JP6134253B2 - Energy consumption prediction system and energy consumption prediction method - Google Patents

Description

  The present invention relates to an energy consumption prediction system and an energy consumption prediction method capable of predicting the consumption of energy such as electric power.

  In recent years, energy conservation awareness has increased. Under such circumstances, energy consumption such as electric power is predicted, and the energy consumer grasps this, so that the consumer's awareness of energy saving can be raised and efficient energy saving activities can be performed.

  As a method for predicting such energy consumption, for example, a demand prediction that builds a prediction model based on multiple regression analysis algorithms from past actual energy demand values and weather information, and predicts energy demand. There is a system (Patent Document 1).

JP 2004-164388 A

  However, the conventional method such as Patent Document 1 requires a lot of past performance data in order to perform multiple regression analysis. Further, Patent Document 1 performs energy demand prediction based on weather information such as temperature, but sets a similar date for the weather information of the day on which the demand prediction is performed. By setting such a similar date, the prediction accuracy is improved. However, in order to set such a similar date, many different past performance values are required.

  In Patent Document 1, it is possible to change the time zone for judging whether the weather condition is similar to the current day from the search target (past performance) to night, morning, afternoon, or the like. However, Patent Document 1 merely sets a time zone in which similarity determination is performed for the purpose of setting a day in which weather conditions are similar to a prediction target day. Therefore, for example, regarding the temperature change in a certain time zone of the prediction target day, the power demand prediction for the entire day of the prediction target date is performed using the past results in which the temperature change in the same time zone is similar. . For this reason, a separate demand prediction is not performed according to a time slot | zone.

  Usually, there is not necessarily a correlation between the temperature change during the daytime and the temperature change during the nighttime. For this reason, it can not be said that it is necessarily necessarily high in accuracy to determine that the temperature change of all prediction days is similar only by looking at the temperature change in a certain time zone. Moreover, since it is necessary to memorize | store the temperature change for every time also as a past performance value, data amount increases. Thus, the conventional method requires a large amount of information in order to perform demand prediction, and the entire system becomes large.

  The present invention has been made in view of such a problem, and an energy consumption prediction system and an energy consumption prediction method capable of predicting energy consumption with only minimum information that can be easily obtained. The purpose is to provide.

In order to achieve the above-described object, a first invention is an energy consumption prediction system, which is a storage unit that stores energy consumption information for each predetermined time in a plurality of past days, and the energy consumption in the storage unit. the amount information, and category classification means that category classified according to operating conditions or day of the week of a store or office, for each classified category that by the category classification means, to distinguish each of the day and night, of energy consumption A pattern creation means for averaging the energy consumption information for each predetermined time in a predetermined period retroactively from the prediction target date to create an average energy consumption pattern for each day and night, and for each category The correlation between temperature information and energy consumption The energy consumption prediction means for calculating the expected energy consumption at night from the expected minimum temperature on the prediction target day, and the total energy consumption and the estimated energy in the average energy consumption pattern for each of day and night The average energy consumption pattern is multiplied by a constant at each predetermined time so that the total energy consumption matches the expected energy consumption, and the corrected energy for each predetermined time is compared. An energy consumption prediction system comprising: energy consumption correction means for calculating consumption; and display means for displaying the corrected energy consumption on a display unit .

Here, it is preferable that the category classification means performs category classification so as to distinguish between business days and closed days as the category classification according to the operation status. The category classification means may further perform category classification based on the form of business hours on business days. Or you may classify | categorize further based on the number of customers.
By doing in this way, the energy consumption pattern of each day and night can be calculated | required for every category according to the operating condition or day of the week of a store or a business establishment . For this reason, energy consumption can be predicted separately for day and night from the relationship between temperature and energy consumption. Thus, since the demand is predicted separately for each day and night, the prediction accuracy is high.

  In particular, the energy demand during the day is predicted based on the highest temperature of the day, and the energy demand during the night is predicted from the lowest temperature of the day. Therefore, the energy demand for the day of the day can be predicted substantially only with the predicted values of the highest temperature and the lowest temperature of the day.

