CHILLER UNIT ENERGY CONSUMPTION CALCULATING METHOD, CALCULATING DEVICE, AND CHILLER UNIT

Description

PRIORITY CLAIM

This application claims benefit of Chinese Patent Application No. 202410333704.4, filed Mar. 21, 2024, and all the benefits accruing therefrom under 35 U.S.C. § 119, the contents of which in their entirety are herein incorporated by reference.

BACKGROUND

This application relates to the field of refrigeration equipment, and specifically relates to a system and method for calculating energy consumption of a chiller unit composed of multiple chillers.

SUMMARY OF THE INVENTION

This application provides a system and method for calculating energy consumption of a chiller unit which can predict and calculate the power of a chiller unit with high accuracy and efficiency.

One or more embodiments of this application provides a chiller unit system, the system comprising:

• • a first chiller and a second chiller; and
  • a controller, the controller being operatively connected to the first chiller and the second chiller, wherein the controller comprises:
  • a processor coupled to a memory storing instructions executable by the processor, which causes the controller to:
  • predict and output, via a chiller unit load prediction module, a total load of the chiller unit based on a cooling load prediction model;
  • distribute, via a chiller load distribution module, the total load of the chiller unit output by the chiller unit load prediction module to the first chiller and the second chiller of the chiller unit, according to a preset chiller load distribution logic;
  • acquire, via a chiller energy efficiency value acquisition module, a first chiller energy efficiency value and a second chiller energy efficiency value according to a chiller load-energy efficiency relationship, based on a first chiller load and a second chiller load distributed and output by the chiller load distribution module; and
  • calculate, via a chiller power calculation module, a first chiller input power and a second chiller input power according to the first chiller energy efficiency value and the second chiller energy efficiency value acquired by the chiller energy efficiency value acquisition module.

In one or more embodiments, the system further comprises:

• • a first water pump operatively connected to the first chiller; and
  • a second water pump operatively connected to the second chiller.

In or more embodiments, the processor coupled to the memory storing instructions executable by the processor further causes the controller to:

• • predict and output, via a water pump load prediction module, a total load of the first and second water pumps based on the cooling load prediction model;
  • distribute, via a water pump load distribution module, the total load of the first and second water pumps according to the chiller load distribution logic;
  • acquire, via a water pump efficiency acquisition module, a first water pump efficiency value and a second water pump efficiency value according to a preset water pump load-efficiency curve, based on the first water pump load and the second water pump load distributed by the water pump load distribution unit; and
  • calculate, via a water pump power calculation module, a first water pump input power and a second water pump input power according to the output of the water pump load distribution module and the water pump efficiency acquisition module.

In one or more embodiments, the cooling load prediction model is a data-driven model, a physical prediction model, or a combination of the data-driven model and the physical prediction model.

In one or more embodiments, the system further comprises:

• • a first sensor operatively connected with the first chiller;
  • a second sensor operatively connected with the second chiller; and
  • wherein the first and the second sensor are configured to acquire working conditions of the first chiller and the second chiller in real-time.

One or more embodiments of this application further provides a chiller unit system, the system comprising:

• • a first chiller, a second chiller, and a third chiller; and
  • a controller, the controller being operatively connected to the first chiller, the second chiller and the third chiller, wherein the controller comprises:
  • a processor coupled to a memory storing instructions executable by the processor, which causes the controller to:
  • predict and output, via a chiller unit load prediction module, a total load of the chiller unit based on a cooling load prediction model;
  • distribute, via a chiller load distribution module, the total load of the chiller unit output by the chiller unit load prediction module to the first chiller, the second chiller and the third chiller of the chiller unit, according to a chiller load distribution logic;
  • acquire, via a chiller energy efficiency value acquisition module, a first chiller energy efficiency value, a second chiller efficiency value and a third chiller energy efficiency value according to a chiller load-energy efficiency relationship, based on a first chiller load, a second chiller load and a third chiller load distributed and output by the chiller load distribution module; and
  • calculate, via a chiller power calculation module, a first chiller input power, a second chiller input power and a third chiller input power according to the first chiller energy efficiency value, the second chiller energy efficiency value and the third chiller energy efficiency value acquired by the chiller energy efficiency value acquisition module.

In one or more embodiments, wherein the system further comprises:

• • a first water pump operatively connected to the first chiller;
  • a second water pump operatively connected to the second chiller; and
  • a third water pump operatively connected to the third chiller.

