Chiller station simulation control method and device based on time series prediction, equipment and medium

Abstract

The application discloses a cold station simulation control method and device based on time sequence prediction, equipment and a medium, comprising: when a cold station simulation control request for a target building space is received, obtaining the associated target building cold station system operation data, inputting into a time sequence prediction model, and obtaining the end cold demand prediction value of the target building space; based on the prediction value and the operation data, calculating the initial water supply temperature value and the initial cold machine load rate as the to-be-optimized parameter combination; inputting the combination and the operation data into the time sequence prediction model, predicting the actual cooling capacity and calculating the deviation value; if the deviation does not satisfy the optimization condition, iteratively adjusting the parameters until the deviation converges; and sending the converged parameters to the cold station controller to realize simulation control on the specified equipment. Through time sequence prediction, closed-loop response and collaborative optimization, the application solves the problems of cold supply and demand imbalance, transient response lag and global optimization loss in traditional cold station control.

Description

Technical Field

[0001] This invention relates to the field of automation control technology, and in particular to a method, apparatus, equipment and medium for simulation control of a chiller plant based on time-series prediction. Background Technology

[0002] The chiller plant is the core cooling unit of a building's energy system, and its operating efficiency directly affects building energy consumption and indoor comfort. Currently, traditional chiller plant control mainly relies on PID control, fuzzy control, and adaptive control.

[0003] While traditional building cooling plant control strategies are feasible in certain scenarios, they are ill-suited to situations involving multi-device coupling and dynamic load forecasting, especially when faced with disturbances such as increased building scale, more equipment, and sudden weather changes. Specific shortcomings include: First, the lack of dynamic modeling of energy transfer between the cooling source and the terminal units makes it impossible to accurately match terminal cooling demand with the cooling capacity of the cooling source, leading to an imbalance between cooling supply and demand. Second, parameter adjustments rely on empirical formulas and do not consider time-delay characteristics such as pipeline delays and equipment inertia, resulting in lagging adjustments during sudden load changes. Third, neglecting system factors such as building inertia, pipeline temperature rise, and equipment heterogeneity prevents multi-device collaborative optimization, leading to increased energy consumption. Summary of the Invention

[0004] Based on this, the present invention provides a cooling plant simulation control method, device, equipment and medium based on time-series prediction to solve the problems of cooling capacity supply and demand imbalance, transient response lag and lack of global optimization in traditional cooling plant control.

[0005] In a first aspect, embodiments of the present invention provide a cooling plant simulation control method based on time-series prediction, comprising:

[0006] In response to a cooling station simulation control request initiated for a target building space, the system acquires the operation data of the target building cooling station system associated with the target building space, and inputs the operation data into a pre-trained time series prediction model to obtain the predicted value of the terminal cooling demand of the target building space within a specified future period.

[0007] Based on the predicted terminal cooling demand and the operating data, the initial water supply temperature and initial chiller load rate of the target building space are calculated and used as the combination of parameters to be optimized.

[0008] The combination of parameters to be optimized and the operating data are input into the time series prediction model to predict the actual cooling capacity of the target building cooling station system to the target building space under the current input parameter combination, and to calculate the deviation between the actual cooling capacity and the predicted value of the terminal cooling capacity demand of the target building space.

[0009] Determine whether the deviation value meets the deviation optimization conditions. If so, iteratively adjust the initial water supply temperature and initial chiller load rate based on the deviation value to obtain a new combination of parameters to be optimized. Then, input the deviation value and the operating data into the time series prediction model to re-predict the actual cooling capacity for the target building space until the deviation value meets the preset convergence conditions.

[0010] The new water supply temperature and the new chiller load rate when the preset convergence conditions are met are taken as the final combination of operating parameters for the target building space, and the final combination of operating parameters is sent to the controller of the target building chiller station system for simulated control of the designated chiller station equipment.

[0011] Secondly, embodiments of the present invention also provide a cooling plant simulation control device based on time-series prediction, comprising:

[0012] The terminal cooling demand prediction module is used to respond to a cooling station simulation control request initiated for a target building space, acquire the operation data of the target building cooling station system associated with the target building space, and input the operation data into a pre-trained time series prediction model to obtain the terminal cooling demand prediction value of the target building space within a specified future period.

[0013] The module for obtaining the combination of parameters to be optimized is used to calculate the initial water supply temperature and initial chiller load rate of the target building space based on the predicted value of the terminal cooling demand and the operating data, and use them as the combination of parameters to be optimized.

[0014] The deviation value calculation module is used to input the combination of parameters to be optimized and the operating data into the time series prediction model, predict the actual cooling capacity of the target building cooling station system to the target building space under the current input parameter combination, and calculate the deviation value between the actual cooling capacity and the predicted value of the terminal cooling capacity demand of the target building space.

[0015] The iterative optimization module is used to determine whether the deviation value meets the deviation optimization conditions. If so, iteratively adjusts the initial water supply temperature value and the initial chiller load rate based on the deviation value to obtain a new combination of parameters to be optimized. By inputting the deviation value and the operating data into the time series prediction model, the actual cooling capacity for the target building space is re-predicted until the deviation value meets the preset convergence conditions.

[0016] The simulation control distribution module is used to take the new water supply temperature value and the new chiller load rate when the preset convergence conditions are met as the final operating parameter combination for the target building space, and send the final operating parameter combination to the controller of the target building chiller station system for simulation control of the specified chiller station equipment.

[0017] Thirdly, embodiments of the present invention also provide an electronic device, the electronic device comprising:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform a time-prediction-based cold storage simulation control method according to any embodiment of the present invention.

[0021] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute and implement a timing prediction-based cold station simulation control method as described in any embodiment of the present invention.

