kite algorithm to solve it to obtain the cooling load distribution result.

[0104] Firstly, the cooling load forecast data is input into the cooling load redistribution model, and the cooling load redistribution strategy is obtained based on the improved Black Kite algorithm.

[0105] Among them, the improvements of the Black Kite algorithm include:

[0106] Improvement 1: Chaotic mapping is introduced for initialization improvement, so that the Black Kite algorithm has a more uniform solution distribution in the initialization stage, so as to increase the diversity of initial solutions and improve the quality of solutions.

[0107] Improvement 2: A reverse learning mechanism is added to enable the Black Kite algorithm to search in both forward and reverse directions during the particle search process, thereby speeding up the search efficiency.

[0108] Improvement 3: Improve the nonlinear factor in the attack phase of the Black Kite algorithm. Specifically, add Beta perturbation to the nonlinear factor, so that a large search range is performed in the early stage of the search, and the search range is gradually reduced in the later stage to achieve convergence faster. The improved nonlinear factor is:

[0109] ;

[0110] in, represents a random perturbation (i.e., generating a random value sampled from a Beta distribution), represents the disturbance intensity control parameter.

[0111] Then, based on the cooling load redistribution strategy, the cooling load prediction data is redistributed to obtain the cooling load distribution result.

[0112] The cooling load redistribution strategy includes the cooling load adjustment value corresponding to each moment in the prediction period. The cooling load prediction data includes the cooling load prediction value corresponding to each moment in the prediction period. In the cooling load redistribution process, the cooling load prediction value is adjusted according to the cooling load adjustment value at each moment to obtain the cooling load value after redistribution. Finally, the cooling load distribution result corresponding to the entire prediction period is obtained.

[0113] In the entire step 2, the cooling load redistribution model is used to shift the cooling load forecast data obtained by the cooling load forecast model in combination with the time-of-use electricity price and human comfort, so as to achieve the effect of "pre-cooling during valley hours and using cooling during peak hours", thereby reducing electricity costs.

[0114] Step S3: Based on the air conditioning water system optimization model, cooling load distribution results, air conditioning equipment constraints and water cycle parameter fluctuation constraints, the air conditioning unit parameters are solved to obtain the optimal parameter group.

[0115] like Figure 5 As shown, step S3 specifically includes the following steps:

[0116] Step S3-1: Based on the operating data of the internal equipment of the air-conditioning unit, the air-conditioning water system optimization model is constructed with the minimum energy consumption and the maximum energy efficiency as the goal.

[0117] The internal equipment of the air conditioning unit may include a chiller, a refrigeration water pump, a cooling water pump, a cooling tower fan, and an air conditioning box fan. The operation data of the internal equipment of the air conditioning unit refers to data related to the energy consumption calculation of the internal equipment of the air conditioning unit.

[0118] First, based on the operating data, the least squares method is used to determine the calculation coefficients in the energy consumption calculation formula of the internal equipment of the air-conditioning unit, which is also the energy consumption model parameter. Then, based on the energy consumption model parameters, the mathematical model of the air-conditioning water system is constructed:

[0119] ;

[0120] in, represents the total energy consumption of the air conditioning water system, represents the energy consumption of the chiller, represents the energy consumption of the chilled water pump, Indicates the energy consumption of the cooling water pump, represents the energy consumption of cooling tower fan, Indicates the energy consumption of the air conditioning box fan.

[0121] Then, based on the mathematical model of the air conditioning water system, with the minimum energy consumption and maximum energy efficiency as the goal, the optimization model of the air conditioning water system was constructed:

[0122] ;

[0123] in, represents the overall goal of the model, represents the minimum total energy consumption target, represents the maximum energy efficiency target, represents the minimum total energy consumption, Indicates maximum energy efficiency, Indicates the total cooling capacity.

[0124] Step S3-2: Based on the water circulation parameters of the internal equipment of the air conditioning water system, establish air conditioning equipment constraints and water circulation parameter fluctuation constraints.

