Demand prediction device, demand prediction system, and demand prediction method

Abstract

This demand prediction device is a demand prediction device that predicts a demanded amount of energy on a data and time for prediction of a consumer, the demand prediction device comprising: an acquisition unit that acquires a past data set including a load item affecting the demanded amount of energy and a past value of a demanded item indicating a demanded amount of energy, and a predicted value of the load item, a similarity determination unit that determines a similarity between the predicted value of the load item and the past value of the load item and extracts the past data set on the basis of the similarity, a regression derivation unit that derives a regression for predicting a demanded amount of energy on the basis of the extracted past data set, and a predicted value calculation unit that calculates a predicted value of the demanded item by inputting the predicted value of the load item into the regression.

Description

Demand forecasting device, demand forecasting system, and demand forecasting method

[0001] The present disclosure relates to a demand prediction device that predicts energy demand at a consumer facility, a demand prediction system having the demand prediction device, and a demand prediction method.

[0002] Conventionally, there has been known a device for predicting the power demand of a facility such as a factory in order to manage the power consumption of the facility (for example, Patent Document 1). The device in Patent Document 1 performs a demand prediction using information on the external environment or information on the internal environment that affects the amount of power demand. The external environment is, for example, temperature. Specifically, the device uses data showing past performance to determine the correlation between temperature and power consumption, and predicts power consumption using this correlation (prediction formula) and the predicted temperature value for the prediction target day, which is the day for which the energy demand prediction is made. Furthermore, the internal environment is, for example, the factory's production plan. In this case, too, the device uses data showing past performance to determine the correlation between the factory's production content and power consumption, and predicts power consumption using this correlation and information on the production plan for the prediction target day.

[0003] International Publication No. 2017 / 051615

[0004] The load on the customer's internal environment may be of a special magnitude that deviates from past performance depending on the target prediction date. For example, if the target prediction date is immediately after the customer facility has returned from a long holiday or if an irregular event is being held, the internal environment may deviate from past performance. In addition, the load on the customer's external environment, such as the outside temperature, may also vary significantly depending on the time of the target prediction date. In such cases, the prediction accuracy of the device disclosed in Patent Document 1 may decrease.

[0005] The present disclosure has been made to solve the above-mentioned problems, and aims to provide a demand forecasting system, a demand forecasting device, and a demand forecasting method that improve the accuracy of demand forecasting.

[0006] The demand forecasting device according to the present disclosure is a demand forecasting device that forecasts the energy demand of a consumer at a target forecast date and time, and includes an acquisition unit that acquires a past dataset consisting of load items that affect the energy demand and past values ​​of demand items that indicate the energy demand, and a predicted value of the load item; a similarity determination unit that determines the similarity between the predicted value of the load item and the past value of the load item and extracts a past dataset based on the similarity; a regression equation derivation unit that derives a regression equation for forecasting the energy demand based on the extracted past dataset; and a predicted value calculation unit that calculates the predicted value of the demand item by inputting the predicted value of the load item into the regression equation.

[0007] The demand forecasting system of the present disclosure includes a demand forecasting device, a storage device that stores past data sets and predicted values ​​of load items, and a data acquisition device that acquires the past data sets and predicted values ​​of load items and stores them in the storage device.

[0008] The demand forecasting method disclosed herein is a demand forecasting method that forecasts a consumer's energy demand at a target forecast date and time, and obtains a past dataset consisting of load items that affect energy demand and past values ​​of demand items that indicate energy demand, and a forecast value of the load item, determines the similarity between the forecast value of the load item and the past value of the load item, extracts a past dataset based on the similarity, derives a regression equation for forecasting energy demand based on the extracted past dataset, and calculates the forecast value of the demand item by inputting the forecast value of the load item into the regression equation.

[0009] The demand forecasting device, demand forecasting system, and demand forecasting method disclosed herein forecast energy demand based on a data set with a high degree of similarity between the load items and the target forecast date and time, thereby improving the accuracy of energy demand forecasts.

[0010] FIG. 1 is a schematic configuration diagram showing a demand forecasting system according to a first embodiment. FIG. 2 is a diagram for explaining overall similarity. FIG. 3 is a hardware configuration diagram of a demand forecasting device according to the first embodiment. FIG. 4 is a flowchart showing a demand forecasting method according to the first embodiment. FIG. 5 is a flowchart showing a demand forecasting method according to the first embodiment. FIG. 6 is a schematic configuration diagram showing a demand forecasting system according to a second embodiment. FIG. 7 is a flowchart showing a demand forecasting method according to the second embodiment. FIG. 8 is a flowchart showing a demand forecasting method according to the second embodiment. FIG. 9 is a flowchart showing a demand forecasting method according to the second embodiment. FIG. 10 is a flowchart showing a demand forecasting method according to the second embodiment. FIG. 11 is a flowchart showing a demand forecasting method according to the third embodiment. FIG. 12 is a flowchart showing a demand forecasting method according to the third embodiment. FIG. 13 is a flowchart showing a demand forecasting method according to the third embodiment. FIG. 14 is a flowchart showing a demand forecasting method according to the third embodiment. FIG. 15 is a flowchart showing a demand forecasting method according to the third embodiment.

[0011] 1 is a schematic configuration diagram showing a demand forecasting system 1 according to embodiment 1. The demand forecasting system 1 includes a data acquisition device 2, a storage device 3, a demand forecasting device 4, and a control instruction device 5. The demand forecasting system 1 is used to forecast the amount of energy demand of a consumer at a target forecast date and time.

[0012] A consumer is, for example, a facility such as a factory, office, hotel, or commercial building, a residence such as a detached house or condominium, or a collection of these located in a specific area. The prediction target date and time is the date and time for which energy demand is predicted, and is, for example, a time period (24 hours) on the day for which the prediction is made. The prediction target date and time may be limited to a specific time period within a day to predict energy demand. The prediction target date and time may also be set to a time period longer than a day to predict energy demand. Here, energy refers to electricity, heat, etc. that needs to be supplied to the consumer. In other words, energy demand at the prediction target date and time refers to the amount of electricity, heat, etc. that needs to be supplied to the consumer per day.

