Intelligent control method and device for ice storage system and storage medium

Abstract

The invention discloses an intelligent control method and device for an ice storage system and a storage medium. The method comprises the steps of obtaining real-time data; constructing a dynamic load prediction model based on the real-time data; predicting the cold load per hour of the next day and the total cold load of the non-ice storage time period based on the dynamic load prediction model, and determining the ice storage amount of the next day; according to the ice storage amount of the next day, the peak value of the cooling load per hour of the next day and a preset electricity price policy, a preset cooling capacity distribution scheme is selected; and optimizing cooling capacity distribution according to the selected preset cooling capacity distribution scheme, and coordinating cooling of the base load refrigerator, cooling of ice melting and cooling of the double-working-condition refrigerator. According to the method, the dynamic load prediction model is constructed, so that the problem that a traditional method depends on static historical data and cannot capture sudden load changes is solved. In addition, by optimizing a cooling capacity distribution strategy, operation of the base load cooling machine, ice melting cooling and the double-working-condition cooling machine is coordinated, and the energy efficiency of the ice storage system is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of ice storage cooling devices, and particularly to an intelligent control method, device and storage medium for an ice storage cooling system. Background Art

[0002] Ice storage cooling systems are widely used in periodic load fluctuation scenarios such as hospitals and factories. Their core goal is to store cold energy during off-peak electricity price periods through ice storage for use during peak periods, in order to reduce operating costs.

[0003] However, traditional load forecasting methods rely on static historical data and fail to integrate real-time environmental parameters and business data, resulting in the prediction model being unable to capture sudden load changes. In addition, the forecasting period is fixed (such as daily updates), lacking the ability to dynamically calibrate hour by hour, and it is difficult to adapt to real-time load fluctuations.

[0004] It can be seen that the existing technology has insufficient load forecasting accuracy and low energy efficiency of the ice storage cooling system. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides an intelligent control method for an ice storage cooling system, which includes the following steps:

[0006] Obtain real-time data, where the real-time data at least includes the ambient air enthalpy value, the chilled water volume flow rate, business data, and the chilled water supply and return temperature difference;

[0007] Build a dynamic load forecasting model based on the real-time data;

[0008] Predict the hourly cooling load for the next day and the total cooling load during the non-ice storage period based on the dynamic load forecasting model, and determine the ice storage volume for the next day;

[0009] Select a preset cooling capacity distribution plan according to the ice storage volume for the next day, the peak value of the hourly cooling load for the next day, and the preset electricity price policy;

[0010] Optimize the cooling capacity distribution according to the selected preset cooling capacity distribution plan, and coordinate the cooling supply of the base load chiller, ice melting cooling supply, and dual-condition chiller cooling supply.

[0011] Optionally, the business data is the total number of people in a preset area or the quantified production energy of a factory.

[0012] Optionally, building a dynamic load forecasting model based on the real-time data at least includes the following steps:

[0013] Calculate the instantaneous cooling load per second according to the ambient air enthalpy value, the chilled water volume flow rate, and the chilled water supply and return temperature difference;

[0014] Calculate the average load per hour according to the instantaneous cooling load per second;

[0015] Calculate the average hourly ambient air enthalpy value according to the ambient air enthalpy value;

[0016] Count the hourly business data;

[0017] Obtain the predicted hourly ambient air enthalpy value for the next day and the predicted hourly business data for the next day;

[0018] Construct a dynamic load prediction formula based on the average hourly load throughout the day, the average hourly ambient air enthalpy value throughout the day, the hourly business data throughout the day, the predicted hourly ambient air enthalpy value for the next day, and the predicted hourly business data for the next day, and obtain a dynamic load prediction model.

