WO2014104829A1 - Procédé de prédiction de charge de puissance et appareil utilisant le procédé - Google Patents

Procédé de prédiction de charge de puissance et appareil utilisant le procédé Download PDF

Info

Publication number
WO2014104829A1
WO2014104829A1 PCT/KR2013/012333 KR2013012333W WO2014104829A1 WO 2014104829 A1 WO2014104829 A1 WO 2014104829A1 KR 2013012333 W KR2013012333 W KR 2013012333W WO 2014104829 A1 WO2014104829 A1 WO 2014104829A1
Authority
WO
WIPO (PCT)
Prior art keywords
time unit
power data
unit power
power
data group
Prior art date
Application number
PCT/KR2013/012333
Other languages
English (en)
Korean (ko)
Inventor
이진호
진보건
Original Assignee
주식회사 효성
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 주식회사 효성 filed Critical 주식회사 효성
Publication of WO2014104829A1 publication Critical patent/WO2014104829A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R22/00—Arrangements for measuring time integral of electric power or current, e.g. electricity meters
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Definitions

  • the present invention relates to a method for estimating power load, and more particularly, to a method and apparatus for predicting power load using weather information.
  • the power exchange is implementing a system to support a part of the installation cost of the maximum demand power management device for general, education and industrial companies with a contract power of 500kW or more.
  • the maximum demand power management device is used, it is automatically managed so as not to exceed the preset target power value, thereby achieving energy savings and economic benefits for the consumer.
  • the maximum demand power management device monitors the current power consumption based on the target power and predicts the amount of power to be used at the end of the set demand time limit.
  • this prediction method has the advantage of being simple, it has a disadvantage that the accuracy of the prediction is poor in the place where the load fluctuates.
  • Power load prediction method for achieving the first object of the present invention is a step of receiving the predicted weather information, the unit of time used to calculate the power load prediction based on the forecast weather information
  • the method may include determining a power data group and calculating the power load prediction amount based on the predicted weather information and the time unit power data included in the determined time unit power data group.
  • the predicted weather information may include predicted temperature information and predicted humidity information
  • the time unit power data may include temperature information in units of time, humidity information in units of time, and power load information in units of time.
  • the time unit power data group is a time unit power data group for each season including the time unit data measured in a seasonal unit, a monthly time unit power data group including the time unit data measured in a monthly unit, a day unit It may include a daily time unit power data group including the measured time unit data and the hourly power data group including the time unit data measured in hours. Determining a time unit power data group used to calculate a power load forecast amount based on the forecast weather information includes: the seasonal time unit power data group in which the forecast weather information is to be used to calculate the power load forecast amount; The method may include determining at least one of a monthly time unit power data group, the daily time unit power data group, and the hourly unit power data group.
  • the calculating of the power load prediction amount based on the predicted weather information and the time unit power data included in the determined time unit power data group may include the prediction weather information and the most predicted weather information among the time unit power data included in the time unit power data. Calculating candidate time unit power data having similar weather information, and calculating power load amount included in the candidate time unit power data as the power load prediction amount.
  • the calculating of the power load prediction amount based on the time unit power data included in the predicted weather information and the determined time unit power data group is consistent with the predicted weather information among the time unit power data included in the time unit power data.
  • the calculating of the power load prediction amount based on the time unit power data included in the predicted weather information and the determined time unit power data group is consistent with the predicted weather information among the time unit power data included in the time unit power data.
  • the method may include calculating the power load prediction amount.
  • the power load prediction method may include generating weather time unit power data by measuring weather information of a time unit and power load amount of the time unit, and generating a time unit power data group including the measured time unit power data.
  • the determining may further include including the measured time unit power data in the determined time unit power data group.
  • the determining of the time unit power data group including the measured time unit power data may include determining a seasonal time unit power data group including the measured time unit power data, wherein the measured time unit power data is Determining a monthly time unit power data group to be included; determining a daily time unit power data group including the measured time unit power data; and hourly power data including the measured time unit power data
  • the method may include at least one of determining the group.
  • the determining of the seasonal time unit power data group including the measured time unit power data may include temperature information included in the measured time unit power data and time unit power data included in the seasonal time unit power data group. And determining a season to which the measured unit of time power data is to be grouped by using a predetermined formula based on temperature information of.
  • An apparatus for estimating power load according to an aspect of the present invention for achieving the second object of the present invention includes an input unit for receiving predicted weather information, and calculating a power load forecast amount based on the predicted weather information input from the input unit.
  • the prediction amount calculation unit may be included.
  • the predicted weather information may include predicted temperature information and predicted humidity information
  • the time unit power data may include temperature information in units of time, humidity information in units of time, and power load information in units of time.
  • the time unit power data group is a time unit power data group for each season including the time unit data measured in a seasonal unit, a monthly time unit power data group including the time unit data measured in a monthly unit, a day unit It may include a daily time unit power data group including the measured time unit data and the hourly power data group including the time unit data measured in hours.