In one or more embodiments, the processor coupled to the memory storing instructions executable by the processor further causes the controller to:

• • predict and output, via a water pump load prediction module, a total load of the first, second and third water pumps based on the cooling load prediction model;
  • distribute, via a water pump load distribution module, the total load of the first, second and third water pumps according to the chiller load distribution logic;
  • acquire, via a water pump efficiency acquisition module, a first water pump efficiency value, a second water pump efficiency value and a third water pump efficiency value according to a water pump load-efficiency curve, based on the first water pump load, second water pump load and the third water pump load distributed by the water pump load distribution unit; and
  • calculate, via a water pump power calculation module, a first water pump input power and a second water pump input power according to the output of the water pump load distribution module and the water pump efficiency acquisition module.

In one or more embodiments, the cooling load prediction model is a data-driven model, a physical prediction model, or a combination of the data-driven model and the physical prediction model.

In one or more embodiments, the system further comprises:

• • a first sensor operatively connected with the first chiller;
  • a second sensor operatively connected with the second chiller;
  • a third sensor operatively connected with the third chiller; and
  • wherein the first, second and the third sensor are configured to acquire working conditions of the first chiller, the second chiller and the third chiller in real-time.

One or more embodiments of this application further provides a method for calculating energy consumption of a chiller unit, the method comprising:

• • calculating energy consumption using the chiller unit system according to one or more embodiments.

DESCRIPTIONS OF THE DRAWINGS

FIG. 1 is a system schematic diagram of a chiller unit according to one or more embodiments.

FIG. 2 is a schematic diagram showing a chiller unit system and steps of a controller for predicting and calculating energy consumption of a chiller unit according to one or more embodiments.

FIG. 3 is a schematic diagram of a chiller load-energy efficiency curve according to one or more embodiments.

FIG. 4 is another schematic diagram showing a chiller unit system and steps of a controller for predicting and calculating energy consumption of a chiller unit according to one or more embodiments.

FIG. 5 is a schematic diagram of a water pump load-efficiency curve according to one or more embodiments.

FIG. 6 is another block schematic diagram showing a chiller unit system and steps of a controller for predicting and calculating energy consumption of a chiller unit according to one or more embodiments.

FIG. 7 is another block schematic diagram showing a chiller unit system and steps of a controller for predicting and calculating energy consumption of a chiller unit according to one or more embodiments.

FIG. 8 is an exemplary block diagram depicting the controller and communication module which are configured to be operatively connected to the one or more chillers according to one or more embodiments.

DETAILED DESCRIPTION

The technical solutions in the one or more embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application, and obviously, any single technical feature illustrated or implicit in the drawings of this application still allows any combination or deletion between these technical features (or their equivalents) without any technical obstacles, thereby obtaining other embodiments of this application that my not be directly mentioned herein. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of this application.

Those skilled in the art can appreciate that in order to apply advanced control methods such as model predictive control (MPC) to a centralized heating ventilation air conditioning building system, there are often two forms of using a physical building model and of using a data-driven model to predict refrigeration load or heating load of the centralized heating ventilation air conditioning building system.

The physical building model acquires information such as building type, number of floors, thermal property of the building envelope, climate zone, meteorological parameters, location, orientation, geometry, area, and occupant density, then establishes a physical model and performs energy consumption simulation analysis on the physical model to acquire energy consumption optimization results. However, the physical building model is usually very complex, with many types and requires large calculations, making them unsuitable for control applications.

The data-driven model acquires historical load data, various historical meteorological parameters such as outdoor dry bulb temperature, outdoor relative humidity, outdoor dew point temperature, wind speed, wind direction, cloud cover and atmospheric pressure, as well as weather or chronosystem feature data such as weather forecast, month, day attributes, hours, and on this basis uses algorithms such as multidimensional clustering, multi-step input-multi-step output, attention mechanism to build a training sample database, establishes a data-driven prediction model, trains the model, and then evaluates the trained model, and uses the evaluated model to predict the load of the chiller unit. However, the data-driven model is highly dependent on quality and availability of collected data. In practice, the operating data of different chiller units may have varying qualities and poor data quality, which may lead to inaccurate load prediction of the chiller unit.

Among these, accurate prediction of an input power of the chiller unit is crucial for realizing model predictive control (MPC) of the centralized heating ventilation air conditioning system and improving energy-saving effects.

The chiller unit according to a method for predicting and calculating energy consumption of a chiller unit and a system for predicting and calculating energy consumption of a chiller unit of this application is composed of multiple chillers. A chiller unit composed of three chillers is used as an example for explanation below. The embodiments of this disclosure are not limited to only three chillers, any combination of multiple chillers may be utilized within the scope of the present disclosure.

