Application method and related equipment of cooling system load prediction model

Abstract

The embodiment of the present application provides an application method and related equipment of a load prediction model for a cooling system, which belongs to the field of load prediction technology. The method includes: obtaining the historical cooling capacity and cooling area in the target area, performing hourly cooling capacity prediction based on the historical cooling capacity, and obtaining the historical average hourly cooling capacity. Performing all-day cooling capacity prediction based on the historical average hourly cooling capacity, and obtaining the historical all-day cooling capacity. Obtaining the ratio between the historical average hourly cooling capacity and the historical all-day cooling capacity, and obtaining the target cooling capacity ratio. Constructing a load prediction model based on the target cooling capacity ratio, the historical all-day cooling capacity and the cooling area, and obtaining a monthly hourly load prediction model. Predicting the cooling load in the preset time period of the target area based on the monthly hourly load prediction model. The monthly hourly load prediction model of this embodiment can predict the cooling load in any future time period, and realize accurate medium- and long-term cooling load prediction.

Description

Technical Field

[0001] The present application relates to the technical field of load forecasting, and in particular to an application method and related equipment of a load forecasting model for a cooling system. Background Art

[0002] The load forecasting of cooling system includes cooling load forecasting and power load forecasting. The existing load forecasting is mainly short-term forecasting. For example, the cooling load of the next day is predicted based on the cooling amount in a certain period of history, which is used to formulate the operation strategy for the next day. There is relatively little research on medium- and long-term load forecasting. Medium- and long-term load forecasting can be used to formulate medium- and long-term operation plans, cooling plans, energy consumption plans, and construction schedule plans. Therefore, how to accurately conduct medium- and long-term cooling load forecasting has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to propose an application method and related equipment of a cooling system load prediction model, aiming to accurately perform medium- and long-term cooling load prediction.

[0004] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes an application method of a cooling system load prediction model, the method comprising:

[0005] Obtain the historical cooling capacity and cooling area in the target area;

[0006] Perform hourly cooling capacity forecasting based on the historical cooling capacity to obtain the historical average hourly cooling capacity;

[0007] According to the historical average hourly cooling capacity, a full-day cooling capacity forecast is performed to obtain the historical full-day cooling capacity;

[0008] Obtaining a ratio between the historical average hourly cooling capacity and the historical full-day cooling capacity to obtain a target cooling capacity ratio;

[0009] A load forecasting model is constructed according to the target cooling capacity ratio, the historical full-day cooling capacity and the cooling area to obtain a monthly hourly load forecasting model; wherein the monthly hourly load forecasting model is used to predict the cooling load in each period;

[0010] The cooling load of the target area within a preset time period is predicted based on the monthly hourly load prediction model.

[0011] In some embodiments, the cooling system includes a cold storage tank and a refrigerating machine constructed at a preset candidate construction time. After predicting the cooling load of the target area within a preset period of time based on the monthly hourly load forecasting model, the method further includes:

[0012] Obtaining the cold storage capacity of the cold storage tank and the installed capacity of the refrigeration machine;

[0013] Predicting the cooling capacity in a preset period of time according to the monthly hourly load forecasting model to obtain cooling capacity forecast data;

[0014] Comparing the cold storage capacity, the installed capacity and the cold consumption prediction data to obtain a comparison result;

[0015] The operation mode of the cooling system is set according to the comparison result.

[0016] In some embodiments, the operation mode includes a full cooling mode, a peak full cooling mode and a flat section combined cooling mode, a peak section combined cooling and a flat section refrigeration machine cooling mode and a peak section combined cooling and a flat section combined cooling mode, the cooling capacity prediction data includes predicted cooling capacity for the whole day, predicted cooling capacity for the peak section and predicted cooling capacity for the flat section, and setting the operation mode of the cooling system according to the comparison result includes:

[0017] If the comparison result indicates that the cold storage capacity is greater than the predicted cooling capacity for the whole day, the operation mode is set to the full cooling mode;

[0018] If the comparison result indicates that the cold storage capacity is less than the predicted full-day cooling capacity and greater than the predicted peak cooling capacity, the operation mode is set to the peak-segment full cooling and flat-segment combined cooling mode;

[0019] If the comparison result indicates that the cold storage capacity is less than the predicted peak-stage cooling capacity, and the installed capacity is greater than the predicted flat-stage cooling capacity, the operation mode is set to the peak-stage combined cooling and flat-stage refrigeration machine cooling mode;

[0020] If the comparison result indicates that the cold storage capacity is less than the predicted peak-segment cooling capacity, and the installed capacity is less than the predicted flat-segment cooling capacity, the operation mode is set to the peak-segment combined cooling and flat-segment combined cooling mode.

[0021] In some embodiments, the step of predicting the cooling capacity in a preset time period according to the monthly hourly load forecasting model to obtain cooling capacity forecast data includes:

[0022] Predicting the cooling capacity for a preset period of time according to the monthly hourly load prediction model to obtain predicted hourly cooling capacity;

[0023] The predicted hourly cooling capacity is summed up for the whole day to obtain the predicted cooling capacity for the whole day;

[0024] According to the predicted hourly cooling capacity, summing the peak cooling capacity is performed to obtain the predicted peak cooling capacity;

[0025] The flat-stage cooling capacity is summed up according to the predicted hourly cooling capacity to obtain the predicted flat-stage cooling capacity.

[0026] In some embodiments, after predicting the cooling capacity in a preset period according to the monthly hourly load forecasting model and obtaining cooling capacity forecast data, the method further includes:

[0027] The predicted cooling capacity for the whole day in a preset period is summed to obtain the target total cooling capacity in the preset period;

[0028] Summing the cold storage capacity and the installed capacity to obtain a total cooling capacity;

[0029] If the total cooling capacity is less than or equal to the target total cooling capacity, the preset time period is used as the target construction time; wherein the target construction time is the next construction time after the candidate construction time.

[0030] In some embodiments, after predicting the cooling capacity in a preset period according to the monthly hourly load forecasting model and obtaining cooling capacity forecast data, the method further includes:

[0031] Obtaining a target coefficient of performance of the cooling system;

[0032] Performing power load forecasting according to the predicted all-day cooling capacity and the target performance coefficient to obtain the predicted all-day power load;

[0033] The predicted all-day power load is counted to obtain the predicted power load within a preset time period.

[0034] In some embodiments, performing hourly cooling capacity prediction based on the historical cooling capacity to obtain the historical average hourly cooling load includes:

[0035] Perform hourly cooling capacity prediction based on the historical cooling capacity to obtain the historical hourly cooling capacity;

[0036] The historical hourly cooling capacity is averaged to obtain the historical average hourly cooling capacity.