[0013] The data acquisition device 2, which may be a computer, acquires data indicating energy demand measured in the past and past data on various factors affecting the energy demand. The data acquisition device 2 and the storage device 3 are connected via a network such as the Internet. The data acquisition device 2 classifies the acquired data into multiple data items and transmits the data to the storage device 3 for storage. Among the data items, data items indicating energy demand are referred to as demand items, and data items regarding factors affecting the energy demand are referred to as load items. Examples of data items include electricity demand data and heat demand data, as well as facility usage data, equipment operation data, and weather data, which will be described later. Of these, electricity demand data and heat demand data correspond to demand items, and facility usage data, equipment operation data, and weather data correspond to load items. Note that, hereinafter, values ​​indicated by data on past events may be referred to as past values, regardless of the data acquisition method.

[0014] The data acquisition device 2 acquires data using various methods depending on the type of data. Specifically, the data acquisition device 2 is connected to an energy management system that monitors and manages the supply of energy to consumers. The data acquisition device 2 acquires past values ​​of electricity demand data and heat demand data from the energy management system. The electricity demand data indicates a date and time and the amount of electricity to be supplied to the consumer on that date and time. The heat demand data indicates a date and time and the amount of heat to be supplied to the consumer on that date and time.

[0015] The data acquisition device 2 acquires past values ​​of facility usage data by accessing a data server of a customer via the Internet. The facility usage data indicates the usage schedule of the facility. For example, if the facility is an office, the facility usage data indicates the date and time and the usage status of a conference room at that date and time. Similarly, if the facility is a hotel, the facility usage data includes the date and time and the usage status of a guest room at that date and time. Note that the facility usage data may also indicate the operating status and utilization rate of the entire facility by integrating the usage status of multiple conference rooms or guest rooms, etc.

[0016] The data acquisition device 2 is connected to each piece of equipment at a consumer's facility and acquires past values ​​of equipment operation data indicating the operating status of each piece of equipment. The equipment may be a home appliance such as an air conditioner or a water heater installed at the consumer's facility, or a factory machine. For example, if the equipment is an air conditioner, the equipment operation data indicates the date and time, the ON / OFF state, and the set temperature at that date and time. Similarly, if the equipment is a water heater, the equipment operation data indicates the date and time, the ON / OFF state, and the hot water temperature at that date and time. The data acquisition device 2 may be connected to a sensor that measures physical quantities that change in relation to the operation of each piece of equipment, and acquire these physical quantities as equipment operation data. In this case, the sensor or part of the data acquisition device 2 may be built into each piece of equipment.

[0017] The data acquisition device 2 acquires past weather data via the Internet. The weather data includes the date and time, the weather in the area where the consumer is located at that date and time, the outside temperature and humidity, the amount of solar radiation, and the like.

[0018] Furthermore, the data acquisition device 2 acquires data on demand items for which the state at the target prediction date and time can be predicted, and transmits it to the storage device 3 for storage. For example, in the case of facility usage data, if the facility is an office, the state at the target prediction date and time can be predicted by referring to the reservation status of conference rooms. Similarly, in the case of a hotel, the state at the target prediction date and time can be predicted by referring to the reservation status of guest rooms. In addition, in the case of weather data, the state at the target prediction date and time can be predicted by referring to a weather forecast. Furthermore, in the case of equipment operation data, if an operation plan for each piece of equipment is determined in advance, the state at the target prediction date and time can be predicted by referring to this. Note that, hereinafter, a value indicated by data predicted for a future event may be referred to as a predicted value, regardless of the method of data acquisition.

[0019] The storage device 3 is composed of a non-volatile semiconductor memory such as a read-only memory (ROM), a flash memory, an erasable and programmable ROM (EPROM), or an electrically erasable and programmable ROM (EEPROM). The storage device 3 stores past values ​​of data transmitted from the data acquisition device 2 in chronological order based on the time period covered by the data for each data item. The past values ​​of the data for multiple data items stored in chronological order are separated by set time periods and treated as a single past data set. The set time period for a past data set is, for example, 24 hours. The date and time covered by the data included in the past data set is referred to as the target acquisition date and time.

[0020] Furthermore, the storage device 3 stores the predicted values ​​of the demand item data transmitted from the data acquisition device 2 for each data item and for each prediction target date and time. The predicted values ​​of the data of multiple data items are treated as one prediction data set for each prediction target date and time. In the following, when there is no need to distinguish between the past data set and the prediction data set, they will simply be referred to as the data set.

[0021] In the storage device 3, the data sets are classified by attribute. The attribute is used to classify the data sets into summer, mid-season, and winter seasons based on the target acquisition date and time of the past data set and the target prediction date and time of the prediction data set. The data sets may also be classified into weekdays and holidays.

[0022] The demand prediction device 4 is, for example, a computer, and predicts the energy demand of a consumer, i.e., calculates predicted values ​​of demand items. The calculated energy demand is transmitted to the control instruction device 5. The demand prediction device 4 has a first acquisition unit 41, a similarity determination unit 42, a regression equation derivation unit 43, and a predicted value calculation unit 44. The storage device 3 and the demand prediction device 4 are connected via a network such as the Internet. The demand prediction device 4 and the control instruction device 5 are also connected via a network such as the Internet.

[0023] The first acquisition unit 41 acquires a predetermined amount of past data sets and a prediction data set for the prediction target date and time from the storage device 3 via the network. The predetermined amount is, for example, the entire amount of past data sets stored in the storage device 3.

