WO2022118524A1 - Prediction system, prediction method, and program - Google Patents

Prediction system, prediction method, and program Download PDF

Info

Publication number
WO2022118524A1
WO2022118524A1 PCT/JP2021/034895 JP2021034895W WO2022118524A1 WO 2022118524 A1 WO2022118524 A1 WO 2022118524A1 JP 2021034895 W JP2021034895 W JP 2021034895W WO 2022118524 A1 WO2022118524 A1 WO 2022118524A1
Authority
WO
WIPO (PCT)
Prior art keywords
power generation
period
amount
generation amount
prediction
Prior art date
Application number
PCT/JP2021/034895
Other languages
French (fr)
Japanese (ja)
Inventor
哲平 手島
一幸 若杉
麗子 川上
Original Assignee
三菱重工業株式会社
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 三菱重工業株式会社 filed Critical 三菱重工業株式会社
Publication of WO2022118524A1 publication Critical patent/WO2022118524A1/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
    • 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
    • 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
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y10/00—Economic sectors
    • G16Y10/35—Utilities, e.g. electricity, gas or water
    • 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

Definitions

  • This disclosure relates to a prediction system, prediction method and program for the amount of power generated by hydroelectric power generation facilities. This disclosure claims priority based on Japanese Patent Application No. 2020-20853 filed in Japan on December 3, 2020, the contents of which are incorporated herein by reference.
  • An electric power company may conclude an electric power sales contract with another power plant having a hydroelectric power generation facility, etc., and supply the electric power supplied from the other power plant to the electric power system.
  • it is important to maintain a balance between supply and demand in order to suppress fluctuations in power frequency.
  • the amount of power that can be supplied in advance is agreed between the two parties, and if the planned amount of power cannot be supplied, hydropower generation The operation is such that a penalty is imposed on the equipment side.
  • Patent Document 1 regarding the power generation amount prediction of a hydroelectric power generation facility, the predicted value of the overflow power amount lost due to the overflow of the water taken for power generation is predicted by a prediction model, and the power generation planned power amount based on the power demand prediction is predicted. Discloses a prediction system that predicts the power supply capacity in an emergency or the like by adding the predicted value of the overflow power amount.
  • Patent Document 2 regarding the power demand forecast, one of the input data for the demand forecast at the forecast target time is the forecast result of the power demand at another time in which the demand has a correlation with the forecast target time.
  • a demand forecasting device that is used as a unit and predicts power demand at a forecast target time is disclosed.
  • Patent Documents 1 and 2 disclose a technique for predicting power demand and a technique for predicting the amount of power generated by a hydropower generation facility based on the power demand, but power generation that can be supplied by the hydropower generation facility regardless of the power demand. There is no disclosure of technology for accurately predicting quantity.
  • the present disclosure provides a prediction system, a prediction method and a program capable of solving the above-mentioned problems.
  • the amount of power generated by the hydroelectric power generation facility in a predetermined period (t) is defined as the amount of power generation (t), and the period of the same length following the period (t) is a period.
  • T + 1 a prediction model in which the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable when the power generation amount in the period (t + 1) is the power generation amount (t + 1).
  • the first period (s) is defined as the period (s)
  • the power generation amount in the period (s) is defined as the power generation amount (s)
  • the prediction model and the power generation amount (s) The process of predicting the power generation amount (s + 1) based on the actual value of the above and predicting the power generation amount (s + 2) based on the power generation amount (s + 1) predicted by the prediction model is sequentially executed. It also includes a prediction unit that predicts the power generation amount for each period in the prediction target period, and an output unit that outputs the prediction result of the power generation amount by the prediction unit.
  • the amount of power generated by the hydroelectric power generation facility in a predetermined period (t) is defined as the amount of power generation (t), and the period of the same length following the period (t) is a period.
  • T + 1 When the power generation amount in the period (t + 1) is the power generation amount (t + 1), a prediction model is used in which the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable.
  • the first period when the predetermined prediction target period is divided into each period is defined as the period (s), the power generation amount in the period (s) is defined as the power generation amount (s), and the period (s) is continued.