  • the unit of time power data group determiner is the seasonal time unit power data group, the monthly time unit power data group, the daily time unit power data group, wherein the predicted weather information is to be used to calculate the power load prediction amount, It may be implemented to determine at least one group of time unit power data group.
  • the power load prediction amount calculation unit calculates candidate time unit power data having weather information most similar to the predicted weather information among the time unit power data included in the time unit power data, and calculates the power load amount included in the candidate time unit power data. It may be implemented to calculate the power load prediction amount.
  • the power load prediction amount calculating unit calculates at least one candidate time unit power data having weather information similar to the predicted weather information in a predetermined range among the time unit power data included in the time unit power data, and the at least one candidate time unit The average value or median value of at least one power load amount included in power data may be calculated as the power load prediction amount.
  • the power load prediction amount calculating unit calculates at least one candidate time unit power data having weather information similar to the predicted weather information in a predetermined range among the time unit power data included in the time unit power data, and the at least one candidate time unit Among the at least one power load included in the power data, the closer the current power load is to the measurement date, the greater the weight may be implemented to calculate the power load prediction amount.
  • the apparatus for estimating power load may measure weather information for a time unit and a power load amount for the time unit, receive measurement time unit power data, and determine a time unit power data group including the measured time unit power data to determine the determined power unit.
  • the apparatus may further include a database configured to include the measured time unit power data in the time unit power data group.
  • the database determines a seasonal time unit power data group including the measured time unit power data, determines a monthly time unit power data group including the measured time unit power data, and includes the measured time unit power data. It may be implemented to determine a time unit of power data group to be determined and to determine the time of each power data group includes the power unit of time data measured.
  • the database may be further configured to measure the power of the unit of time by using a predetermined formula based on temperature information included in the power unit of time data and temperature information of the power of unit of time included in the power unit of the season. It can be implemented to determine the season to be grouped.
  • the power load prediction method and the apparatus for performing the method may calculate the power load prediction amount based on the predicted weather information and the time unit power data group.
  • the power load prediction amount By calculating the power load prediction amount based on the stored database based on the predicted weather information and the time information, it is possible to reflect the characteristics of the power load that varies according to time and weather conditions. Therefore, accurate power load prediction amount can be calculated.
  • FIG. 1 is a conceptual diagram illustrating a method for creating a database for power load prediction according to an embodiment of the present invention.
  • FIG. 2 is a conceptual diagram illustrating a method of grouping time unit power data according to an embodiment of the present invention.
  • FIG. 3 is a conceptual diagram illustrating a method of grouping time unit power data according to an embodiment of the present invention.
  • FIG. 4 is a conceptual diagram illustrating a method of calculating an average temperature for each time and season according to an embodiment of the present invention.
  • FIG. 5 is a flowchart illustrating a power load prediction method according to an embodiment of the present invention.
  • FIG. 6 is a block diagram illustrating an apparatus for predicting power load according to an embodiment of the present invention.
  • first and second may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.
  • the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.
  • the temperature information and the humidity information measured in units of 1 hour are averaged in units of 3 hours in order to collect a database for predicting power demand for convenience of description.
  • measurement time units other than one hour may be used to collect a database for predicting power demand, and an average value may also be used other than three hours.
  • information other than temperature information and humidity information may be used as information for predicting power demand.
  • FIG. 1 is a conceptual diagram illustrating a method for creating a database for power load prediction according to an embodiment of the present invention.
  • FIG. 1 discloses a method of generating power unit data by measuring weather load and power load such as temperature and humidity.
  • T may represent a temperature 100
  • H may represent a humidity 110
  • L may represent a load 120.
  • the temperature information 100 and the humidity information 110 may perform power load prediction including other weather information as an example of weather information, and such embodiments are also included in the scope of the present invention.
  • the temperature T and the humidity H may be measured and recorded in units of 1 hour for 24 hours a day.
  • the power load L generated at the time when the temperature and humidity are measured may be measured and recorded.
  • This data unit is referred to as hourly power data 130. That is, the time unit power data may be one data unit including temperature information, humidity information, and power load information.
  • the hourly power prediction data 130 may be gathered in units of three hours to generate the power data 140 in units of three hours. That is, 1 hour unit power data 130 is 24 hours per day 3 hours (1h ⁇ 3h, 4h ⁇ 6h, 7h ⁇ 9h, 10h ⁇ 12h, 13h ⁇ 15h, 16h ⁇ 18h, 19h ⁇ 21h, 22h ⁇ 24h It can be included in one of eight sets divided by).
  • the time unit power data may be grouped as seasonal data, monthly data, and daily data to generate a time unit power data group.
  • This time unit of power data group may be used to receive the predicted weather information and to calculate the power load forecast based on the power load forecast calculation function.
  • FIG. 2 is a conceptual diagram illustrating a method of grouping time unit power data according to an embodiment of the present invention.
