KR101662809B1 - Apparatus and method for forecasting electrical load in railway station - Google Patents

Apparatus and method for forecasting electrical load in railway station Download PDF

Info

Publication number
KR101662809B1
KR101662809B1 KR1020150075237A KR20150075237A KR101662809B1 KR 101662809 B1 KR101662809 B1 KR 101662809B1 KR 1020150075237 A KR1020150075237 A KR 1020150075237A KR 20150075237 A KR20150075237 A KR 20150075237A KR 101662809 B1 KR101662809 B1 KR 101662809B1
Authority
KR
South Korea
Prior art keywords
power demand
day
factor
time
pattern
Prior art date
Application number
KR1020150075237A
Other languages
Korean (ko)
Inventor
장민석
공성배
고락경
주성관
Original Assignee
고려대학교 산학협력단
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 고려대학교 산학협력단 filed Critical 고려대학교 산학협력단
Priority to KR1020150075237A priority Critical patent/KR101662809B1/en
Application granted granted Critical
Publication of KR101662809B1 publication Critical patent/KR101662809B1/en

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
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • 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
    • Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies

Abstract

The present invention proposes a power demand forecasting method in railroad history. The method of predicting power demand in a railroad history comprises the steps of: selecting input data associated with a forecasted date based on a first factor that is performed in a railroad historical electricity demand forecasting device and that affects prediction of power demand at a forecasted date; Generating a power demand pattern based on the input data based on the first factor using a time series model; Generating a corrected power demand pattern by correcting an error caused by a second factor that affects power demand prediction of the predicted day; And estimating a total load per unit time of the predicted day using the corrected power demand pattern.

Description

TECHNICAL FIELD [0001] The present invention relates to a method of predicting electric power demand in railroad history,

The present invention relates to a method and apparatus for predicting power demand in a railroad history, and more particularly, to a method and apparatus for predicting power demand in a railroad history by reflecting factors of a railroad driving information affecting a power demand pattern in a railroad history .

Accurate power demand forecasting enables a systematic and stable power operation, and also enables economic power saving by enabling power supply at minimum cost.

Generally, power demand is forecasted by using time series model, which is a time series data that varies with seasonal and weekly regular patterns. Even in the case of railroad history, the schedule of railway operations changes according to the day of the week, the demand for electric power required for railroad operation changes, and according to the seasonal factors, the air-conditioning system is operated in addition to the railroad operation. At this time, in the case of railroad history, a constant power demand pattern changes due to the effect of work and time of departure, and it is difficult to accurately predict the load in the railroad history by a general time series prediction method.

The present invention has been made in order to solve a problem of a somewhat large error between the electric power demand amount and the actual usage amount predicted by the time series prediction method in predicting the electric power demand amount in the railroad history, The present invention provides a method and an apparatus for predicting a more accurate electric power demand by performing a correction using the external element and the railway driving information with respect to the electric power demand amount predicted by the electric power demanding unit.

A method for predicting power demand in a railroad history according to an embodiment of the present invention is a method for predicting power demand in a railroad history, which is performed in a power demand forecasting apparatus in a railroad history and selects input data associated with a forecasting date based on a first factor ; Generating a power demand pattern based on the input data based on the first factor using a time series model; Generating a corrected power demand pattern by correcting an error caused by a second factor that affects power demand prediction at a predicted date; And predicting a total load per unit time of the forecast day using the corrected power demand pattern.

An apparatus for predicting power demand in a railway station according to an embodiment of the present invention includes a data selection unit that selects input data associated with a forecasted date based on a first factor affecting a forecasted power demand of a forecasted day; A pattern generation unit for generating a power demand pattern based on the input data based on the first factor using a time series model; An error corrector for generating a corrected power demand pattern by correcting an error caused by a second factor that affects power demand prediction at a predicted date; And a power demand predicting unit for predicting the total load per unit time of the forecast day using the corrected power demand pattern.

The present invention relates to a railway station historical power demand forecasting program according to an embodiment of the present invention, which is a program stored in a recording medium, the program being executed in a computing system, A command set for selecting input data; A set of instructions for generating a power demand pattern based on the input data based on a first factor using a time series model; A set of instructions for generating a corrected power demand pattern by correcting an error due to a second factor affecting a power demand forecast of a predicted day; And a command set for predicting the total load per unit time of the forecast day using the corrected power demand pattern.