[0024] The similarity determination unit 42 determines the similarity of load items between each acquired past data set and the prediction data set, and extracts from each acquired past data set a past data set with a high similarity between the load items and the prediction target date and time. Specifically, the similarity determination unit 42 determines the similarity between the predicted value of the load item at the prediction target date and time and the past value of the load item in a certain past data set. The similarity is calculated, for example, by calculating the error between the predicted value of the load item and the past value of the load item, and the smaller the error, the higher the similarity is determined. The error here is, for example, RMSE (Root Mean Squared Error). The similarity determination unit 42 determines the similarity for each load item and further determines the similarity of the overall past data set from these similarities. The similarity determination unit 42 determines the similarity of the overall past data set for all acquired past data sets and compares them. The similarity determination unit 42 extracts a predetermined number of past data sets in descending order of overall similarity. The predetermined number is an arbitrary number that is determined in advance by the user.

[0025] FIG. 2 is a diagram illustrating the overall similarity. A method for calculating the overall similarity uses the distance from the origin when the similarity is plotted on a graph, as shown in FIG. 2 . In the example of FIG. 2 , the RMSE value of the weather data and the RMSE value of the facility usage data are calculated separately, and a corresponding point on a two-dimensional plane is plotted as the overall RMSE. The overall RMSE is also plotted for each of multiple past data sets. That is, the black and white circles represent the overall RMSE of past data sets acquired at different dates and times. The plotted overall RMSE values ​​are compared based on their distance from the origin, and the closer they are to the origin, the higher the overall similarity is determined to be. In the example of FIG. 2 , the past data sets plotted with white circles have a smaller overall error with the forecast data set than the past data sets plotted with black circles, and are therefore considered to have a higher overall similarity.

[0026] The regression equation deriving unit 43 derives a regression equation for predicting energy demand based on all past data sets extracted by the similarity determining unit 42. Here, in all extracted past data sets, the regression equation is derived using the values ​​of each load item as an explanatory variable and the values ​​of the demand items as a response variable.

[0027] The predicted value calculation unit 44 calculates the predicted value of the demand item by inputting the predicted value of the load item into the regression equation derived by the regression equation derivation unit 43, and transmits it to the control instruction device 5 via the network.

[0028] The control instruction device 5, which is, for example, a computer, converts the calculated predicted values ​​of the demand items into control instructions for controlling each facility of the customer and transmits them to a device that controls each facility. The control instructions may include an operation plan for each facility optimized using the predicted values ​​of the demand items. They may also include control values ​​to instruct the operation of the facility.

[0029] Fig. 3 is a hardware configuration diagram of the demand prediction device 4 according to the first embodiment. As shown in Fig. 3, the demand prediction device 4 is composed of a processor 101 such as a CPU and a memory 102. Each function of the demand prediction device 4 is realized by the processor 101 and the memory 102. Fig. 3 shows that the processor 101 and the memory 102 are communicably connected to each other via a bus 103. Note that if the data acquisition device 2 and the control instruction device 5 are also composed of computers, they have the same configuration as the demand prediction device 4.

[0030] The functions of the demand prediction device 4 are realized by software, firmware, or a combination of software and firmware. The software and firmware are written as programs and stored in the memory 102. The processor 101 realizes the functions of each means by reading and executing the programs stored in the memory 102.

[0031] The memory 102 may be a non-volatile semiconductor memory such as a ROM, flash memory, EPROM, or EEPROM. Alternatively, a volatile semiconductor memory such as a RAM (Random Access Memory) may be used as the memory 102. Alternatively, the memory 102 may be a removable recording medium such as a magnetic disk, a flexible disk, an optical disk, a CD (Compact Disc), an MD (Mini Disc), or a DVD (Digital Versatile Disc).

[0032] FIG. 4 is a flowchart showing a demand forecasting method according to the first embodiment. A general flow of calculating energy demand will be described using FIG. 4 . First, the first acquisition unit 41 of the demand forecasting device 4 acquires a predetermined amount of past data sets stored in the storage device 3 and a forecast data set for the target forecast date and time (step S1). The similarity determination unit 42 determines the overall similarity of the past data sets and extracts past data sets that are highly similar to the target forecast date and time based on this similarity (step S2). Next, the regression equation derivation unit 43 derives a regression equation for calculating a forecast value of a demand item based on the extracted past data sets (step S3). Then, the forecast value calculation unit 44 calculates a forecast value of a demand item from the forecast value of a load item for the target forecast date and time based on the regression equation derived by the regression equation derivation unit 43 (step S4).

[0033] Next, the determination of similarity and the extraction of past data sets will be described in detail. FIG. 5 is a flowchart showing a demand forecasting method according to the first embodiment. FIG. 5 shows the process of step S2 in FIG. 4 in detail. Note that, here, an example is taken in which the set time period of the past data sets is 24 hours. First, the similarity determination unit 42 selects a past data set that is one day before the target prediction date and time (step S201). Next, the similarity determination unit 42 determines whether the attributes of this past data set match the attributes of the prediction data set. If the attributes do not match (step S202: NO), the similarity determination unit 42 does not determine the similarity of this past data set and performs the process of step S206.

[0034] If the attributes match (step S202: YES), the similarity determination unit 42 determines the similarity between the past value included in the past data set and the predicted value at the prediction target date and time for one type of load item included in the acquired past data set (step S203).The similarity determination unit 42 then determines whether the similarity has been determined for all types of load items included in the acquired past data set (step S204).If the similarity has not been determined for all types of load items (step S204: NO), the similarity determination unit 42 repeats the process of step S203 for unselected load items until the similarity has been determined for all types of load items.

[0035] If similarity is determined for all load items (step S204: YES), the similarity determination unit 42 determines the overall similarity (step S205). Then, the similarity determination unit 42 determines whether the overall similarity determination for all acquired past data sets has been completed (step S206). If the overall similarity determination for all acquired past data sets has not been completed (step S206: NO), the similarity determination unit 42 repeats the processes of steps S201 to S205 by going back one day at a time in the acquisition target date and time of the past data sets until the overall similarity determination for all acquired past data sets has been completed.

[0036] When the determination of the overall similarity of all acquired past data sets has been completed (step S206: YES), the similarity determination unit 42 extracts past data sets for a predetermined number of days in order of highest overall similarity (step S207).