  • time unit power data may be grouped in consideration of power load variation characteristics according to time information (season, month, day, time) of the power load.
  • Hourly power data measured in March- May is spring
  • hourly power data measured in June-August is summer
  • hourly power data measured in September-November are autumn, December-February.
  • the time unit power data measured at may be classified as winter to group the time unit power data to include the measured data in a specific time unit power data group.
  • the specific weather information included in the time unit power data can be used to determine in which season the measured time unit power data will be grouped. This embodiment will be further described in detail.
  • the hourly power data can also be grouped monthly.
  • the time unit power data grouped into the spring may be classified and grouped into time unit power data measured in March, time unit power data measured in April, and time unit power data measured in May. .
  • FIG. 2B is a conceptual diagram illustrating time unit power data grouped for each season. Referring to FIG. 2B, power data of three hours may be included with respect to the number of days included in a corresponding season.
  • time unit power data of FIG. 2B is a time unit power data group corresponding to March
  • a power load prediction value that may occur on a specific day in March is calculated based on the time unit power data group. Can be.
  • the Meteorological Agency may use the temperature and humidity prediction values of the Meteorological Agency as inputs for calculating the power load prediction value if the temperature and humidity of a specific day are divided into three hours to provide eight temperature and humidity prediction values.
  • the power load prediction value may be calculated using the power load calculation function based on the time unit power data, the temperature prediction value, and the humidity prediction value included in the time unit power data set of FIG. 2B.
  • Various methods may be used to calculate a power load prediction value that may occur based on the time unit power prediction data group, the temperature prediction value, and the humidity prediction value.
  • a method of calculating a power load prediction value in the time unit power prediction group of FIG. 2B compares all the time unit power data included in the time unit power prediction group with the temperature and the predicted humidity predicted by the Meteorological Administration. Time unit power data having a temperature and humidity most similar to the predicted temperature and the predicted humidity may be calculated. A method of determining the power load value included in the calculated time unit power data as the power load prediction value at the predicted temperature and the predicted humidity may be used.
  • an average value of power load values calculated from time unit power data having a temperature and humidity included in a predetermined range in the predicted temperature and the predicted humidity may be determined as the power load predicted value.
  • the power load prediction value may be calculated by giving more weight to the power load of the recently measured time unit power data among the time unit power data having the temperature and humidity included in a predetermined range in the predicted temperature and the predicted humidity. It may be. Since power loads change gradually with industry developments and population changes, it is likely that recent measured power load data will be the most meaningful value for power load predictions. Can be used to calculate power load estimates.
  • the function of calculating the power load prediction value according to the time unit power data included in the predicted temperature, the predicted humidity, and the time unit power data group as described above may be referred to as a power load prediction value calculation function.
  • the power load prediction value calculation function for calculating the power load prediction value.
  • grouping may be performed not only on a monthly basis, but also on a daily basis.
  • the hourly power data may be grouped again into another hourly power data group by determining whether the data corresponds to a weekday, Saturday, or Sunday.
  • Weekdays, Saturdays, and Sundays are one exemplary classification for initiating groupings based on days when power loads may vary. Therefore, additional classifications (eg, holidays, holidays, etc.) may be further classified and used as a time unit power data group for calculating a power load prediction amount.
  • the power load prediction value can be calculated. For example, if March 1 is a weekday, the hourly power data group grouping the hourly power data corresponding to the weekday in March, and the temperature and the predicted humidity predicted by the Meteorological Administration are input to the power load estimating function. The value can be used to calculate the power load forecast amount. For example, the hourly unit power data having a temperature and humidity corresponding to a predetermined range may be calculated from the hourly unit power data group on the basis of the temperature and the humidity predicted by the Meteorological Agency. An estimated value of the power load may be calculated based on the calculated power load of the time unit power data.
  • the hourly power data group containing hourly data measured seasonally is the hourly power data group by season
  • the hourly power data group containing hourly data measured monthly is the monthly hourly power data group
  • a daily time unit power data group containing hourly unit data measured in days is a daily time unit power data group
  • a time unit power data group containing hourly unit data measured in hours is called hourly power data group. can do.
  • time unit power data is arbitrary and may be grouped in more detail or grouped in a larger time unit. That is, the measured time unit power data may be adaptively grouped as needed to be used to perform power prediction, and such embodiments may also be included in the scope of the present invention.
  • FIG. 3 is a conceptual diagram illustrating a method of grouping time unit power data according to an embodiment of the present invention.
  • FIG. 3 a method of performing grouping by performing seasonal division for a month in which the season is not clear (for example, February, March, June, June, September, November, December) is disclosed.
  • February, March, May, June, August, September, November, and December are examples of months in which the seasons are not clear. These months can be defined and used in terms of seasonally reclassified months.
  • February is a seasonal reclassification month, and the time unit power data measured in February 200 will be grouped into a time unit power data group corresponding to spring according to Equation 1 below, or a time unit corresponding to winter It may be determined whether to be grouped into a power data group.