The method and apparatus for predicting the electric power demand in the railroad history according to the embodiment of the present invention corrects the electric power demand predicted by the time series analysis using the external element and the railway running information, It becomes possible.

In addition, efficient power supply planning and stable power system operation in the railroad history are possible, and the efficiency of operation of regenerative power in railroad history and energy storage scheduling efficiency can be enhanced.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS In order to more fully understand the drawings recited in the detailed description of the present invention, a detailed description of each drawing is provided.
1 is a functional block diagram of an apparatus for predicting power demand in a railroad according to an embodiment of the present invention.
FIG. 2 is a flowchart for explaining a power demand forecasting method in the railroad history performed in the electric power demand forecasting apparatus in the railroad history shown in FIG. 1. FIG.
FIG. 3 shows a detailed flow chart of the power demand correction step shown in FIG.

It is to be understood that the specific structural or functional description of embodiments of the present invention disclosed herein is for illustrative purposes only and is not intended to limit the scope of the inventive concept But may be embodied in many different forms and is not limited to the embodiments set forth herein.

The embodiments according to the concept of the present invention can make various changes and can take various forms, so that the embodiments are illustrated in the drawings and described in detail herein. It should be understood, however, that it is not intended to limit the embodiments according to the concepts of the present invention to the particular forms disclosed, but includes all modifications, equivalents, or alternatives falling within the spirit and scope of the invention.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the meaning of the context in the relevant art and, unless explicitly defined herein, are to be interpreted as ideal or overly formal Do not.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings attached hereto.

1 is a functional block diagram of an apparatus for predicting power demand in a railroad according to an embodiment of the present invention.

Referring to FIG. 1, the power demand prediction apparatus 100 includes a data selection unit 110, a pattern generation unit 120, an error correction unit 130, and a power demand prediction unit 140.

The power demand predicting apparatus 100 includes a data predicting unit 110, a pattern generating unit 120, an error correcting unit 130, and a power demand predicting unit 140, And may further include a processor (not shown). Alternatively, the data selection unit 110, the pattern generation unit 120, the error correction unit 130, and the power demand prediction unit 140 are operated by respective ones of the processors (not shown) The electric power demand forecasting apparatus 100 may be operated as a whole as the electric power demand forecasting apparatus 100 operates mutually organically. Alternatively, the data predicting unit 110, the pattern generating unit 120, the error correcting unit 130, and the power demand predicting unit 140 are controlled by the external processor (not shown) of the power demand predicting apparatus 100 May be controlled.

The power demand predicting apparatus 100 may further include a database (not shown) for storing input / output data generated in processing various data to predict power demand in the railroad history. The control unit 100 may further include a memory control unit (not shown) for controlling data input / output of a database (not shown).

The power demand prediction apparatus 100 can communicate with a central server of a railroad history or a server of each station via a data communication network. The data communication network may be a wired Internet network including an open Internet, a closed intranet, a wireless Internet communication network interworking with a mobile communication network, a protocol based protocol such as TCP (Transmission Control Protocol) / IP (Internet Protocol) And a possible communication means such as a computer network capable of various data communication including data communication. For example, the power demand predicting apparatus 100 can perform data communication based on an IP socket method or a web socket method.

Hereinafter, the operation of the electric power demand forecasting apparatus 100 will be described in detail with reference to FIG. 1 and FIG. FIG. 2 is a flowchart for explaining a power demand forecasting method in the railroad history performed in the electric power demand forecasting apparatus in the railroad history shown in FIG.

In step 210, the data selection unit 110 of the power demand forecasting apparatus 100 may select the input data associated with the prediction date, taking into account the first factor affecting the forecasted power demand.

In the case of railroad history, railroad operation schedules are generally divided into three criteria on weekdays, Saturdays, and holidays (including Sundays). Electricity demand for railway operations varies according to railway schedule.

In one embodiment, the first factor may be a day-to-day factor of the predicted day. For example, each day of the week may be divided into three sections, a first section including weekdays (Monday through Friday), a second section including Saturdays, and a third section including holidays (Sunday and holidays) Can be classified.

As another example, each day of the week may be classified into a first section including a weekday, a second section including a Saturday, a third section including a Sunday, and a fourth section including a holiday. As a result, the first factor may mean information about a section including a prediction date.

Since the input data needs to be selected according to the prediction model in order to accurately predict the power demand when using the time series model, the data selection unit 110 may have the same or similar characteristics as the first factor that affects the power demand of the forecasted day The past power demand data and the past factors are selected as the input data.