[0037] As described above, the demand forecasting device 4 and the demand forecasting method according to the first embodiment forecast energy demand based on past data sets with high similarity in load items with respect to the target forecast date and time. This improves the accuracy of energy demand forecasts. In particular, even in cases where load fluctuations are unusual, it is possible to forecast energy demand in accordance with the load.

[0038] Furthermore, the similarity of the overall load items is determined by taking into consideration both data corresponding to the external environment of the consumer, such as weather data, and data corresponding to the internal environment of the consumer, such as facility usage data or equipment operation data. This makes it possible to improve the accuracy of energy demand prediction even in special situations where load fluctuations deviate from past performance, such as when a facility has just returned from a long holiday, when an irregular event is being held, or when the outside temperature changes suddenly.

[0039] Embodiment 2. Fig. 6 is a schematic configuration diagram showing a demand forecasting system 1A according to embodiment 2. As shown in Fig. 6, a demand forecasting device 4A according to embodiment 2 differs from embodiment 1 in that it includes a data classification unit 45. In embodiment 2, the same components as those in embodiment 1 are denoted by the same reference numerals and their description will be omitted, and the description will focus on the differences from embodiment 1.

[0040] The data division unit 45 divides the past data sets extracted by the similarity determination unit 42 into multiple sections based on time. Specifically, the data division unit 45 acquires the operation start time and operation end time of the facility, which is the consumer, based on the facility usage data for all of the extracted past data sets. Then, the data division unit 45 divides all of the extracted past data sets into three sections: a time before the facility operation starts, a time during operation, and a time after the operation ends. Note that the data division unit 45 may divide the past data sets based on the operation start time and operation end time of the facility specified by the user, rather than the facility usage data. As described above, each past data set is divided by a set time. For example, if one day is divided into sections corresponding to one past data set, the past data sets are divided into sections corresponding to three time periods within the day.

[0041] The regression equation derivation unit 43 derives a regression equation for each section divided by the data division unit 45. That is, the regression equation is derived based on data for sections before the facility started operation in all of the extracted past data sets. Similarly, the regression equation is derived based on data for sections during operation in all of the extracted past data sets. Furthermore, the regression equation is derived based on data for sections after the facility stopped operation in all of the extracted past data sets.

[0042] The predicted value calculation unit 44 calculates the predicted value of the demand item by inputting the predicted value of the load item at the prediction target date and time into the regression equation for each interval derived by the regression equation derivation unit 43.

[0043] The control command device 5 determines the regression equation corresponding to the section that matches the load state of the consumer at the time of control, converts the predicted value calculated by this regression equation, and transmits a control command.

[0044] FIG. 7 is a flowchart showing a demand forecasting method according to the second embodiment. A general flow of calculating energy demand will be described using FIG. 7 . First, the first acquisition unit 41 of the demand forecasting device 4A acquires a predetermined amount of past data sets stored in the storage device 3 and a forecast data set at the target forecast date and time (step S11). The similarity determination unit 42 determines the overall similarity of the past data sets and extracts past data sets that are highly similar to the target forecast date and time based on this similarity (step S12). The data division unit 45 then divides the extracted past data sets into multiple intervals (step S13). Next, the regression equation derivation unit 43 derives a regression equation for calculating a forecast value of a demand item for each interval of the extracted past data sets (step S14). The forecast value calculation unit 44 then calculates a forecast value of a demand item from a forecast value of a load item at the target forecast date and time based on the regression equation derived by the regression equation derivation unit 43 (step S15).

[0045] Next, the classification of past data sets will be described in detail. FIG. 8 is a flowchart showing a demand forecasting method according to the second embodiment. FIG. 8 illustrates the process of step S13 in FIG. 7 in detail. First, the data classification unit 45 acquires the facility operation start time by referring to the facility usage data in each extracted past data set or a user instruction (step S1301). Similarly, the data classification unit 45 acquires the facility operation end time by referring to the facility usage data in each extracted past data set or a user instruction (step S1302). Then, the data classification unit 45 divides each past data set into three based on the facility operation start time and operation end time (step S1303).

[0046] The derivation of the regression equation will now be described in detail. FIG. 9 is a flowchart showing a demand forecasting method according to the second embodiment. FIG. 9 illustrates the process of step S14 in FIG. 7 in detail. First, the regression equation deriving unit 43 selects one of the divided sections (step S1401). Next, the regression equation deriving unit 43 derives a regression equation for the selected section (step S1402). The regression equation deriving unit 43 determines whether regression equations have been derived for all divided sections (step S1403). If regression equations have not been derived for all divided sections (step S1403: NO), the regression equation deriving unit 43 selects an unselected section and repeats the process of step S1402 until regression equations have been derived for all divided sections.

[0047] Next, the calculation of the predicted value of the demand item will be described in detail. FIG. 10 is a flowchart showing a demand forecasting method according to the second embodiment. FIG. 10 illustrates the process of step S15 in FIG. 7 in detail. First, the predicted value calculation unit 44 selects one of the divided sections (step S1501). Next, the predicted value calculation unit 44 calculates a predicted value of the demand item using a regression equation corresponding to the selected section (step S1502). The predicted value calculation unit 44 determines whether predicted values ​​of the demand item have been calculated for all divided sections (step S1503). If predicted values ​​of the demand item have not been calculated for all divided sections (step S1503: NO), the predicted value calculation unit 44 selects an unselected section and repeats the process of step S1502 until predicted values ​​of the demand item have been calculated for all divided sections.

[0048] As described above, according to the second embodiment, the past data set is divided by time period, and multiple types of regression equations are constructed. Therefore, the accuracy of the predicted value can be improved by taking into account the changing tendency of the correlation between the explanatory variables and the dependent variable depending on the time period of the target prediction date and time. In particular, because the past data set is divided according to the operating status of the facility, the correlation between the explanatory variables and the dependent variable can be improved more than when the past data set is simply divided by fixed time period.

[0049] Note that the past data set is not divided when the facility is not operating, etc. In this case, the regression equation deriving unit 43 and the prediction value calculation unit 44 derive one regression equation for the entire past data set and calculate the prediction value of the demand item, as in the case described in the first embodiment.

