Electric power demand prediction system, electric power demand prediction method, consumer profiling system, and consumer profiling method

Patent metadata

Field	Value
Publication number	US-2016266181-A1
Application number	US-201615158729-A
Country	US
Kind code	A1
Filing date	May 19, 2016
Priority date	Nov 20, 2013
Publication date	Sep 15, 2016
Grant date	—

Abstract

An electric power demand prediction system has an extractor to select electric power consumption value data included in a certain period out of a consumer's past electric power consumption value data and to extract an outdoor temperature-electric power relation that is a relation between an outdoor temperature and outdoor-temperature-depend electric power varying in accordance with the outdoor temperature out of electric power consumption, a model generator to generate an electric power consumption prediction model which predicts electric power consumption by the consumer in accordance with the outdoor temperature based on the outdoor temperature-electric power relation extracted by the extractor, and a predictor to predict electric power consumption by the consumer at a time subject to prediction based on the electric power consumption prediction model generated by the model generator and the outdoor temperature at the time subject to prediction.

First claim

1 . An electric power demand prediction system, comprising:
an extractor to select electric power consumption value data included in a certain period out of a consumer's past electric power consumption value data and to extract an outdoor temperature-electric power relation that is a relation between an outdoor temperature and outdoor-temperature-depend electric power varying in accordance with the outdoor temperature out of electric power consumption based on the selected electric power consumption value data; a model generator to generate an electric power consumption prediction model which predicts electric power consumption by the consumer in accordance with the outdoor temperature based on the outdoor temperature-electric power relation extracted by the extractor; and a predictor to predict electric power consumption by the consumer at a time subject to prediction based on the electric power consumption prediction model generated by the model generator and the outdoor temperature at the time subject to prediction.

2 . The electric power demand prediction system according to claim 1 , wherein the extractor selects electric power consumption value data included in a period determined in advance.

3 . The electric power demand prediction system according to claim 1 , wherein the extractor generates several groups of electric power consumption value data, calculates indexes indicating degree of a correlation between an outdoor temperature and electric power consumption in each group, and compares the indexes to select electric power consumption value data included in a group with the highest correlation between the outdoor temperature and the electric power consumption.

4 . The electric power demand prediction system according to claim 1 , wherein the extractor selects electric power consumption value data in a time period in which the consumer is asleep or in a time period in which the consumer is absent from home.

5 . The electric power demand prediction system according to claim 1 , wherein the extractor calculates base electric power as a reference of electric power consumption by the consumer based on the electric power consumption value data and selects the electric power consumption value data with electric power consumption larger than the base electric power.

6 . The electric power demand prediction system according to claim 1 , wherein the extractor performs a regression analysis based on the electric power consumption value data with an outdoor temperature as an explanatory variable and outdoor-temperature-depend electric power as an objective variable and extracts the outdoor temperature-electric power relation based on an analysis result.

7 . The electric power demand prediction system according to claim 5 , wherein the model generator estimates a behavioral state that is a state of use of electric power by the consumer based on the outdoor temperature-electric power relation, generates a behavioral state prediction model for predicting a behavioral state of the consumer in accordance with an outdoor temperature based on the estimated behavioral state, calculates behavioral electric power that is residual electric power obtained by subtracting outdoor-temperature-depend electric power and base electric power from electric power consumption by the consumer, and predicts behavioral electric power of the consumer in each behavioral state based on the behavioral electric power and the behavioral state.

8 . The electric power demand prediction system according to claim 7 , wherein the model generator generates a behavioral state estimation model which estimates a behavioral state of the consumer in accordance with an outdoor temperature and electric power consumption based on the outdoor temperature-electric power relation.

9 . The electric power demand prediction system according to claim 7 , wherein the model generator takes the statistic of the estimated behavioral state to generate the behavioral state prediction model.

10 . The electric power demand prediction system according to claim 7 , wherein the model generator calculates outdoor-temperature-depend electric power based on the outdoor temperature-electric power relation and calculates behavioral electric power by subtracting the calculated outdoor-temperature-depend electric power and base electric power from electric power consumption by the consumer.

11 . The electric power demand prediction system according to claim 7 , wherein the behavioral state includes at least one of a state in which the consumer is using outdoor-temperature-depend electric power, a state in which the consumer Is not using outdoor-temperature-depend electric power, a state in which the consumer is using behavioral electric power, and a state in which the consumer is not using behavioral electric power.

12 . The electric power demand prediction system according to claim 1 , further comprising a preprocessor to perform at least one of smoothing process, supplement process, and abnormal value removal process on the electric power consumption value data to generate preprocessed electric power consumption value data.

13 . The electric power demand prediction system according to claim 1 , wherein the extractor acquires ON/OFF information indicating existence and non-existence of at least part of outdoor-temperature-depend electric power of the consumer and extracts the outdoor temperature-electric power relation based on the ON/OFF information and the electric power consumption value data.

14 . The electric power demand prediction system according to claim 13 , wherein the model generator estimates a behavioral state based on the ON/OFF information and the outdoor temperature-electric power relation.

15 . The electric power demand prediction system according to claim 1 , wherein the extractor acquires part of outdoor-temperature-depend electric power of the consumer and extracts the outdoor temperature-electric power relation based on the acquired outdoor-temperature-depend electric power and the electric power consumption value data.

16 . The electric power demand prediction system according to claim 1 , further comprising an electric power reduction amount estimator to estimate an amount of reduction in electric power by the consumer when demand response is performed based on the electric power consumption by the consumer at the time subject to prediction predicted by the predictor, wherein
the predictor predicts electric power consumption by the consumer at the time subject to prediction when demand response is performed based on the amount of reduction in electric power estimated by the electric power reduction amount estimator.

17 . An electric power demand prediction method, comprising:
selecting electric power consumption value data included in a certain period out of a consumer's past electric power consumption value data and extracting an outdoor temperature-electric power relation that is a relation between an outdoor temperature and outdoor-temperature-depend electric power varying in accordance with the outdoor temperature out of electric power consumption based on the selected electric power consumption value data; generating an electric power consumption prediction model for predicting electric power consumption by the consumer in accordance with the outdoor temperature based on the extracted outdoor temperature-electric power relation; and predicting electric power consumption by the consumer at a time subject to prediction based on the generated electric power consumption prediction model and the outdoor temperature at t

Assignees

• Toshiba Kk

Inventors

• Kawaguchi Takahiro
• Umeno Shinya
• Shingaki Ryusei

Classifications

• H02J3/003

  Load forecast, e.g. methods or systems for forecasting future load demand · CPC title

• G01R21/133 Primary

  by using digital technique · CPC title

• H02J3/00

  Circuit arrangements for AC mains or AC distribution networks · CPC title

• H02J2003/003

  Electricity · mapped topic

• 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 · CPC title