FIG. 1 is a system schematic diagram of a chiller unit according to this application. As shown in FIG. 1, the chiller unit is composed of a first chiller 1, a second chiller 2 and a third chiller 3. The first chiller 1 includes a refrigerant pipeline connected in sequence to a first compressor 11, a first condenser 12, a first expansion valve 13 and a first evaporator 14, forming a refrigerant circulation loop. The high-temperature and high-pressure refrigerant discharged from the first compressor 11 performs heat exchange with an external medium (such as water or air) in the first condenser 12, and after being decompressed and expanded by the first expansion valve 13, performs heat exchange with the external medium (such as water) in the first evaporator 14, absorbs heat from the external medium (such as water) in the first evaporator 14, and enters the first compressor 11 to be compressed and heated again, and the cycle continues. The external medium (such as water) in the first evaporator 14 is cooled after heat being absorbed to form low-temperature cold water of a predetermined temperature, which is driven by the first water pump 15 and supplied to the user terminal 16, and returns to the first evaporator 14 for circulation again after absorbing heat in the user terminal 16.

The second chiller 2 includes a refrigerant pipeline connected in sequence to a second compressor 21, a second condenser 22, a second expansion valve 23, and a second evaporator 24, forming a refrigerant circulation loop. The external medium (such as water) in the second evaporator 24 is cooled after heat being absorbed to form low-temperature cold water of a predetermined temperature, which is driven by the second water pump 25 and supplied to the user terminal 16, and returns to the second evaporator 24 for circulation again after absorbing heat in the user terminal 16. The third chiller 3 includes a refrigerant pipeline connected in sequence to a third compressor 31, a third condenser 32, a third expansion valve 33, and a third evaporator 34, forming a refrigerant circulation loop. The external medium (such as water) in the third evaporator 34 is cooled after heat being absorbed to form low-temperature cold water of a predetermined temperature, which is driven by the third water pump 35 and supplied to the user terminal 16, and returns to the third evaporator 34 for circulation again after absorbing heat in the user terminal 16.

The working principles of the chiller 2 and the chiller 3 are substantially the same as those of the chiller 1 and will not be repeated here.

In addition, the compressor 11, the compressor 21 and the compressor 31 of the first chiller 1, the second chiller 2 and the third chiller 3 according to this application may be screw type, scroll type or centrifugal type, or any combination thereof. Furthermore, there is no particular limitation on a type of refrigerant used.

The method for predicting and calculating energy consumption of a chiller unit of this application is illustrated below by way of example based on the chiller unit described in FIG. 1.

FIG. 2 is a schematic diagram showing steps of a method for predicting and calculating energy consumption of a chiller unit of this application. First, in a chiller unit load prediction step, a total load Q of the chiller unit, i.e., a total load that needs to be provided to a user terminal 16, is predicted and generated based on a preset data-driven model (i.e., a cooling load prediction model). Then, in a chiller load distribution step, the total load Q of the chiller unit output in the chiller unit load prediction step is distributed to generate a first chiller load Q1 corresponding to the first chiller 1, a second chiller load Q2 corresponding to the second chiller 2, and a third chiller load Q3 corresponding to the third chiller 3, according to a preset chiller load distribution logic.

Subsequently, in a chiller energy efficiency value acquisition step, a first chiller energy efficiency value COP1, a second chiller energy efficiency value COP2 and a third chiller energy efficiency value COP3 are correspondingly acquired according to a preset chiller load-energy efficiency relationship data, based on the first chiller load Q1, the second chiller load Q2 and the third chiller load Q3 generated by being distributed in the chiller load distribution step.

In a subsequent chiller power calculation step, a first chiller input power P1, a second chiller input power P2 and a third chiller input power P3 are calculated according to the first chiller energy efficiency value COP1, the second chiller energy efficiency value COP2 and the third chiller energy efficiency value COP3 acquired in the chiller energy efficiency value acquisition step.

FIG. 3 is a schematic diagram of a chiller load-energy efficiency curve under specific working conditions, taking the first chiller 1 as an example. As shown in FIG. 3, after the first chiller load Q1 is generated by distributing in the chiller load distribution step, the first chiller energy efficiency value COP1 corresponding to the first chiller load Q1 can be acquired by referring to the corresponding working conditions (for example, including an evaporator entering water temperature, a condenser entering water temperature, an outside air temperature, etc.), and the first chiller input power P1 can be calculated accordingly. The working conditions are acquired in real-time via first sensor(s) 116-1 operatively connected with a first chiller 1, second sensor(s) 116-2 operatively connected with a second chiller 2, third sensor(s) 116-3 operatively connected with a third chiller 3 or are alternatively based on predetermined data.