  • Ti which is disclosed in Equation 1, represents a temperature value of currently measured three-hour power data.
  • Ti w indicates the average of the temperature for each time unit calculated from the time unit power data included in the time unit power data group corresponding to winter, and Ti, s is the time unit included in the time unit power data group corresponding to spring Indicates the average of the temperature for each time unit calculated from the power data.
  • a1 indicates the set weight. The value of the weight may vary, and may preferably vary in the range of 0 or more and 1 or less.
  • FIG. 4 is a conceptual diagram illustrating a method of calculating an average temperature for each time and season according to an embodiment of the present invention.
  • 4A discloses a method of calculating an average temperature for each time and season.
  • 4B discloses a method of calculating an average temperature for each hour from 3 hourly power data measured during the day.
  • a time unit power data group may exist for each specific season, and time unit power data measured in units of 3 hours may exist in the time unit power data group for each season.
  • time and average temperature corresponding to eight time sets for each season may be calculated.
  • FIG. 4A is a three-hour unit power data set classified as spring
  • the average of temperatures calculated from the power data sets corresponding to 1 to 3h may be calculated as T1, s.
  • the following seasonal time unit power data average values may be calculated.
  • the average temperature may also be calculated from power data measured for three hours.
  • the average temperature included in the three-hour power data calculated in three-hour units is T1 (1 to 3h), T2 (4 to 6h), T3 (7 to 9h), T4 (10 to 12h), and T5, respectively, depending on the time. 13 to 15h, T6 (16 to 18h), T7 (19 to 21h), and T8 (22 to 24h).
  • Seasonal classification is performed on the three-hour power data measured on a specific day by using the above-described time and seasonal average temperature value and the average temperature included in the three-hour power data using the seasonal division formula such as Equation 1 described above. Grouping is performed. That is, eight time unit power data may be calculated per day, and it may be determined whether the eight time unit power data are included in each season.
  • February 300 may be classified as one season of winter and spring, and May 320 may be classified as one season of spring and summer.
  • February 300 and March 340 are time periods from winter to spring, and the hourly power data measured in February 320 and March 340 may be grouped into spring or winter. .
  • seasons may be classified by the above Equation 1.
  • time unit data measured using Equation 2 below is grouped as spring or winter.
  • Equation 1 (February, 300)
  • the sum of winter time and seasonal temperature average value (spring time and seasonal temperature average value-winter time and seasonal temperature average value) is added. If the hourly power data measured in February 300 is greater than or equal to the above value, it is classified as spring and if the hourly power data measured in February 300 is smaller than the above value, it is winter. Are classified.
  • Equation 2 (March, 340), it is a formula that adds (winter time and seasonal temperature average value-spring time and seasonal temperature average value) to the spring time and seasonal temperature average value, and the time unit power measured in March If the data is less than or equal to the above value, it is classified as winter and if the hourly power data measured in March is greater than the above value, it is classified as spring.
  • seasonal classification may be performed on measured power unit data using different equations depending on which season the month is closer to.
  • the above classification method is one example to perform a more detailed classification (for example, full unit classification) to perform the season judgment, or the same classification method (for example, February (300) and March (320) Season judgment can be performed using the same formula), and such embodiments are also included in the scope of the present invention.
  • a more detailed classification for example, full unit classification
  • the same classification method for example, February (300) and March (320) Season judgment can be performed using the same formula
  • formula for classifying the seasons may use other formulas to perform the seasonal classification on the time unit power data measured in a specific month as an example, and such embodiments are also included in the scope of the present invention.
  • FIG. 5 is a flowchart illustrating a power load prediction method according to an embodiment of the present invention.
  • weather information and power load information are collected (step S500).
  • weather information and power load information may be collected to use a method of predicting power load according to weather information.
  • temperature information or humidity information may be used.
  • Seasonal appliances such as heating appliances, air conditioners, dehumidifiers, etc.
  • the weather information may have a different amount of power. That is, the power load measured according to the weather information may be utilized to calculate the power load prediction amount according to the predicted weather information.
  • the temperature information and the humidity information may be other weather information as one example, and such an embodiment may also be included in the scope of the present invention.
  • the weather information and the power load information may be obtained at regular time units.
  • the time unit power data may be data including temperature information, humidity information, and power load information of a specific time unit. For example, one hourly power data measured in one hour unit may exist, and three hourly unit power data of three such one hourly unit power data may be present. Such time-group data constant grouping may be performed to form a time-unit power data group, which may be used to calculate a power load forecast later.
  • the time unit power data is grouped (step S510).
  • the time unit power data may be grouped on a predetermined basis to form a time unit power data group. For example, seasonal grouping, monthly grouping, daily grouping, and hourly grouping may be performed as described above. This grouped data can then be used to calculate power load forecasts at predicted temperatures and predicted humidity.
  • the specific day may be included in a plurality of sets such as a seasonal grouping set, a monthly unit, a grouping set, a daily grouping set, and the like.
  • the time unit power data measured in the month in which the season changes may be grouped through an additional classification step.