  • the prediction model and the power generation amount ( The process of predicting the power generation amount (s + 1) based on the actual value of s) and predicting the power generation amount (s + 2) based on the predicted model and the predicted power generation amount (s + 1) is sequentially performed.
  • the power generation amount for each period in the prediction target period is predicted, and the prediction result of the power generation amount based on the prediction is output.
  • the program sets the amount of power generated by the hydroelectric power generation facility to the computer in a predetermined period (t) as the amount of power generation (t), and the period of the same length following the period (t). Is a period (t + 1), and when the power generation amount in the period (t + 1) is the power generation amount (t + 1), the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable.
  • the predetermined prediction target period is divided into the periods, the first period is defined as the period (s), the power generation amount in the period (s) is defined as the power generation amount (s), and the period (s) is used.
  • FIG. 1 is a functional block diagram showing a configuration example of a prediction system according to an embodiment.
  • the prediction system 10 is a system that predicts the amount of power that can be generated by a hydroelectric power generation facility.
  • the prediction system 10 predicts the power generation amount on the prediction target day based on the power generation amount in the predetermined period immediately before the prediction target date.
  • daily power generation forecasts up to the distant future such as one month ahead, half a year ahead, etc., every hour, every 30 minutes, etc. It is possible to predict the amount of power generation.
  • the prediction system 10 includes a data acquisition unit 11, a prediction model creation unit 12, a prediction unit 13, a storage unit 14, and an output unit 15.
  • the data acquisition unit 11 acquires parameters necessary for predicting the amount of power generation, data necessary for creating a prediction model for predicting the amount of power generation, and the like.
  • the prediction model creation unit 12 processes the data necessary for creating the prediction model to create training data, and creates the prediction model 141 by machine learning or the like using the training data.
  • the prediction unit 13 predicts the amount of power generated by the hydroelectric power generation facility for each unit period in the prediction target period.
  • the storage unit 14 stores parameters, learning data, prediction model 141, and the like acquired by the data acquisition unit 11.
  • the output unit 15 outputs the prediction result of the amount of power generation predicted by the prediction unit 13 to an electronic file or the like.
  • FIG. 2 shows an outline of the prediction model 141.
  • the forecast model 141 uses weather information such as the forecast target date (t + 1), an operation plan such as the forecast target date (t + 1), and the amount of power generation such as the day before the forecast target date (t) as explanatory variables, and forecasts by the hydroelectric power generation facility.
  • This is a prediction model created by learning the relationship between the explanatory variables and the objective variables with the amount of power generation on the target day (t + 1) as the objective variable.
  • t represents a day.
  • the forecast model 141 calculates the predicted value of the power generation amount generated by the hydroelectric power generation facility on the forecast target day. Output.
  • the inventor has obtained the finding that there is almost no change in the amount of power generated between the previous day and the day of the intake type hydroelectric power generation facility.
  • the inventor added the weather information (t + 1), the operation plan (t + 1), etc. to the explanatory variables in addition to the power generation amount (t) of the previous day, and the prediction model 141 as shown in FIG. I envisioned.
  • the inventor replaces the power generation amount (t) of the explanatory variable with the predicted power generation amount (t + 1), and predicts the power generation amount by the prediction model 141, so that the power generation amount on the next day (t + 2) of the prediction target day (t + 1) It was confirmed that (t + 2) can be predicted accurately. That is, according to the prediction model 141, for example, the power generation amount of the current day is predicted based on the actual power generation amount of yesterday, the power generation amount prediction of the current day is used to predict the power generation amount of the next day, and the power generation of the next day is further performed. It is possible to make sequential predictions such as predicting the amount of power generation two days later based on the amount prediction. By sequentially predicting the amount of power generation using the prediction system 10, it is possible to predict the amount of power generation up to the distant future such as one month ahead, half a year ahead, and the like.
  • the explanatory variables of the prediction model 141 can be roughly classified into weather information, an operation plan, and a power generation amount.