[0037] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides an application device of a cooling system load prediction model, the device comprising:

[0038] The first acquisition module is used to obtain the historical cooling capacity and cooling area in the target area;

[0039] The second acquisition module is used to perform hourly cooling capacity prediction based on the historical cooling capacity to obtain the historical average hourly cooling capacity;

[0040] A third acquisition module is used to predict the cooling capacity for the whole day according to the historical average hourly cooling capacity, and obtain the historical cooling capacity for the whole day;

[0041] A fourth acquisition module is used to obtain the ratio between the historical average hourly cooling capacity and the historical full-day cooling capacity to obtain a target cooling capacity ratio;

[0042] A construction module is used to construct a load forecasting model according to the target cooling capacity ratio, the historical full-day cooling capacity and the cooling area to obtain a monthly hourly load forecasting model; wherein the monthly hourly load forecasting model is used to predict the cooling load of each time period;

[0043] A prediction module is used to predict the cooling load in the target area within a preset time period based on the monthly hourly load prediction model.

[0044] To achieve the above objectives, a third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0045] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0046] The application method and related equipment of the cooling system load prediction model proposed in the present application obtain the historical cooling capacity and cooling area in the target area, and perform hourly cooling capacity prediction based on the historical cooling capacity to obtain the historical average hourly cooling capacity. Perform all-day cooling capacity prediction based on the historical average hourly cooling capacity to obtain the historical all-day cooling capacity. Obtain the ratio between the historical average hourly cooling capacity and the historical all-day cooling capacity to obtain the target cooling capacity ratio. Construct a load prediction model based on the target cooling capacity ratio, the historical all-day cooling capacity and the cooling area to obtain a monthly hourly load prediction model. Predict the cooling load in the preset time period of the target area based on the monthly hourly load prediction model. That is, the monthly hourly load prediction model of this embodiment can predict the cooling load of any time period in the future, and realize accurate medium- and long-term cooling load prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of an application method of a cooling system load prediction model provided in an embodiment of the present application;

[0048] Figure 2 yes Figure 1 Flow chart of step S101 in FIG.

[0049] Figure 3It is a graph of the average hourly cooling load of an office building per month provided in an embodiment of the present application;

[0050] Figure 4 It is a monthly average hourly cooling load curve diagram of a shopping mall building provided in an embodiment of the present application;

[0051] Figure 5 It is a graph of the monthly average hourly cooling load of a school building provided in an embodiment of the present application;

[0052] Figure 6 This is a schematic diagram of the proportion of cooling capacity used in peak, valley and normal periods of an office building provided by an embodiment of the present application;

[0053] Figure 7 This is a schematic diagram of the proportion of cooling capacity used in peak, valley and normal periods of a shopping mall building provided by an embodiment of the present application;

[0054] Figure 8 This is a schematic diagram of the proportion of cooling capacity used in school buildings during peak, valley and normal periods provided by an embodiment of the present application;

[0055] Fig. 9 is a schematic diagram of the development progress of the cooling area in the target area provided in the embodiment of the present application;

[0056] Fig.10 is a flow chart of an application method of a cooling system load prediction model provided by another embodiment of the present application;

[0057] Fig.11 yes Fig.10 Flowchart of step S1002 in FIG.

[0058] Fig.12 yes Fig.10 Flowchart of step S1004 in FIG.

[0059] Fig.13 It is a schematic diagram of the cooling capacity curve in the full cooling mode;

[0060] Fig.14 It is a schematic diagram of the cooling capacity curve under the peak full-release cooling mode and the flat combined cooling mode;

[0061] Fig.15 It is a schematic diagram of the cooling capacity curve under the peak-stage combined cooling and flat-stage chiller cooling modes;

[0062] Fig.16 It is a schematic diagram of the cooling capacity curve under the first peak-segment combined cooling mode and the flat-segment combined cooling mode;

[0063] Fig.17 It is a schematic diagram of the cooling capacity curve under the second peak-segment combined cooling mode and the flat-segment combined cooling mode;

[0064] Fig.18is a flow chart of an application method of a cooling system load prediction model provided in a third embodiment of the present application;

[0065] Fig.19 It is a schematic diagram of the first part of the Phase 1 operation strategy in the target area;

[0066] Fig. 20 It is a schematic diagram of the second part of the Phase 1 operation strategy in the target area;

[0067] Fig.21 It is a schematic diagram of the first part of the 2-phase operation strategy in the target area;

[0068] Fig. 22 It is a schematic diagram of the second part of the 2-phase operation strategy in the target area;

[0069] Fig.23 is a flow chart of an application method of a cooling system load prediction model provided in a fourth embodiment of the present application;

[0070] Fig.24 This is a schematic diagram of the first part of the medium- and long-term forecast of power load;

[0071] Fig.25 This is a schematic diagram of the second part of the medium- and long-term forecast of power load;

[0072] Fig.26 It is a schematic diagram of the third part of the medium- and long-term forecast of power load;

[0073] Fig. 27 It is a structural schematic diagram of an application device of a cooling system load prediction model provided in an embodiment of the present application;

[0074] Fig.28 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0076] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0077] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0078] Cooling load forecasting is to optimize energy management and improve efficiency by predicting the future cooling demand of a building or system. Existing load forecasting is mainly short-term forecasting. For example, the cooling load of the next day is predicted based on the cooling supply in a certain period of history, which is used to formulate the operation strategy for the next day. There is relatively little research on medium- and long-term load forecasting. Medium- and long-term load forecasting can be used to formulate medium- and long-term operation plans, cooling plans, energy consumption plans, and construction schedule plans. In related technologies, it is impossible to accurately predict the cooling load in the medium and long term.

[0079] Based on this, the embodiment of the present application provides an application method and related equipment of a load prediction model for a cooling system, which aims to construct a load prediction model based on the target cooling capacity ratio, historical all-day cooling capacity and cooling area, and obtain a monthly hourly load prediction model. Based on the monthly hourly load prediction model, the cooling load in the preset time period of the target area is predicted, thereby achieving accurate medium- and long-term cooling load prediction.

[0080] The application method and related equipment of the cooling system load prediction model provided in the embodiment of the present application are specifically explained through the following embodiments. First, the application method of the cooling system load prediction model in the embodiment of the present application is described.

[0081] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0082] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0083] The application method of the cooling system load prediction model provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application of the application method of the cooling system load prediction model, etc., but is not limited to the above forms.

