CN111787764B - Energy consumption optimization method and device for multi-split refrigerating unit, electronic equipment and storage medium - Google Patents
Energy consumption optimization method and device for multi-split refrigerating unit, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111787764B CN111787764B CN202010624014.6A CN202010624014A CN111787764B CN 111787764 B CN111787764 B CN 111787764B CN 202010624014 A CN202010624014 A CN 202010624014A CN 111787764 B CN111787764 B CN 111787764B
- Authority
- CN
- China
- Prior art keywords
- chilled water
- refrigeration
- water flow
- historical
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
- H05K7/00—Constructional details common to different types of electric apparatus
- H05K7/20—Modifications to facilitate cooling, ventilating, or heating
- H05K7/20709—Modifications to facilitate cooling, ventilating, or heating for server racks or cabinets; for data centers, e.g. 19-inch computer racks
- H05K7/208—Liquid cooling with phase change
- H05K7/20827—Liquid cooling with phase change within rooms for removing heat from cabinets, e.g. air conditioning devices
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
- H05K7/00—Constructional details common to different types of electric apparatus
- H05K7/20—Modifications to facilitate cooling, ventilating, or heating
- H05K7/20709—Modifications to facilitate cooling, ventilating, or heating for server racks or cabinets; for data centers, e.g. 19-inch computer racks
- H05K7/20836—Thermal management, e.g. server temperature control
Landscapes
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The application provides an energy consumption optimization method and device for a multi-split refrigerating unit, electronic equipment and a computer readable storage medium, wherein the method comprises the following steps: judging whether at least one factor of the current environmental state parameters and the total flow demand of the chilled water changes; if yes, determining a variable constraint condition of the constructed objective function; the function value of the objective function is the total power of the multi-split air-conditioning unit, and the variables of the objective function comprise an environmental state parameter, a refrigeration control parameter and a chilled water flow; solving the objective function according to the variable constraint condition to obtain the refrigeration control parameter and the chilled water flow corresponding to each refrigerating unit when the total power is minimum; and controlling the corresponding refrigerating unit according to the solved refrigeration control parameter and the flow of the chilled water. According to the embodiment of the application, personalized chilled water flow distribution is realized, the performance of the multi-split air-conditioning unit is fully exerted, the energy consumption is reduced, and the energy efficiency ratio of the whole refrigeration system is improved.
Description
Technical Field
The present disclosure relates to the field of energy consumption optimization technologies, and in particular, to an energy consumption optimization method and apparatus for a multi-split air conditioning unit, an electronic device, and a computer-readable storage medium.
Background
With the development of technologies such as cloud service, big data, artificial intelligence computing and the like, enterprises and governments have built a large number of data centers. The energy consumption of the data center is very high, the electricity consumption of the Chinese data center accounts for 3 percent of the electricity consumption of the whole society, and the energy-saving optimization of the data center is imperative. The energy efficiency of the data center can be generally evaluated by using Power Usage Efficiency (PUE), which is a quotient of total energy consumption of the data center divided by energy consumption of the IT equipment, as an index. The higher the PUE, the higher the power consumption of other equipment (such as refrigeration equipment, lighting equipment, etc.) except IT equipment. To reduce the PUE, the energy consumption of other equipment must be reduced.
According to data statistics, cooling of the data center accounts for about 40% of the total energy consumption of the data center. Therefore, the current research on energy saving of data centers is mostly to reduce the energy consumption of the refrigeration unit. The related scheme only aims at the refrigerating units of a single machine to carry out energy-saving optimization, and when the refrigerating system is a multi-split refrigerating unit, the refrigerating capacity requirement of the data center is averagely distributed to each refrigerating unit by default. Because performance differences exist in refrigeration equipment in different refrigeration units due to the conditions of maintenance, replacement, degradation and the like, the average distribution of cold energy can cause that a high-performance refrigeration unit cannot be fully exerted and a low-performance refrigeration unit runs inefficiently, so that the energy efficiency ratio of a refrigeration system is low and the energy consumption is excessive.
Disclosure of Invention
An object of the embodiment of the present application is to provide an energy consumption optimization method and apparatus for a multi-split air-conditioning unit, an electronic device, and a computer-readable storage medium, which are used for performing energy consumption optimization on the multi-split air-conditioning unit, improving an energy efficiency ratio of a whole refrigeration system, and reducing energy consumption.
On one hand, the application provides an energy consumption optimization method of a multi-connected unit refrigerating unit, which comprises the following steps:
judging whether at least one factor of the current environmental state parameters and the total flow demand of the chilled water changes or not;
if yes, determining a variable constraint condition of the constructed objective function; the function value of the objective function is the total power of the multi-split air conditioner units, and the variables of the objective function comprise the environmental state parameters, the refrigeration control parameters of each refrigeration unit in the multi-split air conditioner units and the chilled water flow corresponding to each refrigeration unit;
solving the objective function according to the variable constraint condition to obtain a refrigeration control parameter and a chilled water flow corresponding to each refrigerating unit when the total power is minimum;
and controlling the corresponding refrigerating unit according to the solved refrigeration control parameter and the flow of the chilled water.