  At this time, the past performance data may be the nearest several to a dozen or so, so that the amount of data used for the calculation may be small.

  Further, in the present invention, the pattern creating means is configured to have a sufficiently large number of information with respect to the number of information of the energy consumption information used when creating the average energy consumption pattern. For each of the above, the energy that has deviated more than a predetermined amount from the approximate expression obtained by correlating the maximum temperature or the minimum temperature for each of the categories for a predetermined period retroactively from the expected date of energy consumption and the energy consumption. It is desirable to exclude consumption information so that it is not used to create the average energy consumption pattern.

By doing in this way, even if it is prediction by a small number of points, since a singular point can be excluded, accuracy can be secured.
Specifically, for example, in the category having 3 days or more in one week, the predetermined period in the pattern creating means is 10 to 15 days going back to the past from the prediction target day, and 2 days or less in one week. In the category, it is desirable to set 5 to 9 days going back to the past from the prediction target date.

  The display unit displays a plurality of days and times in a predetermined period in a table, and shows one day in a row, and shows a difference between the corrected energy consumption and the energy usage results for each time in each column. It should be displayable.

  For example, one day from 0:00 to 23:59 is displayed in a horizontal row, and each day is displayed side by side. At this time, by displaying the table in blocks for every hour and displaying the results of energy saving for each block, the user can grasp the tendency for each hour and the tendency for each day of the week at a glance.

  The energy consumption includes at least power consumption, and the predetermined time is 30 minutes, and the corrected energy consumption every 30 minutes is divided by 0.5 hours to obtain a maximum demand for 30 minutes on the day. Electric power may be calculated and displayed on the display unit.

  Further, the correction energy consumption amount for each hour may be calculated by adding the two consecutive correction energy consumption amounts for every 30 minutes and displayed on the display unit.

By doing in this way, a consumer can grasp | ascertain reliably the 30 minute maximum demand power and its generation time zone on the day. In addition, the display unit further includes a warning means for displaying a warning on the display unit when the corrected energy consumption for each predetermined time exceeds a predetermined warning level determined based on contract power. It is desirable that the corrected energy consumption is displayed in a graph, and the contract power, the attention level, and the actual energy consumption for each predetermined time are displayed in the graph. Therefore, by selecting a time zone for power saving and performing smart power saving, it is possible to prevent the contract power from being exceeded and to pay a higher amount of electricity.

In the second invention, the computer categorizes the energy consumption information for each predetermined time on a plurality of past days stored in the storage unit according to the operating status of the store or business office or the day of the week. for each category were, to distinguish each of the day and night, and back from the prediction target day of energy consumption in the past averages the energy consumption information for each predetermined number of the predetermined time for a predetermined period, and day Create an average energy consumption pattern for each night, correlate the temperature information and energy consumption for each category, calculate the expected energy consumption for the day from the predicted maximum temperature on the forecast target day, and predict The expected energy consumption at night is calculated from the expected minimum temperature on the target day, and the total energy in the average energy consumption pattern is calculated for each day and night. Compared over consumption and with said expected energy consumption, said such that the total energy consumption is consistent with the predicted energy consumption by multiplying a certain constant relative to the average energy consumption patterns for each of the predetermined time, The energy consumption prediction method is characterized in that the corrected energy consumption for each predetermined time is calculated and the corrected energy consumption is displayed on a display unit .

  The energy consumption includes at least power consumption, and the predetermined time is 30 minutes, and the corrected energy consumption every 30 minutes is divided by 0.5 hours to obtain the maximum demand power for 30 minutes on that day. It may be calculated and displayed on the display unit. Alternatively, the energy consumption amount may include at least a gas consumption amount, and the predetermined time may be one hour.

  From each day and night to the expected target day of energy consumption so that the number of information is sufficiently larger than the number of information of the energy consumption information used when creating the average energy consumption pattern Correlating the maximum or minimum temperature and energy consumption for each category for a predetermined period retroactively in the past, the energy consumption information deviated by a predetermined amount or more from the obtained approximate expression is the creation of the average energy consumption pattern It is desirable to exclude it from being used.