[0022] This invention, through time-series prediction, accurately locks in end-point demand and combines iterative optimization parameters with deviations to overcome the shortcomings of traditional control, such as difficulty in accurately simulating the dynamic balance of energy between the cooling source and the end point, and the tendency of strategies to deviate from the optimal state, thus achieving precise matching of cooling supply and demand. It constructs a "prediction-adjustment-feedback" closed-loop mechanism to overcome the shortcomings of traditional control, such as the inability to accurately predict the time-delay characteristics of temperature change processes and response lag, significantly improving the transient response speed of the chiller plant system. By using water supply temperature and chiller load rate as collaborative optimization parameters, and combining them with operational data, it achieves collaborative optimization of multiple devices, compensating for the lack of unified modeling of building inertia, network temperature rise, and equipment heterogeneity in traditional control, thereby reducing energy waste and minimizing losses caused by frequent equipment switching.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a cooling plant simulation control method based on time-series prediction according to Embodiment 1 of the present invention;

[0026] Figure 2This is a flowchart of another time-series prediction-based simulation control method for chiller plants provided according to Embodiment 2 of the present invention;

[0027] Figure 3 This is a schematic diagram of a cooling plant simulation control device based on time-series prediction according to Embodiment 3 of the present invention;

[0028] Figure 4 This is a schematic diagram of the structure of an electronic device that implements a time-prediction-based cold station simulation control method according to an embodiment of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Example 1

[0032] Figure 1 This is a flowchart of a time-series prediction-based cooling plant simulation control method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where terminal cooling demand prediction and multi-parameter collaborative optimization control are performed on centralized cooling plants through simulation prediction. This method can be executed by a time-series prediction-based cooling plant simulation control device, which can be implemented in hardware and / or software. This device can be configured in a building energy lifecycle simulation platform or a customized cooling plant-specific simulation system. Figure 1 As shown, the method includes:

[0033] S110. In response to the cooling station simulation control request initiated for the target building space, obtain the operation data of the target building cooling station system associated with the target building space, and input the operation data into a pre-trained time series prediction model to obtain the predicted value of the terminal cooling demand of the target building space within a specified future period.

[0034] In this embodiment of the invention, the target building space refers to a specific area requiring independent cooling capacity control, such as a tower in an office building or a restaurant floor in a shopping mall. It must have a clear pipeline connection and data interaction relationship with the chiller plant system. Operational data can cover real-time operating parameters, historical operating sequence data, and related environmental parameters of core equipment such as chillers, chilled water pumps, and cooling water pumps. The pre-trained time-series prediction model used is a specialized model trained using deep learning algorithms based on the historical operating data of the target building's chiller plant. Its special characteristic is that it is adapted to the equipment characteristics of the chiller plant and the cooling usage patterns of the target space, rather than a general model. The predicted terminal cooling demand value within a specified future period is actually a quantitative prediction of the future cooling load of the target space by the model. The period length can be set according to the control accuracy requirements. The underlying logic of this step is: through time-series analysis of multi-dimensional data using a specialized model, it avoids the bias of traditional experience-based demand estimation, providing an accurate demand benchmark for subsequent cooling parameter settings.

[0035] S120. Based on the predicted terminal cooling demand and the operating data, calculate the initial water supply temperature and initial chiller load rate of the target building space and use them as a combination of parameters to be optimized.

[0036] The initial supply water temperature refers to the set temperature at which the chiller plant delivers chilled water to the target space. Setting the temperature too high may lead to insufficient cooling at the terminal, while setting it too low will increase chiller energy consumption. The initial chiller load rate is the proportion of power the chiller needs to output to meet demand relative to its rated power. It needs to be calculated based on the chiller's performance curve to avoid overloading the equipment or wasting energy due to underloading. The combination of these two parameters, forming the set of parameters to be optimized, is essentially a preliminary control scheme to meet predicted demand; that is, an initial benchmark based on the balance of "demand-supply" theory.

[0037] S130. Input the combination of parameters to be optimized and the operating data into the time series prediction model to predict the actual cooling capacity of the target building cooling station system to the target building space under the current input parameter combination, and calculate the deviation between the actual cooling capacity and the predicted value of the terminal cooling capacity demand of the target building space.

[0038] When the combination of parameters to be optimized and operational data are input into the time-series forecasting model, the model's role shifts from demand forecasting to cooling effect simulation. The core function is to simulate the actual cooling capacity that the chiller system can deliver to the target building space under the given parameter combination, after pipeline transportation and terminal heat exchange, using an embedded chiller system mechanism model. The deviation value essentially quantifies the gap between the theoretical control scheme and the actual cooling effect, providing a clear direction for subsequent parameter adjustments.

[0039] S140. Determine whether the deviation value meets the deviation optimization conditions. If so, iteratively adjust the initial water supply temperature value and the initial chiller load rate based on the deviation value to obtain a new combination of parameters to be optimized. Input the parameters together with the operating data into the time series prediction model to re-predict the actual cooling capacity for the target building space until the deviation value meets the preset convergence conditions.

[0040] The existence of deviation values ​​indicates that the initial parameter combination needs further optimization. This embodiment of the invention achieves dynamic approximation of the optimal solution through an iterative adjustment mechanism. The core is to coordinately adjust the initial water supply temperature and initial chiller load rate using a gradient descent algorithm based on the magnitude and direction of the deviation values, generating a new parameter combination to be optimized. The simulation prediction process in S130 is repeated, recalculating the actual cooling capacity and deviation values ​​until the deviation values ​​meet a preset convergence condition. This convergence condition is a preset parameter optimization accuracy target, signifying that the parameter combination has achieved an acceptable match between the cooling capacity and the predicted demand.

[0041] S150. The new water supply temperature and the new chiller load rate when the preset convergence conditions are met are taken as the final operating parameter combination for the target building space, and the final operating parameter combination is sent to the controller of the target building chiller system for simulated control of the designated chiller equipment.

[0042] When the deviation value meets the convergence condition, the water supply temperature and chiller load rate at this point constitute the final operating parameter combination. This combination represents the optimal solution found under the current operating conditions, satisfying both the cooling capacity requirements of the target space and balancing the energy consumption and equipment safety of the chiller plant system. The controller of the target building chiller plant system specifically refers to the centralized control unit of the chiller plant, which has the ability to receive digital commands and convert them into equipment control signals. After receiving the parameter combination, the controller will adjust the designated chiller plant equipment according to the parameters, completing a closed-loop process from parameter optimization at the algorithm level to equipment operation adjustment at the physical level.

[0043] This invention, through time-series prediction, accurately locks in end-point demand and combines iterative optimization parameters with deviations to overcome the shortcomings of traditional control, such as difficulty in accurately simulating the dynamic balance of energy between the cooling source and the end point, and the tendency of strategies to deviate from the optimal state, thus achieving precise matching of cooling supply and demand. It constructs a "prediction-adjustment-feedback" closed-loop mechanism to overcome the shortcomings of traditional control, such as the inability to accurately predict the time-delay characteristics of temperature change processes and response lag, significantly improving the transient response speed of the chiller plant system. By using water supply temperature and chiller load rate as collaborative optimization parameters, and combining them with operational data, it achieves collaborative optimization of multiple devices, compensating for the lack of unified modeling of building inertia, network temperature rise, and equipment heterogeneity in traditional control, thereby reducing energy waste and minimizing losses caused by frequent equipment switching.