The data selection unit 110 inputs data of the past (for example, 20 days before the prediction date) before the prediction date having the same or similar characteristics as the day to be predicted on the basis of the three intervals classified according to the characteristic of each day of the week Data can be selected. The input data uses the data acquired in a predetermined time unit. In this embodiment, the power demand data acquired in units of 15 minutes, which is the unit time of the real-time electricity charge, is used as raw data.

Specifically, when the day to be predicted corresponds to the first section (weekday), the data selection section 110 outputs the first power demand data of the last 20 days belonging to the first section of the power demand data The second power demand data of the last 20 days belonging to the second section of the power demand data before the predicted day (the total of the second power demand data of the last 20 days belonging to the second section) 1920) as the second input data. If the forecast date belongs to the third section (holiday), the third power demand data (1920 total) of the last 20 days belonging to the third section of the power demand data before the forecast date is selected as the third input data.

Unlike the present embodiment, when the day to be predicted belongs to a holiday, if the day to be predicted belongs to a holiday, the power demand data belonging to the fourth section of the same power demand data within the past three years The fourth power demand data of 10 days can be selected as the fourth input data. When the day to be predicted belongs to weekday / Saturday / Sunday, the input data selection method is the same as the input data selection method according to the present embodiment.

In step 220, the pattern generator 120 of the power demand forecasting apparatus 100 generates a power demand pattern according to the input data according to the characteristics of the first factor, Can be generated.

Generally, power demand is predicted using a time series model with time series data varying with seasonal and day of week regular patterns. In one embodiment of the present invention, a power demand pattern is generated using a Seasonal Autoregressive Integrated Moving Average (SARIMA) model.

If the current state of the time series is influenced by the past state and the past continuous error term, the present observation value can be expressed as a function of the past observation and error term, and the autoregressive moving average ) Model. The ARIMA model is called the ARIMA model and the seasonal differential model is used to model the seasonal variation of the seasonal variation. It is called the Autoregressive Cumulative Moving Average (SARIMA) model. The time series models including the SARIMA model are widely used for silver power demand prediction, and a detailed description thereof will be omitted.

The pattern generation unit 120 generates a pattern based on the first factor of the prediction date and the actual power consumption amount over the past predetermined period selected by the data selection unit 110 (for example, 10 days before the prediction date, 20 days before the prediction date) Is applied to the SARIMA model as input data to generate the power demand pattern for the forecasted day.

Specifically, when the forecast date belongs to the first section, the pattern generator 120 generates the first power demand pattern through the SARIMA model using the selected first input data, and if the forecast date belongs to the second section The pattern generator 120 generates the second power demand pattern through the SARIMA model using the selected second input data. If the prediction date belongs to the third period, the pattern generation unit 120 generates the third power demand pattern through the SARIMA model using the selected third input data.

At this time, the pattern generating unit 120 generates a pattern corresponding to each section (weekday, Saturday, holiday) classified according to the first factor (day of week factor) by using the Aka (Akaike Information Criterion) and SBC (Schwartz's Baysian Criterion) The SARIMA optimal model can be determined. The AIC and SBC are statistically significant coefficients of the estimated coefficients and the index of the data fit. The smaller the value, the higher the fit of the model.

Although the power demand pattern was generated using the SARIMA model designed to satisfy the steady state average and variance of time series data, it is difficult to predict when the pattern changes because of the pattern using method, Lt; / RTI > Therefore, additional error correction is needed for more accurate power demand forecasting.

In step 230, the error correction unit 130 of the power demand prediction apparatus 100 performs correction based on the travel information amount error.

FIG. 3 shows a detailed flow chart of the power demand correction step shown in FIG.

In step 231, the error correcting unit 130 calculates an error between the scheduling operation amount and the actual operation amount for each day of the week according to the second factor that affects the power demand prediction on the predicted day using the data of the predetermined period before the prediction date Calculate the error averages (Kn, n = Monday, Tuesday, Wednesday, Thursday, Friday, Saturday and Sunday) for each day of the week. The scheduling operation amount by time period means the operation amount estimated by the operation schedule.

In the embodiment, the number of train users is higher than the other times in the train, so that errors occur frequently in the schedule. Therefore, the second factor is the temporal factor according to the effect of time of work, Lt; / RTI >

Specifically, in order to correct the errors due to the effect of the time of day to work, work, and non-commuting time, the first time zone including each day of the week from Monday to Saturday and the time zone of each day from Monday to Saturday And the third time zone including the time zone of work for each day of the week from Monday to Saturday, and the remaining time zones except for the leaving time zone. In the case of Sunday, the whole time zone is classified into the third time zone, which is the non-attendance / non-attendance time zone.