  By doing in this way, highly accurate energy consumption prediction can be performed from a small amount of information. In addition, by displaying the power consumption every 30 minutes or the gas consumption per hour, you can see the relationship between the contract power and the contract maximum time flow rate of gas, and grasp the necessity of energy saving. Can do.

  According to the present invention, it is possible to provide an energy consumption prediction system and an energy consumption prediction method capable of predicting energy consumption with only minimum information that can be easily obtained.

1 is a configuration diagram showing an energy consumption prediction system 10. FIG. The hardware block diagram which shows the energy consumption prediction apparatus 1. FIG. The flowchart which shows the control method of the energy consumption prediction apparatus 1. FIG. The figure which shows the example of a category. The figure which shows an example of the power consumption for every time. The figure which shows the relationship between the temperature and electric power consumption for every category. The figure which shows the state which correct | amends power consumption with temperature. The figure which shows an example of a display screen. The figure which shows an example of a display screen. The figure which shows an example of a display screen. The figure which shows an example of a long-term track record.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a configuration diagram showing an energy consumption prediction system 10. In the energy consumption prediction system 10, the energy consumption prediction device 1 and the energy consumption management server 20 are connected to each terminal 23 via a network 21. The energy consumption prediction device 1 and the energy consumption management server 20 may be integrated.

  The energy consumption calculated by the energy consumption prediction device 1 is stored in the energy consumption management server 20. Information stored in the energy consumption management server 20 can be displayed on a terminal 23 such as a remote place.

  FIG. 2 is a hardware configuration diagram showing the energy consumption prediction apparatus 1. Note that the energy consumption management server 20 and the terminal 23 have the same configuration as that of the energy consumption prediction apparatus 1, and thus the description thereof is omitted. The energy consumption prediction apparatus 1 is, for example, a computer, and includes a control unit 3, a storage unit 5, a media input / output unit 7, a communication control unit 9, an input unit 11, a display unit 13, a peripheral device I / F unit 15, and the like. They are connected via the bus 17.

  The control unit 3 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like. The CPU calls and executes a program stored in the storage unit 5, ROM, recording medium or the like in a work memory area on the RAM, drives and controls each device connected via the bus 17, and an energy consumption prediction device The processing performed by 1 is realized.

  The ROM is a non-volatile memory and permanently holds a computer boot program, a program such as BIOS, data, and the like. The RAM is a volatile memory, and temporarily stores programs, data, and the like loaded from the storage unit 5, ROM, recording medium, and the like, and includes a work area used by the control unit 3 for performing various processes.

  The storage unit 5 is an HDD (hard disk drive) or SSD (flash SSD) (solid state drive), and stores a program executed by the control unit 3, data necessary for program execution, an OS (operating system), and the like. As for the program, a control program corresponding to an OS (operating system) and an application program corresponding to processing described later are stored. Each of these program codes is read by the control unit 3 as necessary, transferred to the RAM, read by the CPU, and executed as various means. The storage unit 5 stores various data used in the present invention.

  The media input / output unit 7 (drive device) performs data input / output. For example, a floppy (registered trademark) disk drive, a CD drive (-ROM, -R, RW, etc.), a DVD drive (-ROM, -R, -RW etc.) and media input / output devices such as MO drives.

  The communication control unit 9 includes a communication control device, a communication port, and the like, and is a communication interface that mediates communication between the computer and the network. For example, the control unit 3 transmits weather information and temperature information on the Internet via the network. Can be obtained from.

  The input unit 11 inputs data and includes, for example, a keyboard, a pointing device such as a mouse, and an input device such as a numeric keypad. An operation instruction, an operation instruction, data input, and the like can be performed on the computer via the input unit 11.

  The display unit 13 includes a display device such as a CRT monitor and a liquid crystal panel, and a logic circuit (such as a video adapter) for realizing a video function of the computer in cooperation with the display device.