[0084] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0085] Please refer to Figure 1 , Figure 1 It is a flow chart of the application method of the cooling system load prediction model provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0086] Step S101, obtaining the historical cooling capacity and cooling area in the target area;

[0087] Step S102, performing hourly cooling capacity prediction based on historical cooling capacity to obtain historical average hourly cooling capacity;

[0088] Step S103, predicting the cooling capacity for the whole day based on the historical average hourly cooling capacity, and obtaining the historical cooling capacity for the whole day;

[0089] Step S104, obtaining the ratio between the historical average hourly cooling capacity and the historical full-day cooling capacity to obtain a target cooling capacity ratio;

[0090] Step S105, constructing a load forecasting model according to the target cooling capacity ratio, the historical daily cooling capacity and the cooling area to obtain a monthly hourly load forecasting model; wherein the monthly hourly load forecasting model is used to predict the cooling load in each period;

[0091] Step S106: predicting the cooling load of the target area within a preset period based on the monthly hourly load prediction model.

[0092] In step S101 of some embodiments, the historical cooling capacity is obtained by the cumulative cooling capacity recorded by the cooling meter in the target area. The cooling meter can be installed in each building in the target area, and the data recorded by the cooling meter can be the cumulative cooling capacity recorded in the first half of a year. Month The cumulative cooling capacity at the time. The cooling area in the target area is obtained by counting the actual cooling area of ​​each floor of each building in the target area. For example, the target area includes office buildings, shopping malls and school buildings. The cooling area of ​​office buildings is 320,000 square meters, the cooling area of ​​shopping malls is 110,000 square meters, and the cooling area of ​​school buildings is 74,000 square meters. The cooling area in the target area is 504,000 square meters.

[0093] See also Figure 2 In some embodiments, step S101 may include but is not limited to steps S201 to S202:

[0094] Step S201, performing hourly cooling capacity prediction based on historical cooling capacity to obtain historical hourly cooling capacity;

[0095] Step S202, average the historical hourly cooling capacity to obtain the historical average hourly cooling capacity.

[0096] In step S201 of some embodiments, the historical hourly cooling load of each building in the target area may be counted to obtain the historical hourly cooling load of the target area. The historical hourly cooling load of each building may be obtained by the following formula (1):

[0097] , (1)

[0098] in, express Class Building Month Tiandi The cooling load per unit area at the time, in units of / , for Class Building Month Tiandi The cumulative cooling capacity recorded by the cooling meter at the moment, in units of , for Class Building Month Tiandi The cumulative cooling capacity recorded by the cooling meter at the moment, in units of , for Cooling area of ​​buildings of this type. For the Type of building, which can be office, shopping mall, school building, etc., the subscript m is the mth month, and the subscript n is the nth day. It should be noted that the historical hourly cooling capacity is obtained by multiplying the historical hourly cooling load by the unit time.

[0099] In step S202 of some embodiments, the historical hourly cooling load within a day may be averaged to obtain the historical average hourly cooling load. The historical hourly cooling load within a month may also be averaged, and the obtained historical average hourly cooling load is the historical monthly average hourly cooling load. Since the target area includes office buildings, shopping mall buildings, and school buildings, the cooling demand on non-working days can be ignored. Therefore, it is not necessary to count the historical hourly cooling load on non-working days. Different processing can be performed according to the building type in the target area. In this embodiment, the historical monthly average hourly cooling load is obtained by the following formula (2):

[0100] , (2)

[0101] in, express Class Building Month The average hourly cooling load per unit area on working days of the month at the time, in units of / , Indicates It should be noted that the historical monthly average hourly cooling capacity is obtained by multiplying the historical monthly average hourly cooling load by the unit time.

[0102] Specifically, according to formula (2), the historical monthly average hourly cooling loads of office buildings, shopping mall buildings and school buildings for 12 months are calculated respectively, so as to obtain the monthly average hourly cooling load curves of the three types of buildings respectively, as shown in Figure 3-5 shown. Figure 3 This is the average hourly cooling load curve for office buildings. Figure 4 This is the monthly average hourly cooling load curve of the shopping mall building. Figure 5 This is the monthly average hourly cooling load curve of school buildings. The monthly average hourly cooling load curves of the three types of buildings have different characteristics.

[0103] like Figure 3As shown in the figure, for office buildings, 8:00-9:00 in the morning is the period with the largest cooling load. Because the working hours are generally 9:00, the air conditioner is turned on about half an hour to one hour before work. At this time, the thermal storage capacity of the building at night needs to be offset, and the cooling load is relatively large. The hourly cooling load in the figure is obtained by measuring the cooling capacity every hour. If the instantaneous cooling load power collected by the cooling capacity is used, the cooling load at 8:30 is much higher than the value in the figure. Since the building is in a non-steady state at this time, the cooling process is relatively fast, so the cooling load measurement based on the unit time scale is more statistically significant. From 10:00 in the morning to 18:00 in the afternoon, the cooling load is basically in a stable state, and this period does not change much. After that, from 21:00 to 23:00, the cooling load gradually drops to a smaller nighttime load. The change trend of the 12 months of the year is basically the same. In June-August, the monthly average hourly cooling load curves are almost overlapping, which is the season with the largest cooling load throughout the year. In September, the hourly cooling load curve drops slightly. The hourly cooling load in May and October decreased again, and the cooling loads in these two months were relatively close. The hourly cooling load continued to decrease in April and November, and the cooling loads in these two months were also relatively close. In December-March, the hourly cooling load dropped to less than 30% of that in June-August, which is the off-season for cooling. As can be seen from the figure, the hourly cooling load curves of each month have similar shapes.

[0104] like Figure 4 As shown in the figure, for shopping malls, the hourly cooling load curves of each month are also similar. In the morning, 9:30-10:30 is the opening time of the shopping mall. Like office buildings, the heat capacity of the building needs to be cooled before the air conditioner is turned on. In the 10:30-12:30 stage, the load remains basically stable. Then, in the 12:30-18:30 stage, the cooling load changes in a concave curve, reaching the lowest at 14:30-16:30. At 18:30, the cooling load returns to the larger load of 10:30-12:30, and then gradually decreases, reaching a low load at night at 22:30. The cooling load change trend between months is consistent with that of office buildings.

[0105] like Figure 5 As shown in the figure, the hourly cooling load curve for school buildings is similar to that for office buildings, with the difference that the peak load for schools occurs at 7:30, 1-2 hours earlier than for office buildings. In the 8:00-17:00 period, the cooling load is relatively stable, and from 17:00 onwards, the cooling load gradually decreases. The time point when the cooling load begins to drop significantly is also 1 hour earlier than that for office buildings, which is related to the school's start and end times. It should be noted that July and August are the time when schools have summer vacations, but schools also hold summer activities from time to time. Summer activity days are also considered working days here. When counting monthly average data, the number of working days is the total number of activity days for that month. Figure 5The hourly cooling load curves for July and August are the load changes on activity days. As can be seen in the figure, their shapes are slightly different from the curves in June, which is related to the activity time period and number of people on the activity days. In January and February, the school's cooling load is almost zero.

