Electric equipment setting method and electronic device
By establishing an electricity usage prediction model to determine the setting parameters of the electricity usage equipment, the problem of difficulty in setting the electricity usage equipment parameter is solved, and efficient management of electricity usage equipment and improvement of energy usage efficiency is achieved.
Patent Information
- Application Number
- CN202310622471.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-05-05
- Filing Date
- 2023-05-30
- Publication Date
- 2024-11-05
AI Technical Summary
The prior art is difficult to effectively manage and set parameters of electricity use equipment to achieve energy saving purposes, resulting in waste of electricity and inefficient energy use.
By obtaining the operation information of the electricity consumption equipment, establishing an electricity consumption prediction model, using the model to predict the energy efficiency under different set parameters, and controlling the electricity consumption equipment based on the comparison and decision-making parameter values to achieve energy saving and improve energy use efficiency.
Effectively save electricity, improve energy use efficiency, reduce power waste, and reduce production costs.
Smart Images

Figure CN118896366A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to an energy-saving method, and in particular to an electric equipment setting method and an electronic device. Background Art
[0002] As the environmental issues of greenhouse gas reduction and energy conservation and carbon reduction become increasingly important, energy conservation has become one of the key development projects today. If we can effectively find the cause of electricity waste and provide appropriate energy-saving methods, it will not only contribute to environmental protection, but also greatly help factory costs and profits.
[0003] Electrical equipment requires electricity to maintain operation. Electrical equipment with low energy efficiency needs to consume more electricity to achieve operational goals, or even cannot operate normally, resulting in a waste of electricity. Generally speaking, there are multiple electrical equipment in a factory, but not all electrical equipment needs to be turned on during the production process. Since the energy efficiency and equipment status of each electrical equipment are different, the choice of which electrical equipment to use by the equipment manager will directly affect the electricity cost and production efficiency. It is known that the setting of equipment parameters of electrical equipment will also directly affect the electricity cost and production efficiency. At present, professional equipment personnel are required to rely on their long-term accumulated personal subjective experience to try to achieve energy saving by adjusting the equipment parameters of electrical equipment. However, it is often not easy for equipment personnel to know how to set the equipment parameters of multiple electrical equipment in the workplace to meet manufacturing needs and save electricity as much as possible. Summary of the invention
[0004] In view of this, the present invention provides an electric equipment setting method and an electronic device, which can solve the above technical problems.
[0005] An embodiment of the present invention provides a method for setting an electric device, which includes the following steps. Obtain equipment operation information of multiple electric devices. Establish an equipment power consumption prediction model for each electric device based on the equipment operation information of the multiple electric devices. The multiple input characteristic variables of the equipment power consumption prediction model for each electric device include adjustable setting parameters for each electric device. The adjustable setting parameters are set to multiple setting values, and the equipment power consumption prediction model for each electric device is used to obtain multiple equipment energy efficiencies corresponding to the multiple setting values. By comparing the multiple equipment energy efficiencies of each electric device, a decision parameter value of the adjustable setting parameter is determined. Control multiple electric devices according to the decision parameter value.
[0006] An embodiment of the present invention provides an electronic device, which includes a storage device and a processor. The storage device stores multiple instructions. The processor is coupled to the storage device, accesses the instructions and is configured to perform the following operations. Obtain equipment operation information of multiple electrical devices. According to the equipment operation information of the multiple electrical devices, establish an equipment power consumption prediction model for each electrical device. The multiple input characteristic variables of the equipment power consumption prediction model of each electrical device include adjustable setting parameters of each electrical device. The adjustable setting parameters are set to multiple setting values, and the equipment power consumption prediction model of each electrical device is used to obtain multiple equipment energy efficiencies corresponding to the multiple setting values. By comparing the multiple equipment energy efficiencies of each electrical device, the decision parameter value of the adjustable setting parameter is determined. Control multiple electrical devices according to the decision parameter value.
[0007] Based on the above, in an embodiment of the present invention, an equipment power consumption prediction model of each power-consuming device can be established based on the equipment operation information of each power-consuming device, and can be used to predict the predicted power consumption of each power-consuming device. By inputting the adjustable setting parameter set to multiple setting values into the power consumption prediction model, multiple equipment energy efficiencies corresponding to the multiple setting values can be obtained. The decision parameter value of the adjustable setting parameter can be determined by comparing the multiple equipment energy efficiencies of each power-consuming device. Therefore, by controlling these power-consuming devices according to the decision parameter value of the adjustable setting parameter, the goal of effectively saving electricity and improving energy efficiency can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0008] Figure 1 is a schematic diagram of an electronic device according to an embodiment of the present invention;
[0009] Figure 2 is a flow chart of a method for setting an electrical device according to an embodiment of the present invention;
[0010] Figure 3 is a flow chart of establishing a device power consumption prediction model according to an embodiment of the present invention;
[0011] Figure 4 is a flow chart of obtaining device energy efficiency according to an embodiment of the present invention;
[0012] Figure 5 is a flow chart of determining a decision parameter value according to an embodiment of the present invention;
[0013] Figure 6 is a schematic diagram of determining a decision parameter value according to an embodiment of the present invention;
[0014] Figure 7 is a flow chart of controlling multiple electrical devices according to an embodiment of the present invention;
[0015] Figure 8is a flow chart of generating electricity efficiency evaluation information according to an embodiment of the present invention;
[0016] Fig. 9 is a schematic diagram of an air conditioning device according to an embodiment of the present invention;
[0017] Fig.10 FIG. 4 is a schematic diagram of determining a decision parameter value according to an embodiment of the present invention.