[0050] (Variation 1 of Embodiment 2) Variation 1 of Embodiment 2 differs from Embodiment 2 in the method of dividing the past data set. The data division unit 45 divides the past data set into multiple sections by referring to the operating state of the equipment installed in the consumer based on the equipment operation data. The operating state indicates either an ON state in which the equipment is operating, or an OFF state in which the equipment is not operating.

[0051] The data division unit 45 divides the past data set based on, for example, the start time of the ON state and the start time of the OFF state within the target time of the past data set. Specifically, the data division unit 45 determines that the equipment is in the OFF state at the first time of the target time of the past data set, or during the time period from the start time of the OFF state to the start time of the ON state. Similarly, the data division unit 45 determines that the equipment is in the ON state during the time period from the start time of the ON state to the start time of the OFF state. Then, the past data set is divided into multiple intervals based on the time period during which the equipment is in the ON state and the time period during which the equipment is in the OFF state. In this case, if the length of the OFF state is less than a predetermined time, it does not need to be treated as an OFF state time period when dividing the past data set. The predetermined time is, for example, 60 minutes.

[0052] For example, if the start time of the ON state is 7:00 and the start time of the OFF state is 12:00, the data division unit 45 divides the past data set into three intervals, with 0:00 to 7:00 as the OFF state time period, 7:00 to 12:00 as the ON state time period, and 12:00 to 23:59 as the OFF state time period.

[0053] Furthermore, if an OFF state that lasts for a predetermined period of time or longer occurs multiple times during the target time period of the past data set, the data division unit 45 increases the number of divisions of the past data set according to the number of OFF states. For example, if the start time of the first ON state is 7:00, the start time of the first OFF state is 12:00, the start time of the second ON state is 13:00, and the start time of the second OFF state is 17:00, the data division unit 45 divides the past data set as follows: That is, the past data set is divided into five intervals, with 0:00 to 7:00 as the OFF state time period, 7:00 to 12:00 as the ON state time period, 12:00 to 13:00 as the OFF state time period, 13:00 to 17:00 as the ON state time period, and 17:00 to 23:59 as the OFF state time period.

[0054] The regression equation derivation unit 43 derives a regression equation for each section divided by the data division unit 45. That is, the regression equation is derived based on data for sections in which all of the extracted past data sets have equipment in an ON state. Similarly, the regression equation is derived based on data for sections in which all of the extracted past data sets have equipment in an OFF state. Note that different regression equations may be derived for each number of ON and OFF states.

[0055] Next, the classification of past data sets will be described in detail. FIG. 11 is a flowchart showing a demand forecasting method according to Variation 1 of Embodiment 2. FIG. 11 illustrates in detail the processing of step S13 in FIG. 7 described in Embodiment 2. First, the data classification unit 45 references the equipment operation data of each past data set extracted by the similarity determination unit 42 and obtains the start time of the ON state (step S1311). Next, the data classification unit 45 references the equipment operation data of each past data set extracted by the similarity determination unit 42 and obtains the start time of the OFF state (step S1312). Then, the data classification unit 45 divides the past data set into multiple intervals based on the obtained start times of the ON state and the OFF state (step S1313).

[0056] As described above, according to the first modification of the second embodiment, the past data set is also divided by time period, and multiple types of regression equations are constructed. This makes it possible to improve the accuracy of the predicted value by taking into account the changing tendency of the correlation between the explanatory variables and the dependent variable depending on the time period of the target prediction date and time. In particular, because the past data set is divided according to the operating state of the equipment, it is possible to improve the correlation between the explanatory variables and the dependent variable more than when the past data set is simply divided by fixed time period.

[0057] (Variation 2 of Embodiment 2) Variation 2 of Embodiment 2 differs from Embodiment 2 and Variation 1 of Embodiment 2 in the method of dividing the past data set. The data dividing unit 45 extracts the number of intervals X and the time at which the correlation coefficient between the demand item and the load item in each interval is equal to or greater than a predetermined value, and divides the past data set into a plurality of intervals based on the extracted number of intervals X and the time.

[0058] Next, the classification of past data sets will be described in detail. FIG. 12 is a flowchart showing a demand forecasting method according to a second variation of the second embodiment. FIG. 13 is a flowchart showing a demand forecasting method according to a second variation of the second embodiment. FIGS. 12 and 13 show details of the process of step S13 in FIG. 7 described in the second embodiment in FIG. 11. FIGS. 12 and 13 show consecutive processes. First, the data classification unit 45 acquires past values ​​of each load item and past values ​​of each demand item from all past data sets extracted by the similarity determination unit 42 (step S1321). Next, the data classification unit 45 performs multiple regression analysis between the acquired data items and calculates correlation coefficients between each load item and demand item across the entire extracted past data set (step S1322). In this case, the past values ​​of each load item selected by the inference unit 72 in the multiple regression analysis are used as explanatory variables, and the past values ​​of the demand items are used as target variables.

[0059] Next, the data division unit 45 sets a threshold value for the correlation coefficient for each load item (step S1323). This threshold value is used in subsequent processing and refers to an arbitrary numerical value input in advance by the user. Here, the data division unit 45 compares the magnitude relationship between the correlation coefficient of each load item and the threshold value corresponding to the load item (step S1324), and determines whether or not there are a predetermined number of data items whose correlation coefficient is equal to or greater than the threshold value (step S1325). This predetermined number of items is an arbitrary number of items set in advance by the user. If there are a predetermined number of data items whose correlation coefficient is equal to or greater than the threshold value (step S1325: YES), the processing ends without dividing the past data set.