[0044] Optionally, it is determined whether the deviation value meets the deviation optimization condition. If so, a new combination of parameters to be optimized is obtained by iteratively adjusting the initial water supply temperature and initial chiller load rate based on the deviation value. This new combination is then input into the time-series prediction model along with the operating data to re-predict the actual cooling capacity for the target building space until the deviation value meets the preset convergence condition, including:

[0045] The calculated deviation value is compared with a preset deviation optimization threshold. If the deviation value is greater than the deviation optimization threshold, the deviation optimization condition is determined to be met.

[0046] An adjustment range coefficient is determined based on the magnitude of the deviation value, and the initial water supply temperature and the initial chiller load rate are adjusted according to the adjustment range coefficient; wherein the adjustment range coefficient is positively correlated with the deviation value;

[0047] The adjusted water supply temperature and chiller load rate are used as a new combination of parameters to be optimized, and are input together with the operating data into the time series prediction model to re-obtain the actual cooling capacity for the target building space, and the deviation value is recalculated based on the new actual cooling capacity.

[0048] The process of adjusting parameters and calculating the actual cooling capacity and the calculated deviation value is repeated until the recalculated deviation value is less than or equal to the preset convergence threshold, at which point the preset convergence condition is determined to be met.

[0049] The preset deviation optimization threshold is a quantitative standard set according to the control accuracy requirements of the chiller plant system, representing the critical deviation value at which parameter adjustments are needed. The adjustment amplitude coefficient is a correction coefficient set in this embodiment that is positively correlated with the deviation value. Its core function is to match the parameter adjustment amplitude with the severity of the deviation. The new parameter combination and operating data are input into the time series prediction model again. At this time, the model will simulate the actual operating state of the chiller plant based on the new parameters, re-output the actual cooling capacity, and obtain the new deviation value through the calculation of "new actual cooling capacity - terminal cooling demand prediction value". Essentially, this is to simulate and verify the effect of the adjusted parameters. The core purpose is to confirm whether the parameter adjustment has effectively reduced the deviation, providing a basis for the next round of adjustments. If the new deviation value still exceeds the threshold, further adjustments are needed; if it is close to the target, the adjustment amplitude can be slowed down. The preset convergence threshold is the acceptable deviation upper limit set in this embodiment, representing that the matching accuracy between cooling capacity and demand has reached the control requirements. The cooling plant system is affected by factors such as equipment response delay and pipeline thermal inertia, making it difficult to achieve optimal performance with a single adjustment. Through multiple rounds of iteration, the deviation is gradually brought closer to the convergence threshold, ultimately achieving a precise match between cooling parameters and demand.

[0050] Furthermore, determining an adjustment range coefficient based on the magnitude of the deviation value, and adjusting the initial water supply temperature and the initial chiller load rate according to the adjustment range coefficient, may include:

[0051] The adjustment range coefficient is calculated based on the ratio of the deviation value to the predicted value of the terminal cooling demand. And retrieve the preset temperature reference value from the configuration parameter library of the target building's chiller system. and preset load reference value ;

[0052] If the product of the aligned cooling capacity and the conversion coefficient is greater than the predicted terminal cooling demand, then the first water temperature adjustment formula is used. Lower the water supply temperature and simultaneously use the first load rate regulation formula. Reduce chiller load rate;

[0053] If the product of the aligned cooling capacity and the conversion coefficient is less than the predicted terminal cooling demand, then the second water temperature adjustment formula is used. Increase the water supply temperature and simultaneously use the second load rate regulation formula. Increase the load rate of the chiller; among which, To adjust the second water supply temperature, Initial water supply temperature value, To adjust the second load rate, This represents the initial chiller load rate.

[0054] If the product of the aligned cooling capacity and the conversion coefficient equals the predicted terminal cooling demand, then the initial water supply temperature and the initial chiller load rate remain unchanged.

[0055] The adjusted water supply temperature must be limited to the allowable water supply temperature range of the chiller system, and the adjusted chiller load rate must be limited to the allowable safe operating load range of the chiller equipment.

[0056] Adjustment amplitude coefficient It is not a fixed value, but is calculated as the ratio of the deviation value to the predicted value of the terminal cooling demand. For example, with the same deviation of 100kW, if the predicted demand value is 500kW, then... Larger and more aggressive adjustments; if the demand forecast is 2000kW, then Smaller and gentler adjustments. Meanwhile, the "preset temperature reference value" is retrieved from the configuration parameter library. With "Preset load baseline value" "" is a basic adjustment unit set based on the response characteristics of the cooling plant equipment, ensuring that the adjustment range is within the range where the equipment can respond smoothly.

[0057] When "Aligned cooling capacity × conversion coefficient > predicted terminal cooling demand," it indicates that the actual cooling capacity is excessive, and the cooling intensity needs to be reduced. In this case, the first water temperature adjustment formula is used to lower the supply water temperature (lower water temperature weakens heat exchange capacity, reducing the actual cooling capacity received at the terminal), while the first load rate adjustment formula is used to lower the chiller load rate (directly reducing the chiller's cooling output). These two methods work together to reduce the cooling capacity. Conversely, when the cooling capacity is insufficient, the second water temperature adjustment formula is used to increase the water temperature, and the second load rate adjustment formula is used to increase the load rate, with both parameters working in tandem to increase the cooling capacity. If the cooling capacity perfectly matches the demand, the parameters remain unchanged to avoid ineffective adjustments. Through a linear adjustment mode of "initial value ± (coefficient × baseline value)," the parameter adjustment amount is proportional to the severity of the deviation, ensuring both correction efficiency and adjustment stability.

[0058] The requirements are that "the adjusted water supply temperature must be within the allowable range of the chiller system" and "the adjusted chiller load rate must be within the safe operating range". These two ranges are hard constraints set based on the physical limits of the equipment and the system operating specifications, in order to achieve a balance between control accuracy and operational safety.