[0018] Explanation of symbols
[0019] 100: Electronic devices
[0020] 110: Display
[0021] 120: Storage device
[0022] 130: Processor
[0023] L1: The first function segment
[0024] L2: Second function segment
[0025] P1: Intersection point
[0026] 91: Ice water host
[0027] 92: Cooling tower
[0028] 93: Blower
[0029] 911: Evaporator
[0030] 912: Condenser
[0031] 913: Refrigerant pipeline
[0032] S210~S250,S221~S222,S231~S233,S241~S243,S251~S256: Steps DETAILED DESCRIPTION
[0033] Some embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The referenced element symbols in the following description will be regarded as the same or similar elements when the same element symbols appear in different drawings. These embodiments are only part of the present invention and do not disclose all possible implementation methods of the present invention. More specifically, these embodiments are only examples of the devices and methods within the scope of the present invention.
[0034] Please refer to Figure 1, which is a schematic diagram of an electronic device according to an embodiment of the present invention. In different embodiments, the electronic device 100 is a computer device such as a notebook computer, a desktop computer, a server, a workstation, etc. with computing capabilities, but is not limited thereto. The electronic device 100 may include a display 110, a storage device 120, and a processor 130.
[0035] The display 110 is, for example, a liquid crystal display (LCD), a light emitting diode (LED), an organic light emitting diode (OLED) or any other type of display built into the electronic device 100, but is not limited thereto. In other embodiments, the display 110 may also be any display device external to the electronic device 100.
[0036] The storage device 120 is, for example, any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk or other similar device or a combination of these devices, and can be used to record multiple instructions, program codes or software modules.
[0037] The processor 130 is, for example, a central processing unit (CPU), an application processor (AP), or other programmable general-purpose or special-purpose microprocessor, a digital signal processor (DSP), a graphics processing unit (GPU), or other similar devices, integrated circuits, and combinations thereof. The processor 130 can access and execute software modules recorded in the storage device 120 to implement the power device setting method in the embodiment of the present invention. The above-mentioned software module can be broadly interpreted as meaning instructions, instruction sets, codes, program codes, programs, applications, software suites, threads, functions, etc., regardless of whether it is called software, firmware, middleware, microcode, hardware description language, or others.
[0038] Figure 2 FIG. 1 is a flow chart of a method for setting an electrical device according to an embodiment of the present invention. Figure 1 and Figure 2The method of this embodiment is applicable to the electronic device 100 in the above embodiment. The following describes the detailed steps of the method for setting the electrical equipment of this embodiment in conjunction with the various components in the electronic device 100.
[0039] In step S210, the processor 130 obtains equipment operation information of multiple electrical devices. Here, multiple electrical devices are devices with the same function set in a certain field, but the specifications and models of these electrical devices may be the same or different. The above-mentioned field is, for example, a factory, a store, a department store, or an indoor gym, etc. These electrical devices may be multiple air-conditioning devices. Alternatively, these electrical devices may be multiple air compressors. The equipment operation information of the electrical equipment may include power consumption data, equipment status data, or equipment output data, etc. The equipment operation information of the electrical equipment may be obtained by sensing by a sensor or measuring instrument of the electrical equipment. The above-mentioned sensor or measuring instrument may include an electric meter, a thermometer, a pressure gauge, etc., and the present invention is not limited to this.
[0040] From another point of view, the electronic device 100 can be directly or indirectly connected to these electrical devices or measuring instruments to receive the equipment operation information provided by these electrical devices. Alternatively, the electronic device 100 can receive the equipment operation information input by the operator through an input device (such as a keyboard or a mouse, etc.). Alternatively, the electronic device 100 can receive the equipment operation information of these electrical devices from other control devices or data servers.
[0041] In some embodiments, these electrical equipment include multiple air-conditioning equipment, and the equipment operation information of these air-conditioning equipment may include power consumption per unit time period, cooling capacity per unit time, condenser pressure per unit time, cooling water return temperature per unit time, and cooling water supply temperature per unit time, etc.
[0042] In some embodiments, these electrical equipment include multiple air compressors, and the equipment operation information of these air conditioning equipment may include power consumption per unit time period, exhaust pressure per unit time period, exhaust volume per unit time, and exhaust pressure temperature per unit time, etc.
[0043] In step S220, the processor 130 establishes a device power consumption prediction model for each power-consuming device based on the device operation information of the plurality of power-consuming devices. Specifically, the processor 130 may establish a device power consumption prediction model for each power-consuming device based on the device operation information of each power-consuming device, and the model parameters of the device power consumption prediction model trained based on the machine learning algorithm may be recorded in the storage device 120. In other words, the processor 130 may perform machine learning based on the device operation information of the past period of time (also referred to as historical device operation information) as a training data set to create a prediction model for predicting the predicted power consumption of each power-consuming device in a unit time period based on the input feature variables.
[0044] In some embodiments, the equipment power consumption prediction model of each power-consuming device may be a linear regression model. The processor 130 may use the training data set to estimate the weight of each characteristic variable in the linear regression model by the least square method as the training product of the training power consumption prediction model. In this way, the processor 130 may use multiple weights and input characteristic variables of the linear regression model to estimate the power consumption per unit time. It should be particularly noted that the multiple input characteristic variables of the equipment power consumption prediction model of each power-consuming device include adjustable setting parameters of each power-consuming device. For example, the adjustable setting parameters of each air-conditioning device may be the return water temperature of cooling water or the supply water temperature of chilled water. Alternatively, the adjustable setting parameters of each air compressor device may be the exhaust pressure. In other words, the adjustable setting parameters of each power-consuming device and other input characteristic variables will be input into the corresponding equipment power consumption prediction model, so that the equipment power consumption prediction model can output the predicted power consumption of each power-consuming device accordingly. Here, the adjustable setting parameter of each power-consuming device is a device parameter that can be automatically adjusted by the equipment personnel or the electronic device 100.