[0019] Optionally, the dynamic load prediction formula is specifically as follows:

[0020]

[0021] Among them, Qpre 1h～24h is the hourly cooling load for the next day, Q 1h～24h is the average hourly load throughout the day, Hpre 1h～24h is the predicted hourly ambient air enthalpy value for the next day, H 1h～24h is the average hourly ambient air enthalpy value throughout the day, Npre 1h～24h is the predicted hourly business data for the next day, N 1h～24h is the hourly business data throughout the day, and a, b, and c are all model coefficients.

[0022] Optionally, if the total cooling load during the non-ice storage period is greater than the preset percentage of the ice storage preset capacity, then fill the ice tank; if the total cooling load during the non-ice storage period is less than or equal to the preset percentage of the ice storage preset capacity, then store ice according to a preset multiple of the total cooling load during the non-ice storage period.

[0023] Optionally, the preset cooling capacity distribution plan includes at least a first preset cooling capacity distribution plan, a second preset cooling capacity distribution plan, and a third preset cooling capacity distribution plan;

[0024] If the ice storage volume for the next day is greater than the total cooling load during the non-ice storage period, and the preset hourly ice melting cooling capacity is greater than or equal to the peak value of the hourly cooling load for the next day, then select the first preset cooling capacity distribution plan;

[0025] If the ice storage volume for the next day is greater than the total cooling load during the non-ice storage period, but the preset hourly ice melting cooling capacity is less than the peak value of the hourly cooling load for the next day, then select the second preset cooling capacity distribution plan;

[0026] If the ice storage volume for the next day is less than or equal to the total cooling load during the non-ice storage period, then select the third preset cooling capacity distribution plan.

[0027] Optionally, the first preset cooling capacity distribution plan is specifically to only turn on the ice melting cooling supply;

[0028] The second preset cooling capacity distribution scheme is specifically as follows: the base load cooling is turned on during the day to provide cooling capacity simultaneously with the ice melting cooling; when the ice storage cooling system operates to the peak of the hourly cooling load of the next day, the base load chiller cooling is restricted, and the ice melting cooling is preferentially used; when the ice storage volume of the next day reaches the maximum value, the cooling capacity supply of the base load chiller is increased until the hourly cooling load of the next day is lower than the peak of the hourly cooling load of the next day, and then the base load chiller cooling is turned off;

[0029] The third preset cooling capacity distribution scheme is specifically as follows: the base load cooling is turned on during the day to provide cooling capacity simultaneously with the ice melting cooling, and the ice melting cooling supplies cooling according to the preset priority ranking;

[0030] The specific preset priority ranking is: the overlapping part of the peak of the hourly cooling load of the next day and the peak electricity price period > the peak electricity price period > the overlapping part of the peak of the hourly cooling load of the next day and the peak electricity price period > the peak period of the hourly cooling load of the next day > the peak electricity price period > the flat electricity price period.

[0031] Optionally, the parameters of the dynamic load prediction model are calibrated in real time through a closed-loop optimization mechanism to optimize the dynamic load prediction model.

[0032] Corresponding to the intelligent control method of the ice storage cooling system, the present invention provides an intelligent control device for an ice storage cooling system, which includes:

[0033] A data acquisition unit for acquiring real-time data, where the real-time data at least includes the ambient air enthalpy value, the chilled water volume flow rate, the business data, and the temperature difference between the supply and return chilled water;

[0034] A model construction unit for constructing a dynamic load prediction model based on the real-time data;

[0035] A prediction unit for predicting the hourly cooling load of the next day and the total cooling load of the non-ice storage time period based on the dynamic load prediction model, and determining the ice storage volume of the next day;

[0036] An intelligent control unit for selecting a preset cooling capacity distribution scheme according to the ice storage volume of the next day, the peak of the hourly cooling load of the next day, and the preset electricity price policy; and optimizing the cooling capacity distribution according to the selected preset cooling capacity distribution scheme, and coordinating the base load chiller cooling, the ice melting cooling, and the dual-condition chiller cooling.