[0106] Through the above steps S201 to S202, the historical monthly average hourly cooling consumption can be obtained, so as to determine the historical full-day cooling consumption based on the historical monthly average hourly cooling consumption.

[0107] In step S103 of some embodiments, the historical monthly average hourly cooling capacity for 24 hours a day is integrated to obtain the historical daily cooling capacity. The calculation method of the historical daily cooling capacity is shown in the following formula (3):

[0108] , (3)

[0109] in, express Class Building The average cooling capacity per unit area in the month, in units of , represents the time interval. In formula (3), .

[0110] The calculation method of the ratio of the historical average hourly cooling capacity to the historical daily cooling capacity is shown in the following formula (4):

[0111] , (4)

[0112] in, express Class Building Month The ratio of the historical average hourly cooling consumption to the historical all-day cooling consumption at the time, also known as the target cooling consumption ratio. According to practice, the ratio of the historical average hourly cooling consumption to the historical all-day cooling consumption is basically a constant on any day of any month. For example, the ratio of the average hourly cooling consumption to the all-day cooling consumption at 1:00 on a certain day in May is the same as the ratio of the average hourly cooling consumption to the all-day cooling consumption at 1:00 on a certain day in other months. Figure 3-Figure 5 It can also be seen that the shapes of the cooling load curves of each type of building are similar, which also shows that the hourly cooling capacity at each moment is a certain proportional coefficient of the cooling capacity of the whole day. In order to further verify this hypothesis, Figure 3-Figure 5 The data in were further analyzed.

[0113] Specifically, the ratio of the cooling capacity used in each peak, valley and normal period (peak period, valley period and normal period) to the cooling capacity used throughout the day is as shown in the following formula (5):

[0114] , (5)

[0115] in, express Class Building Monthly period The ratio of cooling capacity to cooling capacity for the whole day, express Class Building Monthly period The cooling capacity, express Class Building Cooling capacity for the whole day of the month. Corresponding to each peak, valley and flat period. For example, valley period (23:00-7:00), flat period 1 (7:00-9:00), peak period 1 (9:00-11:30), flat period 2 (11:30-14:00), peak period 2 (14:00-16:30), flat period 3 (16:30-19:00), peak period 3 (19:00-21:00) and flat period 4 (21:00-23:00). Time period It can be valley section, flat section 1, peak section 1, flat section 2, peak section 2, flat section 3, peak section 3 or flat section 4. is peak segment 1, then express Class Building The cooling capacity between 9:00-11:30 in August.

[0116] Specifically, Class Building Monthly period The calculation method of the cooling capacity is shown in the following formula (6):

[0117] , (6)

[0118] in, express Class Building Monthly period The cooling capacity, Indicates a time interval. When it is flat section 1, to .

[0119] right Class Building Month The historical average hourly cooling capacity at the time is integrated with the ratio of the historical full-day cooling capacity to obtain ,right Class Building Monthly period Integrate the ratio of the cooling capacity used in the day to the historical cooling capacity used throughout the day, and we get This means that the sum of the ratios of all historical average hourly cooling capacity to historical daily cooling capacity is 1.

[0120] Averaging the whole year, we get the following formula (7):

[0121] , (7)

[0122] in, express Building-like period The monthly average hourly cooling capacity and The ratio of the average monthly cooling capacity of buildings of this type is based on Figure 3-Figure 5 The data in Calculate and get the average cooling capacity ratio of the three types of buildings in each period of each month, as shown in the figure below: Figure 6-Figure 8 As shown. The figure also shows the average annual proportional coefficient for each period. It can be seen from the figure that the ratio of hourly cooling consumption to all-day cooling consumption of various types of buildings does not change much in the 12 months of the year and can be approximated as a fixed value. The proportion of cooling consumption in each period of the annual average peak, valley and flat is approximately the ratio of hourly cooling consumption to all-day cooling consumption in each month. In some months outside the cooling season, there is a certain deviation between the two, but since the cooling consumption in the non-cooling season is small, it has little impact on the annual calculation. It can be considered that the ratio of hourly cooling consumption to all-day cooling consumption of various types of buildings is a constant. Therefore, the ratio of hourly cooling consumption to all-day cooling consumption in each period can be used as the basis for predicting the hourly cooling load in different months.

[0123] In step S105 of some embodiments, according to the target cooling capacity ratio , Historical cooling capacity throughout the day and cooling area The load forecasting model is constructed to obtain the monthly hourly load forecasting model, as shown in the following formula (8):

[0124] , (8)

[0125] in, Indicates that all buildings in the target area are Month The hourly cooling load at the moment, formula (8) represents the hourly cooling load of each type of building. Month The hourly cooling loads of all buildings in the target area at the time are added up to obtain Month Hourly cooling load .

[0126] In step S106 of some embodiments, a monthly hourly load prediction model is constructed to predict the cooling load in a preset period of time in the target area. The preset period of time may be a time period from a certain time in the future to a certain time in the future. After the hourly cooling load at a certain time in the future is predicted by the monthly hourly load prediction model, all hourly cooling loads in the preset period of time are added together to obtain the cooling load in the preset period of time. Therefore, it is possible to predict the short-term or medium- to long-term cooling load.

[0127] It should be noted that the cooling area of ​​the target area can be considered unchanged in the short term, but in the medium and long term, as the occupancy rate changes, the cooling area is also changing. Therefore, it is also necessary to predict the cooling load in combination with the change in the cooling area in the target area. Fig. 9 , the cooling area development progress is as follows Fig. 9 As shown, it takes about 10 years to reach full occupancy.

[0128] Steps S101 to S106 shown in the embodiment of the present application are to obtain the historical cooling capacity and cooling area in the target area, and perform hourly cooling capacity forecasting based on the historical cooling capacity to obtain the historical average hourly cooling capacity. Perform all-day cooling capacity forecasting based on the historical average hourly cooling capacity to obtain the historical all-day cooling capacity. Obtain the ratio between the historical average hourly cooling capacity and the historical all-day cooling capacity to obtain the target cooling capacity ratio. A load forecasting model is constructed based on the target cooling capacity ratio, the historical all-day cooling capacity and the cooling area to obtain a monthly hourly load forecasting model. The cooling load in the preset time period of the target area is predicted based on the monthly hourly load forecasting model. That is, the monthly hourly load forecasting model of this embodiment can predict the cooling load of any time period in the future, thereby enabling accurate medium- and long-term cooling load forecasting.