[0045] In some embodiments, the processor 130 may adjust the adjustable setting parameters of each electrical device according to the environmental parameters. For example, the environmental parameter may be the ambient temperature, and the adjustable setting parameter may be the cooling water return temperature. The processor 130 may adjust the corresponding cooling water return temperature by looking up a table according to the ambient temperature. Alternatively, the processor 130 may input the ambient temperature into a preset function to adjust the corresponding cooling water return temperature. Alternatively, the processor 130 may adjust the cooling water return temperature according to the temperature difference between the ambient temperature and the preset reference temperature.
[0046] Please refer to Figure 3 , which is a flow chart of establishing a device power consumption prediction model according to an embodiment of the present invention. In some embodiments, step S220 can be implemented as steps S221 to S222. It should be noted that the establishment method of the device power consumption prediction model of each power-consuming device is similar, and the following will be described with the first power-consuming device among the power-consuming devices.
[0047] In step S221, the processor 130 may generate a plurality of input characteristic variables of a plurality of previous unit time periods according to the equipment operation information of the first electrical equipment. Specifically, according to the equipment operation information of the first electrical equipment in a plurality of previous unit time periods, the processor 130 may obtain a plurality of input characteristic variables corresponding to a plurality of previous unit time periods and associated with the first electrical equipment. The time length of the previous unit time period may be a week, a day, a half day, an hour, etc., and the present invention is not limited thereto. In other words, the plurality of input characteristic variables of a plurality of previous unit time periods are model training data generated according to the actual operation of the electrical equipment. For example, according to the temperature difference between the chilled water supply temperature and the chilled water return temperature in a certain previous unit time period (e.g., the previous hour), the processor 130 may generate the unit time cooling capacity of the first electrical equipment in the previous unit time period. According to the same operation mode, the processor 130 may generate the unit time cooling capacity of the first electrical equipment in a plurality of previous unit time periods (e.g., the previous three hours, the previous two hours, the previous hour). In this example, the plurality of input characteristic variables include the cooling capacity of the first electrical equipment in a plurality of previous unit time periods.
[0048] In some embodiments, the first electrical equipment is an air-conditioning equipment, and the multiple input characteristic variables of the first electrical equipment in multiple previous unit time periods may include cooling capacity per unit time, condenser pressure per unit time, cooling water return temperature per unit time, and cooling water supply temperature per unit time, etc.
[0049] In some embodiments, the first electrical equipment is an air compressor, and the multiple input characteristic variables of the first electrical equipment in multiple previous unit time periods may include exhaust volume per unit time, exhaust pressure per unit time, and exhaust temperature per unit time, etc.
[0050] In step S222, the processor 130 uses multiple input feature variables and multiple actual power consumptions of the first power-consuming device in multiple previous unit time periods to train an equipment power consumption prediction model of the first power-consuming device based on a machine learning algorithm. In detail, during the model training process, the actual value (ground truth) used to train the equipment power consumption prediction model is the actual power consumption in the previous unit time period. For example, the processor 130 inputs the input feature variables of a previous unit time period (e.g., 17:00-18:00 on April 25) into the model being trained, and uses the actual power consumption of the first power-consuming device in the same previous unit time period (i.e., 17:00-18:00 on April 25) as the actual value (ground truth) required for model training.
[0051] The machine learning algorithm used to train the equipment power consumption prediction model may include but is not limited to a random forest algorithm, a linear regression algorithm, or a support vector machine (SVM) algorithm. However, the present invention does not limit the machine learning algorithm used to train the equipment power consumption prediction model, and it can be set according to the actual application.
[0052] For example, assuming that the machine learning algorithm used to train the device power consumption prediction model is a linear regression algorithm, the processor 130 can obtain multiple coefficients and constant terms of the linear regression model to establish the device power consumption prediction model. In other words, the processor 130 can obtain the degree of influence of each input feature variable on the power consumption of the first power-consuming device. For example, the processor 130 can obtain the model parameters (i.e., the coefficients corresponding to each input feature variable in the linear regression model) and the constant term "295" of the linear regression model as shown in Table 1.
[0053]
[0054] Table 1
[0055] Then, in step S230, the processor 130 sets the adjustable setting parameter to a plurality of setting values, and uses the device power consumption prediction model of each power-consuming device to obtain a plurality of device energy efficiencies corresponding to each setting value. These device energy efficiencies of each power-consuming device may represent the device operation efficiency that can be achieved per unit power consumption under the condition that the adjustable setting parameter is set to these setting values respectively.
[0056] In detail, after establishing the equipment power consumption prediction model of each power-consuming device, the processor 130 can input the adjustable setting parameters set to multiple setting values into the equipment power consumption prediction model to perform multiple power consumption predictions to obtain the predicted power consumption corresponding to the multiple setting values. Afterwards, the processor 130 can calculate multiple equipment energy efficiencies corresponding to each setting value based on the multiple predicted power consumption corresponding to the multiple setting values and the output statistics corresponding to the multiple setting values. Specifically, the processor 130 can obtain the equipment energy efficiency corresponding to a certain setting value based on the ratio of an output statistic corresponding to a certain setting value to a predicted power consumption corresponding to the setting value.
[0057] Please refer to Figure 4 , which is a flow chart of obtaining device energy efficiency according to an embodiment of the present invention. In some embodiments, step S230 can be implemented as steps S231 to S233. It should be noted that the method of generating multiple device energy efficiencies of each electrical device is similar, and the following will be described with the first electrical device among the electrical devices.