[0037] In addition, to achieve the above object, the present invention also provides a computer-readable storage medium, on which an intelligent control program for an ice storage cooling system is stored, and when the intelligent control program for the ice storage cooling system is executed by a processor, the steps of the intelligent control method of the ice storage cooling system as described above are implemented.

[0038] The present invention solves the problems that traditional methods rely on static historical data and cannot capture sudden load changes by obtaining multi-dimensional data such as real-time ambient air enthalpy value, chilled water volume flow rate, and business data, and constructing a dynamic load prediction model. At the same time, through hourly prediction and a closed-loop optimization mechanism, the model parameters are calibrated in real time, overcoming the defects of the prior art that the prediction period is fixed and there is a lack of dynamic calibration ability. In addition, by optimizing the cooling capacity distribution strategy and coordinating the operation of base load chillers, ice storage cooling, and dual-condition chillers, the energy efficiency of the ice storage cooling system is further improved, and the operating cost is reduced.

[0039] The present invention constructs a dynamic load prediction model through steps such as instantaneous cooling load calculation, hourly average load calculation, ambient air enthalpy value calculation, and business data statistics, ensuring the scientificity and accuracy of the model, and further enhancing the dynamic performance and adaptability of load prediction.

[0040] The present invention quantifies the relationship between cooling load, ambient air enthalpy value, and business data through the specific expression of the dynamic load prediction formula, making the model more transparent and operable, and facilitating practical application and promotion.

[0041] The present invention optimizes the ice storage strategy of the ice storage cooling system by setting the determination rules for the ice storage volume (such as filling the ice tank or storing ice according to a preset multiple), ensuring the economy and rationality of the cooling capacity distribution, and avoiding waste of cooling capacity.

[0042] The present invention clarifies the cooling capacity distribution strategy under different scenarios by presetting the selection conditions for the cooling capacity distribution plan, enabling the ice storage cooling system to flexibly adjust the operation mode according to actual needs, and further enhancing the energy efficiency and economy of the system.

[0043] The present invention ensures the efficient operation of the ice storage cooling system under different electricity price periods and cooling load peaks through the specific operations of three cooling capacity distribution plans, especially the setting of priority sorting, and optimizes the operating cost.

[0044] The present invention calibrates the parameters of the dynamic load prediction model in real time through a closed-loop optimization mechanism, further enhancing the dynamic performance and adaptability of the model, ensuring the accuracy of long-term prediction, and enhancing the robustness of the system. Description of the Drawings

[0045] The drawings described herein are used to provide a further understanding of the present invention, form a part of the present invention, and the schematic embodiments of the present invention and their descriptions are used to explain the present invention, and do not constitute an improper limitation to the present invention. In the drawings:

[0046] Figure 1 is a flow diagram of an embodiment of the intelligent control method for the ice storage cooling system of the present invention;

[0047] Figure 2This is a framework diagram of an intelligent control device for an ice storage cooling system according to an embodiment of the present invention. Detailed implementation manners

[0048] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. 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. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0049] As Figure 1 shown, an intelligent control method for an ice storage cooling system of the present invention includes the following steps:

[0050] Obtain real-time data, where the real-time data at least includes ambient air enthalpy value, chilled water volume flow rate, business data, and chilled water supply and return temperature difference;

[0051] Build a dynamic load prediction model based on the real-time data;

[0052] Predict the hourly cooling load and the total cooling load during the non-ice storage period of the next day based on the dynamic load prediction model, and determine the ice storage volume of the next day;

[0053] Select a preset cooling capacity distribution scheme according to the ice storage volume of the next day, the peak value of the hourly cooling load of the next day, and the preset electricity price policy;

[0054] Optimize the cooling capacity distribution according to the selected preset cooling capacity distribution scheme, and coordinate the cooling supply of the base load chiller, ice melting cooling supply, and dual-condition chiller.

[0055] Preferably, the ambient air enthalpy value is obtained in real time through the installed ambient air parameter sensor, or calculated according to the dry bulb temperature and relative humidity obtained by the temperature and humidity sensor; the chilled water volume flow rate is obtained by multiplying the volume flow rate obtained by the flow meter by the density of water.