  • Various power load prediction functions may be used to calculate a power load prediction amount based on a set of time-grouped power data. For example, when the temperature prediction value and the humidity prediction value are received as input values at a specific time, the power prediction amount may be calculated using the following procedure.
  • a time-based power data group for calculating a power load prediction amount may be determined.
  • time unit power data having weather information most similar to the input temperature predicted value and humidity predicted value may be selected, and the power load amount of the corresponding time unit power data may be determined as the power load predicted amount.
  • Another method is to select the time unit power data having weather information corresponding to a range of values similar to the input temperature predicted value and humidity predicted value in the time unit power data group determined by the average value or median value of the power load of the corresponding power unit power data May be determined as the power load prediction amount.
  • the power load prediction value may be calculated by giving more weight to the recently measured power load among the power loads calculated from time unit power data having temperature and humidity within a predetermined range from the predicted temperature and humidity. have.
  • the power load prediction function that receives the temperature prediction value and the humidity prediction value as an input value at a specific time and calculates the power load prediction amount may be used as well as various functions, and such embodiments are also included in the scope of the present invention.
  • Collecting weather information and power load information and grouping the collected data may be performed continuously. In addition, data collected after a certain period of time can be discarded to improve the accuracy of power load prediction.
  • the temperature prediction value and the humidity prediction value at a specific time point are input (step S520).
  • the specific time point may be information on a specific month, day, and time.
  • the temperature prediction value and the humidity prediction value may be provided by a department that predicts weather information such as the Meteorological Agency.
  • the Meteorological Agency may provide eight three-hour temperature predictions and humidity predictions by dividing the 24-hour period into three-hour increments for the next day's temperature and humidity predictions.
  • the power load management center may calculate the power load prediction amount using the power load prediction amount calculation function as an input value using the hourly temperature prediction value and the humidity prediction value provided by the Meteorological Administration. As described above, a time unit power data set for selecting a power load prediction amount is selected based on an input value. Based on the time unit power data included in the selected time unit power data set, the power load prediction amount for the temperature prediction value and the humidity prediction value for each time point received may be calculated.
  • the power load predicted amount is calculated based on the temperature predicted value and the humidity predicted value received at the specific time point (step S530).
  • the following method may be used to calculate the power load prediction amount based on the input temperature prediction value and the humidity prediction value.
  • a set of grouping time unit power data corresponding to a specific time point input from the database is selected.
  • the power load prediction amount is calculated by using the power load prediction amount calculation function based on the set of grouping the selected unit of time power data and the temperature prediction value and the humidity prediction value at a specific time point received.
  • FIG. 6 is a block diagram illustrating an apparatus for predicting power load according to an embodiment of the present invention.
  • the power load predicting apparatus may include an input unit 600, a database 620, a power unit group determining unit 620, and a power load estimating unit 660.
  • the above components are separately expressed for the sake of function, and may be divided into a plurality of components even when expressed as a single component, and a plurality of components may be combined into a single component.
  • the input unit 600 may input weather information and power load information measured by a specific time unit.
  • the method of configuring the database 620 by collecting weather information and power load information may be continuously performed so that data for predicting power load may reflect more current power load information.
  • the input unit 600 may receive the predicted weather information (for example, the predicted temperature information and the predicted humidity information) and transmit the predicted weather information to the power load estimating calculator 660.
  • the predicted weather information for example, the predicted temperature information and the predicted humidity information
  • the database 620 may store time unit power data including weather information for each time point and power load information input from the input unit 600 and group the data according to a predetermined criterion. For example, you can group by season, month, or day. Although grouping may be performed using only temporal information for grouping, grouping may be performed considering other weather information. For example, grouping of time unit power data measured in a corresponding month may be performed by using a formula for determining which season to classify for months existing in a section in which a season changes.
  • the grouping of the collected data may be continuously performed. Data collected after a certain period of time can be discarded to increase the accuracy of power load prediction.
  • the database 620 may determine a time unit power data group used to calculate a power load forecast amount based on the predicted weather information input from the input unit 600, and then may convert the information into a power load forecast amount calculator 660.
  • the time unit power data group determiner 640 may be included.
  • the power load estimator 660 calculates the power load estimator based on the predicted weather information input from the input unit 600 and the time unit power data group determined by the time unit power data group determiner 640 of the database 620. Can be calculated. That is, the power load estimating calculator 660 may calculate the power load estimating amount based on the predicted weather information and the grouping set information received by using a predetermined power load estimating function. As described above, various functions may be used as the power load prediction amount calculation function.
  • the present invention relates to a method for predicting a power load, which can be used in the field of power systems.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Power Engineering (AREA)
  • Health & Medical Sciences (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