[0058] In step S231, the processor 130 performs statistical operations on multiple outputs of the first electrical equipment in multiple previous unit time periods to obtain multiple output statistics of the first electrical equipment. Here, the multiple output statistics correspond to multiple set values and include the first output statistic. The first output statistic corresponds to the first set value among these set values.
[0059] In some embodiments, if the plurality of electrical devices are a plurality of air conditioning devices, the plurality of outputs include a plurality of cooling capacities (i.e., cooling capacities per unit period). Alternatively, in some embodiments, if the plurality of electrical devices are a plurality of air compressor devices, the plurality of outputs include a plurality of exhaust capacities (i.e., exhaust capacities per unit period).
[0060] In some embodiments, the processor 130 may obtain a plurality of first output quantities corresponding to the first setting value according to the first setting value. Under the condition that the adjustable setting parameter is set to the first setting value, the processor 130 may obtain a plurality of first output quantities corresponding to the first setting value from the historical equipment operation information of the first electrical equipment. For example, the processor 130 may extract a plurality of first output quantities corresponding to the first setting value according to the historical equipment operation information of the first electrical equipment in recent months, wherein these first output quantities are output quantities per unit time. Then, the processor 130 may perform statistical operations on the plurality of first output quantities to obtain the first output statistics of the first electrical equipment. The above statistical operations are, for example, average operations or mode operations. That is, the processor 130 may calculate the average value or mode of a plurality of first output quantities to obtain the first output statistics corresponding to the first setting value.
[0061] In some embodiments, taking the cooling water return temperature as an example, the cooling water return temperature can be set to multiple temperature setting values, such as 20 degrees, 22 degrees, 25 degrees, etc. When the cooling water return temperature is set to 25 degrees, the processor 130 can retrieve multiple unit time cooling capacities corresponding to 25 degrees from the historical equipment operation information, which are the cooling capacities when the cooling water return temperature is set to 25 degrees in the previous unit time period.
[0062] For example, when the cooling water return temperature is set to 25 degrees, the processor 130 can obtain multiple cooling capacities and multiple condenser pressures as shown in Table 2 from the historical equipment operation information of the first electrical equipment. In the example of Table 2, the processor 130 can obtain 100 cooling capacities and 100 condenser pressures that meet the cooling water return temperature setting of 25 degrees. According to Table 2, the cooling water return temperature of the air-conditioning equipment (i.e., the first electrical equipment) from 9:00 to 10:00 on the past A month B day (i.e., a certain unit time period) is set to 25 degrees, and the cooling capacity and condenser pressure of this air-conditioning equipment from 9:00 to 10:00 on the A month B day are "3600" and "5" respectively.
[0063] serial number Cooling capacity per unit time period Condenser pressure 1 3600 5 2 3540 6 … … … 100 3550 4
[0064] Table 2
[0065] Next, the processor 130 may average the 100 records of cooling capacities per unit time period to obtain a first average value (ie, a first output statistic) such as "2106", and average the 100 records of condenser pressures to obtain a second average value such as "5".
[0066] In some embodiments, taking the exhaust pressure as an example, the exhaust pressure can be set to multiple pressure setting values, such as 6 bar, 7 bar, 8 bar, etc. When the exhaust pressure is set to 6 bar, the processor 130 can retrieve multiple unit time exhaust volumes corresponding to 6 bar from the historical equipment operation information, which are the exhaust volumes when the exhaust pressure is set to 6 bar in the previous unit time period.
[0067] In step S232, the processor 130 uses the device power consumption prediction model of the first power-consuming device to estimate multiple predicted power consumptions of the first power-consuming device. Here, the multiple predicted power consumptions correspond to multiple set values and include the first predicted power consumption. The first predicted power consumption corresponds to the first set value among these set values. In some embodiments, the processor 130 inputs the first output statistic and the adjustable setting parameter set to the first set value into the device power consumption prediction model to obtain the first predicted power consumption corresponding to the first set value.
[0068] Continuing with the examples of Tables 1 and 2, when the cooling water return temperature is set to 25 degrees (i.e., the first set value), the processor 130 can input the first average value "2106" of the cooling capacity of 100 units of time periods, the second average value "5" of the condenser pressure of 100 units, and the cooling water return temperature set to 25 degrees into the linear regression model shown in Table 1, thereby obtaining the first predicted power consumption corresponding to 25 degrees. More specifically, based on the examples of Tables 1 and 2, the processor 130 can, for example, estimate the first predicted power consumption of the first electrical equipment to be 295+0.015×2106+0.15×5-0.27×25-0.02×30=320 degrees. Among them, the cooling water supply temperature "30 degrees" is determined according to the cooling water return temperature.
[0069] Similarly, the processor 130 can obtain the predicted power usage and output statistics corresponding to other temperature settings (e.g., 20 degrees, 22 degrees, and 27 degrees, etc.) in the same manner. For example, for the first power-consuming device, the processor 130 can generate multiple output statistics and predicted power usage corresponding to multiple temperature settings as shown in Table 3 below.
[0070] Cooling water return temperature Cooling capacity Forecast electricity consumption 20 2107 312 22 2107 327 25 2106 320 27 2108 324 28 2108 330 30 2109 350 32 2108 374
[0071] Table 3
[0072] According to the example in Table 3, as the return water temperature of the cooling water increases, the predicted power consumption of the air conditioning equipment will also increase. In addition, in some embodiments, when the power-consuming equipment is an air compressor and the adjustable setting parameter is the exhaust pressure, the processor 130 can generate multiple exhaust volumes and predicted power consumption corresponding to multiple pressure setting values.