Because the chiller load-energy efficiency relationship, i.e., the equipment characteristic curve, is preset with corresponding data when a chiller leaves the factory, the above calculation method can be used to accurately obtain the first chiller input power P1 with the simplest calculated amount.

Similarly, according to the above steps, the second chiller energy efficiency value COP2 corresponding to the second chiller load Q2 can be calculated, and the second chiller input power P2 can be calculated accordingly. The third chiller energy efficiency value COP3 corresponding to the third chiller load Q3 can be calculated, and the third chiller input power P3 can be calculated accordingly.

The preset chiller load distribution logic may be an optimal chiller load (OCL) distribution logic, that is, the overall efficiency of the entire chiller unit is maximized and the energy consumption is minimized, by reasonably distributing load to each chiller. For example, a multi-phase genetic algorithm (MPGA), a Lagrangian Algorithm, etc. may be used, and there is no particular limitation. It is sufficient as long as the total load Q of the chiller unit can be distributed into the first chiller load Q1, the second chiller load Q2, and the third chiller load Q3, according to the preset chiller load distribution logic.

Table 1 shows a specific example of the energy efficiency value and input power of each chiller obtained by calculation according to the method for predicting and calculating energy consumption of a chiller unit of this application, taking the total load Q of the chiller unit of 1500 kW as an example.

	TABLE 1
		first chiller	second chiller	third chiller
		1	2	3

load

800

kW

700

kW

0 kW

COP value

4.8

4.5

0

chiller

166.67

kW

155.56

kW

0 kw

input power

Further, in a chiller input power summarizing step, the first chiller input power P1, the second chiller input power P2 and the third chiller input power P3 may be summarized to acquire a total power consumption value P of the chiller unit. For example, as shown in Table 1, 322.23 kW is the total power consumption value P of the chiller unit.

In addition, in some embodiments of this application, FIG. 2 is used as an example to illustrate the chiller load-energy efficiency relationship data, and it is not limited to the COP characteristic curve, the energy efficiency ratio EER characteristic curve and the like can also be used as the chiller load-energy efficiency relationship data.

Meanwhile, no matter whether the preset chiller load-energy efficiency relationship data is COP or EER, the COP value and EER value can be calculated using the input power of the entire machine including the compressor of the chiller, pipe valve controller, fan, etc., or using only the power of the compressor alone as the input power, and there is no particular limitation.

Therefore, according to the method for predicting and calculating energy consumption of a chiller unit of this application, by utilizing characteristic curve of each chiller, the accuracy of chiller power prediction can be greatly improved compared to a pure data-driven model.

Because a cooling load of a building as the demand side is only related to the weather and the state of the building itself, and is not related to the specific operating variables (such as chilled water temperature, chiller load rate, etc.) of the chiller as the supply side, predicting the cooling load of the building by using the data-driven model requires fewer variables than predicting chiller energy consumption, and the prediction results are more reliable. Meanwhile, the method for predicting and calculating energy consumption of a chiller unit of this application combines the building cooling load prediction value acquired by using the data-driven model and the accurate chiller characteristic curve data, thereby making prediction of the energy consumption of a chiller more accurate.

FIG. 4 is another schematic diagram showing steps of a method for predicting and calculating energy consumption of a chiller unit of this application.

The chiller unit according to some embodiments is the same as that in the other one or more embodiments. The same parts as those in the one or more embodiments are described using the same reference numerals and will not be repeated here.

First, in a water pump load prediction step, a total load q of water pumps is predicted and output based on a preset water pump load prediction model. The total load q of water pumps is related to the total load Q of the chiller unit (i.e., the cooling load of the building) and control variables (such as a setting value of the chilled water temperature and a setting value of supply and return water pressure difference) of the chiller unit that needs to be optimized. Therefore, the water pump load prediction model needs to take the cooling load Q and the control variables of the relevant chiller unit as input to obtain the total load q of the water pumps.