In one embodiment, the total chilled water flow demand is obtained by:
collecting the conveying water pressure and the return water pressure of the chilled water;
determining an actual water flow pressure difference based on the delivery water pressure and the delivery water pressure;
calculating a first total flow rate based on the actual water flow pressure difference;
determining the difference between the first total flow and a preset second total flow as the total flow demand of the chilled water; wherein the second total flow rate is calculated based on a specified water flow differential pressure.
In one embodiment, the variable constraints include a sequence of magnitudes of chilled water flow corresponding to each chiller unit;
the determining of the variable constraint condition of the constructed objective function comprises:
weighting and summing the rated refrigeration coefficient and the operation refrigeration coefficient of each refrigeration unit to obtain a reference refrigeration coefficient;
and sequencing the refrigerating units according to the sequence of the reference refrigerating coefficients, and taking the sequencing result as the sequence of the frozen water flow corresponding to each refrigerating unit.
In one embodiment, determining the variable constraints of the constructed objective function comprises:
regarding the refrigeration control parameters as variables of the objective function, taking the upper limit and the lower limit of the refrigeration control parameters of each refrigeration unit as variable constraint conditions of the refrigeration control parameters;
regarding the chilled water flow as a variable of the objective function, an upper limit and a lower limit of the chilled water flow of each refrigerator set are used as variable constraint conditions of the chilled water flow.
In one embodiment, the objective function is constructed by:
acquiring historical environmental state parameters, historical refrigeration control parameters, historical chilled water flow and historical power for each refrigeration unit;
taking the historical environmental state parameter, the historical refrigeration control parameter and the historical chilled water flow as input quantities, and taking the historical power as an output quantity to construct a power calculation model of the refrigeration unit;
and determining the objective function based on each power calculation model in the multi-split refrigerating unit.
In an embodiment, the building a power calculation model of the refrigeration unit with the historical environmental state parameter, the historical refrigeration control parameter, and the historical chilled water flow as input quantities and the historical power as output quantities includes:
inputting the historical environment state parameters, the historical refrigeration control parameters and the historical chilled water flow as sample data into a neural network model to obtain predicted power output by the neural network model; wherein the label of the sample data is the historical power;
adjusting network parameters of the neural network model based on a difference between the predicted power and the historical power;
and repeating the process until the neural network model converges.
In an embodiment, the solving the objective function according to the variable constraint condition to obtain the refrigeration control parameter and the chilled water flow rate corresponding to each refrigeration unit when the total power is minimum includes:
and under the variable constraint condition, carrying out linear programming solving on the refrigeration control parameters and the chilled water flow in the objective function in an alternative updating iteration mode to obtain the refrigeration control parameters and the chilled water flow corresponding to each refrigerating unit when the total power is minimum.
On the other hand, the present application further provides an energy consumption optimization apparatus for a multi-split refrigeration unit, including:
the judging module is used for judging whether at least one factor of the current environmental state parameter and the total flow demand of the chilled water changes;
the determining module is used for determining the variable constraint condition of the constructed target function if the variable constraint condition exists; the function value of the objective function is the total power of the multi-split air conditioner units, and the variables of the objective function comprise the environmental state parameters, the refrigeration control parameters of each refrigeration unit in the multi-split air conditioner units and the chilled water flow corresponding to each refrigeration unit;
the calculation module is used for solving the objective function according to the variable constraint condition to obtain a refrigeration control parameter and a chilled water flow corresponding to each refrigerating unit when the total power is minimum;
and the control module is used for controlling the corresponding refrigerating unit according to the solved refrigeration control parameter and the flow of the chilled water.
Further, the present application also provides an electronic device, including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to execute the energy consumption optimization method of the multi-split refrigerant unit.
In addition, the application also provides a computer readable storage medium, and the storage medium stores a computer program which can be executed by a processor to complete the energy consumption optimization method of the multi-split refrigerant unit.
In the embodiment of the application, when any one of the environmental state parameter and the total flow demand of the chilled water changes, the variable constraint condition of the constructed objective function can be determined, the objective function is solved according to the traversal constraint condition, the refrigeration control parameter and the chilled water flow which enable the total power of the multi-split air-conditioning unit to be minimum are obtained, the corresponding refrigeration unit is controlled according to the refrigeration control parameter and the chilled water flow, personalized chilled water flow distribution is achieved, the performance of the multi-split air-conditioning unit is fully exerted, the energy consumption is reduced, and the energy efficiency ratio of the whole refrigeration system is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments of the present application will be briefly described below.
Fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a refrigeration system according to an embodiment of the present application;
fig. 3 is a schematic flowchart of a method for optimizing energy consumption of a multi-split refrigerant unit according to an embodiment of the present application;
fig. 4 is a block diagram of an energy consumption optimization device of a multi-split refrigerant unit according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
Like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
As shown in fig. 1, an electronic device 1 provided in an embodiment of the present application includes: at least one processor 11 and a memory 12, one processor 11 being exemplified in fig. 1. The processor 11 and the memory 12 are connected by a bus 10, and the memory 12 stores instructions executable by the processor 11, and the instructions are executed by the processor 11, so that the electronic device 1 can execute all or part of the flow of the method in the embodiments described below. In an embodiment, the electronic device 1 may be a host of a method for optimizing energy consumption of a multi-split cooling unit. The main machine is in butt joint with the multi-split air conditioning unit, can collect various parameters of the multi-split air conditioning unit, and controls the multi-split air conditioning unit.
The Memory 12 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk.
The present application further provides a computer-readable storage medium storing a computer program executable by the processor 11 to perform the method for optimizing energy consumption of a multi-split refrigeration unit provided by the present application.
Referring to fig. 2, an architecture diagram of a refrigeration system provided for an embodiment of the present application is shown in fig. 2, and the refrigeration system may include a cooling tower, a cooling pump, a condenser, a compressor, an evaporator, a freezing pump, and a central air conditioner. Wherein, the cooling tower, the cooling pump, the condenser, the compressor, the evaporator and the freezing pump in the dashed line frame form a refrigerating unit.
The refrigerating unit takes away indoor heat by conveying chilled water to the central air conditioner. The temperature of the freezing water rises, the freezing water flows back to the evaporator and exchanges heat with the refrigerant through the evaporator. After the refrigerant absorbs heat, the temperature of the frozen water is reduced. The refrigerating unit then conveys the cooled chilled water to the central air conditioner. The chilled water circulation may carry indoor heat to the refrigeration unit.
The compressor brings the refrigerant absorbing heat to the condenser, and the refrigerant and the cooling water return water perform heat exchange. After the cooling water absorbs heat, the cooling water becomes cooling water effluent and is discharged out of the condenser, and the heat is brought to an outdoor cooling tower for dissipation. And the cooled cooling water is pumped to the condenser by the cooling pump. The cooling water circulation can radiate the heat of the refrigerating unit to the outside.
In the multi-split air conditioner refrigerating unit in the embodiment of the application, a plurality of refrigerating units provide chilled water for the central air conditioner. The multiple refrigerating units have different equipment performances, and the average distribution of the flow of the chilled water supplied by the refrigerating units can cause the whole multi-unit refrigerating unit to generate redundant energy consumption.
Referring to fig. 3, a schematic flowchart of a method for optimizing energy consumption of a multiple refrigerant unit according to an embodiment of the present application is shown in fig. 3, where the method includes steps 310 to 340.
Step 310: and judging whether at least one factor of the current environmental state parameters and the total flow demand of the chilled water changes.
The environmental state parameters may include, among others, outdoor temperature and humidity. The total flow demand of the chilled water is the total flow of the chilled water required by the central air conditioner which is connected with the multi-split refrigerating unit. The ambient condition parameter may be considered one factor and the total chilled water flow demand may be considered another factor.
The host computer can periodically obtain temperature and humidity from outdoor temperature and humidity sensor. The period duration here may be preconfigured based on experience. Illustratively, the cycle duration may be 1 hour.
The main machine can periodically determine the total flow demand of the chilled water through the delivery water pressure and the delivery water pressure of the chilled water. The conveying water pressure is the water pressure of the chilled water output by the multi-unit refrigerating unit, and the conveying water pressure is the water pressure of the chilled water which is circulated and then conveyed back to the multi-unit refrigerating unit. The period duration here may be preconfigured based on experience, and may be consistent with or inconsistent with the period duration for the host to obtain the environmental state parameter.
The main machine can collect the delivery water pressure and the return water pressure of the chilled water from a water pressure metering device (such as a water pressure meter) and calculate the actual water pressure difference between the delivery water pressure and the return water pressure.
The host may calculate the first total flow based on the actual water pressure differential. The main machine can calculate the first total flow based on the actual water pressure difference, the preset length of the water conveying pipeline between the multi-connected refrigerating unit and the central air conditioner and the pipeline specific resistance. The specific calculation mode can refer to a general flow calculation formula.
The host may determine a difference between the first total flow rate and the second total flow rate as a total chilled water flow demand. The second total flow is calculated based on the specified water flow pressure difference; the specified water flow pressure difference is the difference between the delivery water pressure and the delivery water pressure of the chilled water when the refrigeration system is in normal operation.