[0060] If the number of data items whose correlation coefficient is equal to or greater than the threshold is less than a predetermined number (step S1325: NO), the data partitioning unit 45 calculates the correlation coefficient between the load item and the demand item for each case while changing the number of intervals X and the time at which the past data set is divided. Then, a partitioning pattern in which the correlation coefficient satisfies a predetermined condition is searched for. Then, the number of intervals X and the time of the partitioning pattern in which the correlation coefficient satisfies the predetermined condition are extracted. First, the number of intervals X for partitioning the past data set is set to 2 (step S1326). Next, the data partitioning unit 45 divides all past data sets into the number of intervals X at a common time (step S1327). For example, if the number of intervals X is 2, a one-day past data set is divided into two intervals. The minimum unit of time for partitioning is set in advance by the user. Furthermore, the time at which the past data set is divided may be selected sequentially from the beginning of the past data set, or may be selected randomly. For example, if the minimum time unit for division is 30 minutes and the past data set is divided into two intervals from the beginning, the intervals are divided into two, firstly into an interval from 0:00 to 0:29 and another interval from 0:30 to 23:59. Then, the data division unit 45 performs multiple regression analysis between the data items acquired in step S1321 within each divided interval, and calculates a correlation coefficient between each load item and demand item for the entire extracted past data set (step S1328).

[0061] Next, the data division unit 45 compares the correlation coefficient of each load item with the threshold value corresponding to each load item (step S1329) and determines whether or not a predetermined number of data items whose correlation coefficient is equal to or greater than the threshold value exist in each interval (step S1330). This determination is the same as the processing in step S1325. If a predetermined number of data items whose correlation coefficient is equal to or greater than the threshold value exist in all intervals (step S1330: YES), the data division unit 45 extracts the number of intervals divided in the processing in step S1327 and the time selected at the time of division (step S1331), and ends the processing.

[0062] If there is even one section in which the number of data items with correlation coefficients equal to or greater than the threshold is less than the predetermined number (step S1330: NO), the data division unit 45 determines whether all patterns of time have been tried when dividing the past data set (step S1332). For example, if the past data set covers 24 hours from 0:00 to 23:59, the minimum time unit for division is 30 minutes, and the number of sections X is 2, the time patterns will be 0:30, 1:00, ..., 23:00, 23:30, for a total of 47. If all patterns of time have not been tried (step S1332: NO), the data division unit 45 changes the time to be divided (step S1333) and executes steps S1328 to S1330 again. In this case, the time to be divided may be selected from the top of the unselected time slots, or may be selected randomly.

[0063] If all patterns of time division have been tried (step S1332: YES), the data division unit 45 determines whether the number of sections X has reached the maximum number of sections that can be divided (step S1334). For example, if the past data set covers 24 hours from 0:00 to 23:59 and the minimum time division unit is 30 minutes, the maximum number of sections X that can be divided into sections from 0:00 to 0:29, from 0:30 to 0:59, ..., from 23:00 to 23:29, and from 23:30 to 23:59 is 48 sections in total. If the number of sections X has not reached the maximum number of sections that can be divided (step S1334: NO), the data division unit 45 increments the number of sections X by 1 (step S1335) and repeats the processing of steps S1327 to S1330.

[0064] If the number of intervals X reaches the upper limit of the number of intervals that can be divided (step S1334: YES), the data division unit 45 extracts the number of intervals X and the time selected at the time of division when the average value of the minimum correlation coefficient for each interval was the smallest among the processing executed so far (step S1336). The minimum correlation coefficient is the minimum value of the correlation coefficient for each load item within each interval calculated in step S1328. For example, suppose a past data set is divided into two intervals, interval α and interval β, and the load items are data item A and data item B. In interval α, the correlation coefficient for data item A is 0.45 and the correlation coefficient for data item B is 0.55. In interval β, the correlation coefficient for data item A is 0.70 and the correlation coefficient for data item B is 0.65. In this case, the minimum correlation coefficient for interval α is 0.45 for data item A, and the minimum correlation coefficient for interval β is 0.65 for data item B. Therefore, the data division unit 45 extracts the number of sections X and the time of division when the average value of the correlation coefficient 0.45 for data item A and the correlation coefficient 0.65 for data item B is minimum.

[0065] As described above, according to the second modification of the second embodiment, the past data set is also divided by time period, and multiple types of regression equations are constructed. This makes it possible to improve the accuracy of the forecast value by taking into account the changing tendency of the correlation between the explanatory variables and the dependent variable depending on the time period of the target forecast date and time. In particular, since the past data set is divided so that the correlation coefficient between the demand items and the load items within each period is equal to or greater than a predetermined value, the correlation between the explanatory variables and the dependent variable can be improved more than when the past data set is simply divided by fixed time period.

[0066] Third Embodiment Fig. 14 is a schematic configuration diagram showing a demand forecasting system 1B according to a third embodiment. As shown in Fig. 14, a demand forecasting device 4B of the demand forecasting system 1B differs from that of the second embodiment in that it includes a learning device 6 and an inference device 7. Artificial intelligence (AI) is used in the processing of the learning device 6 and the inference device 7. In the third embodiment, the same parts as those in the second embodiment are denoted by the same reference numerals and their description is omitted, and the following description will focus on the differences from the second embodiment.

[0067] The demand forecasting device 4B of the demand forecasting system 1B includes a calculation device 40, a learning device 6, and an inference device 7. The calculation device 40 includes a first acquisition unit 41, a similarity determination unit 42, a regression equation derivation unit 43, a predicted value calculation unit 44, and a data classification unit 45, all of which are described in the third embodiment.

[0068] The learning device 6 is, for example, a computer, and includes a second acquisition unit 61 and a model generation unit 62. The second acquisition unit 61 acquires, as a learning dataset, a past dataset including past values ​​of load items and past values ​​of demand items corresponding to the load items, stored in the storage device 3 via a network. The model generation unit 62 uses the learning dataset to generate a trained model for inferring the type of load item to be used for determining similarity from the load items included in the prediction dataset. Specifically, the model generation unit 62 calculates a correlation coefficient with the demand items for each load item included in the learning dataset to create a model. The model generation unit 62 stores the generated trained model in the storage device 3. If the past values ​​of the load items or demand items have not been updated since the previous model generation, model generation may be omitted.