Then, a water pump load distribution step is executed, that is, the total load q of the water pumps is distributed to the first water pump 15 corresponding to the first chiller 1, the second water pump 25 corresponding to the second chiller 2 and the third water pump 35 corresponding to the third chiller 3, according to the preset chiller load distribution logic. Further, in a water pump efficiency acquisition step, a first water pump efficiency value η1, a second water pump efficiency value η2 and a third water pump efficiency value η3 are correspondingly acquired according to a preset water pump load-efficiency curve, based on the first water pump load q1, the second water pump load q2 and the third water pump load q3 distributed in the water pump load distribution step.

In a water pump power calculation step, the first water pump input power p1, the second water pump input power p2 and the third water pump input power p3 are calculated according to output results in the water pump load distribution step and the water pump efficiency acquisition step.

FIG. 5 is a schematic diagram of a water pump load-efficiency curve, taking the first water pump 15 as an example. As shown in FIG. 5, after the total water pump load is distributed into the first water pump load q1, the second water pump load q2 and the third water pump load q3 in the water pump load distribution step, the first water pump efficiency value η1 corresponding to the first water pump load q1 can be acquired by referring to the water pump load-efficiency curve corresponding to the first water pump 15, and the first water pump input power p1 can be calculated accordingly.

Because the water pump load-efficiency relationship, as the equipment characteristic curve of the water pump, is preset with corresponding data when a water pump leaves the factory, the above calculation method can be used to accurately obtain the first water pump input power p1 by a calculated amount.

Similarly, according to the above steps, the second water pump efficiency value η2 corresponding to the second water pump load q2 can be easily acquired, and the second water pump input power p2 can be calculated accordingly. In addition, the third water pump efficiency value η3 corresponding to the third water pump load q3 can be easily acquired, and the third water pump input power p3 can be calculated accordingly.

Table 2 shows the flow load distribution and water pump efficiency value of each pump, taking the total load q of the water pumps of 300 kg/s corresponding to the total load Q of the chiller unit as an example. According to the following formula, the corresponding input power of each water pump can be calculated.

water pump input power=flow load×lift×medium density/3600/water pump efficiency

	TABLE 2
	first water pump	second water pump	third water pump
	15	25	35

flow load	180 kg/s	120 kg/s	0 kg/s
water pump	0.8	0.7	0
efficiency

Further, as shown in FIG. 3, after obtaining the input power value of each water pump, the first water pump input power p1, the second water pump input power p2 and the third water pump input power p3 may be summarized to acquire a total power p of water pumps in a water pump power summarizing step.

The calculation of the water pump input power is explained above using the water pump flow-efficiency curve as an example. However, this application is not limited thereto. A water pump flow-power curve can also be used to calculate the input power of the water pump, as long as the water pump flow-power curve data is available when the water pump leaves the factory. At this time, the water pump efficiency acquisition step in some embodiments can be omitted, and in the water pump power calculation step, corresponding data can be directly captured according to the preset water pump flow-power curve.

In addition, the characteristic curve of the water pump may vary greatly depending on the type of water pump. This illustration is merely an example and does not constitute any limitation to this application.

Therefore, according to the method for predicting and calculating energy consumption of a chiller unit of this application, by utilizing the preset characteristic curve of the water pump, input power of each water pump is accurately calculated, which can help improve the accuracy of water pump power prediction compared to a pure data-driven model.

Some embodiments of this application provides a system for calculating energy consumption of a chiller unit, which is used for calculating energy consumption of a chiller unit including a first chiller 1, a second chiller 2 and a third chiller 3.

The chiller unit according to some embodiments is the same as that in the other one or more embodiments. The same parts as those in the one or more embodiments are described using the same reference numerals and will not be repeated here.

FIG. 6 is a block schematic diagram of a system for calculating energy consumption of a chiller unit.

As shown in FIG. 6, a chiller unit load prediction module (also referred to as “a chiller load prediction unit”) predicts and generates a total load Q of the chiller unit, i.e., a total load that needs to be provided to the user terminal 16, based on a preset data-driven model (i.e., a cooling load prediction model). Then, the total load Q of the chiller unit is output to a chiller load distribution module (also referred to as “a chiller load distribution unit”), the total load Q of the chiller unit output by the chiller unit load prediction module is distributed to generate a first chiller load Q1 corresponding to the first chiller 1, a second chiller load Q2 corresponding to the second chiller 2, and a third chiller load Q3 corresponding to the third chiller 3 according to the preset chiller load distribution logic (stored in a chiller load distribution logic module (not shown)).