[0125] The water circulation parameters of the internal equipment of the air conditioning water system may include the outlet water temperature of the chilled water pump, the return water temperature of the cooling water pump, the flow rate of the cooling water pump, and the flow rate of the cold water pump. The water circulation parameters reflect the heat balance of the air conditioning water and the energy transfer process of the internal equipment of the air conditioning water system.

[0126] First, establish air conditioning equipment constraints based on water cycle parameters:

[0127] ;

[0128] ;

[0129] ;

[0130] ;

[0131] in, Indicates the chilled water pump outlet temperature. Indicates the minimum outlet water temperature of the chilled water pump. Indicates the maximum outlet water temperature of the chilled water pump. Indicates the return water temperature of the cooling water pump. Indicates the minimum return water temperature of the cooling water pump. Indicates the maximum return water temperature of the cooling water pump. Indicates the cooling water pump flow rate, Indicates the minimum flow rate of the cooling water pump. Indicates the maximum flow rate of the cooling water pump. Indicates the chilled water pump flow rate, Indicates the minimum flow rate of the chilled water pump. Indicates the maximum flow rate of the chilled water pump.

[0132] Then, based on the average value of the water cycle parameters in the past preset period, a water cycle parameter fluctuation constraint is established. Specifically, based on the water cycle parameters under the extreme working conditions where the air conditioning water system can operate stably, a parameter fluctuation threshold is determined. That is, the difference between the characteristic value of the water cycle parameters under the extreme working conditions at this moment and the average value of the water cycle parameters in the past preset period. The water cycle parameter fluctuation constraint is:

[0133] ;

[0134] in, The difference between the characteristic value of the water cycle parameter at this moment and the average value of the water cycle parameter in the past preset period of time. is the parameter fluctuation threshold. The water cycle parameters determine the operating state of the air conditioning water system. Establishing water cycle parameter fluctuation constraints can ensure the stable operation of the air conditioning water system.

[0135] Step S3-3: Input the cooling load distribution result into the air conditioning water system optimization model, and perform multi-objective solution on the air conditioning unit parameters based on the air conditioning equipment constraints and water cycle parameter fluctuation constraints to obtain the optimal parameter group.

[0136] Specifically, the cooling load distribution result obtained in step S2 is first used as the total cooling input to construct the air conditioning water system optimization model, and the NSGA-II algorithm is used to solve the air conditioning unit parameters for multiple objectives in combination with the air conditioning equipment constraints and water cycle parameter fluctuation constraints, and obtain a solution set containing multiple target variables, each of which is a parameter group of the air conditioning unit. Then, the subjective weight z1 and objective weight z2 of the target variable (that is, the solution target) are obtained according to the expert's subjective setting and gray correlation analysis, and then the subjective weight z1 and objective weight z2 are weighted averaged according to the preset ratio of the subjective weight z1 to the objective weight z2 (for example, 4:6) to obtain the comprehensive weight z3. Finally, the Topsis method is used to weight the target variable first using the comprehensive weight z3, and then the distance between each parameter group and the ideal solution is calculated. According to the measurement results, the parameter group with the smallest distance is selected as the optimal parameter group.

[0137] Finally, the optimal parameter group will be obtained for the operation control of the subway station air conditioning, achieving the purpose of cooling regulation of the subway station air conditioning.

[0138] In the entire step S3, based on the air conditioning water system optimization model, cooling load distribution results, air conditioning equipment constraints and water cycle parameter fluctuation constraints, the air conditioning unit parameters are solved. While ensuring that the air conditioning can still meet the water and heat balance conditions under different loads, the energy consumption of the air conditioning can be minimized, energy use can be reduced, and the fluctuation of water cycle parameters can be limited to ensure the stable operation of the air conditioning water system. Therefore, through the multi-generation evolution of the NSGA-II algorithm, the optimal parameter group can achieve the best balance between energy efficiency, performance indicators and stability.