[0059] Optionally, after determining whether the deviation value meets the deviation optimization condition, the process may further include:

[0060] If the deviation value is less than or equal to the preset deviation optimization threshold, it is determined that the deviation optimization condition is not met, and the current combination of parameters to be optimized is directly used as the candidate combination of operating parameters for the target building space.

[0061] The validity of the candidate operating parameter combinations is verified to confirm that the water supply temperature value is within the allowable water supply temperature range of the chiller system and the chiller load rate is within the allowable safe operating load range of the chiller equipment.

[0062] If the verification passes, the candidate combination of operating parameters will be determined as the final combination of operating parameters for the target building space.

[0063] If the verification fails, the water supply temperature or chiller load rate in the candidate operating parameter combinations will be corrected based on the safety operation constraints of the chiller system and chiller equipment until the parameters meet the requirements of the safe operating range. The corrected parameter combination will then be determined as the final operating parameter combination.

[0064] If the deviation value is less than or equal to the preset deviation optimization threshold, it indicates that the deviation between the cooling capacity and demand is within an acceptable range. No further adjustments to the parameters are needed, and the current combination of parameters to be optimized is directly defined as the candidate operating parameter combination. The preset deviation optimization threshold here, as mentioned earlier, is a quantitative standard set based on the control accuracy requirements of the chiller plant. Its core function is to delineate the boundary between what needs optimization and what does not. If the verification fails, the "parameter correction based on safety constraints" process is initiated. The safety operating constraints of the chiller plant system and chiller equipment refer to the hard parameter boundaries determined by the physical characteristics of the equipment and the system operating specifications. Correction requires adjusting parameters exceeding the constraints according to the requirements.

[0065] Example 2

[0066] Figure 2 This is a flowchart of another time-series prediction-based cooling plant simulation control method provided in Embodiment 2 of the present invention. This embodiment is a refinement based on Embodiment 1, specifically as follows: Figure 2 As shown, the method includes:

[0067] S210. In response to the cold station simulation control request initiated for the target building space, obtain the spatial identification information of the target building space, and according to the spatial identification information, match and obtain the target building cold station system identifier that supplies cooling to the target building space in the preset building and cold station association database.

[0068] When a simulated control request for a cooling station is received for a specific target building space, the first step is to clarify the ownership of the controlled object, i.e., which cooling station system is responsible for cooling that space. Space identification information serves as a unique identifier for the target building space, used for matching against a pre-defined building-cooling station association database. This database pre-stores the correspondence between all spaces within a building and their corresponding cooling station systems. By querying this database using the space identification information, the identifier of the target building's cooling station system that supplies cooling to the target space can be determined.

[0069] S220. Based on the target building's chiller system identifier, retrieve the current chiller system's operating data from the chiller data acquisition platform; wherein, the operating data includes the chiller's rated cooling capacity, chiller performance curve, terminal supply and return water temperature measurements corresponding to the target building space, and the chiller's current operating load rate.

[0070] The chiller plant data acquisition platform serves as the real-time data hub of the chiller plant system. It collects and stores operational parameters from various stages of the chiller plant through sensors, smart meters, and other devices. The chiller's rated cooling capacity reflects its maximum cooling capability and is fundamental to determining whether it can meet demand. The chiller performance curve illustrates its energy efficiency characteristics under different load rates, providing a basis for subsequent parameter optimization. The measured supply and return water temperatures at the corresponding terminals of the target building space directly reflect the current cooling status of that space and are key indicators for determining the rationality of the cooling supply. The current operating load rate of the chiller displays its current output level, providing a reference for initial parameter calculations. The operational data encompasses both inherent equipment attributes and real-time operating status, providing comprehensive input dimensions for predictive models.

[0071] S230. Input the operation data into the pre-trained time series prediction model, and obtain the predicted value of the terminal cooling demand of the target building space within a specified future period by analyzing the time series features and spatial correlation features in the operation data.

[0072] The unique feature of pre-trained time-series prediction models lies in their ability to not only analyze the temporal characteristics of the data but also to extract key spatial correlation features (such as the impact of the target space's area, orientation, and functional attributes on cooling demand, as well as the cooling linkage between this space and other areas). By fusing these two types of features, the model can more accurately predict the actual cooling demand of the target space within a specified future period.

[0073] S240. Based on the predicted terminal cooling demand and the operating data, calculate the initial water supply temperature and initial chiller load rate of the target building space and use them as a combination of parameters to be optimized.

[0074] Optionally, based on the predicted terminal cooling demand and the operational data, calculating the initial water supply temperature and initial chiller load rate of the target building space and using them as a combination of parameters to be optimized may include:

[0075] Based on the predicted terminal cooling demand and combined with the rated cooling capacity of the chiller in the operating data, the initial chiller load rate is calculated by using the ratio of the predicted terminal cooling demand to the rated cooling capacity of the chiller.

[0076] Based on the chiller performance curve in the operating data, a corresponding reference water supply temperature is matched to the initial chiller load rate; wherein, the chiller performance curve contains mapping relationship data between different load rates and corresponding reference water supply temperatures;

[0077] Based on the reference water supply temperature and combined with the measured terminal return water temperature of the target building space in the operation data, the initial water supply temperature value is calculated. The initial chiller load rate is associated with and stored as the initial water supply temperature value, which is used as the combination of parameters to be optimized for the target building space.

[0078] The predicted cooling demand at the terminal is the total cooling demand of the target space, while the rated cooling capacity of the chiller is the maximum cooling capacity that the chiller can output. The ratio of the two directly reflects the output ratio that the chiller needs to provide to meet the demand, i.e., the initial chiller load rate. Matching the reference supply water temperature aims to achieve synergy between load rate and equipment energy efficiency. The chiller performance curve is a core technical parameter provided by the chiller manufacturer, which embeds the mapping relationship between different load rates and corresponding reference supply water temperatures. This relationship is set based on the principle of optimal chiller energy efficiency. Matching the corresponding reference supply water temperature to the performance curve based on the calculated initial chiller load rate essentially adapts the supply water temperature parameter to the current output state of the chiller, ensuring that the chiller operates within the optimal energy efficiency range while meeting the demand. Due to practical issues such as heat exchange losses in the pipeline network and differences in heat exchange efficiency of terminal equipment in the chiller station system, the reference supply water temperature relying solely on the chiller performance curve cannot fully adapt to the actual cooling demand of the target space. Therefore, the measured value of the terminal return water temperature is introduced for correction. The terminal return water temperature is the temperature at which cold water returns to the chiller station after passing through the target space for heat exchange. It directly reflects the actual heat exchange effect at the terminal. By combining the reference supply water temperature and the terminal return water temperature for calculation, the initial supply water temperature value is finally obtained.