  The peripheral device I / F (interface) unit 15 is a port for connecting a peripheral device to the computer, and the computer transmits and receives data to and from the peripheral device via the peripheral device I / F unit 15. For example, it is connected to a user's power meter or gas meter, and the energy consumption record can be acquired. Moreover, it is connected to the thermometer installed outside, the external server which has temperature information, etc., and it can acquire temperature information. At this time, the actual temperature at each time point may be acquired, and the predicted temperature may be sequentially corrected by the control unit 3. Note that information exchange with other servers and terminals via the network may be performed by the energy consumption management server 20 or directly by the energy consumption prediction apparatus 1.

  The bus 17 is a path that mediates transmission / reception of control signals, data signals, and the like between the devices. Here, the energy consumption prediction device 1, the energy consumption management server 20, and the terminal 23 are not limited to those including all of the above-described configurations, and have only the configurations necessary for performing the functions of the present invention. do it. In addition, although the following description shows the processing content in the energy consumption prediction apparatus 1, as described above, the information calculated by the energy consumption prediction apparatus 1 is appropriately stored in the energy consumption management server 20. .

  Next, the function of the energy consumption prediction apparatus 1 will be described. In the following description, an example in which the energy is electric power will be described, but it goes without saying that the present invention can be applied to other energy such as gas or water.

  FIG. 3 is a diagram illustrating a process for predicting a daily power consumption amount in a store or business office by the energy consumption amount prediction apparatus 1. First, the control unit 3 classifies the power consumption information stored in advance in the storage unit 5 (the energy consumption prediction device 1 or the storage unit 5 of the energy consumption management server 20; the same applies hereinafter) for each category ( Step 101). The power consumption information is information regarding the power consumption for each target and every predetermined time (in this embodiment, every 30 minutes) for a target store or office. In addition, when there is no past information, you may use the information of the other store or office which takes a similar business form or power consumption.

  FIG. 4 is a diagram illustrating an example of category classification. The category can be classified by, for example, a day of the week or a business form. Each category is divided into day and night.

  For example, the store A has a business form in which business hours on Sundays and holidays are different from those on other days. Further, for example, even if the business form is the same on Saturdays and weekdays, the number of customers is larger on Saturdays, so the categories of weekdays and Saturdays can be divided. In this way, categories are divided according to the day of the week or the business form.

  On the other hand, for example, in the case where Wednesday is a regular holiday, the store B sets other weekdays and Wednesday as different categories. Thus, category classification according to the business form can be performed for each store.

  Each category is divided into day and night. Day and night times can be set as appropriate according to the type of business. For example, if the business hours of the store A are from 9 o'clock to 21 o'clock, the hour before and after that can be daytime, and the other hours can be nighttime. Further, as in the store B, the day and night can be divided in 12 hours. In addition, for example, the daytime may include a normal temperature of 12:00 to 14:00, and the night may include a normal minimum temperature of 3 to 5 am.

  The category classification is not limited to the example described above. For example, long holidays such as New Year holidays and Bon holidays may be considered.

  Next, for each category, the control unit 3 averages the power consumption information for every 30 minutes for each time, and creates each day's and night's average power consumption pattern for each day (step) 102). FIG. 5 is a diagram illustrating an example of an average power consumption pattern. For example, the control unit 3 calculates an average value of power consumption every 30 minutes in the past weekdays for the category 1-daytime.

  Here, the data used for averaging is 10 to 15 days in a category having 5 days or more in one week (in this example, 5 days from Monday to Friday). Moreover, in the category which is 2 days or less within one week, it is set as 5 to 9 days. That is, the data of the same category in the past 3 to 5 weeks is averaged. As shown in the figure, the power consumption per hour for each time (every 30 minutes) is graphed (A in the figure). The control unit 3 creates a similar graph for day and night separately for other categories.

  Next, the control unit 3 correlates the temperature and the power consumption for each category from the temperature information (maximum temperature and minimum temperature) information stored in the storage unit 5 and the power consumption information for each day. For each day and night. Further, the predicted power consumption of the target date is calculated from the temperature information of the prediction target date (step 103).

  FIG. 6A is a diagram showing a state in which the correlation between the temperature and the power consumption of each day and night is created for each category, and FIG. 6B is an enlarged view of category 1-day. The correlation diagram (for example, the least square method) between the temperature and the power consumption is created by plotting the temperature information on the horizontal axis and the total power consumption during the day or night of the day on the vertical axis. At this time, the correlation between the maximum temperature and the total power consumption during the day is taken for the daytime, and the correlation between the minimum temperature and the total power consumption at the night is calculated for the night.

