Prediction system, electronic device, prediction program, and prediction method

Abstract

To improve the accuracy of estimates of power consumption by electronic devices. [Solution] The estimation system comprises an estimation unit that obtains an estimated value of the power consumption when an electronic device performs a job using a power consumption estimation model, which is a regression model for estimating the power consumption. The regression model is constructed using a decision tree algorithm, the target variable of the regression model is the power consumption, and the explanatory variables of the regression model are job execution information, setting value information of the electronic device's state, and time information of the time taken for the job or the duration of the state. Multiple explanatory variables exist for the regression model depending on the type of job setting or the state of the electronic device.

Description

Technical Field

[0001] The present disclosure relates to an electronic device, an estimation system for estimating the power consumption of the electronic device, an estimation system program, and an estimation system method.

Background Art

[0002] Conventionally, the reference power consumption obtained by previously measuring the power consumption is multiplied by a printing mode coefficient corresponding to the printing mode indicating whether to perform printing in color or black and white, and further multiplied by a layout coefficient corresponding to the layout representing the number of pages printed on one sheet of paper, thereby obtaining the power consumption when the image forming apparatus executes one job. By multiplying the obtained power consumption by the carbon dioxide emission amount per unit power consumption, an estimation system (see, for example, Patent Document 1) for obtaining an estimated value of the carbon dioxide emission amount by the image forming apparatus is known. In Patent Document 1, the reference power consumption is, for example, the power consumption when performing black and white printing on one page of A4 size. The printing mode coefficient is "1" in the case of the printing mode of performing black and white printing, and a value larger than "1" is set in the case of the printing mode of performing color printing. The layout coefficient is "1" in the case of "none", which is a layout for printing one page of a document on one side of a sheet of paper, "0.5" in the case of "2in1", which is a layout for printing two pages of a document on one side of a sheet of paper, "0.25" in the case of "4in1", which is a layout for printing four pages of a document on one side of a sheet of paper, and "0.125" in the case of "8in1", which is a layout for printing eight pages of a document on one side of a sheet of paper.

[0003] Also, an estimation system (see, for example, Patent Document 2) is known in which the power consumption specified for each operation unit determined by the printing settings is multiplied by the number of operation times determined by the number of printed sheets and the number of sides, thereby obtaining the power consumption when the image forming apparatus executes one job. By multiplying the obtained power consumption by the carbon dioxide emission coefficient due to power, an estimated value of the carbon dioxide emission amount by the image forming apparatus is obtained. [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2006-021414 [Patent Document 2] Japanese Patent Publication No. 2009-058749 [Overview of the project] [Problems that the invention aims to solve]

[0005] However, conventional estimation systems have the problem of low accuracy in estimating power consumption by image forming machines.

[0006] In light of the circumstances described above, the purpose of this disclosure is to improve the accuracy of estimates of power consumption by electronic devices. [Means for solving the problem]

[0007] An inference system relating to one form of this disclosure is: The system includes an estimation unit that obtains an estimated value of the power consumption when an electronic device performs a job, using a power consumption estimation model, which is a regression model for estimating the power consumption. The aforementioned regression model is constructed using a decision tree algorithm. The dependent variable of the regression model is the amount of electricity consumed. The explanatory variables of the regression model are job execution information, setting value information for the state of the electronic device, and time information for the time taken for the job or the duration of the state. The explanatory variables of the regression model may vary depending on the type of job configuration or the state of the electronic device.

[0008] An electronic device relating to one form of this disclosure is The system includes an estimation unit that obtains an estimated value of the power consumption when an electronic device performs a job, using a power consumption estimation model, which is a regression model for estimating the power consumption. The aforementioned regression model is constructed using a decision tree algorithm. The dependent variable of the regression model is the amount of electricity consumed. The explanatory variables of the regression model are job execution information, setting value information for the state of the electronic device, and time information for the time taken for the job or the duration of the state. The explanatory variables of the regression model may vary depending on the type of job configuration or the state of the electronic device.

[0009] An inference program relating to one form of this disclosure is: Control circuits for electronic devices, An estimation program that operates as an estimation unit to obtain an estimated value of the power consumption when an electronic device performs a job, using a power consumption estimation model, which is a regression model for estimating the power consumption, The aforementioned regression model is constructed using a decision tree algorithm. The dependent variable of the regression model is the amount of electricity consumed. The explanatory variables of the regression model are job execution information, setting value information for the state of the electronic device, and time information for the time taken for the job or the duration of the state. The explanatory variables of the regression model may vary depending on the type of job configuration or the state of the electronic device.