[0129] See also Fig.10 In some embodiments, the cooling system includes a cold storage tank and a refrigerator constructed at a preset candidate construction time. After step S106, the application method of the cooling system load prediction model may also include but is not limited to steps S1001 to S1004:

[0130] Step S1001, obtaining the cold storage capacity of the cold storage tank and the installed capacity of the refrigeration machine;

[0131] Step S1002, predicting the cooling capacity in a preset period according to the monthly hourly load prediction model to obtain cooling capacity prediction data;

[0132] Step S1003, comparing the cold storage capacity, installed capacity and cold usage prediction data to obtain a comparison result;

[0133] Step S1004, setting the operation mode of the cooling system according to the comparison result.

[0134] In step S1001 of some embodiments, the cooling system is constructed in two phases, and the installed capacity of the refrigeration machine in each phase is 13,000 kW, and the cold storage capacity of the cold storage tank is 73,000 kWh. The candidate construction time is the construction time of phase 1. The cold storage capacity of the cold storage tank and the installed capacity of the refrigeration machine in phase 1 are obtained.

[0135] See also Fig.11 In some embodiments, the cooling capacity prediction data includes the prediction of cooling capacity for the whole day, the prediction of cooling capacity for the peak period, and the prediction of cooling capacity for the flat period. Step S1002 may include but is not limited to steps S1101 to S1104:

[0136] Step S1101, predicting the cooling capacity in a preset period according to the monthly hourly load prediction model to obtain the predicted hourly cooling capacity;

[0137] Step S1102, summing up the cooling capacity for the whole day according to the predicted hourly cooling capacity to obtain the predicted cooling capacity for the whole day;

[0138] Step S1103, summing the peak cooling capacity according to the predicted hourly cooling capacity to obtain the predicted peak cooling capacity;

[0139] Step S1104, summing the average cooling capacity according to the predicted hourly cooling capacity to obtain the predicted average cooling capacity.

[0140] In step S1101 of some embodiments, the cooling capacity in a preset period is predicted according to the monthly hourly load prediction model to obtain the predicted hourly cooling capacity at each moment in the preset period.

[0141] In some embodiments, in steps S1102 to S1104, the predicted hourly cooling usage of each day in the preset period is added together to obtain the predicted full-day cooling usage of each day in the preset period. The predicted hourly cooling usage of the peak section of each day in the preset period is added together to obtain the predicted peak cooling usage of the peak section of each day in the preset period. The predicted hourly cooling usage of the average section of each day in the preset period is added together to obtain the predicted average cooling usage of the average section of each day in the preset period.

[0142] Through the above steps S1101 to S1104, the predicted cooling capacity for the whole day, the predicted cooling capacity for the peak period and the predicted cooling capacity for the flat period can be obtained, so as to set the operation mode of the cooling system based on the predicted cooling capacity for the whole day, the predicted cooling capacity for the peak period and the predicted cooling capacity for the flat period.

[0143] In step S1003 of some embodiments, the cooling capacity in a preset period is predicted according to the monthly hourly load prediction model to obtain cooling capacity prediction data, and the cold storage capacity, installed capacity and cooling capacity prediction data are compared to obtain a comparison result.

[0144] Specifically, the operation mode of the cooling system can be that only the cold storage tank releases cold, only the refrigeration machine provides cooling, or the cold storage tank and the refrigeration machine jointly provide cooling. Therefore, the operation mode of the cooling system can be set according to the comparison results of the cold storage capacity, installed capacity and cold usage prediction data.

[0145] See also Fig.12 In some embodiments, the operation modes include full cooling mode, peak full cooling mode and flat section combined cooling mode, peak section combined cooling and flat section refrigeration machine cooling mode and peak section combined cooling and flat section combined cooling mode. Step S1004 may include but is not limited to steps S1201 to S1204:

[0146] Step S1201, if the comparison result indicates that the cold storage capacity is greater than the predicted cold consumption for the whole day, the operation mode is set to the full cold release mode;

[0147] Step S1202: if the comparison result indicates that the cold storage capacity is less than the predicted cooling capacity for the whole day and greater than the predicted cooling capacity for the peak period, the operation mode is set to the peak period full cooling and flat period combined cooling mode;

[0148] Step S1203, if the comparison result indicates that the cold storage capacity is less than the predicted peak-stage cooling capacity, and the installed capacity is greater than the predicted flat-stage cooling capacity, the operation mode is set to the peak-stage combined cooling mode and the flat-stage refrigeration machine cooling mode;

[0149] Step S1204: if the comparison result indicates that the cold storage capacity is less than the predicted peak-period cold consumption, and the installed capacity is less than the predicted flat-period cold consumption, the operation mode is set to the peak-period combined cooling mode and the flat-period combined cooling mode.

[0150] In step S1201 of some embodiments, please refer to Fig.13 , Fig.13 This is a schematic diagram of the cooling capacity curve at different times of the day in the full cooling mode, with the horizontal axis representing the time and the vertical axis representing the cooling capacity. When the cooling capacity is greater than the predicted cooling capacity for the whole day, it means that only the cooling pool needs to release the cooling, so the operation mode can be set to the full cooling mode.

[0151] In step S1202 of some embodiments, see Fig.14 , Fig.14 This is a schematic diagram of the cooling capacity curve at different times of the day in the peak full cooling release and flat joint cooling mode, with the horizontal axis being the time and the vertical axis being the cooling capacity. When the cold storage capacity is less than the predicted full-day cooling capacity and greater than the predicted peak cooling capacity, it means that the peak can be cooled by the cold storage pool, and the flat can be cooled by the cold storage pool and the chiller to prevent the cold storage pool from failing to provide sufficient cooling capacity. Therefore, the operation mode is set to the peak full cooling release and flat joint cooling mode.

[0152] In step S1203 of some embodiments, please refer to Fig.15 , Fig.15 This is a schematic diagram of the cooling capacity curve at different times of the day under the peak-segment combined cooling and flat-segment chiller cooling mode, with the horizontal axis representing the time and the vertical axis representing the cooling capacity. When the cold storage capacity is less than the predicted peak-segment cooling capacity, and the installed capacity is greater than the predicted flat-segment cooling capacity, it means that the cooling capacity released by the cold storage pool does not meet the peak-segment cooling capacity, and the peak segment needs to be cooled by both the cold storage pool and the chiller. The chiller cooling capacity meets the flat-segment cooling capacity, and the flat segment only needs to be cooled by the chiller. Therefore, the operation mode is set to the peak-segment combined cooling and flat-segment chiller cooling mode.