[0139] In this embodiment, the cooling load prediction model is used to accurately predict the cooling load demand on the demand side within the prediction period, and the cooling load prediction data is obtained. On this basis, the cooling load redistribution model is used to comprehensively consider factors such as passenger flow, electricity prices, and human comfort, and the cooling load prediction data is reasonably redistributed in the time dimension, taking into account passenger comfort while saving electricity costs. Finally, the optimal air-conditioning unit parameters are solved by combining the air-conditioning water system optimization model, equipment constraints, and water cycle parameter fluctuation constraints to ensure that the air-conditioning equipment operates in the best state, thereby improving energy efficiency and reducing energy consumption. The present invention improves the operating efficiency of the air-conditioning system as a whole, saves energy costs, and reduces unnecessary energy consumption while ensuring the comfort level in the subway station and the long-term stable operation of the equipment.

[0140] Furthermore, in order to achieve the above-mentioned purpose, the present invention also provides a subway station air conditioning cooling control device, which may include:

[0141] A cooling load prediction module is used to predict the cooling load demand of the ground station in the prediction period based on the cooling load prediction model and obtain cooling load prediction data;

[0142] A cooling load redistribution module is used to redistribute cooling load forecast data in the time dimension based on a cooling load redistribution model to obtain cooling load distribution results;

[0143] The parameter solving module is used to solve the air-conditioning unit parameters based on the air-conditioning water system optimization model, cooling load distribution results, air-conditioning equipment constraints and water cycle parameter fluctuation constraints to obtain the optimal parameter group.

[0144] It should be noted that the functions that can be realized by each module in the subway station air conditioning and cooling control device provided in this embodiment and the corresponding technical effects achieved can refer to the description of the specific implementation methods in each embodiment of the subway station air conditioning and cooling control method of the present invention. For the sake of brevity of the specification, they will not be repeated here.

[0145] In addition, an embodiment of the present invention further proposes a computer-readable storage medium, on which a subway station air conditioning cooling control program is stored. When the subway station air conditioning cooling control program is executed by a processor, the steps of the subway station air conditioning cooling control method as described above are implemented. Therefore, it will not be repeated here. In addition, the description of the beneficial effects of adopting the same method will not be repeated. For technical details not disclosed in the computer-readable storage medium embodiment involved in the present invention, please refer to the description of the method embodiment of the present invention. As an example, the program instructions can be deployed to be executed on one computing device, or on multiple computing devices located at one location, or on multiple computing devices distributed at multiple locations and interconnected by a communication network.

[0146] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, the elements defined by the sentence "including a subway station air conditioning cooling control" do not exclude the existence of other identical elements in the process, method, article or system including the element.

[0147] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0148] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a computer-readable storage medium (such as ROM / RAM, magnetic disk, optical disk) as above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0149] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for controlling cooling supply of air conditioners in a subway station, characterized in that: The subway station air conditioning cooling control method comprises the following steps: S1, based on the cooling load prediction model, predict the cooling load demand of the ground station in the prediction period to obtain cooling load prediction data; S2, based on the cooling load redistribution model, redistribute the cooling load prediction data in the time dimension to obtain a cooling load distribution result; S3, based on the air conditioning water system optimization model, the cooling load distribution result, the air conditioning equipment constraints and the water cycle parameter fluctuation constraints, the air conditioning unit parameters are solved to obtain the optimal parameter group.

2. The subway station air conditioning cooling control method according to claim 1, characterized in that: The S1 specifically includes: S11, extracting and preprocessing features based on historical operation data of the subway station to obtain a second feature set; S12, training the TPA-TCN model based on the second feature set to obtain the cooling load prediction model; S13, inputting the real-time value of the feature corresponding to the second feature set within the prediction period into the cooling load prediction model to obtain the cooling load prediction data.

3. The subway station air conditioning cooling control method according to claim 1, characterized in that: The S2 specifically includes: S2-1, obtain time-of-use electricity price characteristics and passenger flow characteristics, and design adaptive load control factors; S2-2, based on the adaptive load control factor, establish human comfort constraints, cooling load movement constraints and equipment constraints, construct an objective function with the goal of minimizing electricity costs, and thus construct a cooling load redistribution model; S2-3, inputting the cooling load prediction data into the cooling load redistribution model, solving it using the improved Black Kite algorithm, and obtaining the cooling load distribution result.