[0056] The present invention solves the problem that the traditional method relies on static historical data and cannot capture sudden load changes by obtaining multi-dimensional data such as ambient air enthalpy value, chilled water volume flow rate, and business data in real time and building a dynamic load prediction model. At the same time, through hourly prediction and a closed-loop optimization mechanism, the model parameters are calibrated in real time, overcoming the defects of the existing technology with a fixed prediction period and lack of dynamic calibration ability. In addition, by optimizing the cooling capacity distribution strategy and coordinating the operation of the base load chiller, ice melting cooling supply, and dual-condition chiller, the energy efficiency of the ice storage cooling system is further improved, and the operation cost is reduced.

[0057] In this embodiment, the business data is the total number of people in a preset area or the quantified production capacity of a factory. For example, if the application scenario is a hospital, the business data is the total number of people in the preset area, which at least includes the sum of the number of outpatients, the number of people undergoing physical examinations, the number of inpatients, the number of medical staff, and the number of other staff; if the application scenario is a factory, the business data is the quantified production capacity of the factory. For example, for a cigarette factory, the key indicator for quantifying the factory production capacity is the number of cigarette sticks produced.

[0058] In this embodiment, a dynamic load prediction model is constructed based on real-time data, which at least includes the following steps:

[0059] According to the ambient air enthalpy value, the chilled water volume flow rate, and the chilled water supply and return water temperature difference, calculate the instantaneous cooling load per second. The specific calculation formula is: Q = c × m × ΔT; where Q is the instantaneous cooling load per second, c is the specific heat capacity of water, m is the instantaneous cooling load per second, and ΔT is the chilled water supply and return water temperature difference.

[0060] Calculate the average load per hour according to the instantaneous cooling load per second. The specific calculation formula is: where, Q 1h～24h represents the average load corresponding to each hour in 24 hours of the whole day. i is an accumulation timer (accumulating in seconds). When the accumulation from 1 - 3600s is completed for 1 hour, that is, calculate and store the average load per hour. Q i is the current real-time instantaneous cooling load, and Q i-1 is the instantaneous cooling load of the previous second;

[0061] Calculate the average ambient air enthalpy value per hour according to the ambient air enthalpy value. The specific calculation formula is: where, H 1h～24h represents the average ambient air enthalpy value corresponding to each hour in 24 hours of the whole day, H i is the current real-time ambient air enthalpy value, and H i-1 is the ambient air enthalpy value of the previous second;

[0062] Count the business data per hour;

[0063] Obtain the predicted ambient air enthalpy value per hour for the next day and the predicted business data per hour for the next day;

[0064] According to the average load per hour within the whole day, the average ambient air enthalpy value per hour within the whole day, the business data per hour within the whole day, the predicted ambient air enthalpy value per hour for the next day, and the predicted business data per hour for the next day, construct a dynamic load prediction formula to obtain a dynamic load prediction model.

[0065] The present invention constructs a dynamic load prediction model through steps such as instantaneous cooling load calculation, average hourly load calculation, ambient air enthalpy value calculation, and business data statistics, ensuring the scientificity and accuracy of the model, and further enhancing the dynamic performance and adaptability of load prediction.

[0066] In this embodiment, the dynamic load prediction formula is specifically as follows:

[0067]

[0068] Wherein, Qpre 1h～24h is the hourly cooling load for the next day, Q 1h～24h is the average hourly load throughout the day, Hpre 1h～24h is the predicted hourly ambient air enthalpy value for the next day, H 1h～24h is the average hourly ambient air enthalpy value throughout the day, Npre 1h～24h is the predicted hourly business data for the next day, N 1h～24h is the hourly business data throughout the day, and a, b, and c are all model coefficients.

[0069] Preferably, a, b, and c can be initially set to 1, and then obtained through historical data and automatically optimized during operation.