[0073] Afterwards, in step S233, the processor 130 determines one of the multiple equipment energy efficiencies of the first electrical equipment based on the ratio between the first output statistic and the first predicted power consumption. By dividing the first output statistic by the first predicted power consumption, the processor 130 can obtain one of the multiple equipment energy efficiencies of the first electrical equipment. For example, the processor 130 can divide the first output statistic "2106" by the first predicted power consumption "320" to calculate the equipment efficiency corresponding to 25 degrees as "6.58". In addition, in some embodiments, when the electrical equipment is an air compressor and the adjustable setting parameter is the exhaust pressure, the processor 130 can obtain the multiple equipment efficiencies by dividing the average values of the multiple exhaust volumes by the corresponding predicted power consumption.
[0074] Please come back again Figure 2 Based on the execution of step S230, the processor 130 may generate a plurality of equipment energy efficiencies corresponding to different set values for each electrical device. For example, when the cooling water return temperature is set to a plurality of set values, the processor 130 may obtain the estimated power consumption and equipment energy efficiency corresponding to the different set values for the first electrical device and the second electrical device, as shown in Table 4 below. The first electrical device is, for example, an air conditioner including a fixed-frequency chiller main unit, and the second electrical device is, for example, an air conditioner including a variable-frequency chiller main unit.
[0075]
[0076] Table 4
[0077] Afterwards, in step S240, the processor 130 determines the decision parameter value of the adjustable setting parameter by comparing the multiple device energy efficiencies of each electrical device. In detail, the processor 130 can generate multiple function segments for multiple electrical devices based on the multiple device energy efficiencies of each electrical device. Based on the intersection of these function segments, the processor 130 can obtain one or more decision parameter values of the adjustable setting parameter. The unit of this decision parameter value is the same as the unit of the adjustable setting parameter. For example, assuming that the adjustable setting parameter is the cooling water return temperature, the decision parameter value is also a temperature value. Assuming that the adjustable setting parameter is the exhaust pressure, the decision parameter value is also a pressure value.
[0078] Please refer to Figure 5, which is a flow chart of determining the decision parameter value according to an embodiment of the present invention. In some embodiments, step S240 can be implemented as steps S241 to S243. It should be noted that the following description will be given by taking the first power-consuming device and the second power-consuming device as an example, but the present invention does not limit the number of power-consuming devices. For the convenience of description, please refer to Figure 5 and Figure 6 , which is a schematic diagram of determining a decision parameter value according to an embodiment of the present invention.
[0079] In step S241, the processor 130 may establish a first function line segment L1 according to multiple device energy efficiencies of the first power-consuming device and corresponding setting values. In step S242, the processor 130 may establish a second function line segment L2 according to multiple device energy efficiencies of the second power-consuming device and corresponding setting values. For example, Figure 6 The data in Table 4 is used as an example. When the cooling water return temperature is 27 to 32 degrees, the processor 130 can generate a first function line segment L1 according to multiple equipment energy efficiencies of the first electrical equipment, and generate a second function line segment L2 according to multiple equipment energy efficiencies of the second electrical equipment.
[0080] In step S243, the processor 130 may determine the decision parameter value of the adjustable setting parameter according to the intersection point P1 of the first function line segment L1 and the second function line segment L2. Figure 6 In the example of , the decision parameter value corresponding to the intersection point P1 of the first function line segment L1 and the second function line segment L2 may be, for example, 29.2 degrees. Figure 6 It can be seen that when the cooling water return temperature is less than the decision parameter value "29.2 degrees", it is better to turn on the second electrical equipment. On the contrary, when the cooling water return temperature is greater than the decision parameter value "29.2 degrees", it is better to turn on the first electrical equipment. It can be seen that the decision parameter value "29.2 degrees" corresponding to the cooling water return temperature can be used as a decision reference value for deciding whether to turn on the first electrical equipment or the second electrical equipment.
[0081] In step S250, the processor 130 controls multiple electrical devices according to the decision parameter value. Specifically, after the equipment personnel determine the target setting value of the adjustable setting parameter based on environmental factors or other factors, the processor 130 can compare the target setting value with the decision parameter value to decide to use a certain electrical device and disable other electrical devices. In other words, after determining the target setting value of the adjustable setting parameter, the processor 130 can know which electrical device can have higher equipment energy efficiency when the adjustable setting parameter is set to the target setting value. In addition, the processor 130 can also evaluate the benefits of the equipment setting method that has been implemented according to the decision parameter value.
[0082] Please refer to Figure 7, which is a flow chart of controlling multiple electrical devices according to an embodiment of the present invention. In some embodiments, step S250 can be implemented as steps S251 to S252. It should be noted that the following description will be made by taking the first electrical device and the second electrical device as an example, but the present invention does not limit the number of electrical devices.
[0083] In step S251, the processor 130 obtains the target setting value of the adjustable setting parameter. It should be noted that for each electrical device, the adjustable range of the adjustable setting parameter may be the same or different. Assuming that the adjustable setting parameter is the cooling water return temperature or the chilled water supply temperature of the air-conditioning equipment, the adjustable range of the adjustable setting parameter may also be affected by the ambient temperature. For example, within a single time, the cooling return water temperature shall not be lower than 20 degrees or higher than 32 degrees. Exceeding this adjustable range will have an adverse effect on the heat exchange efficiency of the water host. Therefore, 20 degrees and 32 degrees can be used as limit thresholds for setting the target setting value, that is, the equipment personnel can set the target setting value between 20 degrees and 32 degrees.