  • the weather information is, for example, the amount of rainfall. Since the amount of power generated by hydroelectric power generation is related to the amount of water in the river at the intake destination, the amount of rainfall is used as the explanatory variable. Since changes in river water volume are delayed from rainfall, the prediction accuracy is improved by using the total rainfall and rainfall for the past few days from the forecast target date as explanatory variables.
  • the weather information of the explanatory variables (1) the rainfall of each day from the forecast target day and several days ago, and (2) the total rainfall from the day before to several days before the forecast target day are used.
  • the actual value of rainfall for the past several days is used.
  • the predicted value of the amount of rainfall in several days going back from one week is used.
  • Actual and predicted rainfall values can be obtained from the Japan Meteorological Agency and companies that provide weather forecast information.
  • the amount of rainfall to be input as an explanatory variable may be calculated based on the actual value or the predicted value of the amount of rainfall observed at a plurality of observation stations around the position where the hydroelectric power generation facility is located.
  • the operation plan is, for example, the operating time of a hydroelectric power generation facility. Since the amount of power generated by hydroelectric power generation is related to the operating time, the operating time is used as an explanatory variable.
  • the operation plan information of the explanatory variables (1) the operation time of each day from the prediction target day and several days ago, and (2) the total operation time from the day before to several days before the prediction target day are used.
  • the past operating hours can be grasped from the actual operation data owned by the hydroelectric power generation equipment, and the future operating hours can be grasped from the operation plan of the hydroelectric power generation equipment.
  • the total of the operation time from several days ago it is possible to make a prediction including the tendency of the operation plan as compared with using only the operation time of the day, and the prediction accuracy can be improved.
  • the operation plan is the calendar information that the hydroelectric power generation facility operates. Since hydroelectric power generation is affected by the seasons, calendar information such as months and days of the week is used as an explanatory variable.
  • the amount of power generation is the actual value of the amount of power generated by the hydroelectric power generation facility or the predicted value of the amount of power generation predicted using the prediction model 141.
  • the power generation amount of the explanatory variables is (1) the power generation amount (actual value or predicted value) of each day from the day before the prediction target day to several days before, and (2) the total power generation amount from the day before to several days before the prediction target day. Is used.
  • the actual value of the past power generation amount can be grasped from the actual power generation amount data owned by the hydroelectric power generation facility, and the future power generation amount can be obtained by sequentially predicting using the prediction model 141. ..
  • the unit period for predicting the amount of power generation is set to one day, but for example, the length of the unit period may be one hour or 30 minutes. That is, for example, the prediction model 141 may be created to output the predicted value of the power generation amount every 30 minutes on the prediction target day (t + 1).
  • the explanatory variables may be as follows.
  • As the weather information (1) rainfall every 30 minutes from the forecast target day and several days before, and (2) total rainfall from the day before to several days before the forecast target day are used.
  • the operation plan (1) the operation time every 30 minutes from the day before the prediction target day and several days before, (2) the total operation time from the day before to several days before the prediction target day, and (3) the calendar. Use information and.
  • the amount of power generation is (1) the amount of power generation (actual value or predicted value) every 30 minutes on each day from 30 minutes before to several days before the forecast target date, and (2) 30 minutes before to several days before the forecast target date. The total amount of power generation and is used. Then, when predicting the power generation amount for the next 30 minutes, the power generation amount predicted value for the immediately preceding 30 minutes is used for the prediction.
  • the prediction model 141 predicts the power generation amount on the prediction target day, but the prediction model 141 is created to output the difference between the power generation amount on the prediction target day and the power generation amount on the previous day. May be good. That is, the prediction model may be created with the objective variable as the power generation amount (t + 1) on the prediction target day-the power generation amount (t) on the previous day.
  • the prediction model may be created with the objective variable as the power generation amount (t + 1) on the prediction target day-the power generation amount (t) on the previous day.
  • FIG. 4 is a flowchart showing an example of a prediction model creation process according to an embodiment.