  Here, when calculating the correlation formula, the order of the correlation formula can be changed for each category. For example, for a category with a large number of plots (as described above, a category with 3 days or more per week), a category with a quadratic curve is approximated, and a category with a small number of plots (for example, a category with 2 days or less per week) is You may approximate with a straight line.

  The control unit 3 acquires the predicted temperature information (the predicted maximum temperature and the predicted minimum temperature) of the day via the network. Next, the control unit 3 acquires the expected power consumption of day and night corresponding to the obtained predicted temperature according to the category of the target day. For example, in FIG. 6B, the daytime power consumption C corresponding to the maximum temperature B is calculated. In the case of night, the power consumption at night corresponding to the lowest temperature is calculated.

  Next, the control unit 3 compares the total power consumption in the average power consumption pattern created in step 102 with the predicted power consumption acquired in step 103. In addition, the control unit 3 multiplies the average power consumption pattern by a constant every 30 minutes so that the total power consumption in the average power consumption pattern matches the expected power consumption, and corrects the corrected power every 30 minutes. A consumption amount is calculated (step 104).

  FIG. 7 is a conceptual diagram illustrating a process of calculating the corrected power consumption. When the expected power consumption in the daytime is 20% larger than the total power consumption in the daytime according to the average power consumption pattern in the daytime (A in the figure), x for all the power consumption every 30 minutes Multiply by 1.2. Accordingly, the power consumption per hour shifts upward as a whole (in the direction of arrow F in the figure). The obtained graph (D in the figure) is the corrected power consumption. That is, the area C surrounded by the graph D in the daytime (E in the figure) matches the expected power consumption (C in FIG. 6B). Similarly, the corrected power consumption is calculated for the night.

  Next, the control unit 3 displays the obtained information on the display unit 13 (step 105). FIG. 8 is a diagram illustrating an example of display on the display unit 13. The display unit 13 displays, for example, the date, the predicted maximum temperature, the minimum temperature, the contract power, the power saving setting, the display setting, the corrected power consumption (predicted value), the actual result, and the like of the target date.

  The predicted maximum temperature and minimum temperature are information acquired from the network. In addition, the control unit 3 compares the predicted temperature of each time with the actual temperature, and if there is a difference between the predicted temperature and the actual temperature, the control unit 3 corrects the predicted temperature thereafter by the difference, The corrected power consumption may be recalculated.

  In the power saving setting, the power saving rate and the scheduled execution time can be set. The power saving rate can be set to what percentage of power saving with respect to the expected corrected power consumption. In addition, the time for power saving can be set. Such setting is input by the input unit 11.

  The contract power is the allowable energy usage at the target store or business. Here, normally, when the power consumption (converted to one hour) every 30 minutes exceeds the contract power, it is necessary to pay a higher power charge. Therefore, it is necessary to save power so that the power consumption every 30 minutes (one hour equivalent) does not exceed the contract power.

  Therefore, in the present invention, the control unit 3 compares the expected amount of power every 30 minutes with the contract power and alerts the consumer. For example, if the contract power is set to 120 kW and the attention level is set to 10%, a warning is issued when the predicted power consumption every 30 minutes in the corrected power consumption is calculated to exceed 108 kW. In this case, as shown in the figure, the display “Warning about power consumption at the time of ○ to ○” is performed. In response to this, the consumer can make the aforementioned power saving schedule. Note that the maximum power forecast displayed on the display unit 13 is a 30-minute maximum power forecast, which is obtained by dividing the maximum power usage every 30 minutes by 0.5 and converted into one hour.

  FIG. 9 is a diagram illustrating an example of a graph that is displayed on the display unit 13 and shows the corrected power consumption, the actual results, and the like. The broken line indicated by J in the figure is the corrected power consumption predicted in the above-described process. At the same time, the contract power (H in the figure) and the attention level (I in the figure) are displayed on the graph. Further, when the power saving setting is performed, a consumption forecast after the power saving setting is displayed (K in the figure). Further, the actual value of power consumption for each hour (G in the figure) is displayed. In addition, the performance value of power consumption is acquired by the control part 3 with a power meter.