L'invention porte sur un procédé de prédiction de charge de puissance et sur un appareil utilisant un tel procédé. Le procédé de prédiction de charge de puissance peut comprendre les étapes consistant : à recevoir des informations de prévisions météorologiques ; à déterminer un groupe de données de puissance par unité de temps à utiliser pour calculer une charge de puissance prédite sur la base des informations de prévisions météorologiques ; et à calculer la charge de puissance prédite sur la base des prévisions météorologiques et des données de puissance par unité de temps contenues dans le groupe de données de puissance par unité de temps déterminé. En conséquence, la charge de puissance prédite peut se calculer avec précision en se basant sur les données de temps et de température.
PCT/KR2013/012333 2012-12-28 2013-12-27 Procédé de prédiction de charge de puissance et appareil utilisant le procédé WO2014104829A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020120157648A KR20140087411A (ko) 2012-12-28 2012-12-28 전력 부하 예측 방법 및 이러한 방법을 수행하는 장치
KR10-2012-0157648 2012-12-28

Publications (1)

Publication Number Publication Date
WO2014104829A1 true WO2014104829A1 (fr) 2014-07-03

Family

ID=51021766

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2013/012333 WO2014104829A1 (fr) 2012-12-28 2013-12-27 Procédé de prédiction de charge de puissance et appareil utilisant le procédé

Country Status (2)

Country Link
KR (1) KR20140087411A (fr)
WO (1) WO2014104829A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105590140A (zh) * 2015-11-26 2016-05-18 国网北京市电力公司 电力系统短期负荷的预测方法和装置
CN111091217A (zh) * 2018-10-23 2020-05-01 中国电力科学研究院有限公司 一种楼宇短期负荷预测方法及系统