  • the data acquisition unit 11 acquires data for creating the prediction model 141 (step S1). For example, the data acquisition unit 11 acquires the daily rainfall, operating time, and power generation amount in the past predetermined period. The data acquisition unit 11 records these data in the storage unit 14.
  • the prediction model creation unit 12 performs preprocessing to create learning data (step S2).
  • the prediction model creation unit 12 sets the prediction target day “D1” as the prediction target day from the data acquired in step S1, and the data of the rainfall amount of each day from several days before the prediction target days D1 and D1. Are extracted and these are set as explanatory variables for the prediction target date D1.
  • the prediction model creation unit 12 calculates the total amount of rainfall from the day before the prediction target day D1 to several days before, and sets the calculated total value as an explanatory variable for the prediction target day D1.
  • the prediction model creation unit 12 extracts the operation time and the amount of power generation of each day from several days before the prediction target day D1 and D1, and further, the total of the operation time and the total amount of power generation from the day before the prediction target day D1 to several days before.
  • the prediction model creation unit 12 sets the calendar information (month and day of the week) of the prediction target day D1 as an explanatory variable for the prediction target day D1.
  • the prediction model creation unit 12 extracts the amount of power generation on the prediction target day D1 from the data acquired in step S1 and sets this value as the objective variable for the prediction target day D1.
  • the prediction model creation unit 12 creates a combination of explanatory variables and objective variables, that is, a large number of learning data, while changing the prediction target date D1.
  • the prediction model creation unit 12 writes and stores a large number of created learning data in the storage unit 14.
  • the predictive model creation unit 12 creates the predictive model 141 (step S3).
  • the prediction model creation unit 12 learns the relationship between the explanatory variable and the objective variable by a method such as a random forest using the training data created in step S12, and creates the prediction model 141.
  • the prediction model creation unit 12 writes and stores the prediction model 141 in the storage unit 14.
  • the method for constructing the prediction model 141 is not limited to the random forest, and may be a method by regression analysis or other machine learning.
  • FIG. 5 is a flowchart showing an example of the power generation amount prediction process according to the embodiment.
  • the data acquisition unit 11 accepts the setting of the prediction target period and the unit period (step S11).
  • the forecast target period indicates from the beginning to the end of the period for predicting the power generation amount
  • the unit period means how long the power generation amount is predicted for each period in the forecast target period.
  • the user inputs to the prediction system 10 information instructing that the power generation amount for each day is predicted as a unit period from the day of the prediction date (the day when the prediction is executed) to 3 days after the prediction target period.
  • the data acquisition unit 11 records in the storage unit 14 the setting of "current day to 3 days later" as the prediction target period and "1 day” as the unit period.
  • the data acquisition unit 11 acquires the data necessary for prediction (step S12).
  • the day when the prediction is made is October 31, and the "several days ago" explained using FIG. 3 is uniformly 3 days ago.
  • the data required for the forecast on October 31, which is the first day of the forecast period is the amount of power generated from October 28 to October 30, the weather information, the actual value of the operation plan (white circle), and The weather information for October 31 and the predicted value of the operation plan (black circles).
  • the data required for the forecast of November 3, which is the final day of the forecast period is the forecast value of the amount of power generation from October 31 to November 2 (black circle), and from October 31 to November 3.
  • the user inputs the amount of power generated from October 28 to October 30, the weather information, the actual value of the operation plan, the weather information from October 31 to November 3, and the forecast value of the operation plan into the prediction system 10. do.
  • the data acquisition unit 11 acquires these data as data necessary for prediction and records them in the storage unit 14.
  • the predicted value of the amount of power generation from October 31st to November 2nd will be calculated by the following processing.
  • the prediction unit 13 sets initial values for the variables m and t (step S13).
  • t indicates the predicted date.
  • the prediction unit 13 predicts the power generation amount Y (t + m) in the first prediction target period of the prediction target period (step S14). In the case of this example, the prediction unit 13 predicts the power generation amount Y (October 31).