After the host computer obtains the environmental state parameters and the total flow demand of the chilled water, whether at least one of the environmental state parameters and the total flow demand of the chilled water changes can be judged.
On one hand, if the environmental state parameter and the total flow demand of the chilled water are not changed, the environmental state parameter and the total flow demand of the chilled water can be continuously obtained for the next round of judgment.
On the other hand, if at least one of the two changes, it indicates that the host needs to adjust the multi-split cooling unit, and step 320 may be executed.
In an embodiment, the process of acquiring the environmental state parameter and the process of acquiring the total flow demand of the chilled water by the host may be performed asynchronously, and in this case, the host may immediately determine whether the acquired environmental state parameter or the total flow demand of the chilled water changes every time the host acquires one of the environmental state parameter and the total flow demand of the chilled water.
Step 320: if yes, determining a variable constraint condition of the constructed objective function; the function value of the objective function is the total power of the multi-split air conditioner units, and the variables of the objective function comprise the environmental state parameters, the refrigeration control parameters of each refrigeration unit in the multi-split air conditioner units and the freezing water flow corresponding to each refrigeration unit.
The variable constraint conditions are constraint conditions for environment state parameters, refrigeration control parameters of each refrigerating unit and chilled water flow corresponding to each refrigerating unit. In one embodiment, the refrigeration control parameter may be a cooling tower frequency and a cooling water pump frequency, or the refrigeration control parameter may be a cooling water temperature.
In one embodiment, the environment state parameter in the objective function is equal to the current environment state parameter since the host has already obtained the current environment state parameter. In other words, the environmental state parameters are not changed in the subsequent solving of the objective function. The variable constraints on the environmental state parameters can be expressed as: s is 0 S represents an environmental state parameter in the objective function, S 0 Representing the environmental status parameters acquired by the host.
In one embodiment, the total chilled water flow provided by all of the multiple refrigerant units must meet the total chilled water flow requirement. The constraint condition of the chilled water flow corresponding to each refrigerating unit can be expressed as follows: r is a radical of hydrogen 1 +r 2 +r 3 +……+r n R, where R represents total chilled water flow demand, n represents the total number of refrigeration units in the multiple refrigerant unit train, and R i And (i is more than or equal to 1 and less than or equal to n) represents the flow of the chilled water corresponding to the ith refrigerating unit.
In one embodiment, the main unit may allocate a higher chilled water flow rate to the high-performance chiller unit to provide more chilled water from the high-performance chiller unit due to different performance of the chiller unit. The performance of the refrigeration unit may be expressed by ERR (Energy Efficiency Ratio) or COP (coefficient of performance). Both ERR and COP may be referred to as the refrigeration factor of the refrigeration unit.
The host machine can carry out weighted summation on the rated refrigeration coefficient and the operation refrigeration coefficient of each refrigeration unit to obtain a reference refrigeration coefficient.
The rated refrigeration coefficient is the maximum refrigeration coefficient of the refrigeration unit in a normal operation state, and the operation refrigeration coefficient is the refrigeration coefficient of the refrigeration unit in a current operation state; the reference refrigeration coefficient is a refrigeration coefficient that combines a rated refrigeration coefficient and an operating refrigeration coefficient. The weighting of the nominal and operating refrigeration factors may be pre-configured empirical values.
The host machine may sequence the chiller units according to a magnitude order of the reference refrigeration coefficient and take the sequencing result as a magnitude order of chilled water flow corresponding to each chiller unit. Illustratively, there are 4 refrigerating units in the multi-split air-conditioning unit, and the refrigerating coefficients corresponding to the refrigerating units are COP (coefficient of performance) 3 ＜COP 1 ＜COP 4 ＜COP 2 ，COP i And (i is more than or equal to 1 and less than or equal to 4) represents the refrigeration coefficient corresponding to the ith refrigeration unit. The freezing water flow corresponding to the refrigerating unit has the sequence of r 3 ＜r 1 ＜r 4 ＜r 2 ，r i And (i is more than or equal to 1 and less than or equal to 4) represents the flow rate of the chilled water corresponding to the ith refrigerating unit.
The host machine can use the magnitude sequence of the flow of the chilled water corresponding to each refrigerating unit as a variable constraint condition for the chilled water.
In one embodiment, the host may use the upper limit and the lower limit of the chilled water flow rate that each refrigerator set can provide as the constraint condition of the chilled water flow rate corresponding to each refrigerator set. The variable constraint can be expressed as: r is i_lower ＜r i ＜r i_upper ，r i (i is more than or equal to 1 and less than or equal to n) represents the flow rate of the chilled water corresponding to the ith refrigerating unit in the multi-split air conditioner unit comprising n refrigerating units, and r is i_lower Represents the lower limit, r, of the flow rate of the chilled water that can be supplied during normal operation of the ith refrigeration unit i_upper Which represents the upper limit of the chilled water flow that can be provided during normal operation of the ith refrigeration unit.