Subsequently, a chiller energy efficiency value acquisition module (also referred to as “a chiller energy efficiency value acquisition unit”) correspondingly acquires a first chiller energy efficiency value COP1, a second chiller energy efficiency value COP2 and a third chiller energy efficiency value COP3 according to a preset chiller load-energy efficiency relationship data, based on the first chiller load Q1, the second chiller load Q2 and the third chiller load Q3 generated by being distributed by the chiller load distribution module.

Then, a chiller power calculation module (also referred to as a “chiller power calculation unit”) calculates a first chiller input power P1, a second chiller input power P2 and a third chiller input power P3 according to the first chiller energy efficiency value COP1, the second chiller energy efficiency value COP2 and the third chiller energy efficiency value COP3 acquired from the chiller energy efficiency value acquisition module.

By utilizing a characteristic curve of each chiller, the accuracy of chiller power prediction can be greatly improved compared to a pure data-driven model. Meanwhile, the method for predicting and calculating energy consumption of a chiller unit of this application is more robust than a purely data-driven method.

Some embodiments of this application provide a system for calculating energy consumption of a chiller unit, which is used for calculating energy consumption of a chiller unit including a first chiller 1, a second chiller 2 and a third chiller 3.

The chiller unit according to some embodiments is the same as that in the other one or more embodiments. The same parts as those in the one or more embodiments are described using the same reference numerals and will not be repeated here.

FIG. 7 is a block schematic diagram of a system for calculating energy consumption of a chiller unit.

As shown in FIG. 7, a water pump load prediction module predicts and outputs a total load q of water pumps based on a preset cooling load prediction model. A water pump load distribution module distributes the total load q of the water pumps to the first water pump 15 corresponding to the first chiller 1, the second water pump 25 corresponding to the second chiller 2 and the third water pump 35 corresponding to the third chiller 3 according to the preset chiller load distribution logic. A water pump efficiency acquisition module correspondingly acquires a first water pump efficiency value η1, a second water pump efficiency value η2 and a third water pump efficiency value η3 according to a preset water pump load-efficiency curve, based on the first water pump load q1, the second water pump load q2 and the third water pump load q3 distributed by the water pump load distribution module. A water pump power calculation module calculates a first water pump input power p1, a second water pump input power p2 and a third water pump input power p3 according to output results of the water pump load distribution unit and the water pump efficiency acquisition module.

As shown in FIG. 8, one or more processor(s) 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, graphical processing units, logic circuitries, and/or any devices that manipulate data based on operational instructions. Among other capabilities, the one or more processor(s) 202 may be configured to fetch and execute computer-readable instructions stored in a memory 204. The memory 204 may store the computer-readable instructions or routines, which may be fetched and executed to create or share the data units to other elements of the controller 114. The memory 204 may include any non-transitory storage device including, for example, volatile memory such as Random Access Memory (RAM), or non-volatile memory such as an Erasable Programmable Read-Only Memory (EPROM), flash memory, and the like.

In one or more embodiments, the chiller unit system may include a communication module 206 operatively coupled to the controller 114, which may enable the chiller unit system to establish secured communication with the sensors 116-1, 116-2, 116-3, the first chiller 1, the second chiller 2, the third chiller 3, the first water pump 15, the second water pump 25, the third water pump 35, and various other components associated with the chiller unit system. The communication module 206 may be wired media and/or wireless media. For instance, the communication module may include, but is not limited to, an antenna, an Ethernet port, a USB port, or any other port that may be configured to receive and transmit location and attributes data. Further, in one or more embodiments, the communication module 206 may include ethernet modules, wireless-fidelity (Wi-Fi) modules, Bluetooth modules, Zigbee modules, GSM/GPRS modules, LoRa modules, 5G modules, Recommended Standard (RS)-232/RS-485 serial communication modules, Controller Area Network (CAN) modules, but not limited to the like.

Therefore, according to the system for predicting and calculating energy consumption of a chiller unit of this application, by utilizing the preset characteristic curve of the water pump, input power of each water pump is accurately calculated, which can help improve the accuracy of water pump power prediction compared to a pure data-driven model.

Because a cooling load of a building as the demand side is only related to the weather and the state of the building itself, and is not related to the specific operating variables (such as chilled water temperature, chiller load rate, etc.) of the chiller as the supply side, predicting the cooling load of the building by using the data-driven model requires fewer variables than predicting chiller energy consumption, and the prediction results are more reliable. Meanwhile, the prediction of energy consumption of a chiller unit of this application combines the building cooling load prediction and the accurate chiller characteristic curve data, thereby making prediction of the energy consumption of a chiller more accurate.

The above embodiments are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included in the protection scope of this application.