  • the forecasting unit 13 inputs the power generation amount from October 28 to October 30, the actual value of the weather information and the operation plan, and the weather information of October 31 and the predicted value of the operation plan into the prediction model 141.
  • the prediction model 141 outputs the amount of power generation on October 31st.
  • the amount of power generated by the prediction model 141 is the amount of power generation Y (October 31).
  • the prediction unit 13 records the power generation amount Y (t + m) in the storage unit 14.
  • the prediction unit 13 predicts the power generation amount Y (t + m) using the predicted value of the power generation amount and the power generation amount Y (t + m-1) (step S16). That is, the power generation amount in the next unit period (November 1st) is predicted by using the predicted value of the power generation amount in the previous unit period (October 31st).
  • the prediction unit 13 has weather information from October 29th to October 31st, actual values of the operation plan, weather information of November 1st, predicted values of the operation plan, and power generation from October 29th to October 30th.
  • the actual value of the amount and the predicted value of the amount of power generation on October 31 are input to the prediction model 141.
  • the prediction model 141 outputs the amount of power generation on November 1.
  • the prediction unit 13 records the power generation amount Y (t + m-1) in the storage unit 14.
  • the output unit 15 When m is N or more (step S17; Yes), the output unit 15 outputs the predicted value of the power generation amount for each unit period in the prediction target period (step S18). For example, the output unit 15 outputs the predicted value of the amount of power generated by the daily hydroelectric power generation facility from October 31st to November 3rd to a display device, an electronic file, or the like.
  • an example of predicting the amount of power generation per day for 4 days is given. For example, using the prediction model 141 created to output the predicted value of the amount of power generation every 30 minutes, 3 days ahead.
  • the power generation amount may be predicted every 30 minutes up to, or the daily power generation amount may be predicted up to one month ahead.
  • the power generation amount prediction of the present embodiment does not require power demand prediction or the like, and can predict the power generation amount according to the capacity of the own facility based on the actual results. For example, when the inventor constructed a prediction model 141 and evaluated the results by performing sequential prediction using the flowchart of FIG. 5, the amount of power generation was estimated to be about 95% in the prediction several days ahead and about 90% in January. It was confirmed that it can be predicted.
  • FIG. 7 is a diagram showing an example of the hardware configuration of the prediction system according to the embodiment.
  • the computer 900 includes a CPU 901, a main storage device 902, an auxiliary storage device 903, an input / output interface 904, and a communication interface 905.
  • the prediction system 10 described above is mounted on the computer 900.
  • Each of the above-mentioned functions is stored in the auxiliary storage device 903 in the form of a program.
  • the CPU 901 reads a program from the auxiliary storage device 903, expands it to the main storage device 902, and executes the above processing according to the program.
  • the CPU 901 reserves a storage area in the main storage device 902 according to the program.
  • the CPU 901 secures a storage area for storing the data being processed in the auxiliary storage device 903 according to the program.
  • a program for realizing all or a part of the functions of the prediction system 10 is recorded on a computer-readable recording medium, and the program recorded on the recording medium is read into the computer system and executed. May be processed by.
  • the term "computer system” as used herein includes hardware such as an OS and peripheral devices.
  • the "computer system” shall include the homepage providing environment (or display environment) if the WWW system is used.
  • the "computer-readable recording medium” refers to a portable medium such as a CD, DVD, or USB, or a storage device such as a hard disk built in a computer system.
  • the above program may be for realizing a part of the above-mentioned functions, and may be further realized for realizing the above-mentioned functions in combination with a program already recorded in the computer system.
  • the prediction system 10 may be composed of a plurality of computers 900.
  • the amount of power generated by the hydroelectric power generation facility in a predetermined period (t) is set as the amount of power generation (t), and a period of the same length following the period (t) is set.
  • Prediction model 141 in which the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable when the power generation amount in the period (t + 1) and the period (t + 1) is the power generation amount (t + 1).
  • the first period is the period (s)
  • the power generation amount in the period (s) is the power generation amount (s)
  • the period (s) is continued.