In one implementationIn one example, the host machine may use the upper limit and the lower limit of the refrigeration control parameter of each refrigeration unit as the constraint condition of the refrigeration control parameter of each refrigeration unit. The variable constraint can be expressed as: c i_lower ＜C i ＜C i_upper ，C i (i is more than or equal to 1 and less than or equal to n) represents a refrigeration control parameter corresponding to the ith refrigerating unit in the multi-split air conditioning unit comprising n refrigerating units, and C i_lower Lower limit of refrigeration control parameter, C, representing normal operation of ith refrigeration unit i_upper And represents the upper limit of the refrigeration control parameter when the ith refrigerating unit operates normally.
Step 330: and solving the objective function according to the variable constraint conditions to obtain the refrigeration control parameters and the chilled water flow rate corresponding to each refrigerating unit when the total power is minimum.
The host machine may solve the objective function under the constraints of the variable constraints described above.
In one embodiment, the objective function may consist of a power calculation model for each refrigeration unit. The power calculation model includes, but is not limited to, a physical model, a linear regression model, and a neural network model. The power calculation model may be expressed as: p is a radical of i ＝F i (S，C i ，r i )，p i (i is more than or equal to 1 and less than or equal to n) represents the power of the ith refrigerating unit in the multi-split air conditioner unit comprising n refrigerating units, S represents an environmental state parameter, C represents an environmental state parameter i Indicating a refrigeration control parameter, r, of the ith refrigeration unit i Indicating the chilled water flow rate for the ith chiller unit.
The objective function can be expressed as:
in the objective function, the refrigeration control parameter as a variable and the chilled water flow as a variable are coupled with each other to influence the solution, so that the two variables cannot be solved simultaneously in the same iterative calculation process.
And aiming at the refrigeration control parameters and the chilled water flow, the host can carry out linear programming solution in an alternate updating and iteration mode. When each iteration is updated and solved, the host can fix one type of variable and solve the other type of variable; and when the next iteration is used for updating the solution, the host machine replaces the fixed variables and the solved variables.
Such as: the host can fix the refrigeration control parameters in the objective function and solve the refrigerating water flow corresponding to each refrigerating unit; the host machine fixedly solves the obtained chilled water flow, and solves the refrigeration control parameters of each refrigeration unit; after the refrigeration control parameters are solved, the host machine fixes the refrigeration control parameters again, and the flow of the frozen water is solved; this process is repeated until the optimum refrigeration control parameters and chilled water flow are solved that minimize the total power.
The host computer can adopt an operation and research algorithm or a heuristic algorithm (such as an ant colony algorithm, a simulated annealing method and the like) to carry out linear programming solution.
Step 340: and controlling the corresponding refrigerating unit according to the solved refrigeration control parameter and the chilled water flow.
The host computer may issue the refrigeration control parameters and the chilled water flow to the refrigeration unit corresponding to the refrigeration control parameters through a BACnet gateway (building automation and control network).
Each device of the refrigerating unit is provided with a controller, and the controller can control the device after receiving the refrigeration control parameters. Illustratively, the host issues a cooling tower frequency to the controller of the cooling tower. The controller may control the cooling tower to operate at the cooling tower frequency.
After the flow of the chilled water is calculated by the host, the flow of the chilled water can be converted into the frequency of the refrigerating pump in a direct proportion relation with the flow of the chilled water, and the frequency of the refrigerating pump is sent to the controller of the refrigerating pump. The controller may control the freeze pump to operate at the freeze pump frequency to provide a flow of chilled water corresponding to the freeze pump frequency.
In one embodiment, the host computer may construct the objective function before performing step 310.
For each refrigerating unit, the host can acquire historical environmental parameters, historical refrigeration control parameters, historical chilled water flow and historical power.
Wherein the historical environmental parameters, the historical refrigeration control parameters, the historical chilled water flow, and the historical power are historical data collected by the host prior to performing step 310.
The host computer can collect the above four kinds of data each time to form a history data record. After a large number of historical data records are collected, the host computer can construct a power calculation model of the refrigerating unit.
The host machine takes the historical environmental state parameters, the historical refrigeration control parameters and the historical chilled water flow as input quantities and takes the historical power as output quantities to construct a power calculation model of the refrigeration unit.
The power calculation model can be a physical model, a linear regression model and a neural network model.
Taking a linear regression model as an example, based on a large amount of historical data (historical environmental state parameters, historical refrigeration control parameters, historical chilled water flow as independent variables, and historical power as dependent variables), fitting the linear regression model by a least square method, and obtaining a power calculation model of the refrigerating unit.