[0070] It can be understood that the subscripts 1h to 24h of all parameters in the present invention refer to the data corresponding to each hour in the 24 hours of the whole day. Therefore, 24 pieces of data corresponding to each hour will be obtained after calculation according to the above dynamic load prediction formula, and the model directly outputs the cooling load corresponding to each hour of the next day.

[0071] In this embodiment, the predicted hourly ambient air enthalpy value for the next day is obtained based on meteorological prediction data.

[0072] Preferably, when the business data is the total number of people in a preset area, it includes at least the sum of the number of outpatient appointments, the number of physical examination appointments, the number of inpatients, the number of medical staff, and the number of other staff. Currently, hospital visits / physical examinations, etc. usually require appointments, and the number of personnel in each position is also recorded, so relatively accurate numbers can be obtained.

[0073] The present invention quantifies the relationship between the cooling load, the ambient air enthalpy value, and the business data through the specific expression of the dynamic load prediction formula, making the model more transparent and operable, and facilitating practical application and promotion.

[0074] In this embodiment, if the total cooling load during the non-ice storage period is greater than a preset percentage of the ice storage preset capacity, the ice tank is filled; if the total cooling load during the non-ice storage period is less than or equal to a preset percentage of the ice storage preset capacity, ice is stored according to a preset multiple of the total cooling load during the non-ice storage period.

[0075] Preferably, the preset percentage is 85% and the preset multiple is 1.1.

[0076] It can be understood that ice storage usually occurs from 0:00 to 8:00, and during this period, the base load chiller is used for cooling. Therefore, usually, the total cooling load during the non-ice storage period is only calculated as the sum of the hourly cooling loads from 8:00 to 24:00. However, the calculation period corresponding to the total cooling load during the non-ice storage period can also be adjusted according to the actual situation.

[0077] The present invention optimizes the ice storage strategy of the ice storage cooling system by setting the determination rule of the ice storage volume (such as filling the ice tank or storing ice according to a preset multiple), ensuring the economy and rationality of the cooling capacity distribution, and avoiding waste of cooling capacity.

[0078] In this embodiment, the preset cooling capacity distribution scheme at least includes a first preset cooling capacity distribution scheme, a second preset cooling capacity distribution scheme, and a third preset cooling capacity distribution scheme;

[0079] If the ice storage volume for the next day is greater than the total cooling load during the non-ice storage period, and the preset hourly ice melting cooling capacity is greater than or equal to the peak value of the hourly cooling load for the next day, then the first preset cooling capacity distribution scheme is selected;

[0080] If the ice storage volume for the next day is greater than the total cooling load during the non-ice storage period, but the preset hourly ice melting cooling capacity is less than the peak value of the hourly cooling load for the next day, then the second preset cooling capacity distribution scheme is selected;

[0081] If the ice storage volume for the next day is less than or equal to the total cooling load during the non-ice storage period, then the third preset cooling capacity distribution scheme is selected.

[0082] The present invention clarifies the cooling capacity distribution strategy under different scenarios through the selection conditions of the preset cooling capacity distribution scheme, enabling the ice storage cooling system to flexibly adjust the operation mode according to actual needs, and further improving the energy efficiency and economy of the system.

[0083] In this embodiment, the first preset cooling capacity distribution scheme is specifically to only turn on the ice melting cooling;

[0084] The second preset cooling capacity distribution scheme is specifically to turn on the base load cooling during the day and provide cooling capacity simultaneously with the ice melting cooling; when the ice storage cooling system runs to the peak value of the hourly cooling load for the next day, limit the base load chiller cooling and give priority to using the ice melting cooling; when the ice storage volume for the next day reaches the maximum value, increase the cooling capacity supply of the base load chiller until the hourly cooling load for the next day is lower than the peak value of the hourly cooling load for the next day, and then turn off the base load chiller cooling;

[0085] The third preset cooling capacity distribution scheme is specifically to turn on the base load cooling during the day and provide cooling capacity simultaneously with the ice melting cooling, and the ice melting cooling supplies cooling according to the preset priority ranking;

[0086] The preset priority order is specifically: the part of the peak value of the cooling load per hour on the next day that overlaps with the peak electricity price period > the peak electricity price period > the part of the peak value of the cooling load per hour on the next day that overlaps with the peak electricity price period > the peak period of the cooling load per hour on the next day > the peak electricity price period > the flat electricity price period.