  • the prediction model and the power generation amount ( The process of predicting the power generation amount (s + 1) based on the actual value of s) and predicting the power generation amount (s + 2) based on the predicted model and the predicted power generation amount (s + 1) is sequentially performed. It is provided with a prediction unit 13 for predicting the power generation amount for each period in the prediction target period, and an output unit 15 for outputting the prediction result of the power generation amount by the prediction unit.
  • the amount of power that can be generated does not fluctuate significantly between the day before and the day.
  • the power generation amount (t) as the explanatory variable and the power generation amount (t + 1) as the objective variable, and the predicted value by this prediction model, the power generation amount (s) in the period (s).
  • the power generation amount (s) in the period (s). Predicts the amount of power generation (s + 1) in the period (s + 1), predicts the amount of power generation (s + 2) in the period (s + 2) from the amount of power generation (s + 1), and so on.
  • the prediction system 10 is the prediction system 10 of (1), and the explanatory variables of the prediction model 141 are the said in the period (t) in addition to the power generation amount (t). It includes the amount of rainfall in a predetermined range around the hydroelectric power generation facility and the operating time of the hydroelectric power generation facility during the period (t) (FIG. 2). This makes it possible to improve the accuracy of predicting the amount of power generation.
  • the prediction system 10 is the prediction system 10 of (1) to (2), and the explanatory variables of the prediction model 141 are the period (t) in addition to the power generation amount (t).
  • the prediction system 10 is the prediction system 10 of (1) to (3), and creates the prediction model by learning the relationship between the explanatory variable and the objective variable. It also has a predictive model creation unit. As a result, the prediction model 141 can be created.
  • the prediction system 10 is the prediction system 10 of (1) to (4), in which the objective variable of the prediction model 141 is replaced with the power generation amount (t + 1). It is the difference between the power generation amount (t) and the power generation amount (t + 1).
  • the prediction model 141 can also be created by setting the objective variable as the difference between the power generation amount (t) and the power generation amount (t + 1).
  • the amount of power generated by the hydroelectric power generation facility in a predetermined period (t) is defined as the amount of power generation (t), and the period of the same length following the period (t) is a period.
  • T + 1) when the power generation amount in the period (t + 1) is the power generation amount (t + 1), a prediction model is used in which the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable.
  • the first period when the predetermined prediction target period is divided into each period is defined as the period (s)
  • the power generation amount in the period (s) is defined as the power generation amount (s)
  • the period (s) is continued.
  • the prediction model and the power generation amount ( The process of predicting the power generation amount (s + 1) based on the actual value of s) and predicting the power generation amount (s + 2) based on the predicted model and the predicted power generation amount (s + 1) is sequentially performed.
  • the power generation amount for each period in the prediction target period is predicted, and the prediction result of the power generation amount based on the prediction is output.
  • the amount of power generated by the hydroelectric power generation facility in a predetermined period (t) is set as the power generation amount (t), and the period of the same length following the period (t) is set. Is a period (t + 1), and when the power generation amount in the period (t + 1) is the power generation amount (t + 1), the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable.
  • the predetermined prediction target period is divided into the periods, the first period is defined as the period (s), the power generation amount in the period (s) is defined as the power generation amount (s), and the period (s) is used.

Landscapes

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

Abstract

Provided is a prediction system for predicting the amount of power generated by a hydroelectric power generation facility. The prediction system is provided with: a prediction model that, when the amount of power generated by a hydroelectric power generation facility in a prescribed period (t) is defined as a power generation amount(t), a period having the same length and subsequent to the period (t) is defined as (t+1), and an amount of power generated in the period (t+1) is defined as a power generation amount(t+1), includes the power generation amount(t) as an explanatory variable and sets the power generation amount(t+1) as the objective variable; a prediction unit for using the prediction model and a prediction result from the prediction model to successively predict the power generation amount for each period of a prescribed prediction subject period; and an output unit for outputting a prediction result by the prediction unit regarding the power generation amount.