  In this way, since the corrected power consumption, target value, and actual value can be visually recognized at the same time, the consumer can easily visually recognize how much power is consumed and how much power is required. it can. In addition, it is possible to immediately grasp the time zone in which a large amount of power is used with respect to the prediction (corrected power consumption).

  In addition, as power consumption (corrected power consumption) every 30 minutes displayed on the display unit, two consecutive data every 30 minutes may be added and displayed as power consumption per hour. it can. Further, as described above, the power consumption for every 30 minutes may be divided by 0.5 hours and displayed as an hourly converted value of the power consumption for 30 minutes.

  Whether or not to display each item described above on the graph can be easily changed by display setting. That is, only necessary information can be displayed on the display unit 13.

  Moreover, the control part 3 can also display the past data collectively. FIG. 10 is a display example displayed in this way. Show the day in a horizontal row, and for each column of multiple days (for example, for the past month), the horizontal axis shows the time (from 0:00 to 23:00). You can see at a glance.

  For example, the time during which power of a predetermined level or more is used for prediction (M in the figure) and the time during which power consumption of the predetermined level or more can be suppressed for prediction (L in the figure) may be displayed by color coding. In this way, by arranging a plurality of time zones for each day in a plurality of columns, it is possible to grasp at a glance the tendency for each hour and the tendency for each day of the week (category). That is, it is possible to easily grasp the time period in which the difference between the predicted power consumption and the actual result is large. In addition, it is possible to clearly visualize the causes of forgetting to turn off electricity and the results of power saving activities. The table may be assigned a category number, and the display color of characters and frames may be changed depending on the category.

  In addition, the control unit 3 acquires the actual power consumption amount of day and night and the maximum temperature and minimum temperature of the day (the predicted values can be used, but the actual maximum temperature information and minimum temperature information of the day must be acquired separately). Is desirable) is stored in the storage unit 5. The stored information is used for prediction of power consumption from the next day. Here, the control unit 3 of the energy consumption amount prediction device 1 can also save the record or the like in the storage unit 5 of the energy consumption amount management server 20. In this case, the control unit 3 of the energy consumption management server 20 may cause the display unit 13 of the terminal 23 to display the display content described above, or from the energy consumption prediction device 1 or the energy consumption management server 20, The terminal 23 can acquire various types of information (such as temperature information, prediction results, and actual values), and can be displayed on the display unit 13 of the terminal 23 by the control unit 3 of the terminal 23.

  As mentioned above, according to this invention, electric power prediction can be performed only using the temperature information (maximum temperature and minimum temperature) which can be obtained easily, and the actual value of the power consumption of the past several weeks. At this time, since the data is classified for each category, the prediction accuracy is high. In particular, it is possible to perform category classification according to the operating status of the store or business office, such as a closed day of a store or a business day of a holiday, so that it is possible to perform category classification optimal for the user.

  In particular, according to the present invention, power consumption is predicted separately for day and night. At this time, the power consumption during the day is predicted based on the maximum temperature information, and the power consumption during the night is predicted based on the minimum temperature information. This is because the highest temperature is usually recorded during the daytime and the lowest temperature is often recorded during the nighttime. Also, the maximum daytime temperature and the nighttime minimum temperature are not necessarily correlated.

  In other words, there are days when the day is hot even when the night is cool, and days when the day is cool and the temperature does not drop at night. Therefore, by predicting the time of day and night with different temperature information, for example, the power consumption at night is not predicted by the maximum temperature information of daytime. Therefore, more accurate power consumption prediction can be performed. At this time, the information used is only the maximum temperature and the minimum temperature, and the amount of information used is small. For example, it is not necessary to acquire the predicted temperature of the day at all times and calculate the power consumption for each hour.