[0087] Preferably, the peak electricity price periods are 11:00-12:00 and 17:00-18:00 from July to September, the peak electricity price periods are 10:00-12:00, 15:00-20:00 and 21:00-22:00, and the flat electricity price periods are 8:00-10:00, 12:00-15:00, 20:00-21:00 and 22:00-24:00.

[0088] The present invention ensures efficient operation of the ice storage system under different electricity price periods and cooling load peaks and optimizes operating costs through specific operations of three cooling capacity allocation schemes, especially setting of priority rankings.

[0089] In this embodiment, the dynamic load prediction model parameters are calibrated in real time through a closed-loop optimization mechanism to optimize the dynamic load prediction model. As the program is continuously executed, the actual hourly cooling load, the total cooling load during the non-ice storage period, the ambient air enthalpy value, and the business data can be obtained. Therefore, the latest data can be compared with the data previously predicted by the model every day to verify whether the current model is accurate and continuously optimize the iterative model coefficients.

[0090] The specific model verification steps are as follows:

[0091] 1) Calculate the actual model predicted load according to the following formula:

[0092] Among them, Qact 1h～24h is the average load per hour Qlast in the previous day (specifically the day before a certain day described below). 1h～24h , the average ambient air enthalpy value per hour in the previous day Hlast 1h～24h , hourly business data Nlast of the previous day 1h～24h , the actual hourly ambient air enthalpy Hact for a certain day 1h～24h And the current actual hourly business data Nact 1h～24h Calculated actual model forecast load per hour;

[0093] 2) Calculate the deviation between the actual model predicted load and the actual load according to the following formula: Among them, DQ 1h～24h It represents the deviation between the actual model load and the actual load at the corresponding time each hour, Q 1h～24h is the actual load per hour.

[0094] 3) Calculate the average deviation: DQavg = avg(DQ 1h～24h ); where DQavg is the average of the deviations between the actual model load and the actual load at the corresponding time within 24 hours.

[0095] Preferably, if DQavg is less than 5%, there is no need to optimize the model; otherwise, model optimization is performed.

[0096] The model optimization is as follows:

[0097] 1) Data to be obtained: Q 1h～24h , H 1h～24h , N 1h～24h , Qlast 1h～24h , Hlast 1h～24h and Nlast 1h～24h ;

[0098] 2) Use multiple linear regression (least squares method) to fit and obtain coefficients a, b, c:

[0099] x1 is the average load Qlast per hour within the previous day 1h～24h ;

[0100] x2 is the enthalpy change rate, and

[0101] x3 is the business data change rate:

[0102] y is the actual model prediction load per hour;

[0103] The relationship model is y = x1 + x1 * (a * x2 + b * x3 + c);

[0104] According to the data x1, x3, x3, y, the parameters a, b, c are fitted, and the subsequent optimization program can be carried out using the optimized coefficients a, b, c.

[0105] The present invention calibrates the dynamic load prediction model parameters in real time through a closed-loop optimization mechanism, further improving the dynamic performance and adaptability of the model, ensuring the accuracy of long-term prediction, and enhancing the robustness of the system.