4. The subway station air conditioning cooling control method according to claim 3, characterized in that: The S2-1 specifically includes: S2-1-1, obtain passenger flow characteristics and construct passenger flow control factors : ； in, It represents the normalized time distance from the peak passenger flow at time t; is the distance threshold; k is the curve steepness coefficient; Represents power function calculation; S2-1-2, obtain time-of-use electricity price characteristics and construct time-of-use electricity price regulation factors : ； in, is the countdown time to the peak electricity price. is the time attenuation coefficient, is the electricity price benchmark factor; S2-1-3, based on passenger flow control factors and time-of-use electricity price control factors Establishing adaptive load regulation factors : ； in, To regulate the willingness factor; is the dynamic weight factor, and the calculation formula is: ； in, is the time difference from time t to the nearest cooling load peak, It is the time difference between time t and the nearest electricity price peak.

5. The subway station air conditioning cooling control method according to claim 1, characterized in that: The S3 specifically includes: S3-1, based on the operation data of the internal equipment of the air-conditioning unit, constructing the air-conditioning water system optimization model with the minimum energy consumption and maximum energy efficiency as the goal; S3-2, based on the water circulation parameters of the internal equipment of the air conditioning water system, establish air conditioning equipment constraints and water circulation parameter fluctuation constraints; S3-3, input the cooling load distribution result into the air conditioning water system optimization model, and based on the air conditioning equipment constraints and the water cycle parameter fluctuation constraints, perform multi-objective solution on the air conditioning unit parameters to obtain the optimal parameter group.

6. The subway station air conditioning cooling control method according to claim 5, characterized in that: The S3-1 specifically includes: S3-1-1, based on the operation data of the internal equipment of the air-conditioning unit, determine the energy consumption model parameters of the internal equipment of the air-conditioning unit by using the least square method; S3-1-2, based on the energy consumption model parameters, construct a mathematical model of the air conditioning water system: ； in, represents the total energy consumption of the air conditioning water system, represents the energy consumption of the chiller, represents the energy consumption of the chilled water pump, Indicates the energy consumption of the cooling water pump, represents the energy consumption of cooling tower fan, Indicates the energy consumption of the air conditioning box fan; S3-1-3, based on the mathematical model of the air conditioning water system, with the minimum energy consumption and maximum energy efficiency as the goal, construct the optimization model of the air conditioning water system: ； in, represents the overall goal of the model, represents the minimum total energy consumption target, represents the maximum energy efficiency target, represents the minimum total energy consumption, Indicates maximum energy efficiency, Indicates the total cooling capacity.

7. The subway station air conditioning cooling control method according to claim 5, characterized in that: The S3-2 specifically includes: S3-2-1, establishing the air conditioning equipment constraints based on the water circulation parameters of the internal equipment of the air conditioning water system; S3-2-2, establishing a water cycle parameter fluctuation constraint based on the characteristic value of the water cycle parameter at this moment and the average value of the water cycle parameter in the past preset time period.

8. A subway station air conditioning cooling control device, characterized in that: The device comprises: A cooling load prediction module is used to predict the cooling load demand of the ground station in the prediction period based on the cooling load prediction model and obtain cooling load prediction data; A cooling load redistribution module, used for redistributing the cooling load prediction data in a time dimension based on a cooling load redistribution model to obtain a cooling load distribution result; The parameter solving module is used to solve the air conditioning unit parameters based on the air conditioning water system optimization model, the cooling load distribution result, the air conditioning equipment constraints and the water cycle parameter fluctuation constraints to obtain the optimal parameter group.

9. A subway station air conditioning cooling control device, characterized in that: The device includes: a memory, a processor, and a subway station air conditioning and cooling control program stored in the memory and executable on the processor, wherein the subway station air conditioning and cooling control program is configured to implement the steps of the subway station air conditioning and cooling control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a subway station air conditioning and cooling control program, and when the subway station air conditioning and cooling control program is executed by the processor, the steps of the subway station air conditioning and cooling control method according to any one of claims 1 to 7 are implemented.

Images