[0079] S250. Integrate the initial water supply temperature value and initial chiller load rate in the parameter combination to be optimized, along with the chiller performance curve in the operating data and the terminal supply and return water temperature measurement values ​​corresponding to the target building space, into a model input dataset.

[0080] The initial supply water temperature and initial chiller load rate in the parameter combination to be optimized are the core variables for cooling regulation, while the chiller performance curve and terminal supply and return water temperature measurements in the operating data are key evidence for characterizing the actual operating environment of the system. Integrating these four types of parameters into the model input dataset essentially provides the time series prediction model with a complete input of "regulation variables + system characteristics," ensuring that the model can simulate the real effect of the parameter combination based on actual equipment performance and terminal status, and avoiding simulation bias caused by incomplete input information.

[0081] S260. Input the model input dataset into the time series prediction model to obtain the actual cooling capacity of the target building cooling station system. Based on the conversion coefficient obtained by fitting the historical operation data of the target building space, perform alignment calculation on the actual cooling capacity to obtain the aligned cooling capacity in the same dimension as the predicted value of the terminal cooling demand.

[0082] The time-series forecasting model outputs the actual cooling capacity based on the input dataset, which is the theoretical cooling capacity of the chiller system under the current parameter combination. However, this value may have dimensional differences from the predicted value of end-user cooling demand. Therefore, this embodiment of the invention introduces a "conversion coefficient obtained by fitting historical operating data of the target building space." This coefficient is a correction value calculated by analyzing the correspondence between the historical cooling capacity of the chiller and the actual cooling capacity received by the end-user, and is used to eliminate dimensional inconsistencies caused by factors such as system transmission loss and metering deviation.

[0083] S270. By calculating the difference between the aligned cooling capacity and the predicted terminal cooling demand, the deviation between the actual cooling capacity and the predicted terminal cooling demand of the target building space is obtained.

[0084] The deviation value, calculated by subtracting the predicted cooling demand from the actual cooling capacity, is essentially a quantitative difference between the actual cooling capacity and the terminal demand under the current parameter combination. A positive deviation indicates oversupply of cooling, requiring a reduction in cooling intensity; a negative deviation indicates undersupply of cooling, requiring an increase in cooling capacity.

[0085] S280. Determine whether the deviation value meets the deviation optimization conditions. If so, iteratively adjust the initial water supply temperature value and the initial chiller load rate based on the deviation value to obtain a new combination of parameters to be optimized. Input the deviation value and the operating data into the time series prediction model to re-predict the actual cooling capacity for the target building space until the deviation value meets the preset convergence conditions.

[0086] S290. The new water supply temperature and the new chiller load rate when the preset convergence conditions are met are taken as the final operating parameter combination for the target building space, and the final operating parameter combination is sent to the controller of the target building chiller station system for simulated control of the designated chiller station equipment.

[0087] This invention, through spatial identification matching of dedicated cooling stations and targeted retrieval of chiller parameters and terminal water temperature data, combined with spatiotemporal characteristics to predict cooling demand, directly solves the problems of data chaos and inaccurate demand prediction in multi-cooler station scenarios. It calculates chiller load rate based on cooling demand, selects the optimal reference water temperature according to chiller performance curves, and then corrects it with terminal return water temperature, ensuring that initial cooling parameters conform to both equipment operating patterns and actual cooling usage. By integrating cooling parameters and operating data to simulate actual cooling capacity, and correcting for dimensional deviations using historical data, the supply-demand gap is calculated, providing specific and accurate quantitative basis for subsequent parameter adjustments.

[0088] Example 3

[0089] Figure 3 This is a schematic diagram of a cooling plant simulation control device based on time-series prediction, provided in Embodiment 3 of the present invention. Figure 3As shown, the device includes:

[0090] The terminal cooling demand prediction module 310 is used to respond to a cooling station simulation control request initiated for the target building space, acquire the operation data of the target building cooling station system associated with the target building space, and input the operation data into a pre-trained time series prediction model to obtain the terminal cooling demand prediction value of the target building space within a specified future period.

[0091] The parameter combination acquisition module 320 is used to calculate the initial water supply temperature and initial chiller load rate of the target building space based on the predicted terminal cooling demand and the operating data, and use them as the parameter combination to be optimized.

[0092] The deviation value calculation module 330 is used to input the combination of parameters to be optimized and the operating data into the time series prediction model, predict the actual cooling capacity of the target building cooling station system to the target building space under the current input parameter combination, and calculate the deviation value between the actual cooling capacity and the predicted value of the terminal cooling capacity demand of the target building space.

[0093] The iterative optimization module 340 is used to determine whether the deviation value meets the deviation optimization conditions. If so, iteratively adjusts the initial water supply temperature value and the initial chiller load rate based on the deviation value to obtain a new combination of parameters to be optimized. By inputting the deviation value and the operating data into the time series prediction model, the actual cooling capacity for the target building space is re-predicted until the deviation value meets the preset convergence conditions.

[0094] The simulation control sending module 350 is used to take the new water supply temperature value and the new chiller load rate when the preset convergence conditions are met as the final operating parameter combination for the target building space, and send the final operating parameter combination to the controller of the target building chiller station system for simulation control of the specified chiller station equipment.

[0095] This invention, through time-series prediction, accurately locks in end-point demand and combines iterative optimization parameters with deviations to overcome the shortcomings of traditional control, such as difficulty in accurately simulating the dynamic balance of energy between the cooling source and the end point, and the tendency of strategies to deviate from the optimal state, thus achieving precise matching of cooling supply and demand. It constructs a "prediction-adjustment-feedback" closed-loop mechanism to overcome the shortcomings of traditional control, such as the inability to accurately predict the time-delay characteristics of temperature change processes and response lag, significantly improving the transient response speed of the chiller plant system. By using water supply temperature and chiller load rate as collaborative optimization parameters, and combining them with operational data, it achieves collaborative optimization of multiple devices, compensating for the lack of unified modeling of building inertia, network temperature rise, and equipment heterogeneity in traditional control, thereby reducing energy waste and minimizing losses caused by frequent equipment switching.