[0084] In step S252, the processor 130 activates the first electrical device and deactivates the second electrical device according to the decision parameter value and the target setting value. Specifically, after determining the target setting value, the processor 130 may determine whether the target setting value is greater than the decision parameter value. Figure 6 In the example shown, in response to the target setting value being greater than the decision parameter value "29.2 degrees", the processor 130 may start the first electrical device and shut down the second electrical device. Conversely, in response to the target setting value being less than the decision parameter value "29.2 degrees", the processor 130 may shut down the first electrical device and start the second electrical device. In other words, when the target setting value is greater than the decision parameter value, the first electrical device may be started and its adjustable setting parameter may be set to the target setting value, while at the same time, the second electrical device may be shut down. In this way, by selecting the first electrical device with better energy efficiency to operate, the purpose of energy saving and improving energy efficiency can be achieved.
[0085] In some embodiments, the processor 130 may use a transceiver based on a wired or wireless transmission standard to send a control signal to these electrical devices to turn on or off these electrical devices. These electrical devices will react to the control signal and turn off or on. In addition, in some embodiments, the processor 130 may determine the order of use of each electrical device based on the decision parameter value and the target setting value.
[0086] Please refer to Figure 8 , which is a flow chart of generating electricity efficiency evaluation information according to an embodiment of the present invention. In some embodiments, step S250 can be implemented as steps S253 to S256.
[0087] In some embodiments, the processor 130 obtains actual device settings of multiple previous unit time periods, and examines the device settings of multiple previous unit time periods to generate power efficiency evaluation information.
[0088] In step S253, the processor 130 selects a recommended electrical device from a plurality of electrical devices for an evaluation period according to the decision parameter value. The evaluation period may include one or more previous unit periods. Specifically, when the actual setting value applied to the adjustable setting parameter in each previous unit period has been determined, the processor 130 may compare the actual setting value actually applied in the evaluation period with the decision parameter value, and determine the recommended electrical device for the evaluation period. Figure 6 Taking the determined decision parameter value "29.2 degrees" as an example, the actual operation data of the first electrical equipment in the evaluation period can be shown in Table 5, and the recommended electrical equipment corresponding to each evaluation period can be shown in Table 6.
[0089]
[0090] Table 5
[0091]
[0092] Table 6
[0093] Referring to Table 5, it can be seen that the first electrical equipment is actually turned on in 4 evaluation periods to reduce the ambient temperature. However, since the target setting values applied to the evaluation periods "15:00-16:00", "16:00-17:00", and "17:00-18:00" are "29.0", "29.0", and "28.5", respectively, in the case of the decision parameter value "29.2 degrees", the recommended electrical equipment corresponding to the evaluation periods "15:00-16:00", "16:00-17:00", and "17:00-18:00" is the second electrical equipment.
[0094] In step S254, the processor 130 generates the predicted power consumption of the recommended power-consuming device during the evaluation period using the device power consumption prediction model. By using the device power consumption prediction model of the recommended power-consuming device, the processor 130 can obtain the predicted power consumption during the evaluation period. For example, according to the example of Table 6, the processor 130 can obtain the predicted power consumption of the recommended power-consuming device (i.e., the second power-consuming device) during these evaluation periods, as shown in Table 7. It should be noted that the processor 130 can estimate the predicted power consumption of the recommended power-consuming device during these evaluation periods based on the actual setting value applied to the adjustable setting parameter and the historical operation information of the recommended power-consuming device.
[0095]
[0096] Table 7
[0097] In step S255, the processor 130 generates power efficiency evaluation information according to the actual power consumption of the first power-consuming device in the evaluation period and the predicted power consumption of the recommended power-consuming device in the evaluation period. For example, the processor 130 may obtain the power efficiency evaluation information shown in Table 7 or Table 8.
[0098]
[0099] Table 8
[0100] In addition, in some embodiments, the processor 130 may also calculate the power consumption gap and cost saving benefit in the power consumption benefit evaluation information based on the actual power consumption of the first power-consuming device during the evaluation period and the predicted power consumption of the recommended power-consuming device during the evaluation period. Taking Table 8 as an example, the power consumption gap may be (348-329)+(346-330)+(343-325)=53 degrees. For a single unit period, about 2% of power consumption can be saved. In some embodiments, the processor 130 may also calculate the cost saving benefit based on the power consumption gap and the unit electricity charge, and the cost saving benefit may be, for example, the cost saving amount.
[0101] In step S256, the processor 130 displays the power efficiency evaluation information through the display 110. That is, the processor 130 can provide the power efficiency evaluation information through the display 110, so that the equipment management personnel can adjust the setting mode of the power equipment according to the power efficiency evaluation information to reduce energy waste. For example, the display 110 can display the power efficiency evaluation information on an operation interface for reference by the equipment personnel.
[0102] Fig. 9 is a schematic diagram of an air conditioning device according to an embodiment of the present invention. Fig. 9 , the air conditioning device may include a chilled water main unit 91, a blower 93, and a cooling water tower 92. The chilled water main unit 91 may include an evaporator 911, a condenser 912, and a refrigerant pipeline 913. The evaporator 911 supplies chilled water FW1 to the blower 93, and receives chilled water FW2 from the blower 93. The evaporator 911 may cool the chilled water FW2 to chilled water FW1 by using a refrigerant. The chilled water supply temperature of the chilled water FW1 may be an adjustable setting parameter of the air conditioning device. The condenser 912 supplies cooling water CW1 to the cooling water tower 92, and receives cooling water CW2 from the cooling water tower 92. The condenser 912 may use the cooling water CW2 from the cooling water tower 92 to cool the refrigerant and produce a higher temperature cooling water CW1. The cooling water return temperature of the cooling water CW2 may be an adjustable setting parameter of the air conditioning device.
[0103] In addition, in some embodiments, the cooling capacity of the air conditioning device can be generated according to the following formula (1). Formula (1): Cooling capacity = temperature difference of chilled water × flow rate × specific heat of water. The temperature difference of the chilled water is the temperature difference between the chilled water FW1 and the chilled water FW2.
