Forecast system and method of electric power demand

Patent metadata

Field	Value
Publication number	US-9852483-B2
Application number	US-201214238309-A
Country	US
Kind code	B2
Filing date	Aug 14, 2012
Priority date	Sep 20, 2011
Publication date	Dec 26, 2017
Grant date	Dec 26, 2017

Abstract

A plurality of forecast weather groups in a period comprising a plurality of days including a forecast target day for forecasting the electric power demand, and a plurality of actual weather groups in a period in a plurality of days in the past are set as the target period, and the similarity between the forecast weather group and the plurality of actual weather groups is calculated, a trend of a subsequent electric power demand is predicted based on the comparison of the plurality of calculated similarities whereby the electric power demand of a forecast target day is known.

First claim

The invention claimed is:

1. An electric power demand forecast system which calculates a similarity between a weather record in the past and subsequent forecast weather data, and with the use of the similarity, which predicts a subsequent electric power demand from forecast weather data of a forecast target day and electric power demand data corresponding to the weather record, the system comprising:
a demand forecast target setting unit configured to carry out condition setting for calculating the similarity;
a similar period search condition setting unit configured to set a target period in which the similarity is calculated and to set a similarity variable associated with the condition for the target period and a weighting factor corresponding to the similarity variable, wherein the similarity variable is selectively adoptable or non-adoptable for similarity calculation by user input via an input device by selecting a first graphical symbol on the input device to adopt the similarity variable and selecting a second graphical symbol different from the first graphical symbol on the input device to not adopt the similarity variable, and if the condition is not or cannot initially be associated with a numerical value, the condition is converted into one or more numbers related to the condition in order calculate the similarity;
a similarity calculation unit configured to calculate the similarity based on the condition set by the demand forecast target setting unit and based on the target period and the weighting factor for the similarity variable set by the similar period search condition setting unit;
a demand forecast model construction unit configured to model a trend of a subsequent electric power demand based on the similarity calculated by the similarity calculation unit; and
a demand forecast unit configured to forecast an electric power demand based on forecast weather data of a forecast target day from the trend of a subsequent electric power demand modeled by the demand forecast model construction unit, wherein
the similar period search condition setting unit sets, as the target period, a plurality of forecast weather groups in a period comprising a plurality of days including a forecast target day for forecasting the electric power demand, and a plurality of actual weather groups in a period in a plurality of days in the past, wherein
the similarity calculation unit calculates the similarity between the forecast weather group and the plurality of actual weather groups, wherein
the demand forecast model construction unit models a trend of a subsequent electric power demand using an actual weather group selected based on comparison of the plurality of calculated similarities, and wherein
the demand forecast unit calculates an electric power demand of a forecast target day; and
the electric power demand forecast system controls operation of equipment of an electric power system based on the calculated electric power demand.

2. The electric power demand forecast system according to claim 1 , wherein the condition used to calculate the similarity include one or more of barometric pressure, a rainfall amount, temperature, humidity, wind direction, wind velocity, daylight hours, an amount of snowfall, weather, a day of the week, and singularity.

3. The electric power demand forecast system according to claim 1 , wherein the similarity calculation unit weights all weighting factors for all similarity variables associated with the condition set for the target period used to calculate the similarity, and calculates the similarity.

4. The electric power demand forecast system according to claim 1 , wherein the similarity calculation unit clusters a collection of data based on the conditions in the forecast weather group and the actual weather group, and calculates the similarity using cluster analysis.

5. The electric power demand forecast system according to claim 1 , wherein the similarity calculation unit converts the collection of data based on the conditions in the forecast weather group and the actual weather group, and calculates the similarity using a cosine angle.

6. The electric power demand forecast system according to claim 1 , wherein the demand forecast model construction unit predicts a trend of a subsequent electric power demand using a regression formula or a neural network, which calculates the trend using a least square method or particle Swarm optimization.

7. An electric power demand forecast method, which calculates a similarity between a weather record in the past and subsequent forecast weather data, and with the use of the similarity, which predicts a subsequent electric power demand from forecast weather data of a forecast target day and electric power demand data corresponding to the weather record, the method comprising the steps of:
setting a weather condition for calculating the similarity;
setting, as a target period, a plurality of forecast weather groups in a period comprising a plurality of days including a forecast target day for forecasting the electric power demand, and a plurality of actual weather groups in a period in a plurality of days in the past;
setting a similarity variable associated with the weather condition for the target period and a weighting factor corresponding to the similarity variable, wherein the similarity variable is selectively adoptable or non-adoptable for similarity calculation by user input via an input device by selecting a first graphical symbol on the input device to adopt the similarity variable and selecting a second graphical symbol different from the first graphical symbol on the input device to not adopt the similarity variable, and if the condition is not or cannot initially be associated with a numerical value, the condition is converted into one or more numbers related to the condition in order to calculate the similarity;
calculating the similarity between the forecast weather group and the plurality of actual weather groups based on the weather condition and the target period and the weighting factor for the similarity variable;
modeling a trend of a subsequent electric power demand based on comparison of the plurality of calculated similarities; and
forecasting an electric power demand of the forecast target day based on the trend of the modeled subsequent electric power demand and forecast weather data of the forecast target day; and
the electric power demand forecast system controls operation of equipment of an electric power system based on the calculated electric power demand.

Assignees

• Sawa Toshiyuki
• Mori Shigeki
• Yamazaki Jun
• Hitachi Ltd

Inventors

• Sawa Toshiyuki
• Mori Shigeki
• Yamazaki Jun

Classifications

• H02J3/003

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

• H02J3/00

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

• G06Q10/04

  Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) · CPC title

• G06Q50/06 Primary

  Energy or water supply · CPC title

• Y02A30/00

  Adapting or protecting infrastructure or their operation · CPC title