[0010] The inference method relating to one form of this disclosure is: The control circuit of the electronic device executes a prediction program, An estimated value of the power consumption when an electronic device performs a job is obtained using a power consumption estimation model, which is a regression model for estimating the power consumption. The aforementioned regression model is constructed using a decision tree algorithm. The dependent variable of the regression model is the amount of electricity consumed. The explanatory variables of the regression model are the execution information of the job, the set value information of the state of the electronic device, and the time information of the time taken for the job or the duration of the state. There are a plurality of explanatory variables of the regression model according to the type of setting of the job or the state of the electronic device.

Advantages of the Invention

[0011] According to the present disclosure, the accuracy of the estimated value of the power consumption by the electronic device can be improved.

[0012] Note that the effects described here are not necessarily limited, and any of the effects described in the present disclosure may be applicable.

Brief Description of the Drawings

[0013] [Figure 1] It is a block diagram of an example of an image forming apparatus as an estimation system according to an embodiment of the present invention. [Figure 2] It is a diagram showing an example of job history information shown in FIG. 1. [Figure 3] It is a block diagram of an example of an estimation model generation system for generating an estimation model used by the image forming apparatus shown in FIG. 1. [Figure 4] It is a flowchart of a method for generating an estimation model used by the image forming apparatus shown in FIG. 1. [Figure 5] It is a flowchart of the operation of the image forming apparatus shown in FIG. 1 when executing a copy job. [Figure 6] It is a flowchart of the operation of the image forming apparatus shown in FIG. 1 when displaying the total amount of carbon dioxide emissions. [Figure 7] It is a block diagram of an example different from the example shown in FIG. 1 of the estimation system according to an embodiment of the present invention. <000009?7>An example of a power consumption estimation model which is a regression model constructed by a decision tree algorithm is shown.

Embodiments for Carrying Out the Invention

[0014] Embodiments of this disclosure will be described below with reference to the drawings. In these embodiments, the electronic device will be described as an image forming apparatus such as an MFP, but other electronic devices may also be used.

[0015] First, the configuration of the image forming apparatus as an inference system according to one embodiment of the present invention will be described.

[0016] Figure 1 is a block diagram of an example of an image forming apparatus 10 according to this embodiment.

[0017] As shown in Figure 1, the image forming apparatus 10 is a computer comprising: an operation unit 11 which is an operation device such as buttons into which various operations are input; a display unit 12 which is a display device such as an LCD (Liquid Crystal Display) which displays various information; a printer 13 which is a printing device which prints images onto a recording medium such as paper; a scanner 14 which is a reading device which reads images from an original document; a communication unit 15 which is a communication device which communicates with external devices via a network such as a LAN (Local Area Network) or the Internet, or directly by wired or wireless connection without going through a network; a fax communication unit 16 which is a fax device which communicates faxes with an external facsimile device (not shown) via a communication line such as a public telephone line; a storage unit 17 which is a non-volatile storage device such as a semiconductor memory or HDD (Hard Disk Drive) which stores various information; and a control unit 18 which controls the entire image forming apparatus 10.

[0018] The memory unit 17 can store an estimation program 17a for estimating the amount of carbon dioxide emitted by the image forming apparatus 10. The estimation program 17a may, for example, be installed in the image forming apparatus 10 during the manufacturing stage, or it may be additionally installed in the image forming apparatus 10 from an external storage medium such as a USB (Universal Serial Bus) memory, or it may be additionally installed in the image forming apparatus 10 from a network.

[0019] The memory unit 17 is capable of storing job history information 17b, which stores the history of jobs performed by the image forming apparatus 10.

[0020] Figure 2 shows an example of job history information 17b.

[0021] As shown in Figure 2, the history stored in the job history information 17b includes the job execution time, the job type (such as a copy job or a print job), and the job settings for each job. The history stored in the job history information 17b contains all the information necessary for estimating carbon dioxide emissions using the estimation model described later.

[0022] The control unit 18 shown in Figure 1 includes, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory) that stores programs and various data, and a RAM (Random Access Memory) used as a working area for the CPU of the control unit 18. The CPU of the control unit 18 executes programs stored in the storage unit 17 or the ROM of the control unit 18.