[0153] In step S1204 of some embodiments, please refer to Fig.16 and Fig.17 , Fig.16 This is a schematic diagram of the cooling capacity curve at different times of the day under the first peak-segment combined cooling and flat-segment combined cooling modes. Fig.17 This is a schematic diagram of the cooling capacity curve at different times of the day in the second peak-segment combined cooling and flat-segment combined cooling modes, with the horizontal axis representing time and the vertical axis representing cooling capacity. When the cold storage capacity is less than the predicted peak-segment cooling capacity, and the installed capacity is less than the predicted flat-segment cooling capacity, it means that the cooling capacity released by the cold storage pool does not meet the peak-segment cooling capacity, and the peak segment needs to be cooled by both the cold storage pool and the refrigeration mechanism. The cooling capacity of the refrigeration mechanism also does not meet the flat-segment cooling capacity, and the flat segment also needs to be cooled by both the cold storage pool and the refrigeration mechanism. Therefore, the operation mode is set to the peak-segment combined cooling and flat-segment combined cooling mode. Among them, Fig.16 and Fig.17 The difference is whether the peak refrigeration mechanism reaches the maximum refrigeration capacity.

[0154] In steps S1001 to S1004 of this embodiment, after obtaining cooling consumption prediction data by predicting cooling consumption in a preset period, the operation mode of the cooling system for each day in the preset period is predicted based on the cooling consumption prediction data.

[0155] See also Fig.18 In some embodiments, after step S1002, the application method of the cooling system load prediction model may include but is not limited to steps S1801 to S1803:

[0156] Step S1801, summing the predicted cooling capacity for the whole day in a preset period to obtain the target total cooling capacity in the preset period;

[0157] Step S1802, summing the cold storage capacity and the installed capacity to obtain the total cooling capacity;

[0158] Step S1803, if the total cooling capacity is less than or equal to the target total cooling capacity, the preset time period is used as the target construction time; wherein the target construction time is the next construction time after the candidate construction time.

[0159] In some embodiments, in steps S1801 to S1802, the target total cooling capacity within the preset period is the sum of all predicted cooling capacities for the whole day within the preset period. For example, if the preset period is within 6 years, the sum of the predicted cooling capacities for the whole day for each day within 6 years is the target total cooling capacity within 6 years. The cooling capacity of the cold storage pool constructed in Phase 1 is 73,000 kWh, and the cooling capacity of the chiller is 13,000 kWh, so the total cooling capacity is 96,000 kWh.

[0160] In step S1803 of some embodiments, when the total cooling capacity is less than or equal to the target total cooling capacity, it means that the cooling capacity of Phase 1 is close to the cooling demand of users, and Phase 2 needs to be constructed and put into operation. For example, in the sixth year, the total cooling capacity is equal to the target total cooling capacity, and the construction time of Phase 2 (target construction time) is the sixth year, or Phase 2 needs to start equipment installation and construction in the fifth year. In one example, the target total cooling capacity for each year can be calculated, and the target total cooling capacity for each year can be compared with the total cooling capacity, so that the target construction time can be accurately obtained.

[0161] In steps S1801 to S1803 shown in this embodiment, after the target total cooling consumption in the preset time period is obtained by predicting the cooling consumption in the preset time period, the target construction time is predicted based on the target total cooling consumption to prevent waste of investment caused by early construction and production, and insufficient cooling capacity of the system caused by late construction and production.

[0162] See also Fig.19 and Fig. 20 , Fig.19 This is a schematic diagram of the first part of the Phase 1 operation strategy in the target area. Fig. 20 This is a schematic diagram of the second part of the Phase 1 operation strategy in the target area. Fig.19 The various curves obtained by predicting the hourly cooling load data during the period of 2023.1-2028.6 based on the monthly hourly load forecasting model, as well as the curves obtained based on the installed capacity and cold storage capacity of Phase 1, Fig. 20The various curves obtained based on the hourly cooling load data from 2027.6 to 2032.12 predicted by the monthly hourly load forecasting model, as well as the curves obtained based on the installed capacity and cold storage capacity of Phase 1. During 2023.1-2025.4, the cold storage capacity is sufficient to meet the user's cooling demand, so it is in full cooling mode (mode M1 in the figure). During 2025.5-2025.11, the cold storage capacity is greater than the peak cooling demand, and the installed capacity is sufficient to meet the user's cooling demand. The cooling system operates in the peak full cooling and flat section combined cooling mode (mode M2 ​​in the figure). In June of the fourth year (2026.6), the peak cooling capacity does not meet the peak user cooling demand, and the peak section needs to turn on the chiller. At this time, the peak section chiller cooling load is greater than zero, and the cooling system operates in the peak section combined cooling and flat section chiller cooling mode (mode M4 in the figure). During the period from July 2026 to October 2026, the cooling load of the flat-segment chiller reaches the installed capacity of the chiller, and it is necessary to release cold to supplement it in order to meet the cooling demand of users in the flat segment. Therefore, the system operates in the peak-segment combined cooling and flat-segment combined cooling mode (mode M7 in the figure). The cooling load of the flat-segment chiller is equal to the installed capacity of the chiller, reaching the maximum cooling capacity of the chiller. Starting from the fourth year, the operation time of modes M2 and M4 is very short, and the main operation mode is mode M1 and mode M7 throughout the year. In July of the sixth year (July 2028), the maximum cooling capacity of the cooling system is reached, and the system operates in the peak-segment combined cooling and flat-segment combined cooling mode (mode M8 in the figure) or exceeds the system cooling capacity for part of the time. From June to October of the seventh year, the cooling capacity of the system is already much lower than the cooling demand of users. It can be seen from this that in the sixth year of the operation of the cooling system, the cooling capacity of Phase 1 is close to or less than the cooling demand of users, and Phase 2 needs to start production and operation, or Phase 2 needs to start equipment installation and construction in the fifth year.

[0163] See also Fig.21 and Fig. 22 , Fig.21 This is a schematic diagram of the first part of the two-phase operation strategy in the target area. Fig. 22 This is a schematic diagram of the second part of the 2-phase operation strategy in the target area. Fig.21 The various curves obtained by predicting the hourly cooling load data during the period of 2023.1-2028.6 based on the monthly hourly load forecasting model, as well as the curves obtained based on the installed capacity and cold storage capacity of Phase 1 and Phase 2, Fig. 22 These are the various curves obtained by predicting the hourly cooling load data during the period of June 2027-December 2032 based on the monthly hourly load forecasting model, as well as the curves obtained based on the installed capacity and cold storage capacity of Phases 1 and 2. Fig.21 and Fig. 22In the cooling system, the maximum cooling capacity is increased after the second phase is put into operation. In the peak cooling season of the sixth and seventh years, the cooling system can adopt mode M2, and the full cooling mode can be adopted in the peak period. The remaining cold storage capacity of the day can also be used for flat-segment cooling. In the eighth to tenth years, during the peak cooling season, the flat-segment refrigeration machine needs to provide cooling according to the maximum cooling capacity, and the duration of this operation mode increases year by year. In the eleventh year, the number of operating days of mode M7 is basically stable, and it will basically operate according to this law in the future. Starting from the ninth year, the operating time of mode M2 ​​and mode M4 is very short, and the main operation throughout the year is mode M1 and mode M7. The most basic requirement for the construction and commissioning time of the second phase is to meet the development of user cooling capacity. Accurately predicting the construction and commissioning time of the second phase can reduce the depreciation cost of equipment investment while meeting the user's cooling demand, and increase the future service life, delay equipment installation, and delay equipment replacement time, thereby improving investment efficiency.