[0106] As Figure 2 shown, the present invention also correspondingly provides an intelligent control device for an ice storage cooling system, which includes:

[0107] A data acquisition unit 10 for acquiring real-time data, and the real-time data at least includes the ambient air enthalpy value, the chilled water volume flow rate, business data, and the temperature difference between the supply and return chilled water;

[0108] A model construction unit 20 for constructing a dynamic load prediction model based on real-time data;

[0109] A prediction unit 30 for predicting the hourly cooling load and the total cooling load during the non-ice storage period of the next day based on the dynamic load prediction model, and determining the ice storage amount of the next day;

[0110] An intelligent control unit 40 for selecting a preset cooling capacity distribution scheme according to the ice storage amount of the next day, the peak value of the hourly cooling load of the next day and a preset electricity price policy, and optimizing the cooling capacity distribution according to the selected preset cooling capacity distribution scheme, coordinating the cooling supply of the base load chiller, ice melting cooling supply, and dual-condition chiller cooling supply.

[0111] The embodiment of the present invention also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the memory in the above embodiment; or it may exist alone and is not assembled into the device. At least one instruction is stored in the computer-readable storage medium, and the instruction is loaded and executed by a processor to implement Figure 1 The intelligent control method of the ice storage cooling system shown. The computer-readable storage medium may be a read-only memory, a magnetic disk or an optical disc, etc.

[0112] It should be noted that each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other. For the device embodiment and the storage medium embodiment, since they are basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment.

[0113] Moreover, in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including one..." does not exclude the existence of other identical elements in the process, method, article or device including the said element.

[0114] The above description shows and describes the preferred embodiments of the present invention. It should be understood that the present invention is not limited to the form disclosed herein, should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications and environments, and can be changed within the scope of the inventive concept of this article through the above teachings or the technology or knowledge in the relevant field. And the changes and modifications made by those skilled in the art without departing from the spirit and scope of the present invention should all be within the protection scope of the appended claims of the present invention.

Claims

1. An intelligent control method for an ice thermal energy storage system, characterized in that, It includes the following steps: Obtain real-time data, which at least includes the ambient air enthalpy value, the chilled water volume flow rate, business data, and the chilled water supply and return temperature difference; Construct a dynamic load prediction model based on the real-time data; Predict the hourly cooling load for the next day and the total cooling load during the non-ice storage period based on the dynamic load prediction model, and determine the ice storage volume for the next day; Select a preset cooling capacity distribution plan according to the ice storage volume for the next day, the peak value of the hourly cooling load for the next day, and the preset electricity price policy; Optimize the cooling capacity distribution according to the selected preset cooling capacity distribution plan, and coordinate the cooling supply of the base load chiller, ice melting cooling supply, and dual-condition chiller.

2. The intelligent control method of the ice storage cooling system according to claim 1, wherein The business data is the total number of people in a preset area or the quantified production energy of a factory.

3. The intelligent control method of the ice storage cooling system according to claim 2, wherein, Constructing a dynamic load prediction model based on real-time data includes at least the following steps: Calculate the instantaneous cooling load per second according to the ambient air enthalpy value, the chilled water volume flow rate, and the chilled water supply and return temperature difference; Calculate the average load per hour according to the instantaneous cooling load per second; Calculate the average ambient air enthalpy value per hour according to the ambient air enthalpy value; Count the business data per hour; Obtain the predicted hourly ambient air enthalpy value for the next day and the predicted hourly business data for the next day; Construct a dynamic load prediction formula according to the average load per hour throughout the day, the average ambient air enthalpy value per hour throughout the day, the business data per hour throughout the day, the predicted hourly ambient air enthalpy value for the next day, and the predicted hourly business data for the next day, and obtain the dynamic load prediction model.

4. The intelligent control method for an ice storage cooling system according to claim 3, wherein The dynamic load prediction formula is specifically as follows: Among them, Qpre 1h～24h is the hourly cooling load for the next day, Q 1h～24h is the average hourly load within the whole day, Hpre 1h～24h is the predicted hourly ambient air enthalpy value for the next day, H 1h～24h is the average hourly ambient air enthalpy value within the whole day, Npre 1h～24h is the predicted hourly business data for the next day, N 1h～24h is the hourly business data within the whole day, and a, b, and c are all model coefficients.