The error correction unit 130 calculates an error average Kn by time unit by calculating an error between the scheduling operation amount and the actual operation amount for each day of the week for a predetermined period (for example, one year) before the prediction date. The time average error average Kn is calculated from a first error average Gn, which is an error average of each working time zone from Monday to Saturday, a second error average Ln, which is an error average of each leaving time zone from Monday to Saturday, And a third error mean (Dn), which is an average of the error between the non-attendance and non-attendance time zones from Monday to Saturday and the entire time zone on Sunday.

In step 232, the error correction unit 130 corrects the scheduling operation amount St of the predicted day n by using the time average error average Kn. The scheduling operation amount (St) at the predicted day means the operation amount set at the unit time t by the operation schedule of the forecast day, and the corrected operation amount

Figure 112015051605917-pat00001
) Can be determined according to the following relationship.

Figure 112015051605917-pat00002

Since the power demand data acquired by the data selection unit 110 in units of 15 minutes is used, the unit time as a reference for the calculation of the scheduling operation amount or the modified operation amount can be set to 15 minutes, so that the predicted value to be corrected per each hour can be four .

In step 233, the error correction unit 130 corrects the corrected operating amount per hour

Figure 112015051605917-pat00003
) And the average of past power demand data (
Figure 112015051605917-pat00004
) Can be calculated by time. More specifically, the error correction unit 130 corrects the correction operation amount at the time t
Figure 112015051605917-pat00005
), The average of the power demand data corresponding to the search time ("
Figure 112015051605917-pat00006
) Can be obtained. For example, if the predicted day is a weekday, the average of the power demand data corresponding to the search time can be obtained after searching for a time having the same operation amount as the corrected operation amount of the data for the past one week, In the case of a holiday, the average of the power demand data corresponding to the search time can be obtained after searching for the time having the same operation amount as the corrected operation amount among the data for the past three weeks.

In step 234, the error correction unit 130 can calculate the power demand fluctuation ratio Rt for error correction. The error correcting unit 130 compares the power demand pattern predicted by the pattern generating unit 120

Figure 112015051605917-pat00007
) "Contrast" The average power demand data per hour calculated by the error corrector 130
Figure 112015051605917-pat00008
) &Quot;, it is possible to calculate the power demand fluctuation ratio (Rt).

Figure 112015051605917-pat00009

At this time, before calculating the power demand fluctuation ratio Rt, the power demand pattern predicted by the pattern generating unit 120

Figure 112015051605917-pat00010
) To the time average power demand data (
Figure 112015051605917-pat00011
) (15 minutes).

In step 235, the error correction unit 130 may perform time-based correction using the power demand fluctuation ratio (Rt) value. Power demand pattern after correction (

Figure 112015051605917-pat00012
) Is as follows.

Figure 112015051605917-pat00013

In step 240, the power demand predicting unit 140 calculates a corrected power demand pattern

Figure 112015051605917-pat00014
) Can be used to predict the total load per unit time of the forecast day.

The above-described method of predicting power demand in the railroad history can be realized by a general-purpose digital computer that can be implemented as a program that can be executed by a computer and operates the program using a computer-readable recording medium. Specifically, a power demand forecasting program in a railroad history comprises: a set of instructions to be executed in a computing system to select input data associated with the forecasting date based on a first factor affecting a forecasted power demand forecast; A set of instructions for generating a power demand pattern based on the input data selected based on the first factor using a time series model; A command set for generating a corrected power demand pattern by correcting an error caused by a second factor that affects power demand prediction of the predicted day; And a command set for predicting a total load per unit time of the predicted day using the corrected power demand pattern.

The power demand prediction program is stored in the recording medium, and the recording medium may be a magnetic storage medium such as a ROM, a floppy disk, a hard disk, etc., an optical reading medium such as a CD-ROM, a DVD, And a storage medium. In addition, the recording medium may be distributed and distributed to a network-connected computer system so that a computer-readable instruction set can be stored and executed in a distributed manner.

The block diagrams disclosed herein may be construed to those skilled in the art to conceptually represent circuitry for implementing the principles of the present invention. Likewise, any flow chart, flow diagram, state transitions, pseudo code, etc., may be substantially represented in a computer-readable medium to provide a variety of different ways in which a computer or processor, whether explicitly shown or not, It will be appreciated by those skilled in the art.