[0164] See also Fig.23 In some embodiments, after step S1002, the application method of the cooling system load prediction model may include but is not limited to steps S2301 to S2303:

[0165] Step S2301, obtaining a target performance coefficient of the cooling system;

[0166] Step S2302, predicting the power load according to the predicted cooling capacity for the whole day and the target performance coefficient, and obtaining the predicted power load for the whole day;

[0167] Step S2303, collect statistics on the predicted power load for the whole day to obtain the predicted power load within a preset time period.

[0168] In step S2301 of some embodiments, the coefficient of performance (COP) can be used to evaluate the efficiency of the cooling system, where COP = heat output / power input. The target coefficient of performance is generally 4.5. A refrigerator with a COP of 4.5 means that 1 unit of electricity is used to provide 4.5 units of cooling capacity, that is, during the cooling process, the refrigerator absorbs 4.5 times the heat from the environment, thereby providing an effective cooling effect.

[0169] In some embodiments, in steps S2301 to S2303, the predicted cooling capacity for the whole day is obtained based on the monthly hourly load forecasting model, and the ratio of the predicted cooling capacity for the whole day to the COP is the predicted power load for the whole day. By counting the predicted power load for the whole day in the future preset period, the medium- and long-term power load situation can be predicted.

[0170] It should be noted that this embodiment can not only predict the power load for the whole day, but also predict the cooling consumption in the valley section and the peak section of each day, and then predict the power load in the valley section and the peak section of each day based on the cooling consumption in the valley section and the peak section of each day.

[0171] For details, please refer to Figure 24-26 , Fig.24 This is a schematic diagram of the first part of the medium- and long-term forecast of power load, which is the power load curve for the period from January 2023 to June 2028. Fig.25 This is the schematic diagram of the second part of the medium- and long-term forecast of power load, which is the power load curve for the period from June 2027 to December 2032. Fig.26 This is a schematic diagram of the third part of the medium- and long-term forecast of power load, which is a power load curve for the period from 2031.1 to 2036.6. As can be seen from the figure, with the development of user cooling, the equivalent electric power of the cooling load in the three peak segments gradually increases, among which peak segments 1 and 2 have larger values, and peak segment 3 is relatively small. For the valley power load, with the increase of user cooling, the valley segment of Phase 1 reaches its maximum value in the third year, and then it maintains the maximum power load for most of the year. After Phase 2 is put into operation, the valley power load operates at twice the scale of Phase 1. Except for the non-cooling season from January to March each year, the other months are operated at full power in the valley segment, and the power demand for the power grid remains stable. For the peak power load, the power load of the three peak segments during the day is basically the same, and the three curves basically overlap. During the operation of Phase 1, since the peak full-release cooling was adopted in the first three years, the peak power demand was almost 0. The peak power load began to appear in the fourth year and increased rapidly in the fifth year. After the second phase was put into operation in the 6th year, the peak period could be fully cooled for two consecutive years. Starting from the 8th year, the peak power load increased year by year and reached a stable change in the 12th year. Compared with the equivalent electric power of the cooling load, the power load of Peak 1 and Peak 2 is reduced by about 40%, which has the effect of reducing the peak power demand and increasing the valley power consumption in terms of power. In this embodiment, the valley refrigeration machines are all operated according to the 8-hour average cooling load, so the valley power load curve can also represent the amount of electricity shifted to fill the valley. If offshore wind power is used for cooling at night, the valley power represents the amount of electricity consumed by the offshore wind power at night. Figure 24-26 Focus on the power load in valley and peak periods, analyze the effect of peak-load shifting and valley-filling in the cooling system, and can be used for power transmission and distribution planning analysis in the target area.

[0172] In steps S2301 to S2303 shown in this embodiment, after predicting the medium- and long-term cooling load changes through the monthly hourly load forecasting model, the medium- and long-term predicted power load is obtained based on the medium- and long-term cooling load changes and the target performance coefficient, and the medium- and long-term valley and peak power load development can be further obtained.

[0173] See also Fig. 27 The embodiment of the present application further provides an application device of the cooling system load prediction model, which can implement the application method of the cooling system load prediction model, and the device includes:

[0174] The first acquisition module 2701 is used to obtain the historical cooling capacity and cooling area in the target area;

[0175] The second acquisition module 2702 is used to perform hourly cooling capacity prediction based on historical cooling capacity to obtain historical average hourly cooling capacity;

[0176] The third acquisition module 2703 is used to predict the cooling capacity for the whole day according to the historical average hourly cooling capacity, and obtain the historical cooling capacity for the whole day;

[0177] The fourth acquisition module 2704 is used to obtain the ratio between the historical average hourly cooling capacity and the historical full-day cooling capacity to obtain a target cooling capacity ratio;

[0178] The construction module 2705 is used to construct a load forecasting model according to the target cooling capacity ratio, the historical full-day cooling capacity and the cooling area, and obtain a monthly hourly load forecasting model; wherein the monthly hourly load forecasting model is used to predict the cooling load in each period;

[0179] The prediction module 2706 is used to predict the cooling load of the target area within a preset period of time based on the monthly hourly load prediction model.

[0180] The specific implementation of the application device of the cooling system load prediction model is basically the same as the specific implementation of the application method of the cooling system load prediction model mentioned above, and will not be repeated here.

[0181] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the application method of the cooling system load prediction model when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0182] See also Fig.28 , Fig.28 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0183] The processor 2801 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0184] The memory 2802 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 2802 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 2802, and the processor 2801 calls and executes the application method of the cooling system load prediction model in the embodiment of this application;

[0185] Input / output interface 2803, used to implement information input and output;

[0186] Communication interface 2804, used to realize communication interaction between the device and other devices, which can be realized through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0187] A bus 2805 that transmits information between the various components of the device (e.g., the processor 2801, the memory 2802, the input / output interface 2803, and the communication interface 2804);

[0188] The processor 2801 , the memory 2802 , the input / output interface 2803 and the communication interface 2804 are connected to each other in communication within the device via the bus 2805 .