[0069] The inference device 7 is, for example, a computer, and includes a third acquisition unit 71 and an inference unit 72. The third acquisition unit 71 acquires the types of load items included in the trained model and the prediction dataset stored in the storage device 3 via a network. The load items included in the prediction dataset are candidates for load items used to determine the similarity. The inference unit 72 selects load items to use to determine the similarity based on the trained model and the types of load items input from the third acquisition unit 71. Specifically, the inference unit 72 inputs the types of load items input from the third acquisition unit 71 into the trained model, thereby obtaining a predetermined number of types of load items that have a high correlation coefficient with the demand items output by the trained model. The number of load items to be output is set in advance by the user. The inference unit 72 transmits the types of load items to use to determine the similarity to the demand prediction device 4B.

[0070] FIG. 15 is a flowchart showing a demand forecasting method according to the third embodiment. A general flow of calculating energy demand will be described using FIG. 15 . First, the first acquisition unit 41 acquires a predetermined amount of past data sets stored in the storage device 3 and a prediction data set for the target prediction date and time (step S21). Next, the learning device 6 generates a trained model for inferring data items to be used in determining similarity from the load items included in the prediction data set using the training data set acquired by the second acquisition unit 61 of the learning device 6 (step S22). Next, the inference device 7 selects load items to be used in determining similarity based on the trained model and the prediction data set acquired from the third acquisition unit 71 of the inference device 7 (step S23). Furthermore, the similarity determination unit 42 determines the overall similarity of the past data sets based on the selected load items, and extracts past data sets that are highly similar to the target prediction date and time based on this similarity (step S24). Furthermore, the data division unit 45 divides the extracted past data sets into multiple sections (step S25). Next, the regression equation deriving unit 43 derives a regression equation for calculating a predicted value of the demand item for each interval of the extracted past data set (step S26).Then, the predicted value calculating unit 44 calculates a predicted value of the demand item from the predicted value of the load item at the prediction target date and time based on the regression equation derived by the regression equation deriving unit 43 (step S27).

[0071] The generation of a trained model and the selection of load items will now be described in more detail. FIG. 16 is a flowchart illustrating a demand forecasting method according to the third embodiment. FIG. 16 illustrates the details of steps S22 and S23 in FIG. 15 . First, the model generation unit 62 of the learning device 6 selects one type of load item from the training dataset acquired by the second acquisition unit 61 (step S2201). Next, the model generation unit 62 acquires past values ​​of the selected load item and past values ​​of the demand items using a past dataset for a period one day prior to the target prediction date and time as the training dataset (step S2202). Next, the model generation unit 62 calculates a correlation coefficient between the past values ​​of the selected load item and the past values ​​of the demand items across the entire training dataset (step S2203). The model generation unit 62 determines whether correlation coefficients have been calculated for all types of load items included in the training dataset (step S2204). If correlation coefficients have not been calculated for all types of load items included in the training dataset (step S2204: NO), unselected load items are selected and the processes of steps S2201 to S2203 are repeated until correlation coefficients have been calculated for all types of load items included in the training dataset. If correlation coefficients have been calculated for all types of load items included in the training dataset (step S2204: YES), generation of the trained model is completed. Then, the inference unit 72 of the inference device 7 inputs the types of load items included in the prediction dataset acquired by the third acquisition unit 71 into the trained model, thereby selecting a predetermined number of load items having high correlation coefficients with demand items (step S2301).

[0072] According to the third embodiment, the type of load item used to determine the similarity is selected based on the correlation coefficient between the load item and the demand item, which can further improve the accuracy of the similarity determination and, ultimately, the prediction of the energy demand.

[0073] In the above explanation, the learning device 6 generates a model based on the load items included in the learning dataset, i.e., the past dataset, but it may also be configured to generate a model based on the load items included in the prediction dataset.

[0074] (Variant 1 of Embodiment 3) Variant 1 of Embodiment 3 differs from Embodiment 3 in the method of generating a trained model and selecting load items. The model generation unit 62 of the learning device 6 calculates, for each load item, the error between the predicted value of the demand item calculated from a simple regression equation between the load item and the demand item and the past value of the demand item to create a model. The inference unit 72 of the inference device 7 inputs the types of candidate load items included in the prediction dataset into the trained model, thereby obtaining a predetermined number of load items for which the error between the predicted value of the demand item output by the trained model and the past value is small. The number of load items to be output is set in advance by the user.

[0075] The generation of the trained model and the selection of load items will now be described in more detail. FIG. 17 is a flowchart illustrating a demand forecasting method according to Variation 1 of Embodiment 3. FIG. 17 illustrates the processing of steps S22 and S23 in FIG. 15 in detail. First, the model generation unit 62 of the learning device 6 selects one of the load items included in the training dataset acquired by the second acquisition unit 61 (step S2211). Next, the model generation unit 62 acquires past values ​​of the selected load item and past values ​​of the demand item using a past dataset for a period two days prior to the target prediction date and time as the training dataset (step S2212). Next, the model generation unit 62 derives a simple regression equation for the entire training dataset, using the acquired past values ​​of the load item as an explanatory variable and the past values ​​of the demand item as a target variable (step S2213).

[0076] The model generation unit 62 also acquires past values ​​of the load items and demand items selected in step S2211 for the day before the target prediction date and time (step S2214). Next, the model generation unit 62 calculates a predicted value of the demand item using the simple regression equation derived in step S2213 and the past values ​​of the load items acquired in step S2214 (step S2215). The model generation unit 62 then compares the past values ​​of the demand items acquired in step S2214 with the predicted values ​​of the demand items calculated in step S2215, and calculates an error therebetween (step S2216). The error may be, for example, RMSE.