Description

予測システム、予測方法およびプログラムPrediction systems, prediction methods and programs
　本開示は、水力発電設備による発電量の予測システム、予測方法およびプログラムに関する。本開示は、２０２０年１２月３日に、日本に出願された特願２０２０－２００８５３号に基づき優先権を主張し、その内容をここに援用する。 This disclosure relates to a prediction system, prediction method and program for the amount of power generated by hydroelectric power generation facilities. This disclosure claims priority based on Japanese Patent Application No. 2020-20853 filed in Japan on December 3, 2020, the contents of which are incorporated herein by reference.
　電力会社では、水力発電設備などを有する他の発電所との間で電力の売買契約を結び、他の発電所から供給された電力を電力系統へ供給している場合がある。電力系統では、電力周波数の変動を抑えるため、需要と供給のバランスを保つことが重要である。安定した電力の供給を実現するため、水力発電設備から電力会社へ供給（売電）する電力については、予め供給可能な電力量を両者の間で取り決め、予定した電力量が供給できないと水力発電設備側へペナルティを課すような運用が行われている。 An electric power company may conclude an electric power sales contract with another power plant having a hydroelectric power generation facility, etc., and supply the electric power supplied from the other power plant to the electric power system. In the power system, it is important to maintain a balance between supply and demand in order to suppress fluctuations in power frequency. Regarding the power to be supplied (sold) from the hydropower generation facility to the power company in order to realize a stable power supply, the amount of power that can be supplied in advance is agreed between the two parties, and if the planned amount of power cannot be supplied, hydropower generation The operation is such that a penalty is imposed on the equipment side.
　特許文献１には、水力発電設備の発電量予測に関し、発電用に取水される水のうち溢水によって逸失する溢水電力量の予測値を予測モデルによって予測し、電力需要予測に基づく発電予定電力量に、溢水電力量の予測値を加算することによって、非常時等における電力供給能力を予測する予測システムが開示されている。
　特許文献２には、電力の需要予測に関し、予測対象時刻との間で需要が相関関係を有する他の時刻での電力需要の予測結果を予測対象時刻での需要予測のための入力データの一部として使用し、予測対象時刻での電力需要を予測する需要予測装置が開示されている。 In Patent Document 1, regarding the power generation amount prediction of a hydroelectric power generation facility, the predicted value of the overflow power amount lost due to the overflow of the water taken for power generation is predicted by a prediction model, and the power generation planned power amount based on the power demand prediction is predicted. Discloses a prediction system that predicts the power supply capacity in an emergency or the like by adding the predicted value of the overflow power amount.
In Patent Document 2, regarding the power demand forecast, one of the input data for the demand forecast at the forecast target time is the forecast result of the power demand at another time in which the demand has a correlation with the forecast target time. A demand forecasting device that is used as a unit and predicts power demand at a forecast target time is disclosed.
特開２０１５－１４６０６５号公報Japanese Unexamined Patent Publication No. 2015-146065 日本国特許第５６１８５０１号公報Japanese Patent No. 5618501 Gazette
　特許文献１、２には、電力需要を予測する技術や電力需要に基づく水力発電設備の発電量を予測する技術は開示されているが、電力需要に依らず、水力発電設備が供給可能な発電量を正確に予測する技術については開示が無い。 Patent Documents 1 and 2 disclose a technique for predicting power demand and a technique for predicting the amount of power generated by a hydropower generation facility based on the power demand, but power generation that can be supplied by the hydropower generation facility regardless of the power demand. There is no disclosure of technology for accurately predicting quantity.
　本開示は、上述の課題を解決することのできる予測システム、予測方法およびプログラムを提供する。 The present disclosure provides a prediction system, a prediction method and a program capable of solving the above-mentioned problems.