In one embodiment, the host may use the historical environmental state parameter, the historical refrigeration control parameter, and the historical chilled water flow in the historical data record as sample data, and use the historical power in the historical data record as a tag of the sample data.
The host can input the sample data into the neural network model to obtain the predicted power output by the neural network model. The Neural network model may be a general network model such as DNN (Deep Neural Networks), LSTM (Long Short-Term Memory network), and the like.
The host can calculate the difference between the predicted power and the historical power according to the preconfigured loss function to obtain a function value, so as to evaluate the accuracy of the neural network model and adjust the network parameters of the neural network model.
After multiple times of iterative training, the host computer can stop training when the function value is smaller than the preset loss threshold value or the iteration times reach the preset times, and at the moment, the neural network model converges and can be used as a power calculation model.
After the power calculation models of all the refrigerating units are constructed by the host computer, the objective function can be determined. The host machine can obtain a function value which is an objective function of the total power of the multi-split air-conditioning unit by accumulating all power calculation models.
Fig. 4 is a block diagram of an energy consumption optimization device for an on-line refrigerator group according to an embodiment of the present invention, as shown in fig. 4, the device may include:
the determining module 410 is used for determining whether at least one of the current environmental status parameter and the total flow demand of the chilled water changes.
A determining module 420, configured to determine a variable constraint condition of the constructed objective function if the variable constraint condition is positive; the function value of the objective function is the total power of the multi-split air conditioner units, and the variables of the objective function comprise the environmental state parameters, the refrigeration control parameters of each refrigeration unit in the multi-split air conditioner units and the freezing water flow corresponding to each refrigeration unit.
And the calculating module 430 is configured to solve the objective function according to the variable constraint condition, and obtain a refrigeration control parameter and a chilled water flow rate corresponding to each refrigeration unit when the total power is minimum.
And the control module 440 is configured to control the corresponding refrigerating unit according to the solved refrigeration control parameter and the flow rate of the chilled water.
In one embodiment, the apparatus includes an acquisition module configured to:
collecting the conveying water pressure and the return water pressure of the chilled water;
determining an actual water flow pressure difference based on the delivery water pressure and the delivery water pressure;
calculating a first total flow rate based on the actual water flow pressure difference;
determining the difference between the first total flow and a preset second total flow as the total flow demand of the chilled water; wherein the second total flow rate is calculated based on a specified water flow differential pressure.
In an embodiment, the determining module 420 is configured to:
weighting and summing the rated refrigeration coefficient and the operation refrigeration coefficient of each refrigeration unit to obtain a reference refrigeration coefficient;
and sequencing the refrigerating units according to the magnitude sequence of the reference refrigerating coefficient, and taking the sequencing result as the magnitude sequence of the chilled water flow corresponding to each refrigerating unit.
In an embodiment, the determining module 420 is configured to:
regarding the refrigeration control parameters as variables of the objective function, taking the upper limit and the lower limit of the refrigeration control parameters of each refrigeration unit as variable constraint conditions of the refrigeration control parameters;
and regarding the chilled water flow as a variable of the objective function, taking the upper limit and the lower limit of the chilled water flow of each refrigerating unit as a variable constraint condition of the chilled water flow.
In an embodiment, the apparatus further comprises a construction module for:
acquiring historical environmental state parameters, historical refrigeration control parameters, historical chilled water flow and historical power for each refrigeration unit;
taking the historical environmental state parameter, the historical refrigeration control parameter and the historical chilled water flow as input quantities, and taking the historical power as an output quantity to construct a power calculation model of the refrigeration unit;
and determining the objective function based on each power calculation model in the multi-split refrigerant unit.
In one embodiment, the building module is configured to:
inputting the historical environment state parameters, the historical refrigeration control parameters and the historical chilled water flow as sample data into a neural network model to obtain the predicted power output by the neural network model; wherein the label of the sample data is the historical power;
adjusting network parameters of the neural network model based on a difference between the predicted power and the historical power;
and repeating the process until the neural network model converges.
In one embodiment, the calculation module 430 is configured to:
and under the variable constraint condition, carrying out linear programming solving on the refrigeration control parameters and the chilled water flow in the objective function in an alternate updating iteration mode to obtain the refrigeration control parameters and the chilled water flow corresponding to each refrigerating unit when the total power is minimum.
The implementation processes of the functions and actions of the modules in the device are specifically described in the implementation processes of the corresponding steps in the energy consumption optimization method of the multi-split refrigerating unit, and are not described herein again.