[0096] Optionally, based on the above embodiments, the terminal cooling demand prediction module 310 may include:

[0097] The cooling station system identifier acquisition unit is used to respond to a cooling station simulation control request initiated for a target building space, acquire the spatial identifier information of the target building space, and match and acquire the target building cooling station system identifier that supplies cooling to the target building space in a preset building and cooling station association database based on the spatial identifier information.

[0098] The operation data retrieval unit is used to retrieve the current operation data of the chiller system from the chiller data acquisition platform based on the target building chiller system identifier; wherein, the operation data includes the chiller rated cooling capacity, chiller performance curve, terminal supply and return water temperature measurement values ​​corresponding to the target building space, and chiller current operating load rate;

[0099] The cooling demand forecasting unit is used to input the operating data into a pre-trained time-series forecasting model, and obtain the predicted value of the terminal cooling demand of the target building space within a specified future period by analyzing the time-series features and spatial correlation features in the operating data.

[0100] Optionally, based on the above embodiments, the parameter combination acquisition module 320 to be optimized may include:

[0101] The initial chiller load rate calculation unit is used to calculate the initial chiller load rate based on the predicted terminal cooling demand value and the rated cooling capacity of the chiller in the operating data, using the ratio of the predicted terminal cooling demand value to the rated cooling capacity of the chiller.

[0102] A reference water supply temperature matching unit is used to match a corresponding reference water supply temperature to the initial chiller load rate based on the chiller performance curve in the operating data; wherein, the chiller performance curve contains mapping relationship data between different load rates and corresponding reference water supply temperatures;

[0103] The initial water supply temperature calculation unit is used to calculate the initial water supply temperature based on the reference water supply temperature and in combination with the measured terminal return water temperature of the target building space in the operation data. The initial chiller load rate is associated with and stored as a combination of parameters to be optimized for the target building space.

[0104] Optionally, based on the above embodiments, the deviation value calculation module 330 may include:

[0105] The input data integration unit is used to integrate the initial water supply temperature value and initial chiller load rate in the combination of parameters to be optimized with the chiller performance curve in the operating data and the terminal supply and return water temperature measurement values ​​corresponding to the target building space into a model input dataset;

[0106] The cooling capacity alignment calculation unit is used to input the model input dataset into the time series prediction model to obtain the actual cooling capacity of the target building cooling station system, and to perform alignment calculation on the actual cooling capacity based on the conversion coefficient obtained by fitting the historical operation data of the target building space to obtain the aligned cooling capacity in the same dimension as the predicted value of the terminal cooling demand.

[0107] The cooling capacity difference calculation unit is used to obtain the deviation value between the actual cooling capacity and the predicted value of the terminal cooling capacity of the target building space by calculating the difference between the aligned cooling capacity and the predicted value of the terminal cooling capacity demand.

[0108] Optionally, based on the above embodiments, the iterative optimization module 340 may include:

[0109] The first type of optimization condition determination unit is used to compare the calculated deviation value with a preset deviation optimization threshold. If the deviation value is greater than the deviation optimization threshold, it is determined that the deviation optimization condition is met.

[0110] The deviation adjustment unit is used to determine the adjustment range coefficient based on the magnitude of the deviation value, and to adjust the water temperature and the initial chiller load rate according to the adjustment range coefficient; wherein the adjustment range coefficient is positively correlated with the deviation value;

[0111] The deviation value update unit is used to take the adjusted water supply temperature value and the chiller load rate as a new combination of parameters to be optimized, and input them together with the operating data into the time series prediction model to re-obtain the actual cooling capacity for the target building space, and recalculate the deviation value based on the new actual cooling capacity.

[0112] The convergence judgment unit is used to repeatedly perform the process of parameter adjustment, calculating the actual cooling capacity and the calculated deviation value until the recalculated deviation value is less than or equal to the preset convergence threshold, and then determine that the preset convergence condition is met.

[0113] Optionally, based on the above embodiments, the deviation adjustment unit can also be used to calculate an adjustment range coefficient based on the ratio of the deviation value to the predicted value of the terminal cooling demand. And retrieve the preset temperature reference value from the configuration parameter library of the target building's chiller system. and preset load reference value ;

[0114] If the product of the aligned cooling capacity and the conversion coefficient is greater than the predicted terminal cooling demand, then the first water temperature adjustment formula is used. Lower the water supply temperature and simultaneously use the first load rate regulation formula. Reduce chiller load rate;

[0115] If the product of the aligned cooling capacity and the conversion coefficient is less than the predicted terminal cooling demand, then the second water temperature adjustment formula is used. Increase the water supply temperature and simultaneously use the second load rate regulation formula. Increase the load rate of the chiller; among which, To adjust the second water supply temperature, Initial water supply temperature value, To adjust the second load rate, This represents the initial chiller load rate.

[0116] If the product of the aligned cooling capacity and the conversion coefficient equals the predicted terminal cooling demand, then the initial water supply temperature and the initial chiller load rate remain unchanged.

[0117] The adjusted water supply temperature must be limited to the allowable water supply temperature range of the chiller system, and the adjusted chiller load rate must be limited to the allowable safe operating load range of the chiller equipment.

[0118] Optionally, based on the above embodiments, it may also include: a second type of optimization condition determination unit, used to determine whether the deviation value meets the deviation optimization condition after determining whether the deviation value meets the deviation optimization condition; if the deviation value is less than or equal to a preset deviation optimization threshold, and it is determined that the deviation optimization condition is not met, then the current combination of parameters to be optimized is directly used as a candidate combination of operating parameters for the target building space.

[0119] The validity of the candidate operating parameter combinations is verified to confirm that the water supply temperature value is within the allowable water supply temperature range of the chiller system and the chiller load rate is within the allowable safe operating load range of the chiller equipment.

[0120] If the verification passes, the candidate combination of operating parameters will be determined as the final combination of operating parameters for the target building space.

[0121] If the verification fails, the water supply temperature or chiller load rate in the candidate operating parameter combinations will be corrected based on the safety operation constraints of the chiller system and chiller equipment until the parameters meet the requirements of the safe operating range. The corrected parameter combination will then be determined as the final operating parameter combination.

[0122] The time-prediction-based chiller plant simulation control device provided in this embodiment of the invention can execute the time-prediction-based chiller plant simulation control method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0123] Example 4

[0124] Figure 4A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0125] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0126] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0127] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a timing prediction-based cold station simulation control method.