The functions of the various elements shown in the figures may be provided through use of dedicated hardware as well as hardware capable of executing the software in association with the appropriate software. When provided by a processor, such functionality may be provided by a single dedicated processor, a single shared processor, or a plurality of individual processors, some of which may be shared.

Also, the explicit use of the term " control portion "or" portion "should not be construed to refer exclusively to hardware capable of executing software and includes, without limitation, digital signal processor (DSP) hardware, (ROM), a random access memory (RAM), and a non-volatile storage device.

Reference throughout this specification to " one embodiment " of the principles of the invention and various modifications of such expression in connection with this embodiment means that a particular feature, structure, characteristic or the like is included in at least one embodiment of the principles of the invention it means. Thus, the appearances of the phrase " in one embodiment " and any other variation disclosed throughout this specification are not necessarily all referring to the same embodiment.

Claims (11)

In a method for predicting power demand in a railroad history performed by a power demand forecasting apparatus in a railroad history,
Selecting input data associated with the prediction date based on a first factor that affects power demand prediction at a prediction date;
Generating a power demand pattern based on the input data based on the first factor using a time series model;
Generating a corrected power demand pattern by correcting an error caused by a second factor that affects power demand prediction of the predicted day; And
Estimating a total load per unit time of the predicted day using the corrected power demand pattern,
The first factor is a day-to-day factor,
Wherein the step of generating the corrected power demand pattern comprises:
Dividing the time zone according to the second factor, calculating an error between the scheduling operation amount and the actual operation amount for each day of the first period before the prediction day, and calculating an error average for each day of the week;
Correcting a scheduling operation amount of the predicted day by using the average error for each day of the week;
Calculating an average of the power demand data of the second period before the prediction date having the same operating amount as the modified scheduling operating amount of the predicted day;
Calculating a power demand fluctuation ratio (Rt) for error correction using the power demand data average; And
And performing the correction of the power demand pattern using the value of the power demand variation ratio (Rt). The method according to claim 1,
The first factor is a day-to-day factor,
Wherein the input data includes power demand data of the day having the same or similar characteristics as those of the first factor of the predicted day among the power demand data of a predetermined period before the predicted day. The method according to claim 1,
The time series model is a seasonal autoregressive integrated moving average (SARIMA) model, which is a method for predicting power demand in railroad history. The method according to claim 1,
Wherein the second factor is a time factor depending on the time of the work, the time of the work, the time of the work, and the time outside the work time. delete A data selection unit that selects input data associated with the prediction date based on a first factor that affects power demand prediction at a prediction date;
A pattern generator for generating a power demand pattern corresponding to the input data selected based on the first factor using a time series model;
An error corrector configured to generate a corrected power demand pattern by correcting an error caused by a second factor that affects power demand prediction of the predicted day; And
And a power demand predicting unit for predicting a total load per unit time of the predicted day using the corrected power demand pattern,
The first factor is a day-to-day factor,
Wherein the error correcting unit comprises:
And calculating an error between the scheduling operation amount and the actual operation amount for each day of the first period before the predicted day to calculate an error average for each day of the week,
And corrects the scheduling operation amount of the predicted day by using the error average for each day of the week,
Calculating an average of the electricity demand data of the second period before the forecast date having the same operating amount as the corrected scheduling run amount of the predicted day,
Calculates a power demand fluctuation ratio (Rt) for error correction using the power demand data average,
And the power demand pattern is corrected using the power demand fluctuation ratio (Rt) value. The method according to claim 6,
The first factor is a day-to-day factor,
Wherein the data selection unit selects the power demand data of the day having the same or similar characteristic as the characteristic of the day of the forecast day from the power demand data of the predetermined period before the forecast date as the input data, Prediction device. The method according to claim 6,
Wherein the pattern generator uses the SARIMA model to generate the power demand pattern. The method according to claim 6,
Wherein the second factor is a time factor depending on a time of the work, a work time, and a time outside the work time and the work time. delete A computer-readable recording medium storing a program for executing the method according to any one of claims 1 to 4.
KR1020150075237A 2015-05-28 2015-05-28 Apparatus and method for forecasting electrical load in railway station KR101662809B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020150075237A KR101662809B1 (en) 2015-05-28 2015-05-28 Apparatus and method for forecasting electrical load in railway station