5. The intelligent control method of the ice storage cooling system according to claim 1, characterized in that If the total cooling load during the non-ice storage period is greater than the preset percentage of the ice storage preset capacity, then fill the ice tank; if the total cooling load during the non-ice storage period is less than or equal to the preset percentage of the ice storage preset capacity, then store ice according to the preset multiple of the total cooling load during the non-ice storage period.

6. The intelligent control method for an ice storage cooling system according to claim 1, characterized in that, The preset cooling capacity distribution plan at least includes the first preset cooling capacity distribution plan, the second preset cooling capacity distribution plan, and the third preset cooling capacity distribution plan; If the ice storage volume for the next day is greater than the total cooling load during the non-ice storage period, and the preset hourly ice melting cooling supply capacity is greater than or equal to the peak value of the hourly cooling load for the next day, then select the first preset cooling capacity distribution plan; If the ice storage volume for the next day is greater than the total cooling load during the non-ice storage period, but the preset hourly ice melting cooling supply capacity is less than the peak value of the hourly cooling load for the next day, then select the second preset cooling capacity distribution plan; If the ice storage volume for the next day is less than or equal to the total cooling load during the non-ice storage period, then select the third preset cooling capacity distribution plan.

7. The intelligent control method of the ice storage cooling system according to claim 6, characterized in that, The first preset cooling capacity distribution plan is specifically to only turn on the ice melting cooling supply; The second preset cooling capacity distribution plan is specifically to turn on the base load cooling supply during the day and provide cooling capacity simultaneously with the ice melting cooling supply; when the ice storage system runs to the peak value of the hourly cooling load for the next day, limit the base load chiller cooling supply and give priority to using the ice melting cooling supply; when the ice storage volume for the next day reaches the maximum value, increase the base load chiller cooling capacity supply until the hourly cooling load for the next day is lower than the peak value of the hourly cooling load for the next day, and then turn off the base load chiller cooling supply; The third preset cooling capacity distribution plan is specifically to turn on the base load cooling supply during the day and provide cooling capacity simultaneously with the ice melting cooling supply, and the ice melting cooling supply supplies cooling according to the preset priority ranking; The preset priority sorting is specifically as follows: the overlapping part of the peak value of the hourly cooling load the next day and the peak electricity price period > the peak electricity price period > the overlapping part of the peak value of the hourly cooling load the next day and the peak electricity price period > the peak period of the hourly cooling load the next day > the peak electricity price period > the flat electricity price period.

8. The intelligent control method of the ice storage cooling system according to claim 1, wherein It further includes: Real-time calibrating the parameters of the dynamic load prediction model through a closed-loop optimization mechanism to optimize the dynamic load prediction model.

9. An intelligent control device for an ice energy storage system, characterized in that, It includes: A data acquisition unit for acquiring real-time data, where the real-time data at least includes the ambient air enthalpy value, the chilled water volume flow rate, business data, and the temperature difference between the supply and return chilled water; A model construction unit for constructing a dynamic load prediction model based on the real-time data; A prediction unit for predicting the hourly cooling load the next day and the total cooling load during the non-ice storage period based on the dynamic load prediction model, and determining the ice storage volume the next day; An intelligent control unit for selecting a preset cooling capacity distribution scheme according to the ice storage volume the next day, the peak value of the hourly cooling load the next day, and the preset electricity price policy, and optimizing the cooling capacity distribution according to the selected preset cooling capacity distribution scheme, coordinating the cooling supply of the base load chiller, ice melting cooling supply, and dual-condition chiller cooling supply.

10. A computer-readable storage medium, characterized in that, An ice storage cooling system intelligent control program is stored on the computer-readable storage medium, and when the ice storage cooling system intelligent control program is executed by a processor, the steps of the ice storage cooling system intelligent control method according to any one of claims 1 to 8 are implemented.

Images