[0023] The control unit 18 implements an estimation unit 18a and estimation method for estimating carbon dioxide emissions from the image forming apparatus 10 by executing the estimation program 17a.

[0024] The power consumption estimation model, which is a regression model used by the estimation unit 18a to estimate the amount of carbon dioxide emissions when the image forming apparatus 10 performs one job, will be explained below with specific examples.

[0025] Figure 8 shows an example of a power consumption estimation model, which is a regression model constructed using a decision tree-based algorithm.

[0026] The estimation unit 18a calculates an estimated value of the power consumption when the image forming apparatus 10 performs a job, using a power consumption estimation model, which is a regression model for estimating power consumption. The estimation unit 18a calculates an estimated value of carbon dioxide emissions by multiplying the estimated power consumption by a carbon dioxide emission coefficient. The regression model is constructed using a decision tree algorithm. The dependent variable of the regression model is power consumption. The independent variables of the regression model are job execution information, setting information for the state of the image forming apparatus 10, and time information for the time taken for the job or the duration of the state. There are multiple independent variables of the regression model depending on the type of job setting or the state of the image forming apparatus 10.

[0027] In this embodiment, the objective variable is power consumption, and the explanatory variables include job execution information such as the number of printed pages and the number of copies, setting information such as Light Sleep or Deep Sleep and drum heater settings, and information representing the respective times. A power consumption estimation model, which is a regression model, is constructed using a decision tree algorithm. Figure 8 is a tree diagram showing the contents of an example of such a power consumption estimation model. For example, if Full Color total is less than 100, Black & White total is 100 or more, Sleep Mode is Deep, and Sleep time is 300 or more, the power consumption is estimated to be 350 kWh.

[0028] The power consumption estimation model may use an algorithm that utilizes a single tree, or it may employ an algorithm (ensemble learning) that creates multiple trees and calculates a value by averaging or combining their results by majority vote. Ensemble learning is more accurate than a single model. That is, the estimation unit 18a may calculate an estimated power consumption value by averaging or combining the results obtained using multiple regression models, which are power consumption estimation models, through ensemble learning.

[0029] Next, we will describe the configuration of the inference model generation system for generating inference models.

[0030] Figure 3 is a block diagram of an example of an inference model generation system 20 for generating an inference model used by the image forming apparatus 10.

[0031] As shown in Figure 3, the prediction model generation system 20 includes an image forming apparatus 30 of the same model as the image forming apparatus 10 (see Figure 1), a power meter 40 for measuring the power consumption of the image forming apparatus 30, and an electronic device 50, such as a smartphone or tablet, for storing the power consumption measured by the power meter 40.

[0032] Next, we will explain how to generate an inference model.

[0033] Figure 4 is a flowchart of the method for generating the inference model used by the image forming apparatus 10.

[0034] As shown in Figure 4, the operator collects a large amount of data to generate a power consumption estimation model (S101). Specifically, the operator stores data in the electronic device 50 for each job setting, relating the power consumption measured by the power meter 40 when the image forming apparatus 30 performs a job with the job settings performed by the image forming apparatus 30.

[0035] When the process in S101 is completed, the operator generates a power consumption estimation model using a decision tree algorithm with the data collected in S101 (S102). Specifically, the operator instructs the electronic device 50 to generate a power consumption estimation model, which is a regression model, using a decision tree algorithm with the data collected in S101. Therefore, the electronic device 50 generates a power consumption estimation model, which is a regression model, using a decision tree algorithm with the data collected in S101. The generation of the power consumption estimation model in S102 may be performed by machine learning.

[0036] When the process in S102 is completed, the operator generates a carbon dioxide emission estimation model using the power consumption estimation model generated in S102 (S103). Specifically, the operator instructs the electronic device 50 to generate a carbon dioxide emission estimation model using the power consumption estimation model generated in S102. Therefore, the electronic device 50 generates a carbon dioxide emission estimation model by multiplying the power consumption estimation model generated in S102 by a carbon dioxide emission factor.

[0037] The inference model generation system 20 shown in Figure 3 can generate inference models only for the same model as the image forming apparatus 30. Therefore, by changing the model of the image forming apparatus in the inference model generation system 20, it is possible to generate inference models for various models.

[0038] The inference model generated by the method shown in Figure 4 can be installed in an image forming apparatus of the same type as the image forming apparatus 30, such as the image forming apparatus 10.

[0039] Next, we will describe the operation of the image forming apparatus 10 when a job is executed.

[0040] In the following explanation, copy jobs will be used as an example of job types. However, the same principles apply to jobs other than copy jobs.

[0041] Figure 5 is a flowchart showing the operation of the image forming apparatus 10 when executing a copy job.

[0042] As shown in Figure 5, when the control unit 18 of the image forming apparatus 10 is instructed via the operation unit 11 to display the copy job setting screen (hereinafter referred to as the "copy setting screen"), it displays the copy setting screen on the display unit 12 (S131).

[0043] When the processing in S131 is completed, the estimation unit 18a of the image forming apparatus 10 uses the estimation model for the copy job and the copy setting pattern to determine the estimated carbon dioxide emissions from the image forming apparatus 10 for each of the multiple patterns of copy job settings (hereinafter referred to as "copy settings") (S132).

[0044] When the processing in S132 is completed, the estimation unit 18a displays the multiple copy setting patterns and the estimated carbon dioxide emissions from the image forming apparatus 10, which were determined in S132, on the copy setting screen displayed in S131 (S133). Therefore, when a user of the image forming apparatus 10 specifies a copy setting, for example by selecting an arbitrary pattern from multiple copy setting patterns, they can take into account the estimated carbon dioxide emissions from the image forming apparatus 10.

[0045] When the processing in S133 is completed, the control unit 18 of the image forming apparatus 10 determines whether or not the execution of the copy job has been instructed via the operation unit 11 until it determines that the execution of the copy job has been instructed via the operation unit 11 (S134).

[0046] If the control unit 18 determines in S134 that the execution of a copy job has been instructed via the operation unit 11, it executes the copy job with the copy settings specified on the copy settings screen (S135).

[0047] When the processing in S135 is completed, the control unit 18 saves the history of the copy jobs executed in S135 to the job history information 17b (S136), and then terminates the operation shown in Figure 5.

[0048] In the operation shown in Figure 5, the estimation unit 18a displays the estimated carbon dioxide emissions from the image forming apparatus 10 for each of the multiple copy setting patterns. However, when a copy setting is specified on the copy setting screen, the estimation unit 18a may use the copy setting specified on the copy setting screen and the estimation model for the copy job to obtain an estimated carbon dioxide emissions from the image forming apparatus 10, and display the obtained estimated value on the copy setting screen.

[0049] Next, we will explain the operation of the image forming apparatus 10 when displaying the total amount of carbon dioxide emissions.

[0050] Figure 6 is a flowchart showing the operation of the image forming apparatus 10 when displaying the total amount of carbon dioxide emissions.

[0051] The user of the image forming apparatus 10 can instruct the image forming apparatus 10 via the operation unit 11 to display the total amount of carbon dioxide emissions from the image forming apparatus 10. When the estimation unit 18a of the image forming apparatus 10 is instructed to display the total amount of carbon dioxide emissions from the image forming apparatus 10, it uses the job settings shown in the job history information 17b and an estimation model corresponding to the job type shown in the job history information 17b to determine an estimated value of carbon dioxide emissions from the image forming apparatus 10 for each job shown in the job history information 17b, as shown in Figure 6 (S161).

[0052] When the processing in S161 is completed, the estimation unit 18a calculates the total estimated amount of carbon dioxide emissions from the image forming apparatus 10 by summing up all the estimated values ​​obtained in S161 (S162).

[0053] When the processing in S162 is completed, the estimation unit 18a displays the total estimated amount of carbon dioxide emissions from the image forming apparatus 10, calculated in S162, on the display unit 12 (S163). Therefore, the user of the image forming apparatus 10 can recognize the total estimated amount of carbon dioxide emissions from the image forming apparatus 10.

[0054] In the operation shown in Figure 6, the estimation unit 18a displays the total estimated amount of carbon dioxide emissions from the image forming apparatus 10 over all past periods. However, the estimation unit 18a may also display the total estimated amount of carbon dioxide emissions from the image forming apparatus 10 over a specific period, such as a period specified by the user of the image forming apparatus 10 via the operation unit 11.

[0055] Even if the power consumption of the image forming apparatus 10 is not measured by a power meter, an estimated value of the carbon dioxide emissions from the image forming apparatus 10 can be determined using an estimation model.

[0056] The recording medium on which images are printed by the image forming apparatus 10 is shipped with the carbon dioxide emissions already calculated during the manufacturing process of the recording medium itself. Similarly, the toner used for printing on the recording medium by the image forming apparatus 10 is shipped with the carbon dioxide emissions already calculated during the manufacturing process of the toner itself. Therefore, the estimated carbon dioxide emissions when the image forming apparatus 10 performs a job should not include the estimated carbon dioxide emissions for the amount of recording medium used and the amount of toner used. Since the estimation unit 18a does not include the estimated carbon dioxide emissions for the amount of recording medium used and the amount of toner used in the estimated carbon dioxide emissions when the image forming apparatus 10 performs a job, the accuracy of the estimated carbon dioxide emissions when the image forming apparatus 10 performs a job can be improved.

[0057] In this embodiment, the estimation unit 18a notifies the estimated carbon dioxide emissions from the image forming apparatus 10 by display. However, the estimation unit 18a may also notify the estimated carbon dioxide emissions from the image forming apparatus 10 by means other than display. For example, the estimation unit 18a may notify the estimated carbon dioxide emissions from the image forming apparatus 10 by voice.

[0058] In the above, the inference system is composed solely of an image forming apparatus. However, the inference system according to this embodiment may be composed of an image forming apparatus and at least one computer other than the image forming apparatus. For example, the inference system according to this embodiment may have the configuration shown in Figure 7.

[0059] Figure 7 is a block diagram of an example of the prediction system according to this embodiment, which differs from the example shown in Figure 1.

[0060] The estimation system 60 shown in Figure 7 comprises an image forming apparatus 70 and a computer 80. The image forming apparatus 70 and the computer 80 are connected to each other so as to be able to communicate with each other. The computer 80 receives from the image forming apparatus 70 the type and settings of jobs that the image forming apparatus 70 is scheduled to perform or has performed, and based on the received job type and settings, it calculates an estimated value of carbon dioxide emissions by the image forming apparatus 70, similar to the processing in S132 or S161. The estimated value of carbon dioxide emissions by the image forming apparatus 70, calculated by the computer 80, may be notified by either the image forming apparatus 70 or the computer 80.

[0061] According to Patent Document 1, carbon dioxide emissions from electricity use are calculated and added to the carbon dioxide emissions from paper type, paper usage, and toner usage. However, since the carbon dioxide emissions from paper and toner are already calculated during their production and shipped, including their carbon dioxide emissions in the calculation of carbon dioxide emissions from the use of the image forming apparatus is not an accurate calculation of carbon dioxide emissions. The calculation of carbon dioxide emissions from electricity use also involves maintaining a reference power amount, which is calculated from the power consumption of one A4-size monochrome page, either measured by an internal module or by a built-in power meter, and then calculating the power consumption by multiplying it by a print mode coefficient (color) and a layout coefficient. The carbon dioxide emissions are then determined by multiplying the calculated power consumption by the carbon dioxide emissions per unit power consumption. Determining the reference power requires actual measurement and necessitates equipment for power measurement. Furthermore, it is difficult to accurately calculate power consumption using only two coefficients: a color coefficient and a layout coefficient.

[0062] According to Patent Document 2, carbon dioxide emissions from electricity use are calculated and added to the carbon dioxide emissions from paper type, paper usage, and toner usage. However, since the carbon dioxide emissions from paper and toner are already calculated during their production and shipped, including their carbon dioxide emissions in the calculation for the use of the image forming apparatus is not an accurate calculation of carbon dioxide emissions. In calculating carbon dioxide emissions from electricity use, the operating parts of the mechanism are identified based on the print settings, and the number of operations of each operating part is determined by the number of pages / faces to be printed. The power consumption of the job is calculated by multiplying the power consumption determined for each mechanism by the number of operations and summing them up. The carbon dioxide emissions generated by electricity consumption are obtained by multiplying the calculated power consumption by the carbon dioxide emissions per unit power consumption. This requires determining the power consumption of each operating part and measuring it in advance. Furthermore, it cannot reflect factors that cannot be measured by the number of operations alone. For example, if the printing speed changes depending on the paper size and type, the power required to maintain the fixing temperature changes due to fluctuations in printing time, making it difficult to predict based solely on the number of operations.

[0063] According to this embodiment, the settings of the image forming apparatus, counter values, job execution information, and logs of the image forming apparatus are acquired. Based on the acquired information, a decision tree model is created, and this model can estimate the power consumption used by the image forming apparatus in one day.

[0064] Carbon dioxide emissions can be calculated by multiplying the amount of electricity consumed by the carbon dioxide emission factor set by the Ministry of the Environment. Therefore, by estimating the amount of electricity consumed by an image forming machine, it is possible to derive the amount of carbon dioxide emissions from that.

[0065] Image forming machines are used to perform jobs such as copying and printing, and it is believed that the majority of power consumption is due to job execution. However, in reality, it is possible to estimate power consumption with high accuracy based on factors other than job execution, such as sleep conditions and certain heater-related settings.

[0066] Even without a power meter, it is possible to estimate the daily power consumption of an image forming machine and predict carbon dioxide emissions from its settings and job execution information using a regression model. However, constructing a regression model is difficult unless there is linearity between the data used to construct it, and unique feature engineering is required to ensure linearity.

[0067] In contrast, this embodiment employs a decision tree algorithm. Decision tree models have the characteristics of being able to directly handle categorical variables, automatically capturing nonlinear relationships, and being independent of the scale of features. By adopting a decision tree algorithm, it is possible to realize a model that reduces the burden of feature engineering and further improves accuracy.

[0068] Although various embodiments and modifications of this technology have been described above, this technology is not limited to the embodiments described above, and various modifications can be made without departing from the gist of this technology. [Explanation of Symbols]

[0069] 10 Image forming apparatus 17a Prediction Program 18a Guessing part

Claims

1. The system includes an estimation unit that obtains an estimated value of the power consumption when an electronic device performs a job, using a power consumption estimation model, which is a regression model for estimating the power consumption. The aforementioned regression model is constructed using a decision tree algorithm. The dependent variable of the regression model is the amount of electricity consumed. The explanatory variables of the regression model are job execution information, setting value information for the state of the electronic device, and time information for the time taken for the job or the duration of the state. The explanatory variables of the regression model may vary depending on the type of job configuration or the state of the electronic equipment. A prediction system.

2. The prediction system according to claim 1, The estimation unit calculates an estimated value of power consumption by combining the results obtained using multiple regression models, which are power consumption estimation models, through ensemble learning, either by averaging or by majority vote. A prediction system.

3. An inference system according to claim 1 or 2, The estimation unit multiplies the estimated power consumption by the carbon dioxide emission factor to obtain an estimated carbon dioxide emission value. A prediction system that further possesses the following features.

4. The system includes an estimation unit that obtains an estimated value of the power consumption when an electronic device performs a job, using a power consumption estimation model, which is a regression model for estimating the power consumption. The aforementioned regression model is constructed using a decision tree algorithm. The dependent variable of the regression model is the amount of electricity consumed. The explanatory variables of the regression model are job execution information, setting value information for the state of the electronic device, and time information for the time taken for the job or the duration of the state. The explanatory variables of the regression model may vary depending on the type of job configuration or the state of the electronic equipment. electronic equipment.

5. Control circuits for electronic devices, An estimation program that operates as an estimation unit to obtain an estimated value of the power consumption when an electronic device performs a job, using a power consumption estimation model, which is a regression model for estimating the power consumption, The aforementioned regression model is constructed using a decision tree algorithm. The dependent variable of the regression model is the amount of electricity consumed. The explanatory variables of the regression model are job execution information, setting value information for the state of the electronic device, and time information for the time taken for the job or the duration of the state. The explanatory variables of the regression model may vary depending on the type of job configuration or the state of the electronic equipment. A prediction program.

6. The control circuit of the electronic device executes a prediction program, An estimated value of the power consumption when an electronic device performs a job is obtained using a power consumption estimation model, which is a regression model for estimating the power consumption. The aforementioned regression model is constructed using a decision tree algorithm. The dependent variable of the regression model is the amount of electricity consumed. The explanatory variables of the regression model are job execution information, setting value information for the state of the electronic device, and time information for the time taken for the job or the duration of the state. The explanatory variables of the regression model may vary depending on the type of job configuration or the state of the electronic equipment. Guessing method.

Images