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101718976B1 (ko) * 2015-06-22 2017-03-22 주식회사 케이티 계절 및 시간에 따른 에너지 부하를 고려한 지능형 에너지 수요 관리 장치 및 그 방법
KR102495494B1 (ko) * 2016-03-14 2023-02-06 주식회사 직방 가정의 에너지 사용량 예측 방법 및 장치
KR102011314B1 (ko) * 2017-10-12 2019-10-21 전자부품연구원 단위 가구 피크 전력 수요량 예측 방법 및 시스템

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003180032A (ja) * 2001-12-10 2003-06-27 Toshiba Corp 電力需要予測システム及びその予測方法
JP2012143098A (ja) * 2011-01-05 2012-07-26 Kankyo Keiei Senryaku Soken:Kk 使用電力量予測システム、及び使用電力量予測システムの制御方法
JP2012196017A (ja) * 2011-03-15 2012-10-11 Chugoku Electric Power Co Inc:The 電力需要予測装置及び電力需要予測方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003180032A (ja) * 2001-12-10 2003-06-27 Toshiba Corp 電力需要予測システム及びその予測方法
JP2012143098A (ja) * 2011-01-05 2012-07-26 Kankyo Keiei Senryaku Soken:Kk 使用電力量予測システム、及び使用電力量予測システムの制御方法
JP2012196017A (ja) * 2011-03-15 2012-10-11 Chugoku Electric Power Co Inc:The 電力需要予測装置及び電力需要予測方法

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105590140A (zh) * 2015-11-26 2016-05-18 国网北京市电力公司 电力系统短期负荷的预测方法和装置
CN111091217A (zh) * 2018-10-23 2020-05-01 中国电力科学研究院有限公司 一种楼宇短期负荷预测方法及系统
CN111091217B (zh) * 2018-10-23 2022-07-08 中国电力科学研究院有限公司 一种楼宇短期负荷预测方法及系统

Also Published As

Publication number Publication date
KR20140087411A (ko) 2014-07-09

Similar Documents

Publication Publication Date Title
WO2014104829A1 (fr) Procédé de prédiction de charge de puissance et appareil utilisant le procédé
WO2015163732A1 (fr) Procédé et appareil de fonctionnement d'un système intelligent pour une optimisation de consommation d'énergie
JP5355147B2 (ja) 排出係数算定器および排出係数算定方法
WO2013039336A1 (fr) Appareil et procédé d'exécution d'un processus de réponse à une demande en énergie dans un réseau d'alimentation électrique
WO2017142241A1 (fr) Procédé de gestion d'énergie pour un système ess connecté à une énergie nouvelle et renouvelable
JP5126308B2 (ja) 電力コントロール装置
JP6543145B2 (ja) ピーク電力予測装置、電力管理システム及びピーク電力予測方法
Tang et al. Impacts of technology-guided occupant behavior on air-conditioning system control and building energy use
CN103208085B (zh) 企业用电提高负荷率与降低最大需量的分析智能系统
WO2011052957A2 (fr) Procédé de commande d'un système en réseau
US20140371933A1 (en) Electric power consumption management system and method
CN107103091B (zh) 一种物联网大数据接入节能管控方法及装置
CN108922157A (zh) 一种自学习智能抄表方法及系统
CN112598155A (zh) 一种变电站的负荷增减预估方法及系统
JP2018160990A (ja) 負荷管理装置および方法
KR20180098179A (ko) 대상 건물에 대한 에너지 절감 가이드를 제공하는 시스템
CN202870163U (zh) 空调耗电处理装置及系统
KR20160044640A (ko) 도시에너지관리를 위한 용도별 시간대별 전력수요 예측시스템
CN102156918A (zh) 智能电网播报系统及方法
CN104380556A (zh) 电力管理设备及电力管理方法
CN113746105A (zh) 电力需求响应的优化控制方法、装置、设备和存储介质
CN210801358U (zh) 利用电价杠杆的新能源消纳供暖系统
Wang et al. Consumer-centric spatiotemporal reliability assessment and compensation model with sensitive component analysis in smart grid
WO2019074173A1 (fr) Procédé et système de prédiction de pic de demande d'électricité par foyer unitaire
WO2019132054A1 (fr) Système de commande de demande de puissance maximale utilisant un dispositif de stockage d'énergie

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13868909

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 13868909

Country of ref document: EP

Kind code of ref document: A1