[0128] That is: in response to a cooling station simulation control request initiated for the target building space, the system obtains the operation data of the target building cooling station system associated with the target building space, and inputs the operation data into a pre-trained time series prediction model to obtain the predicted value of the terminal cooling demand of the target building space within a specified future period;

[0129] Based on the predicted terminal cooling demand and the operating data, the initial water supply temperature and initial chiller load rate of the target building space are calculated and used as the combination of parameters to be optimized.

[0130] The combination of parameters to be optimized and the operating data are input into the time series prediction model to predict the actual cooling capacity of the target building cooling station system to the target building space under the current input parameter combination, and to calculate the deviation between the actual cooling capacity and the predicted value of the terminal cooling capacity demand of the target building space.

[0131] Determine whether the deviation value meets the deviation optimization conditions. If so, iteratively adjust the initial water supply temperature and initial chiller load rate based on the deviation value to obtain a new combination of parameters to be optimized. Then, input the deviation value and the operating data into the time series prediction model to re-predict the actual cooling capacity for the target building space until the deviation value meets the preset convergence conditions.

[0132] The new water supply temperature and the new chiller load rate when the preset convergence conditions are met are taken as the final combination of operating parameters for the target building space, and the final combination of operating parameters is sent to the controller of the target building chiller station system for simulated control of the designated chiller station equipment.

[0133] In some embodiments, a timing-prediction-based chiller plant simulation control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the timing-prediction-based chiller plant simulation control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a timing-prediction-based chiller plant simulation control method by any other suitable means (e.g., by means of firmware).

[0134] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0135] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0136] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0137] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0138] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0139] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0140] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0141] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A cooling plant simulation control method based on time-series prediction, characterized in that, The method includes: In response to a cooling station simulation control request initiated for a target building space, the system acquires the operation data of the target building cooling station system associated with the target building space, and inputs the operation data into a pre-trained time series prediction model to obtain the predicted value of the terminal cooling demand of the target building space within a specified future period. Based on the predicted terminal cooling demand and the operating data, the initial water supply temperature and initial chiller load rate of the target building space are calculated and used as the combination of parameters to be optimized. The combination of parameters to be optimized and the operating data are input into the time series prediction model to predict the actual cooling capacity of the target building cooling station system to the target building space under the current input parameter combination, and to calculate the deviation between the actual cooling capacity and the predicted value of the terminal cooling capacity demand of the target building space. Determine whether the deviation value meets the deviation optimization conditions. If so, iteratively adjust the initial water supply temperature and initial chiller load rate based on the deviation value to obtain a new combination of parameters to be optimized. Then, input the deviation value and the operating data into the time series prediction model to re-predict the actual cooling capacity for the target building space until the deviation value meets the preset convergence conditions. The new water supply temperature and the new chiller load rate when the preset convergence conditions are met are taken as the final operating parameter combination for the target building space, and the final operating parameter combination is sent to the controller of the target building chiller station system for simulated control of the specified chiller station equipment. In response to a chiller station simulation control request initiated for a target building space, the system acquires operational data of the target building chiller station system associated with the target building space, and inputs the operational data into a pre-trained time-series prediction model to obtain a predicted value of the terminal cooling demand of the target building space within a specified future period, including: In response to a cold station simulation control request initiated for a target building space, the spatial identification information of the target building space is obtained, and based on the spatial identification information, the target building cold station system identifier that supplies cooling to the target building space is obtained by matching in a preset building and cold station association database. Based on the target building's chiller system identifier, the current chiller system's operating data is retrieved from the chiller data acquisition platform; wherein, the operating data includes the chiller's rated cooling capacity, chiller performance curve, terminal supply and return water temperature measurements corresponding to the target building space, and the chiller's current operating load rate; The operational data is input into a pre-trained time-series prediction model. By analyzing the time-series features and spatial correlation features in the operational data, the predicted value of the terminal cooling demand of the target building space within a specified future period is obtained. After determining whether the deviation value meets the deviation optimization condition, the process further includes: If the deviation value is less than or equal to the preset deviation optimization threshold, it is determined that the deviation optimization condition is not met, and the current combination of parameters to be optimized is directly used as the candidate combination of operating parameters for the target building space. The validity of the candidate operating parameter combinations is verified to confirm that the water supply temperature value is within the allowable water supply temperature range of the chiller system and the chiller load rate is within the allowable safe operating load range of the chiller equipment. If the verification passes, the candidate combination of operating parameters will be determined as the final combination of operating parameters for the target building space. If the verification fails, the water supply temperature or chiller load rate in the candidate operating parameter combinations will be corrected based on the safety operation constraints of the chiller system and chiller equipment until the parameters meet the requirements of the safe operating range. The corrected parameter combination will then be determined as the final operating parameter combination.

2. The method according to claim 1, characterized in that, Based on the predicted terminal cooling demand and the operational data, the initial water supply temperature and initial chiller load rate of the target building space are calculated and used as the combination of parameters to be optimized, including: Based on the predicted terminal cooling demand and combined with the rated cooling capacity of the chiller in the operating data, the initial chiller load rate is calculated by using the ratio of the predicted terminal cooling demand to the rated cooling capacity of the chiller. Based on the chiller performance curve in the operating data, a corresponding reference water supply temperature is matched to the initial chiller load rate; wherein, the chiller performance curve contains mapping relationship data between different load rates and corresponding reference water supply temperatures; Based on the reference water supply temperature and combined with the measured terminal return water temperature of the target building space in the operation data, the initial water supply temperature value is calculated. The initial chiller load rate is associated with and stored as the initial water supply temperature value, which is used as the combination of parameters to be optimized for the target building space.

3. The method according to claim 2, characterized in that, The combination of parameters to be optimized and the operating data are input into a time-series prediction model to predict the actual cooling capacity of the target building's cooling station system to the target building space under the current input parameter combination, and to calculate the deviation between the actual cooling capacity and the predicted terminal cooling capacity demand of the target building space, including: The initial water supply temperature and initial chiller load rate in the parameter combination to be optimized are integrated with the chiller performance curve in the operating data and the terminal supply and return water temperature measurement values ​​corresponding to the target building space into the model input dataset; The model input dataset is input into the time series prediction model to obtain the actual cooling capacity of the target building's cooling station system. Based on the conversion coefficient obtained by fitting the historical operating data of the target building space, the actual cooling capacity is aligned and calculated to obtain the aligned cooling capacity in the same dimension as the predicted value of the terminal cooling demand. The deviation between the actual cooling capacity and the predicted terminal cooling demand is obtained by calculating the difference between the aligned cooling capacity and the predicted terminal cooling demand of the target building space.