  Moreover, when estimating about power consumption, it can contrast with contract power by using the data for every 30 minutes (time unit which determines the maximum power consumption in contract power). Therefore, it is possible not only to predict the hourly power consumption transition but also to compare with contract power, and to make consumers aware of power saving so as not to exceed this.

  At this time, since the display unit displays the hourly converted value of power consumption every 30 minutes (unit of power consumption in the contract power), it is easy to compare with the contract power.

  In addition, normally, for the prediction of power consumption, the use of data over a long period of time in the past has a larger parameter, so that stable prediction can be performed. However, the situation that affects the power consumption is not always constant, and when the power consumption situation changes, the prediction cannot be performed accurately immediately after that.

  On the other hand, in the present invention, an average power consumption pattern is obtained from the results of power consumption over the last few weeks. For this reason, even if the power consumption state changes, the change is immediately reflected. Therefore, calculation according to the current power consumption state can be performed.

  On the other hand, the present invention uses only a few weeks of data for the prediction of power consumption, so that the number of parameters is small and the influence of irregular results becomes large. Therefore, in the present invention, past actual values over a long period of time (for example, the past year) are also stored in the storage unit 5, and the correlation between the maximum temperature and the daytime power consumption results and the minimum temperature and the nighttime power for each category. Maintains a correlation of actual consumption. FIG. 11 is a diagram illustrating an example of the category 1-day long-term results. When one day has passed and the temperature information of the day and the power consumption record of day and night are acquired, the control unit 3 compares the correlation between the long-term results of the same category and the day and night separately. At this time, data that deviates more than a predetermined amount (for example, ± 30% or more) with respect to the correlation of long-term results (black circle in the figure) can be treated as a specific day and not be used for power consumption prediction on the next day or later. . Therefore, the average power consumption pattern created in step 102 uses the most recent predetermined number of data except for the excluded day.

  By doing in this way, the data of a peculiar day are not used for power consumption prediction. Note that such unique date data can also be stored as long-term data in the storage unit 5 and used as information on long-term results.

  As mentioned above, although embodiment of this invention was described referring an accompanying drawing, the technical scope of this invention is not influenced by embodiment mentioned above. It is obvious for those skilled in the art that various modifications or modifications can be conceived within the scope of the technical idea described in the claims, and these are naturally within the technical scope of the present invention. It is understood that it belongs.

  For example, the embodiment in the case where the energy is electric power has been shown. However, when the target of energy is not electric power but gas, it may be changed as follows. If the maximum flow rate for gas is exceeded, the gas unit price for the following year may increase. However, in the case of gas, unlike electric power, the contract maximum time flow rate is not the maximum usage amount for 30 minutes, but the usage amount for one hour is applied as it is. Therefore, when the energy target is gas, all the 30-minute units in the above-described embodiment may be replaced with one-hour units.

DESCRIPTION OF SYMBOLS 1 ......... Energy consumption prediction apparatus 3 ......... Control part 5 ......... Storage part 7 ......... Media input / output part 9 ......... Communication control part 10 ......... Energy consumption prediction system 11 ......... Input Unit 13 ... Display unit 15 Peripheral device I / F unit 17 Bus 20 Energy management server 21 Network 23 Terminal

Claims (14)