In the embodiments provided in the present application, the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Claims (8)
1. A method for optimizing energy consumption of a multi-split refrigerating unit is characterized by comprising the following steps:
judging whether at least one factor of the current environmental state parameters and the total flow demand of the chilled water changes;
if yes, determining a variable constraint condition of the constructed objective function; the function value of the objective function is the total power of the multi-split air conditioner, the variables of the objective function comprise the environmental state parameter, the refrigeration control parameter of each refrigerating unit in the multi-split air conditioner and the chilled water flow corresponding to each refrigerating unit, and the chilled water total flow demand is the chilled water total flow required by the central air conditioner connected with the multi-split air conditioner; the variable constraint comprises a magnitude sequence of chilled water flow corresponding to each chiller unit; the determining of the variable constraint condition of the constructed objective function comprises: weighting and summing the rated refrigeration coefficient and the operation refrigeration coefficient of each refrigeration unit to obtain a reference refrigeration coefficient; sequencing the refrigerating units according to the magnitude sequence of the reference refrigerating coefficient, and taking the sequencing result as the magnitude sequence of the chilled water flow corresponding to each refrigerating unit;
under the variable constraint condition, carrying out linear programming solving on the refrigeration control parameters and the chilled water flow in the objective function in an alternate updating iteration mode to obtain the refrigeration control parameters and the chilled water flow corresponding to each refrigerating unit when the total power is minimum;
and controlling the corresponding refrigerating unit according to the solved refrigeration control parameter and the flow of the chilled water.
2. The method of claim 1, wherein the total chilled water flow demand is obtained by:
collecting the conveying water pressure and the return water pressure of the chilled water;
determining an actual water flow pressure difference based on the delivery water pressure and the delivery water pressure;
calculating a first total flow rate based on the actual water flow pressure difference;
determining the difference between the first total flow and a preset second total flow as the total flow demand of the chilled water; wherein the second total flow rate is calculated based on a specified water flow differential pressure.
3. The method of claim 1, wherein determining variable constraints for the constructed objective function comprises:
regarding the refrigeration control parameters as variables of the objective function, taking the upper limit and the lower limit of the refrigeration control parameters of each refrigeration unit as variable constraint conditions of the refrigeration control parameters;
and regarding the chilled water flow as a variable of the objective function, taking the upper limit and the lower limit of the chilled water flow of each refrigerating unit as a variable constraint condition of the chilled water flow.
4. The method of claim 1, wherein the objective function is constructed by:
acquiring historical environmental state parameters, historical refrigeration control parameters, historical chilled water flow and historical power for each refrigeration unit;
taking the historical environmental state parameter, the historical refrigeration control parameter and the historical chilled water flow as input quantities, and taking the historical power as an output quantity to construct a power calculation model of the refrigeration unit;
and determining the objective function based on each power calculation model in the multi-split refrigerant unit.
5. The method of claim 4, wherein said building a power calculation model of the refrigeration unit with the historical environmental state parameters, the historical refrigeration control parameters, and the historical chilled water flow as inputs and the historical power as an output comprises:
inputting the historical environment state parameters, the historical refrigeration control parameters and the historical chilled water flow as sample data into a neural network model to obtain the predicted power output by the neural network model; wherein the label of the sample data is the historical power;
adjusting network parameters of the neural network model based on a difference between the predicted power and the historical power;
and repeating the process until the neural network model converges.
6. The utility model provides an energy consumption optimizing device of multi-connected air-cooled unit which characterized in that includes:
the judging module is used for judging whether at least one factor of the current environmental state parameters and the total flow demand of the chilled water changes;
the determining module is used for determining the variable constraint conditions of the constructed target function if the variable constraint conditions are the same as the variable constraint conditions of the constructed target function; the function value of the objective function is the total power of the multi-split air conditioner, the variables of the objective function comprise the environmental state parameter, the refrigeration control parameter of each refrigerating unit in the multi-split air conditioner and the chilled water flow corresponding to each refrigerating unit, and the chilled water total flow demand is the chilled water total flow required by the central air conditioner connected with the multi-split air conditioner; the variable constraint comprises a magnitude sequence of chilled water flow corresponding to each chiller unit; the determining module is also used for weighting and summing the rated refrigeration coefficient and the operation refrigeration coefficient of each refrigerating unit to obtain a reference refrigeration coefficient; sequencing the refrigerating units according to the magnitude sequence of the reference refrigerating coefficient, and taking the sequencing result as the magnitude sequence of the chilled water flow corresponding to each refrigerating unit;
the calculation module is used for carrying out linear programming solving on the refrigeration control parameters and the chilled water flow in the objective function in an alternate updating iteration mode under the variable constraint condition to obtain the refrigeration control parameters and the chilled water flow corresponding to each refrigerating unit when the total power is minimum;
and the control module is used for controlling the corresponding refrigerating unit according to the solved refrigeration control parameter and the flow of the chilled water.
7. An electronic device, characterized in that the electronic device comprises:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to perform the method for optimizing energy consumption of a multiple refrigerant unit according to any of claims 1-5.