4. The method according to claim 3, characterized in that, Determine whether the deviation value meets the deviation optimization conditions. If so, iteratively adjust the initial water supply temperature and initial chiller load rate based on the deviation value to obtain a new combination of parameters to be optimized. Input this new combination, along with the operating data, into the time-series prediction model to re-predict the actual cooling capacity for the target building space until the deviation value meets the preset convergence conditions, including: The calculated deviation value is compared with a preset deviation optimization threshold. If the deviation value is greater than the deviation optimization threshold, the deviation optimization condition is determined to be met. An adjustment range coefficient is determined based on the magnitude of the deviation value, and the initial water supply temperature and the initial chiller load rate are adjusted according to the adjustment range coefficient; wherein the adjustment range coefficient is positively correlated with the deviation value; The adjusted water supply temperature and chiller load rate are used as a new combination of parameters to be optimized, and are input together with the operating data into the time series prediction model to re-obtain the actual cooling capacity for the target building space, and the deviation value is recalculated based on the new actual cooling capacity. The process of adjusting parameters and calculating the actual cooling capacity and the calculated deviation value is repeated until the recalculated deviation value is less than or equal to the preset convergence threshold, at which point the preset convergence condition is determined to be met.

5. The method according to claim 4, characterized in that, Based on the magnitude of the deviation value, an adjustment range coefficient is determined, and the initial water supply temperature is adjusted according to the adjustment range coefficient, and the initial chiller load rate is adjusted, including: The adjustment range coefficient is calculated based on the ratio of the deviation value to the predicted value of the terminal cooling demand. And retrieve the preset temperature reference value from the configuration parameter library of the target building's chiller system. and preset load reference value ; If the product of the aligned cooling capacity and the conversion coefficient is greater than the predicted terminal cooling demand, then the first water temperature adjustment formula is used. Lower the water supply temperature and simultaneously use the first load rate regulation formula. Reduce chiller load rate; If the product of the aligned cooling capacity and the conversion coefficient is less than the predicted terminal cooling demand, then the second water temperature adjustment formula is used. Increase the water supply temperature and simultaneously use the second load rate regulation formula. Increase the load rate of the chiller; among which, To adjust the second water supply temperature, Initial water supply temperature value, To adjust the second load rate, This represents the initial chiller load rate. If the product of the aligned cooling capacity and the conversion coefficient equals the predicted terminal cooling demand, then the initial water supply temperature and the initial chiller load rate remain unchanged. The adjusted water supply temperature must be limited to the allowable water supply temperature range of the chiller system, and the adjusted chiller load rate must be limited to the allowable safe operating load range of the chiller equipment.

6. A cooling plant simulation control device based on time-series prediction, characterized in that, The device includes: The terminal cooling demand prediction module is used to respond to a cooling station simulation control request initiated for a target building space, acquire the operation data of the target building cooling station system associated with the target building space, and input the operation data into a pre-trained time series prediction model to obtain the terminal cooling demand prediction value of the target building space within a specified future period. The module for obtaining the combination of parameters to be optimized is used to calculate the initial water supply temperature and initial chiller load rate of the target building space based on the predicted value of the terminal cooling demand and the operating data, and use them as the combination of parameters to be optimized. The deviation value calculation module is used to input the combination of parameters to be optimized and the operating data into the time series prediction model, predict the actual cooling capacity of the target building cooling station system to the target building space under the current input parameter combination, and calculate the deviation value between the actual cooling capacity and the predicted value of the terminal cooling capacity demand of the target building space. The iterative optimization module is used to determine whether the deviation value meets the deviation optimization conditions. If so, iteratively adjusts the initial water supply temperature value and the initial chiller load rate based on the deviation value to obtain a new combination of parameters to be optimized. By inputting the deviation value and the operating data into the time series prediction model, the actual cooling capacity for the target building space is re-predicted until the deviation value meets the preset convergence conditions. The simulation control distribution module is used to take the new water supply temperature value and the new chiller load rate when the preset convergence conditions are met as the final operating parameter combination for the target building space, and send the final operating parameter combination to the controller of the target building chiller station system for simulation control of the specified chiller station equipment. The terminal cooling demand prediction module includes: The cooling station system identifier acquisition unit is used to respond to a cooling station simulation control request initiated for a target building space, acquire the spatial identifier information of the target building space, and match and acquire the target building cooling station system identifier that supplies cooling to the target building space in a preset building and cooling station association database based on the spatial identifier information. The operation data retrieval unit is used to retrieve the current operation data of the chiller system from the chiller data acquisition platform based on the target building chiller system identifier; wherein, the operation data includes the chiller rated cooling capacity, chiller performance curve, terminal supply and return water temperature measurement values ​​corresponding to the target building space, and chiller current operating load rate; The cooling demand forecasting unit is used to input the operating data into a pre-trained time series forecasting model, and obtain the predicted value of the terminal cooling demand of the target building space within a specified future period by analyzing the time series features and spatial correlation features in the operating data. It also includes: a second type of optimization condition determination unit, which is used to determine whether the deviation value meets the deviation optimization condition after determining whether the deviation value meets the deviation optimization condition. If the deviation value is less than or equal to the preset deviation optimization threshold, it is determined that the deviation optimization condition is not met, and the current combination of parameters to be optimized is directly used as the candidate combination of operating parameters for the target building space. The validity of the candidate operating parameter combinations is verified to confirm that the water supply temperature value is within the allowable water supply temperature range of the chiller system and the chiller load rate is within the allowable safe operating load range of the chiller equipment. If the verification passes, the candidate combination of operating parameters will be determined as the final combination of operating parameters for the target building space. If the verification fails, the water supply temperature or chiller load rate in the candidate operating parameter combinations will be corrected based on the safety operation constraints of the chiller system and chiller equipment until the parameters meet the requirements of the safe operating range. The corrected parameter combination will then be determined as the final operating parameter combination.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a time-prediction-based cold storage station simulation control method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute and implement the timing prediction-based cold station simulation control method according to any one of claims 1-5.

Images