[0077] The model generation unit 62 determines whether errors have been calculated for all types of load items included in the training dataset (step S2217). If errors have not been calculated for all types of load items included in the training dataset (step S2217: NO), unselected load items are selected and the processes of steps S2211 to S2216 are repeated until errors have been calculated for all types of load items included in the training dataset. If errors have been calculated for all types of load items included in the training dataset (step S2217: YES), the generation of the trained model is completed. Then, the inference unit 72 of the inference device 7 inputs the types of load items included in the prediction dataset acquired by the third acquisition unit 71 into the trained model, thereby selecting a predetermined number of load items with small errors between the predicted values ​​and past values ​​of the demand items (step S2311).

[0078] In the first modification of the third embodiment, for each load item, the error between the predicted value of the demand item calculated from the simple regression equation between the load item and the demand item and the past value of the demand item is calculated, and the type of load item to be used for determining the similarity is selected. This makes it possible to further improve the accuracy of the similarity determination, and ultimately the prediction of the energy demand.

[0079] Embodiment 4. Fig. 18 is a schematic configuration diagram showing a demand forecasting system 1C according to embodiment 4. As shown in Fig. 18, a demand forecasting device 4C according to embodiment 4 differs from embodiment 2 in that it does not have a similarity determination unit 42. In embodiment 4, the same parts as those in embodiment 2 are denoted by the same reference numerals and description thereof will be omitted, and the description will focus on the differences from embodiment 2.

[0080] FIG. 19 is a flowchart showing a demand forecasting method according to the fourth embodiment. A general flow of calculating energy demand will be described using FIG. 19 . First, the first acquisition unit 41 of the demand forecasting device 4C acquires a predetermined amount of past data sets stored in the storage device 3 and a forecast data set at the target forecast date and time (step S31). Next, the data division unit 45 divides the past data sets into multiple intervals (step S32). Next, the regression equation derivation unit 43 derives a regression equation for calculating a forecast value of a demand item for each interval of the past data sets (step S33). Then, the forecast value calculation unit 44 calculates a forecast value of a demand item from a forecast value of a load item at the target forecast date and time based on the regression equation derived by the regression equation derivation unit 43 (step S34).

[0081] As described above, the demand forecasting device 4C and the demand forecasting method according to the fourth embodiment forecast energy demand based on past data sets that have a high similarity to the target forecast date and time, thereby improving the accuracy of the energy demand forecast.

[0082] The above is a description of the embodiments of the present disclosure, but the present disclosure is not limited to the configurations of the above embodiments and various modifications or combinations are possible within the scope of the technical concept. For example, in the embodiments, the data acquisition device 2 and the storage device 3, the storage device 3 and the demand forecasting device 4, and the demand forecasting device 4 and the control instruction device 5 are each configured to communicate via a network such as the Internet. However, any two or more of the data acquisition device 2, the storage device 3, the demand forecasting device 4, and the control instruction device 5 may be integrated into an information processing device such as a server.

[0083] Furthermore, the learning device 6 or the inference device 7 may be provided outside the demand prediction device 4 and may communicate with the demand prediction device 4 via a network such as the Internet.

[0084] Furthermore, the data division unit 45 described in the second embodiment may be omitted from the demand forecasting system 1B described in the third embodiment.

[0085] 1, 1A, 1B, 1C Demand forecasting system, 2 Data acquisition device, 3 Storage device, 4, 4A, 4B, 4C Demand forecasting device, 5 Control command device, 6 Learning device, 7 Inference device, 40 Arithmetic device, 41 First acquisition unit, 42 Similarity determination unit, 43 Regression formula derivation unit, 44 Prediction value calculation unit, 45 Data classification unit, 61 Second acquisition unit, 62 Model generation unit, 71 Third acquisition unit, 72 Inference unit, 101 Processor, 102 Memory, 103 Bus.

Claims

1. A demand prediction device that predicts an energy demand of a consumer at a prediction target date and time, An acquisition unit that acquires a past data set including past values ​​of a load item that affects the energy demand and a demand item that indicates the energy demand, and a predicted value of the load item; a similarity determination unit that determines a similarity between the predicted value of the load item and a past value of the load item and extracts the past data set based on the similarity; A data division unit that divides the past data set into a plurality of time intervals based on an operation state of the consumer; a regression equation deriving unit that derives a regression equation for predicting the energy demand for each of the plurality of intervals based on the extracted past data set; a prediction value calculation unit that calculates a prediction value of the demand item by inputting a prediction value of the load item into the regression equation; Demand forecasting device.

2. The data division unit divides the past data set into a plurality of the sections based on an operating state of equipment installed in the consumer. The demand forecasting device according to claim 1 .

3. The data division unit divides the past data set into a plurality of intervals such that a correlation coefficient between the demand item and the load item in each of the intervals is equal to or greater than a predetermined value. The demand forecasting device according to claim 1 or 2.

4. Further comprising a learning device, The learning device includes: An acquisition unit that acquires a learning dataset including the load items and the demand items; a model generation unit that generates a trained model for inferring the load item used to determine the similarity from the candidate load items by using the training data set. The demand forecasting device according to claim 1 .

5. Further comprising an inference device, The inference device comprises: an acquisition unit that acquires a type of the load item that is a candidate to be used for determining the similarity of the demand item; an inference unit that selects the load item to be used for determining the similarity from the type of the load item input from the acquisition unit by using a trained model for inferring the load item to be used for determining the similarity from the candidate load items. The demand forecasting device according to claim 1 .

6. The demand forecasting device according to claim 1 ; a storage device that stores the past data set and the predicted values ​​of the load items; a data acquisition device that acquires the past data set and the predicted value of the load item and stores them in the storage device. Demand forecasting system.

7. A demand forecasting method for forecasting an energy demand of a consumer at a forecast target date and time, comprising: A past data set including past values ​​of a load item that affects the energy demand and a demand item that indicates the energy demand, and a predicted value of the load item are obtained; determining a similarity between the predicted value of the load item and a past value of the load item, and extracting the past data set based on the similarity; Dividing the past data set into a plurality of time intervals based on the operation state of the consumer; deriving a regression equation for predicting the energy demand for each of the plurality of intervals based on the extracted past data set; a predicted value of the demand item is calculated by inputting the predicted value of the load item into the regression equation.