An energy consumption prediction system,
A storage unit for storing energy consumption information for each predetermined time in a plurality of past days;
Category classification means for categorizing the energy consumption information in the storage unit according to the operating status or day of the week of the store or establishment ;
For each of the countries are classified by category classifying means categories, to distinguish each of the day and night, the energy consumption information for each predetermined number of the predetermined time in the past going back a predetermined period from the prediction target day Energy consumption Pattern creation means for averaging the average energy consumption patterns of day and night,
For each category, correlation between temperature information and energy consumption is calculated, and the expected energy consumption for the day is calculated from the predicted maximum temperature on the prediction target day. Energy consumption forecasting means for calculating consumption,
For each day and night, the comparing total energy consumption in the average energy consumption patterns and the estimated energy consumption, so that the total energy consumption is consistent with the predicted energy consumption, the average energy consumption patterns Energy consumption correcting means for calculating a corrected energy consumption for each predetermined time by multiplying a predetermined constant for each predetermined time,
Display means for displaying the corrected energy consumption amount on a display unit ;
An energy consumption prediction system comprising: The pattern preparation means includes
From the target day of energy consumption prediction for each day and night so that the number of information is sufficiently large with respect to the number of information of the energy consumption information used when creating the average energy consumption pattern Correlating the maximum or minimum temperature and energy consumption for each category for a predetermined period retroactively in the past, the energy consumption information deviated by a predetermined amount or more from the obtained approximate expression is the creation of the average energy consumption pattern 2. The energy consumption prediction system according to claim 1, wherein the energy consumption prediction system is excluded so as not to be used. The energy consumption includes at least power consumption,
The predetermined time is 30 minutes,
3. The corrected energy consumption every 30 minutes is divided by 0.5 hour to calculate the maximum demand power for 30 minutes on the day and display on the display unit. The energy consumption prediction system described in 1.   The correction energy consumption amount for every hour can be calculated by adding the two consecutive correction energy consumption amounts for every 30 minutes, and can be displayed on the display unit. Energy consumption prediction system.   The display unit displays a plurality of days and times in a predetermined period in a table, and shows one day in a row, and shows a difference between the corrected energy consumption and the energy usage results for each time in each column. The energy consumption prediction system according to any one of claims 1 to 4, wherein the energy consumption prediction system can be displayed.   The energy consumption prediction system according to claim 1, wherein the category classification unit performs category classification so as to distinguish business days and closed days as the category classification based on the operation status.   7. The energy consumption prediction system according to claim 6, wherein the category classification unit further classifies the category based on a form of business hours on business days.   The energy consumption prediction system according to claim 6 or 7, wherein the category classification means further performs category classification based on the number of customers.   In the category having three or more days in one week, the predetermined period in the pattern preparation means is 10 to 15 days retroactive from the prediction target day, and in the category having two or less days in one week, the prediction The energy consumption prediction system according to claim 1, wherein the energy consumption amount prediction system is set to 5 to 9 days dating back from the target date.   A warning means for displaying a warning on the display unit when the corrected energy consumption for each predetermined time exceeds a predetermined warning level determined based on contract power;
  2. The display unit according to claim 1, wherein the display unit displays the corrected energy consumption in a graph, and displays the contract power, the attention level, and the actual value of the energy consumption for each predetermined time in the graph. The energy consumption prediction system described. Computer
The energy consumption information for each predetermined time in a plurality of past days stored in the storage unit is categorized according to the operating status of the store or business office or the day of the week ,
For each classified category, to distinguish each of the day and night, by averaging the energy consumption information for each predetermined number of the predetermined time for a predetermined period going back from the prediction target day of energy consumption in the past, Create an average energy consumption pattern for day and night,
For each category, correlation between temperature information and energy consumption is calculated, and the expected energy consumption for the day is calculated from the predicted maximum temperature on the prediction target day. Calculate consumption,
For each day and night, the comparing total energy consumption in the average energy consumption patterns and the estimated energy consumption, so that the total energy consumption is consistent with the predicted energy consumption, the average energy consumption patterns Is multiplied by a certain constant for each predetermined time to calculate a corrected energy consumption for each predetermined time,
The corrected energy consumption amount is displayed on a display unit . The energy consumption includes at least power consumption,
The predetermined time is 30 minutes,
12. The energy consumption according to claim 11 , wherein the corrected energy consumption every 30 minutes is divided by 0.5 hours to calculate the maximum demand power for 30 minutes on the day and display it on the display unit. Quantity prediction method. The energy consumption includes at least a gas consumption,
12. The energy consumption prediction method according to claim 11 , wherein the predetermined time is one hour. From the target day of energy consumption prediction for each day and night so that the number of information is sufficiently large with respect to the number of information of the energy consumption information used when creating the average energy consumption pattern Correlating the maximum or minimum temperature and energy consumption for each category for a predetermined period retroactively in the past, the energy consumption information deviated by a predetermined amount or more from the obtained approximate expression is the creation of the average energy consumption pattern energy consumption prediction method according to any one of claims 13 claim 11, characterized in that to eliminate not to use the.

Images