8. A computer-readable storage medium, characterized in that the storage medium stores a computer program executable by a processor to perform the method for optimizing energy consumption of a multi-split refrigerant unit as set forth in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010624014.6A CN111787764B (en) | 2020-06-30 | 2020-06-30 | Energy consumption optimization method and device for multi-split refrigerating unit, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010624014.6A CN111787764B (en) | 2020-06-30 | 2020-06-30 | Energy consumption optimization method and device for multi-split refrigerating unit, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111787764A CN111787764A (en) | 2020-10-16 |
| CN111787764B true CN111787764B (en) | 2022-09-30 |
Family
ID=72760114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010624014.6A Active CN111787764B (en) | 2020-06-30 | 2020-06-30 | Energy consumption optimization method and device for multi-split refrigerating unit, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111787764B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114017904B (en) * | 2021-11-04 | 2023-01-20 | 广东电网有限责任公司 | Operation control method and device for building HVAC system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109556236A (en) * | 2018-10-22 | 2019-04-02 | 珠海格力电器股份有限公司 | Energy efficiency controlling method and device |
| CN109945402A (en) * | 2019-03-07 | 2019-06-28 | 东南大学 | A kind of central air conditioning water system power-economizing method |
| CN109960147A (en) * | 2019-03-12 | 2019-07-02 | 北京百度网讯科技有限公司 | Determination method and device, equipment and the storage medium of cold source control parameter |
| CN110454959A (en) * | 2019-09-17 | 2019-11-15 | 南方电网科学研究院有限责任公司 | A kind of air conditioner energy saving control method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012048443A1 (en) * | 2010-10-13 | 2012-04-19 | 日滔贸易（上海）有限公司 | Energy-saving optimized control system and method for refrigeration plant room |
-
2020
- 2020-06-30 CN CN202010624014.6A patent/CN111787764B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109556236A (en) * | 2018-10-22 | 2019-04-02 | 珠海格力电器股份有限公司 | Energy efficiency controlling method and device |
| CN109945402A (en) * | 2019-03-07 | 2019-06-28 | 东南大学 | A kind of central air conditioning water system power-economizing method |
| CN109960147A (en) * | 2019-03-12 | 2019-07-02 | 北京百度网讯科技有限公司 | Determination method and device, equipment and the storage medium of cold source control parameter |
| CN110454959A (en) * | 2019-09-17 | 2019-11-15 | 南方电网科学研究院有限责任公司 | A kind of air conditioner energy saving control method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111787764A (en) | 2020-10-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021063033A1 (en) | Energy consumption model training method for air conditioner and air conditioning system control method | |
| CN111811110B (en) | Control method and device of refrigerating unit, electronic equipment and storage medium | |
| CN104134100B (en) | A kind of energy-saving management system based on cloud computing | |
| CN104566868A (en) | Central air-conditioning control system and control method thereof | |
| CN104713197A (en) | Central air conditioning system optimizing method and system based on mathematic model | |
| CN113739365A (en) | Central air-conditioning cold station group control energy-saving control method, device, equipment and storage medium | |
| CN114383299B (en) | Central air-conditioning system operation strategy optimization method based on big data and dynamic simulation | |
| CN112283890A (en) | Cold and heat quantity control method and device suitable for building heating and ventilation equipment monitoring system | |
| CN115325682A (en) | Optimization control method and device for performance monitoring of efficient intelligent refrigeration machine room | |
| CN115776795A (en) | Data center air conditioning system diagnosis method and device | |
| CN111787764B (en) | Energy consumption optimization method and device for multi-split refrigerating unit, electronic equipment and storage medium | |
| CN115049141A (en) | Control method and control device for refrigeration system and refrigeration system | |
| CN115560430B (en) | Cloud computing-based air conditioner model optimization method and system | |
| Xue et al. | A novel method of minimizing power consumption for existing chiller plant | |
| CN113028610B (en) | Method and device for global optimization and energy-saving control of dynamic load of central air conditioner | |
| US20220373206A1 (en) | Chiller controller for optimized efficiency | |
| US11732942B2 (en) | Building system with automatic chiller anti-surge control | |
| CN204853838U (en) | Central air conditioning control system | |
| Kumar et al. | Data center air handling unit fan speed optimization using machine learning techniques | |
| CN112902392A (en) | Adaptive adjustment air conditioner control method, electronic equipment and storage medium | |
| CN117241561B (en) | Data center distributed precise air conditioning unit optimized operation parameter estimation method | |
| CN117537450B (en) | Method, device, equipment and medium for controlling operation feedback of central air-conditioning refrigeration system | |
| CN114543273B (en) | Self-adaptive deep learning optimization energy-saving control algorithm for central air conditioner cooling system | |
| CN117267910B (en) | Method, device, equipment and medium for flexibly adjusting load of central air-conditioning refrigeration system | |
| CN112966707B (en) | Automatic identification method and system for universal heating ventilation air conditioning equipment model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |