JP7099805B2 - Predictors, prediction systems, prediction methods and programs - Google Patents

Description

The present invention relates to a prediction device, a prediction system, a prediction method and a program.

In order to use energy and resources efficiently, consumers need to anticipate the demand for energy and resources and create a plan to secure supply according to the demand.
For example, when using electric power, the consumer predicts the demand for each unit time (for example, 30 minutes) and concludes a contract to purchase the necessary electric power from the electric power company. At this time, the consumer sets the electric power purchased from the electric power company, that is, the contracted electric power, based on the maximum demand amount among the demand amounts for each unit time.
In addition, the consumer pays the electric power company a basic charge according to the contracted electric power and a metered charge according to the amount of electric power actually used. Consumers can reduce the basic charge by reducing the contracted power, but on the other hand, if they use (purchase) more power than the contracted power, they must pay an excess penalty to the power company. .. Therefore, consumers need to make highly accurate demand forecasts in order to reduce basic charges and excess penalties.

As a method of predicting electric power demand, for example, Patent Document 1 discloses a method of predicting electric power demand for each electric load by inputting conditions such as weather into a prediction model prepared for each electric load. ..
In addition, a physical model that imitates the equipment owned by the customer is created, and a large number of simulations in which multiple conditions (explanatory variables) are stochastically changed in the physical model are executed to obtain the power demand (objective variable). , A prediction method using Monte Carlo simulation is known.

Japanese Unexamined Patent Publication No. 2015-201772

However, in the conventional prediction method, it is necessary to create a detailed physical model that covers a large number of facilities owned by the customer, and it takes a lot of time to create such a physical model.
Further, in the prediction method using the Monte Carlo simulation, it is necessary to execute many simulations in order to improve the prediction accuracy, and it takes a long time to obtain the prediction result. Therefore, for example, when the power demand is predicted with 30 minutes as the prediction target period, all the simulations cannot be completed by the prediction target period, and the prediction result can be obtained before actually procuring the power. May not be.

The present invention has been made in view of such problems, and provides a forecasting device, a forecasting system, a forecasting method, and a program capable of performing demand forecasting at high speed.

In order to solve the above problems, the present invention employs the following means.
According to the first aspect of the present invention, the prediction device (100) includes a waveform acquisition unit (110) for acquiring a waveform representing the value of the objective variable measured in the past in time series, and the plurality of said waveforms. , The classification processing unit (131) that classifies similar waveforms into one pattern and sets explanatory variables showing the characteristics common to the waveforms classified into the one pattern, and the explanation in the future prediction target period. A probability calculation unit (132) that calculates a probability distribution of values that the objective variable can take in the prediction target period by selecting a pattern that matches the variable and performing statistical processing on the waveforms classified into the pattern. A prediction unit (133) for obtaining the value of the objective variable in the prediction target period based on the probability distribution is provided.
In this way, the prediction device calculates the probability distribution for the waveforms classified into patterns that match the explanatory variables in the prediction target period, and obtains the value of the objective variable based on the probability distribution, thereby performing the calculation and prediction. Can be executed quickly. Therefore, the time required for calculation and prediction can be shortened as compared with the existing prediction method using, for example, Monte Carlo simulation.

According to the second aspect of the present invention, in the prediction device according to the above aspect, the prediction unit has the objective variable within the range of the confidence interval predetermined in the prediction target period based on the probability distribution. Find the upper and lower limits of the possible values.
By doing so, the predictor can obtain a highly accurate upper limit value and lower limit value after excluding the values having low certainty from the values that the objective variable can take in the prediction target period.

According to the third aspect of the present invention, the prediction device according to any one of the above aspects is a supply / demand plan for the object related to the objective variable based on the value of the objective variable obtained by the prediction unit. Further includes a planning unit (134) for creating the above.
In this way, the forecasting device creates a supply and demand plan for the forecast target period based on the value of the objective variable predicted by the forecast unit, so that the optimal operation of the equipment in the forecast target period becomes possible.

According to the fourth aspect of the present invention, the prediction system determines the measuring device (10) for measuring the actual value of the objective variable in the plant and the possible value of the objective variable in the future prediction target period of the plant. It is provided with a desired prediction device (100).
The prediction device includes a waveform acquisition unit (110) that acquires a waveform that represents the value of the objective variable measured by the measurement device in time series, and a plurality of the waveforms that are similar to each other in one pattern. A classification processing unit (131) that classifies and sets an explanatory variable showing characteristics common to the waveform classified into the one pattern, and a value that the objective variable can take in the prediction target period that matches the explanatory variable. It has a probability calculation unit (132) for calculating the probability distribution of the above based on statistical processing, and a prediction unit (133) for obtaining the value of the objective variable in the prediction target period based on the probability distribution.

According to the fifth aspect of the present invention, the prediction method includes a waveform acquisition step of acquiring a waveform representing the value of the objective variable measured in the past in time series, and a plurality of said waveforms having similar waveforms. The objective variable is taken in a classification process step of classifying into one pattern and setting explanatory variables showing characteristics common to the waveforms classified in the one pattern, and in a future prediction target period that matches the explanatory variables. It has a probability calculation step of calculating the probability distribution of the obtained value based on statistical processing, and a prediction step of obtaining the value of the objective variable in the prediction target period based on the probability distribution.

According to the sixth aspect of the present invention, the program uses the computer of the prediction device as a waveform acquisition unit that acquires a waveform representing the value of the objective variable measured in the past in time series, and is similar to the plurality of said waveforms. The purpose of the classification processing unit, which classifies the waveforms to be processed into one pattern and sets explanatory variables showing the characteristics common to the waveforms classified into the one pattern, in the future prediction target period that matches the explanatory variables. It functions as a probability calculation unit that calculates the probability distribution of the value that the variable can take based on statistical processing, and a prediction unit that obtains the value of the objective variable in the prediction target period based on the probability distribution.

According to the forecasting device, forecasting system, forecasting method and program according to the present invention, demand forecasting can be performed at high speed.

It is a figure which shows the functional structure of the prediction apparatus which concerns on one Embodiment of this invention. It is the first figure which shows the processing flow of the classification apparatus which concerns on one Embodiment of this invention. It is a figure for demonstrating the classification process which concerns on one Embodiment of this invention. It is a 2nd figure which shows the processing flow of the classification apparatus which concerns on one Embodiment of this invention. It is the first figure for demonstrating the prediction process which concerns on one Embodiment of this invention. It is a 2nd figure for demonstrating the prediction process which concerns on one Embodiment of this invention. It is a figure which shows the hardware composition of the prediction apparatus which concerns on one Embodiment of this invention.

(Functional configuration of prediction system)
Hereinafter, the prediction system according to the embodiment of the present invention will be described with reference to FIGS. 1 to 7.
In this embodiment, a plant that consumes electric power will be described as an example of a consumer. The plant is, for example, a facility such as a power plant, a factory, a warehouse, or a commercial facility. Further, in the present embodiment, an example in which the prediction system predicts the electric power consumed in the plant, that is, the demand amount of the electric power will be described.
Further, in the following description, the demand amount predicted by the prediction system is also referred to as an "objective variable". The objective variable is the variable you want to predict. The objective variable is also called the "dependent variable" or "external standard" and can be regarded as the result of things.

FIG. 1 is a diagram showing a functional configuration of a prediction device according to an embodiment of the present invention.
As shown in FIG. 1, the prediction system 1 includes a measurement device 10, a server 20, and a prediction device 100.
The measuring device 10 is provided in the plant A, and measures the amount of electric power used by the plant A (the amount of electric power demand) and the state of the plant A every unit time (for example, 30 minutes).
The state information of the plant A includes, for example, when the plant A is a factory, information such as the production amount of the plant A and the operating state of the equipment. The operating state of production equipment is the operating rate of equipment that consumes electric power, such as air conditioning, lighting, and production equipment, by unit time.
The measuring device 10 has a power meter 11 for measuring the actual power demand in the plant A, and a sensor unit 12 for measuring the actual production amount and the operating state of the plant A.
Further, the measuring device 10 transmits "demand information" associated with the measured power demand amount and the measured date and time and "state information" associated with the measured state and the measured date and time to the prediction device 100 as the measurement result.
The server 20 is communicably connected to the prediction device 100 via the network NW.
The server 20 collects "weather information" for each region and each time and sends it to the forecasting device 100. The weather information includes, for example, information such as weather, maximum temperature, minimum temperature, humidity, rainfall, and wind speed.

The forecasting device 100 predicts the power demand amount in the future prediction target period of the plant A for each unit time based on the measurement result received from the measuring device 10 and the weather information acquired from the server 20. The prediction target period is, for example, from 0:00 to 24:00 on the next day.
As shown in FIG. 1, the prediction device 100 includes a waveform acquisition unit 110, a variable acquisition unit 120, a processing unit 130, and a storage unit 140.

The waveform acquisition unit 110 acquires a waveform representing the power demand amount of the plant A measured in the past in time series.
Specifically, the waveform acquisition unit 110 divides a plurality of demand information received from the measuring device 10 for each predetermined period, and arranges the divided demand information in chronological order to change the time of the power demand amount. Get the waveform represented in the series. Then, the waveform acquisition unit 110 stores and stores the waveform in the storage unit 140.
In the present embodiment, the waveform acquisition unit 110 acquires a daily waveform, for example, with a predetermined period of one day (0:00 to 24:00 each day).

The variable acquisition unit 120 acquires explanatory variables. An explanatory variable is a variable that describes the objective variable. Explanatory variables are also called "independent variables" and can be regarded as the cause of things. In the present embodiment, the explanatory variables indicate factors (characteristics) that affect the amount of electric power demand.
Specifically, the variable acquisition unit 120 acquires "facility information" including information such as the location, holiday, start time, and end time of the plant A stored in advance in the storage unit 140 as an explanatory variable. The calendar is stored in the storage unit 140, and the variable acquisition unit 120 may acquire the day of the week corresponding to the date from the calendar.
Further, "state information" is acquired from the measuring device 10 and "weather information" of the area including the location of the plant A is acquired from the server 20 as explanatory variables.
Further, the variable acquisition unit 120 acquires "planned information" in the prediction target period of the plant A as an explanatory variable. The scheduled information is, for example, when the plant A is a factory, the planned production amount of the plant A in the forecast target period, the planned operating state of the equipment, and the like. The schedule information may be stored in advance in the storage unit 140, or may be input by the operator via the server 20.

The processing unit 130 includes a classification processing unit 131, a probability calculation unit 132, a prediction unit 133, and a plan creation unit 134.
The classification processing unit 131 classifies similar waveforms into one pattern (as one pattern / one type) among the plurality of waveforms stored in the storage unit 140, and the waveforms are classified into the one pattern. Set explanatory variables that show the characteristics common to. The classification processing unit 131 creates a decision tree showing the relationship of what kind of waveform tendency (pattern) appears with respect to the characteristic by performing machine learning using a plurality of waveforms.
The characteristic indicates the value of at least one of the information contained in the state information, the weather information, and the facility information. For example, when many waveforms similar to the holidays of plant A appear, the characteristic common to these waveforms is "holiday". That is, the characteristics common to waveforms are also factors that affect the amount of power demand and change the waveform.
In addition, "common" is not limited to the fact that the values match (for example, the acquired date is a "holiday"), and the values are within a predetermined range (for example, the maximum temperature is "10 degrees or more and less than 15 degrees". ”), The value exceeds a predetermined threshold value (for example, the maximum temperature is“ 30 degrees or more ”,“ less than 0 degrees ”).

The probability calculation unit 132 selects a pattern that matches the explanatory variables in the future prediction target period, and performs statistical processing on the waveforms classified in the pattern, so that the probability of the value that the power demand can take in the prediction target period. Calculate the distribution. For example, in the present embodiment, the probability calculation unit 132 describes an example in which the probability distribution is calculated by using the method of the normal distribution as statistical processing, but the present invention is not limited to this. In another implementation, the probability calculation unit 132 may calculate the probability distribution by using a method such as maximum likelihood estimation, Poisson distribution, t distribution, or binomial distribution as statistical processing.
Further, in the present embodiment, the probability calculation unit 132 further divides the prediction target period into unit times and calculates the probability distribution for each unit time.

The prediction unit 133 predicts the power demand amount in the prediction target period based on the probability distribution calculated by the probability calculation unit 132.

The planning unit 134 creates an electric power procurement plan for the forecast target period of the plant A based on the electric power demand amount predicted by the forecasting unit 133.

The waveform acquired by the waveform acquisition unit 110 and the explanatory variables acquired by the variable acquisition unit 120 are sequentially stored in the storage unit 140. In addition, facility information is stored in advance in the storage unit 140.

(Processing flow of prediction system)
FIG. 2 is a first diagram showing a processing flow of the classification device according to the embodiment of the present invention.
FIG. 3 is a diagram for explaining a classification process according to an embodiment of the present invention.
The prediction device 100 accumulates the waveform of the plant A and performs a process of classifying the waveform before predicting the power demand amount. Hereinafter, the details of the classification process will be described with reference to FIGS. 2 to 3.

As shown in FIG. 2, the waveform acquisition unit 110 acquires a waveform representing the transition of the electric power demand amount in time series based on the plurality of demand information received from the measuring device 10 (step S100).
In the present embodiment, the waveform acquisition unit 110 acquires a waveform in which a plurality of demand information is arranged in time series. Further, the waveform acquisition unit 110 acquires the waveform of each day (from 0:00 to 24:00 each day) by dividing the waveform every day. Further, the waveform acquisition unit 110 stores and stores daily waveforms in the storage unit 140.
At this time, the variable acquisition unit 120 acquires the state information and the weather information of the plant A measured in the same period as each waveform from each of the measuring device 10 and the server 20.

Next, the classification processing unit 131 performs machine learning using a plurality of waveforms stored in the storage unit 140 to create a decision tree (step S101).
The classification processing unit 131 uses machine learning to obtain a waveform that is more similar to any of the characteristics (the value of at least one of the information contained in the state information, the weather information, and the facility information) and the waveform. Classify whether many appear. Then, as shown in FIG. 3, the classification processing unit 131 classifies similar waveforms into one pattern, and sets a decision tree showing characteristics common to the waveforms classified into the one pattern. create.
For example, as shown in FIG. 3, it is assumed that similar waveforms are classified into pattern 1, pattern 2, pattern 3, and so on, respectively. At this time, when many waveforms of the pattern 1 appear when the "maximum temperature is 20 degrees or more", the characteristic that the "maximum temperature is 20 degrees or more" is set as an explanatory variable of the pattern 1.

The prediction device 100 updates the decision tree by repeating the above-mentioned processing every time a new waveform is acquired or at a predetermined timing (for example, every other month).

FIG. 4 is a second diagram showing a processing flow of the classification device according to the embodiment of the present invention.
FIG. 5 is a first diagram for explaining a prediction process according to an embodiment of the present invention.
FIG. 6 is a second diagram for explaining a prediction process according to an embodiment of the present invention.
Hereinafter, with reference to FIGS. 4 to 6, the details of the process in which the prediction device 100 predicts the electric power demand amount and creates the electric power procurement plan will be described.
As shown in FIG. 4, first, the variable acquisition unit 120 acquires the explanatory variables in the future prediction target period of the plant A (step S200).
For example, when predicting the power demand amount of the next day, the variable acquisition unit 120 acquires various information associated with the date of the next day from the storage unit 140 and the server 20. For example, the variable acquisition unit 120 acquires schedule information including the planned production amount of the plant A on the next day and the scheduled operating state of the equipment from the storage unit 140 or the server 20. Further, the variable acquisition unit 120 acquires the weather information of the area including the location of the plant A on the next day from the server 20.

Next, the probability calculation unit 132 estimates and selects the waveform pattern in the prediction target period based on the explanatory variables acquired by the variable acquisition unit 120 and the decision tree created by the classification processing unit 131 (step S201). ).

Next, the probability calculation unit 132 divides the prediction target period by unit time by performing statistical processing on a plurality of waveforms included in the selected pattern, and the probability of the value that the power demand can take for each unit time. Calculate the distribution (step S202).
For example, assuming that the possible value of the power demand follows a normal distribution, the probability calculation unit 132 represents the probability distribution by a normal distribution as shown in FIG.

Next, the prediction unit 133 predicts the lower limit value and the upper limit value of the electric power demand amount included in the range of the predetermined confidence interval based on the normal distribution for each unit time (step S203). For example, when a confidence interval with a confidence level of 97% is set, the lower limit (MIN in FIG. 5) is approximately "μ-2σ", where μ is the average of power demand and σ is the standard deviation from the average. The value and the upper limit value (MAX in FIG. 5) are the values indicated by approximately “μ + 2σ”.
Then, as shown in FIG. 6, the prediction unit 133 arranges the lower limit value and the upper limit value of the electric power demand calculated for each unit time in chronological order, and displays a waveform showing the transition of the lower limit value in the prediction target period (FIG. 6). MIN) and a waveform (MAX in FIG. 6) showing the transition of the upper limit value are predicted.

Next, the planning unit 134 creates an electric power procurement plan for the forecast target period of the plant A based on the electric power demand amount predicted by the forecasting unit 133 (step S204).
For example, the plan creation unit 134 creates a procurement plan in which the contract power is set so that the power of the maximum value or more among the upper limit values of the power demand predicted by the probability calculation unit 132 can be procured. If the power generation device and cogeneration system of the plant A can be used to reduce the amount of power procured (purchased) from the electric power company, the planning unit 134 shall make a procurement plan in consideration of the reduced amount. You may create it.

The prediction device 100 repeats the above-mentioned processing at predetermined timings (for example, each day), predicts the amount of electric power demand in the future prediction target period, and creates an electric power procurement plan.

(Hardware configuration of predictor)
FIG. 7 is a diagram showing a hardware configuration of a prediction device according to an embodiment of the present invention.
Hereinafter, the hardware configuration of the prediction device 100 according to the present embodiment will be described with reference to FIG. 7.

The computer 900 includes a CPU 901, a main storage device 902, an auxiliary storage device 903, an input / output interface 904, and a communication interface 905.
The prediction device 100 described above is mounted on the computer 900. The operation of each part of the prediction device 100 described above is stored in the auxiliary storage device 903 of each computer 900 in the form of a program. The CPU 901 (processing unit 130) reads a program from the auxiliary storage device 903, expands it to the main storage device 902, and executes the above processing according to the program. Further, the CPU 901 secures a storage area corresponding to the storage unit 140 in the main storage device 902 according to the program. Further, the CPU 901 secures a storage area for storing the data being processed in the auxiliary storage device 903 according to the program.
The computer 900 is connected to the external storage device 910 via the input / output interface 904, and the storage unit 140 may be secured in the external storage device 910. Further, the computer 900 is connected to the external storage device 920 via the communication interface 905, and the storage unit 140 may be secured in the external storage device 920.

In at least one embodiment, the auxiliary storage device 903 is an example of a non-temporary tangible medium. Other examples of non-temporary tangible media include magnetic disks, magneto-optical disks, CD-ROMs, DVD-ROMs, semiconductor memories, etc. connected via the input / output interface 904. Further, when this program is distributed to the computer 900 by a communication line, the distributed computer 900 may expand the program to the main storage device 902 and execute the above processing.

Further, the program may be for realizing a part of the above-mentioned functions. Further, the program may be a so-called difference file (difference program) that realizes the above-mentioned function in combination with another program already stored in the auxiliary storage device 903.

(Action effect)
As described above, the prediction device 100 according to the present embodiment includes the waveform acquisition unit 110 that acquires a waveform representing the value of the power demand amount (objective variable) measured in the past in time series, and the plurality of waveforms. A pattern that matches the explanatory variables in the future prediction target period and the classification processing unit 131 that classifies similar waveforms into one pattern and sets explanatory variables showing the characteristics common to the waveforms classified in the one pattern. By selecting It is provided with a prediction unit 133 for predicting the amount of power demand in a period (obtaining an objective variable).
In this way, the prediction device 100 calculates the probability distribution only for the waveforms classified into the patterns matching the explanatory variables in the prediction target period, and obtains the value of the objective variable based on the probability distribution. And can make predictions quickly. Therefore, the time required for calculation and prediction can be shortened as compared with the existing prediction method using, for example, Monte Carlo simulation.
Further, in the above-described embodiment, the prediction device 100 performs classification processing in advance based on a plurality of past waveforms before performing prediction processing of the electric power demand amount. Therefore, when performing the prediction process, the prediction device 100 can easily estimate and select a pattern estimated in the future prediction target period based on the decision tree created in advance as a result of the classification process. can. As a result, the arithmetic processing in the probability arithmetic unit 132 can be further speeded up.
Further, since the forecasting device 100 only needs to be given the power demand amount and the explanatory variables (state information, facility information, weather information of the plant A) measured in the past, a detailed physical model covering the equipment of the plant A is required. Can be omitted. As a result, the forecasting device 100 can reduce the cost of demand forecasting.

Further, the prediction unit 133 obtains an upper limit value and a lower limit value among the values that the power demand can take within the range of the confidence interval predetermined in the prediction target period based on the probability distribution.
By doing so, the prediction device 100 can obtain a highly accurate upper limit value and lower limit value after excluding values with low certainty from the values that the power demand can take in the prediction target period. ..

Further, the prediction device 100 further includes a planning unit 134 that creates a power procurement plan based on the power demand amount predicted by the prediction unit 133.
In this way, since the prediction device 100 creates the procurement plan in the forecast target period based on the predicted power demand amount, the optimal operation of the equipment in the forecast target period becomes possible. For example, by making a contract based on the plan created by the planning unit 134, the contracted power that greatly exceeds the predicted power demand in the forecast target period can be set, or the contracted power can be set to be small and the excess breach of contract can be set. It is possible to reduce the possibility of generating money. As a result, the prediction device 100 can suppress an increase in the cost of procuring electric power.

Although the embodiments of the present invention have been described in detail above, they are not limited to these as long as they do not deviate from the technical idea of the present invention, and some design changes and the like are possible.
For example, in the above-described embodiment, the example in which the prediction system 1 predicts the electric power demand has been described, but the present invention is not limited to this.
In another embodiment, for example, the plant A may be equipment such as a gas turbine, an air conditioner, and a refrigerator provided in the facility. Further, the prediction system 1 may predict the demand amount of energy (heat, etc.) and resources (water, steam, fuel, etc.) in the plant A, or may predict the demand amount and sales of the product to be sold.
In this case, the measuring device 10 has a measuring instrument for measuring the amount of energy, resources, and goods instead of the power meter 11.
In addition, the planning unit 134 of the prediction device 100 creates a procurement plan for energy, resources, and goods (inventory). The planning unit 134 may create a supply plan for energy, resources, and products to be supplied to the plant A based on the demand amount and the sales forecast.

Further, in the above-described embodiment, the mode in which one forecasting device 100 performs demand forecasting in one plant A has been described, but the present invention is not limited to this. In another embodiment, one forecasting device 100 may be connected to measuring devices 10 of a plurality of plants to forecast demand for each of the plurality of plants.

1 Prediction system 10 Measuring device 11 Power meter 12 Sensor unit 100 Predicting device 110 Waveform acquisition unit 120 Variable acquisition unit 130 Processing unit 131 Classification processing unit 132 Probability calculation unit 133 Prediction unit 134 Planning unit 140 Storage unit 20 Server

Claims (6)

A waveform acquisition unit that acquires a waveform that represents the value of the objective variable measured in the past in chronological order,
A classification processing unit that classifies similar waveforms into one pattern among the plurality of the waveforms and sets a first explanatory variable showing characteristics common to the waveforms classified into the one pattern.
A variable acquisition unit that acquires scheduled information including the planned operating status of the plant in the future forecast target period as the second explanatory variable in the forecast target period.
By selecting a pattern in which the first explanatory variable matching the second explanatory variable in the prediction target period is set and performing statistical processing on the waveforms classified into the pattern, the said in the prediction target period. A probability calculation unit that calculates the probability distribution of the values that the objective variable of the plant can take for each unit time obtained by dividing the prediction target period by a predetermined time.
A prediction unit that obtains the value of the objective variable in the prediction target period based on the probability distribution, and
A predictor equipped with. Based on the probability distribution, the prediction unit obtains an upper limit value and a lower limit value among the values that the objective variable can take within a range of a predetermined confidence interval in the prediction target period.
The prediction device according to claim 1. Further provided with a planning unit for creating a supply and demand plan for an object related to the objective variable based on the value of the objective variable obtained by the forecasting unit.
The prediction device according to claim 1 or 2. A measuring device that measures the actual value of the objective variable in the plant,
A prediction device that obtains possible values of the objective variable in the future prediction target period of the plant, and
Equipped with
The prediction device is
A waveform acquisition unit that acquires a waveform that represents the value of the objective variable measured by the measuring device in time series, and
A classification processing unit that classifies similar waveforms into one pattern among the plurality of the waveforms and sets a first explanatory variable showing characteristics common to the waveforms classified into the one pattern.
A variable acquisition unit that acquires scheduled information including the planned operating status of the plant in the future forecast target period as the second explanatory variable in the forecast target period.
By selecting a pattern in which the first explanatory variable matching the second explanatory variable in the prediction target period is set and performing statistical processing on the waveforms classified into the pattern, the said in the prediction target period. A probability calculation unit that calculates the probability distribution of the values that the objective variable of the plant can take for each unit time obtained by dividing the prediction target period by a predetermined time.
A prediction unit that obtains the value of the objective variable in the prediction target period based on the probability distribution, and
Prediction system with. It ’s a computer-executed prediction method.
A waveform acquisition step to acquire a waveform that represents the value of the objective variable measured in the past in chronological order,
A classification processing step of classifying similar waveforms among a plurality of the waveforms into one pattern and setting a first explanatory variable showing characteristics common to the waveforms classified into the one pattern.
A variable acquisition step to acquire scheduled information including the planned operating status of the plant in the future forecast target period as a second explanatory variable in the forecast target period.
By selecting a pattern in which the first explanatory variable matching the second explanatory variable in the prediction target period is set and performing statistical processing on the waveforms classified into the pattern, the said in the prediction target period. A probability calculation step for calculating the probability distribution of the values that the objective variable of the plant can take for each unit time obtained by dividing the prediction target period by a predetermined time.
A prediction step for obtaining the value of the objective variable in the prediction target period based on the probability distribution, and
Prediction method with. Predictor computer,
Waveform acquisition unit that acquires a waveform that represents the value of the objective variable measured in the past in chronological order,
A classification processing unit that classifies similar waveforms into one pattern among a plurality of the above waveforms, and sets a first explanatory variable showing characteristics common to the waveforms classified into the one pattern.
A variable acquisition unit that acquires scheduled information including the planned operating status of the plant in the future forecast target period as the second explanatory variable in the forecast target period.
By selecting a pattern in which the first explanatory variable matching the second explanatory variable in the prediction target period is set and performing statistical processing on the waveforms classified into the pattern, the said in the prediction target period. A probability calculation unit that calculates the probability distribution of the values that the objective variable can take for each unit time obtained by dividing the prediction target period by a predetermined time.
A prediction unit that obtains the value of the objective variable in the prediction target period based on the probability distribution.
A program that functions as.

Images