[0104] Fig.10 is a schematic diagram of determining the decision parameter value according to an embodiment of the present invention. Fig.10 In this exemplary embodiment, the processor 130 can determine two decision parameter values based on the function line segments of the three electrical devices, which are "29.2 degrees" and "28.5 degrees". Therefore, the processor 130 can decide to start one of the three electrical devices based on the two decision parameter values and the target setting value of the adjustable setting parameter, and can generate power efficiency evaluation information based on the two decision parameter values. Fig.10 In the example, after determining the target setting value according to the ambient temperature, if the processor 130 determines that the target setting value is less than "28.5 degrees", the processor 130 will turn on "device #2". If the processor 130 determines that the target setting value is greater than "28.5 degrees" and less than "29.2 degrees", the processor 130 will turn on "device #3". If the processor 130 determines that the target setting value is greater than "29.2 degrees", the processor 130 will turn on "device #3". In other words, in response to changes in ambient temperature, when the target setting value changes from less than "28.5 degrees" to greater than "29.2 degrees", the processor 130 can switch from turning on "device #2" to turning on "device #3".
[0105] The processing procedure of the method for setting the electric equipment executed by at least one processor is not limited to the above-mentioned embodiments. For example, part of the above-mentioned steps (processing) may be omitted, or the steps may be executed in another order. Furthermore, any two or more of the above-mentioned steps may be combined, or part of the steps may be modified or deleted. Alternatively, other steps may be executed in addition to the above-mentioned steps.
[0106] In summary, in an embodiment of the present invention, an equipment power consumption prediction model can be established based on the equipment operation information of multiple electrical devices. When the adjustable setting parameters are set to multiple setting values respectively, the equipment power consumption prediction model of each electrical device can be used to generate the equipment energy efficiency corresponding to each setting value. Multiple equipment energy efficiencies of multiple electrical devices can be used to determine decision parameter values associated with the adjustable setting parameters, and this decision parameter value can determine the setting method of these electrical devices. Since the embodiment of the present invention can recommend the use of electrical devices with higher equipment energy efficiency based on the decision parameter value, it can effectively save electricity and improve energy utilization while meeting the requirements of the production environment.
[0107] Although the present invention is disclosed in conjunction with the above embodiments, they are not intended to limit the present invention. Any ordinary technician in the technical field may make slight changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be based on the definition of the attached claims.
Claims
1. A method for setting an electrical device, comprising: Obtain equipment operation information of multiple electrical equipment; Establishing a device power consumption prediction model for each of the multiple power-consuming devices according to the device operation information of the multiple power-consuming devices, wherein the multiple input characteristic variables of the device power consumption prediction model for each of the multiple power-consuming devices include adjustable setting parameters for each of the multiple power-consuming devices; The adjustable setting parameter is set to a plurality of setting values, and the device power consumption prediction model of each of the plurality of power-consuming devices is used to obtain a plurality of device energy efficiencies corresponding to the plurality of setting values respectively; Determining a decision parameter value of the adjustable setting parameter by comparing the multiple device energy efficiencies of each of the multiple electrical devices; as well as The plurality of electrical devices are controlled according to the decision parameter value.
2. The method for setting an electric device according to claim 1, wherein the plurality of electric devices include a first electric device, and the steps of setting the adjustable setting parameter to the plurality of setting values, and using the device power consumption prediction model of each of the plurality of electric devices to obtain the plurality of device energy efficiencies corresponding to the plurality of setting values respectively include: Performing statistical operations on a plurality of output quantities of the first electrical equipment in a plurality of previous unit time periods to obtain a plurality of output statistics of the first electrical equipment, wherein the plurality of output statistics are respectively equivalent to the plurality of set values and include the first output statistics; Using the device power consumption prediction model of the first power-consuming device, estimate multiple predicted power consumptions of the first power-consuming device, wherein the multiple predicted power consumptions are respectively equal to the multiple set values and include the first predicted power consumption; as well as One of the plurality of equipment energy efficiencies of the first electrical equipment is determined according to a ratio between the first output statistic and the first predicted power consumption, wherein the first output statistic and the first predicted power consumption correspond to a first set value among the set values.
3. The method for setting an electric device according to claim 2, wherein the step of performing statistical calculations on the output quantities of the first electric device in the previous unit time periods to obtain the output statistics of the first electric device comprises: Acquire a plurality of first output quantities corresponding to the first set value according to the first set value; as well as A statistical operation is performed on the multiple first output quantities to obtain the first output statistic of the first electrical equipment.
4. The method for setting an electric device according to claim 2, wherein the step of using the device power consumption prediction model of the first electric device to estimate the plurality of predicted power consumptions of the first electric device comprises: The first output statistic and the adjustable setting parameter set to the first setting value are input into the equipment power consumption prediction model to obtain the first predicted power consumption corresponding to the first setting value.
5. The method for setting electrical equipment according to claim 2, wherein the plurality of electrical equipment comprises a plurality of air-conditioning equipment, and the plurality of outputs comprises a plurality of cooling capacities.
6. The method for setting electrical equipment as described in claim 2, wherein the plurality of electrical equipment includes a plurality of air compressors, and the plurality of outputs includes a plurality of exhaust volumes.
7. The method for setting an electric device according to claim 1, wherein the plurality of electric devices include a first electric device and a second electric device, and the step of determining the decision parameter value of the adjustable setting parameter by comparing the plurality of device energy efficiencies of each of the plurality of electric devices comprises: Establishing a first function line segment according to the plurality of device energy efficiencies of the first electrical device and the corresponding set values; Establishing a second function line segment according to the plurality of device energy efficiencies of the second electrical device and the corresponding set values; as well as The decision parameter value of the adjustable setting parameter is determined according to the intersection point of the first function line segment and the second function line segment.