[0189] An embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements an application method of the above-mentioned cooling system load prediction model.

[0190] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0191] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0192] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0193] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0194] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0195] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0196] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0197] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0198] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0199] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0200] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0201] The preferred embodiments of the present application are described above with reference to the accompanying drawings, but the scope of the rights of the present application is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present application should be within the scope of the rights of the present application.

Claims

1. An application method of a cooling system load prediction model, characterized in that: The method comprises: Obtain the historical cooling capacity and cooling area in the target area; Perform hourly cooling capacity forecasting based on the historical cooling capacity to obtain the historical average hourly cooling capacity; According to the historical average hourly cooling capacity, a full-day cooling capacity forecast is performed to obtain the historical full-day cooling capacity; Obtaining a ratio between the historical average hourly cooling capacity and the historical full-day cooling capacity to obtain a target cooling capacity ratio; A load forecasting model is constructed according to the target cooling capacity ratio, the historical full-day cooling capacity and the cooling area to obtain a monthly hourly load forecasting model; wherein the monthly hourly load forecasting model is used to predict the cooling load of each period; the monthly hourly load forecasting model is: ； in, Indicates that all buildings in the target area are Month Hourly cooling load at any time, express Class Building Month The target cooling ratio at the moment, express Class Building Monthly historical cooling capacity for the whole day, express Cooling area of ​​buildings of this type; The cooling load of the target area within a preset time period is predicted based on the monthly hourly load prediction model.

2. The method according to claim 1, characterized in that The cooling system includes a cold storage tank and a refrigerating machine constructed at a preset candidate construction time. After predicting the cooling load of the target area within a preset period of time based on the monthly hourly load forecasting model, the method further includes: Obtaining the cold storage capacity of the cold storage tank and the installed capacity of the refrigeration machine; Predicting the cooling capacity in a preset period of time according to the monthly hourly load forecasting model to obtain cooling capacity forecast data; Comparing the cold storage capacity, the installed capacity and the cold consumption prediction data to obtain a comparison result; The operation mode of the cooling system is set according to the comparison result.

3. The method according to claim 2, characterized in that The operation modes include full cooling mode, peak full cooling mode and flat section combined cooling mode, peak section combined cooling and flat section refrigeration machine cooling mode and peak section combined cooling and flat section combined cooling mode. The cooling capacity prediction data includes predicted cooling capacity for the whole day, predicted cooling capacity for the peak section and predicted cooling capacity for the flat section. The operation mode of the cooling system is set according to the comparison result, including: If the comparison result indicates that the cold storage capacity is greater than the predicted cooling capacity for the whole day, the operation mode is set to the full cooling mode; If the comparison result indicates that the cold storage capacity is less than the predicted full-day cooling capacity and greater than the predicted peak cooling capacity, the operation mode is set to the peak-segment full cooling and flat-segment combined cooling mode; If the comparison result indicates that the cold storage capacity is less than the predicted peak-stage cooling capacity, and the installed capacity is greater than the predicted flat-stage cooling capacity, the operation mode is set to the peak-stage combined cooling and flat-stage refrigeration machine cooling mode; If the comparison result indicates that the cold storage capacity is less than the predicted peak-segment cooling capacity, and the installed capacity is less than the predicted flat-segment cooling capacity, the operation mode is set to the peak-segment combined cooling and flat-segment combined cooling mode.

4. The method according to claim 3, characterized in that: The method of predicting the cooling capacity in a preset time period according to the monthly hourly load prediction model to obtain cooling capacity prediction data includes: Predicting the cooling capacity for a preset period of time according to the monthly hourly load forecasting model to obtain predicted hourly cooling capacity; The predicted hourly cooling capacity is summed up for the whole day to obtain the predicted cooling capacity for the whole day; According to the predicted hourly cooling capacity, summing the peak cooling capacity is performed to obtain the predicted peak cooling capacity; The flat-stage cooling capacity is summed up according to the predicted hourly cooling capacity to obtain the predicted flat-stage cooling capacity.

5. The method according to claim 3, characterized in that: After predicting the cooling capacity of a preset period according to the monthly hourly load forecasting model and obtaining cooling capacity forecast data, the method further includes: The predicted cooling capacity for the whole day in a preset period is summed to obtain the target total cooling capacity in the preset period; Summing the cold storage capacity and the installed capacity to obtain a total cooling capacity; If the total cooling capacity is less than or equal to the target total cooling capacity, the preset time period is used as the target construction time; wherein the target construction time is the next construction time after the candidate construction time.

6. The method according to claim 3, characterized in that After predicting the cooling capacity of a preset period according to the monthly hourly load forecasting model and obtaining cooling capacity forecast data, the method further includes: Obtaining a target coefficient of performance of the cooling system; Performing power load forecasting according to the predicted all-day cooling capacity and the target performance coefficient to obtain the predicted all-day power load; The predicted all-day power load is counted to obtain the predicted power load within a preset time period.

7. The method according to claim 1, characterized in that The step of performing hourly cooling capacity prediction based on the historical cooling capacity to obtain the historical average hourly cooling load includes: Perform hourly cooling capacity prediction based on the historical cooling capacity to obtain the historical hourly cooling capacity; The historical hourly cooling capacity is averaged to obtain the historical average hourly cooling capacity.

8. An application device of a cooling system load prediction model, characterized in that: The device comprises: The first acquisition module is used to obtain the historical cooling capacity and cooling area in the target area; The second acquisition module is used to perform hourly cooling capacity prediction based on the historical cooling capacity to obtain the historical average hourly cooling capacity; A third acquisition module is used to predict the cooling capacity for the whole day according to the historical average hourly cooling capacity, and obtain the historical cooling capacity for the whole day; A fourth acquisition module is used to obtain the ratio between the historical average hourly cooling capacity and the historical full-day cooling capacity to obtain a target cooling capacity ratio; A construction module is used to construct a load forecasting model according to the target cooling capacity ratio, the historical full-day cooling capacity and the cooling area to obtain a monthly hourly load forecasting model; wherein the monthly hourly load forecasting model is used to predict the cooling load of each period; the monthly hourly load forecasting model is: ； in, Indicates that all buildings in the target area are Month Hourly cooling load at any time, express Class Building Month The target cooling ratio at the moment, express Class Building Monthly historical cooling capacity for the whole day, express Cooling area of ​​buildings of this type; A prediction module is used to predict the cooling load in the target area within a preset time period based on the monthly hourly load prediction model.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the application method of the cooling system load prediction model according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the application method of the cooling system load prediction model according to any one of claims 1 to 7 is implemented.

Images