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150075237A KR101662809B1 (en) 2015-05-28 2015-05-28 Apparatus and method for forecasting electrical load in railway station

Publications (1)

Publication Number Publication Date
KR101662809B1 true KR101662809B1 (en) 2016-10-06

Family

ID=57164573

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020150075237A KR101662809B1 (en) 2015-05-28 2015-05-28 Apparatus and method for forecasting electrical load in railway station

Country Status (1)

Country Link
KR (1) KR101662809B1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107358318A (en) * 2017-06-29 2017-11-17 上海电力学院 Based on GM（1,1）The urban power consumption Forecasting Methodology of model and Grey Markov chain predicting model
CN110298490A (en) * 2019-05-31 2019-10-01 广州水沐青华科技有限公司 Time series Combination power load forecasting method and computer readable storage medium based on multiple regression
CN112561159A (en) * 2020-12-11 2021-03-26 国家电网有限公司 Hierarchical power supply and demand prediction method and system for metro level
KR102268104B1 (en) * 2020-02-18 2021-06-22 국민대학교산학협력단 Method of predicting load and apparatus thereof

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10322905A (en) * 1997-05-22 1998-12-04 Mitsubishi Electric Corp Contract power excess prevention device for railway substation

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10322905A (en) * 1997-05-22 1998-12-04 Mitsubishi Electric Corp Contract power excess prevention device for railway substation

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
전기학회 논문지* *
한국철도학회 논문지* *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107358318A (en) * 2017-06-29 2017-11-17 上海电力学院 Based on GM（1,1）The urban power consumption Forecasting Methodology of model and Grey Markov chain predicting model
CN110298490A (en) * 2019-05-31 2019-10-01 广州水沐青华科技有限公司 Time series Combination power load forecasting method and computer readable storage medium based on multiple regression
KR102268104B1 (en) * 2020-02-18 2021-06-22 국민대학교산학협력단 Method of predicting load and apparatus thereof
CN112561159A (en) * 2020-12-11 2021-03-26 国家电网有限公司 Hierarchical power supply and demand prediction method and system for metro level

Similar Documents

Publication Publication Date Title
JP5618501B2 (en) Demand prediction device, program and recording medium
Belderbos et al. Accounting for flexibility in power system planning with renewables
KR101662809B1 (en) Apparatus and method for forecasting electrical load in railway station
JP5789421B2 (en) Load amount prediction apparatus, load amount prediction method, and load amount prediction program
US20150142179A1 (en) Air-conditioning management device, air-conditioning management method, and program
Nieße et al. Conjoint dynamic aggregation and scheduling methods for dynamic virtual power plants
JP6617476B2 (en) Demand power prediction apparatus, demand power prediction method, and computer program
JP7099805B2 (en) Predictors, prediction systems, prediction methods and programs
JP6293291B2 (en) Power consumption estimation device, device management system, power consumption estimation method and program
Sun et al. Event-based optimization with non-stationary uncertainties to save energy costs of HVAC systems in buildings
KR101705869B1 (en) System for performing optimal managing of complex equipments based thermal energy demanding forcasting and method thereof
JP5833267B1 (en) Power generation amount predicting control device, power generation amount prediction method, and power generation amount prediction program
KR20130044765A (en) Appratus and method for estimation of weekly power load to improve processing time using neural network and revision factor
JP5622698B2 (en) Target power setting system, target power setting method and program
JP2017175845A (en) Energy demand prediction system, energy demand prediction method, and energy management system
Spencer et al. Selecting sensors when forecasting temperature in smart buildings
JP6605342B2 (en) Power demand forecasting device, power demand forecasting method, and power demand forecasting program
Spencer et al. Accurately forecasting temperatures in smart buildings using fewer sensors
JP6086561B1 (en) Partial supply control device, partial supply method, and partial supply program
Rasheed et al. Artificial intelligence-enabled probabilistic load demand scheduling with dynamic pricing involving renewable resource
JP2018061314A (en) Demand response planning system, demand response planning method, and demand response planning program
JP6029901B2 (en) Load amount prediction apparatus and load amount prediction method
Steens et al. A forecast based load management approach for commercial buildings--comparing LSTM and standardized load profile techniques
Agheb et al. Robust provisioning of demand-side flexibility under electricity price uncertainty
JP6520386B2 (en) Power system planning device

Legal Events

Date Code Title Description
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 20190808

Year of fee payment: 4