8. The method for setting an electric device according to claim 1, wherein the plurality of electric devices include a first electric device and a second electric device, and the step of controlling the plurality of electric devices according to the decision parameter value comprises: Obtaining a target setting value of the adjustable setting parameter; as well as According to the decision parameter value and the target setting value, the first electrical device is started and the second electrical device is shut down.
9. The method for setting an electric device according to claim 1, wherein the plurality of electric devices include a first electric device, and the step of controlling the plurality of electric devices according to the decision parameter value comprises: Selecting a recommended electrical device from the plurality of electrical devices for an evaluation period according to the decision parameter value; Using the equipment power consumption prediction model to generate the predicted power consumption of the recommended power-consuming equipment within the evaluation period; as well as Electricity efficiency evaluation information is generated based on the actual electricity consumption of the first electricity-consuming equipment during the evaluation period and the predicted electricity consumption of the recommended electricity-consuming equipment during the evaluation period.
10. The method for setting electric equipment according to claim 1, wherein the plurality of electric equipment includes a first electric equipment, and the step of establishing the equipment power consumption prediction model of each of the plurality of electric equipment according to equipment operation information of the plurality of electric equipment comprises: generating the plurality of input characteristic variables of a plurality of previous unit time periods according to the equipment operation information of the first electrical equipment; as well as The device power consumption prediction model of the first power-consuming device is trained based on a machine learning algorithm by utilizing the multiple input feature variables and multiple actual power consumptions of the first power-consuming device in the multiple previous unit time periods.
11. An electronic device comprising: A storage device storing a plurality of instructions; A processor is coupled to the storage device and accesses the instructions to execute: Obtain equipment operation information of multiple electrical equipment; Establishing a device power consumption prediction model for each of the multiple power-consuming devices according to the device operation information of the multiple power-consuming devices, wherein the multiple input characteristic variables of the device power consumption prediction model for each of the multiple power-consuming devices include adjustable setting parameters for each of the multiple power-consuming devices; The adjustable setting parameter is set to a plurality of setting values, and the device power consumption prediction model of each of the plurality of power-consuming devices is used to obtain a plurality of device energy efficiencies corresponding to the plurality of setting values respectively; Determining a decision parameter value of the adjustable setting parameter by comparing the multiple device energy efficiencies of each of the multiple electrical devices; as well as The plurality of electrical devices are controlled according to the decision parameter value.
12. The electronic device of claim 11, wherein the plurality of powered devices include a first powered device, and the processor further executes: Performing statistical operations on a plurality of output quantities of the first electrical equipment in a plurality of previous unit time periods to obtain a plurality of output statistics of the first electrical equipment, wherein the plurality of output statistics are respectively equivalent to the plurality of set values and include the first output statistics; Using the device power consumption prediction model of the first power-consuming device, estimate multiple predicted power consumptions of the first power-consuming device, wherein the multiple predicted power consumptions are respectively equal to the multiple set values and include the first predicted power consumption; as well as One of the plurality of equipment energy efficiencies of the first electrical equipment is determined according to a ratio between the first output statistic and the first predicted power consumption, wherein the first output statistic and the first predicted power consumption correspond to a first set value among the set values.
13. The electronic device of claim 12, wherein the processor further executes: Acquire a plurality of first output quantities corresponding to the first set value according to the first set value; and A statistical operation is performed on the multiple first output quantities to obtain the first output statistic of the first electrical equipment.
14. The electronic device of claim 12, wherein the processor further executes: The first output statistic and the adjustable setting parameter set to the first setting value are input into the equipment power consumption prediction model to obtain the first predicted power consumption corresponding to the first setting value. 15 . The electronic device as claimed in claim 12 , wherein the plurality of electrical appliances include a plurality of air-conditioning appliances, and the plurality of outputs include a plurality of cooling capacities.
16. The electronic device as claimed in claim 12, wherein the plurality of electrical devices include a plurality of air compressor devices, and the plurality of outputs include a plurality of exhaust volumes.
17. The electronic device as claimed in claim 11, wherein the plurality of powered devices include a first powered device and a second powered device, and the processor further executes: Establishing a first function line segment according to the plurality of device energy efficiencies of the first electrical device and the corresponding set values; Establishing a second function line segment according to the plurality of device energy efficiencies of the second electrical device and the corresponding set values; as well as The decision parameter value of the adjustable setting parameter is determined according to the intersection point of the first function line segment and the second function line segment.
18. The electronic device as claimed in claim 11, wherein the plurality of electric devices include a first electric device and a second electric device, and the processor further executes: Obtaining a target setting value of the adjustable setting parameter; and According to the decision parameter value and the target setting value, the first electrical device is started and the second electrical device is shut down.
19. The electronic device of claim 11, wherein the plurality of powered devices include a first powered device, and the processor further executes: Selecting a recommended electrical device from the plurality of electrical devices for an evaluation period according to the decision parameter value; generating predicted power consumption of the recommended power-consuming equipment within the evaluation period using the equipment power consumption prediction model; and Electricity efficiency evaluation information is generated based on the actual electricity consumption of the first electricity-consuming equipment during the evaluation period and the predicted electricity consumption of the recommended electricity-consuming equipment during the evaluation period.
20. The electronic device of claim 11, wherein the plurality of powered devices include a first powered device, and the processor further executes: generating the plurality of input characteristic variables of a plurality of previous unit time periods according to the equipment operation information of the first electrical equipment; and The device power consumption prediction model of the first power-consuming device is trained based on a machine learning algorithm by utilizing the multiple input feature variables and multiple actual power consumptions of the first power-consuming device in the multiple previous unit time periods.