　本開示の一態様によれば、予測システムは、所定の期間（ｔ）に水力発電設備が発電する発電量を発電量（ｔ）とし、前記期間（ｔ）に続く同じ長さの期間を期間（ｔ＋１）、前記期間（ｔ＋１）における前記発電量を発電量（ｔ＋１）としたときに、前記発電量（ｔ）を説明変数に含み、発電量（ｔ＋１）を目的変数とする予測モデルと、所定の予測対象期間を前記期間ごとに分割した場合の最初の前記期間を期間（ｓ）、前記期間（ｓ）における前記発電量を発電量（ｓ）とし、前記期間（ｓ）に続く期間（ｓ＋１）における前記発電量を発電量（ｓ＋１）とし、前記期間（ｓ＋１）に続く期間（ｓ＋２）における前記発電量を発電量（ｓ＋２）としたときに、前記予測モデルと前記発電量（ｓ）の実績値に基づいて、前記発電量（ｓ＋１）を予測し、前記予測モデルと予測した前記発電量（ｓ＋１）に基づいて、前記発電量（ｓ＋２）を予測する、という処理を逐次的に実行し、前記予測対象期間における前記期間ごとの前記発電量を予測する予測部と、前記予測部による前記発電量の予測結果を出力する出力部と、を備える。 According to one aspect of the present disclosure, in the prediction system, the amount of power generated by the hydroelectric power generation facility in a predetermined period (t) is defined as the amount of power generation (t), and the period of the same length following the period (t) is a period. (T + 1), a prediction model in which the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable when the power generation amount in the period (t + 1) is the power generation amount (t + 1). When the predetermined prediction target period is divided into the periods, the first period (s) is defined as the period (s), the power generation amount in the period (s) is defined as the power generation amount (s), and the period following the period (s) (s). When the power generation amount in s + 1) is the power generation amount (s + 1) and the power generation amount in the period (s + 2) following the period (s + 1) is the power generation amount (s + 2), the prediction model and the power generation amount (s) The process of predicting the power generation amount (s + 1) based on the actual value of the above and predicting the power generation amount (s + 2) based on the power generation amount (s + 1) predicted by the prediction model is sequentially executed. It also includes a prediction unit that predicts the power generation amount for each period in the prediction target period, and an output unit that outputs the prediction result of the power generation amount by the prediction unit.
　本開示の一態様によれば、予測方法は、所定の期間（ｔ）に水力発電設備が発電する発電量を発電量（ｔ）とし、前記期間（ｔ）に続く同じ長さの期間を期間（ｔ＋１）、前記期間（ｔ＋１）における前記発電量を発電量（ｔ＋１）としたときに、前記発電量（ｔ）を説明変数に含み、発電量（ｔ＋１）を目的変数とする予測モデルを用いて、所定の予測対象期間を前記期間ごとに分割した場合の最初の前記期間を期間（ｓ）、前記期間（ｓ）における前記発電量を発電量（ｓ）とし、前記期間（ｓ）に続く期間（ｓ＋１）における前記発電量を発電量（ｓ＋１）とし、前記期間（ｓ＋１）に続く期間（ｓ＋２）における前記発電量を発電量（ｓ＋２）としたときに、前記予測モデルと前記発電量（ｓ）の実績値に基づいて、前記発電量（ｓ＋１）を予測し、前記予測モデルと予測した前記発電量（ｓ＋１）に基づいて、前記発電量（ｓ＋２）を予測する、という処理を逐次的に実行し、前記予測対象期間における前記期間ごとの前記発電量を予測し、前記予測による前記発電量の予測結果を出力する。 According to one aspect of the present disclosure, in the prediction method, the amount of power generated by the hydroelectric power generation facility in a predetermined period (t) is defined as the amount of power generation (t), and the period of the same length following the period (t) is a period. (T + 1) When the power generation amount in the period (t + 1) is the power generation amount (t + 1), a prediction model is used in which the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable. The first period when the predetermined prediction target period is divided into each period is defined as the period (s), the power generation amount in the period (s) is defined as the power generation amount (s), and the period (s) is continued. When the power generation amount in the period (s + 1) is the power generation amount (s + 1) and the power generation amount in the period (s + 2) following the period (s + 1) is the power generation amount (s + 2), the prediction model and the power generation amount ( The process of predicting the power generation amount (s + 1) based on the actual value of s) and predicting the power generation amount (s + 2) based on the predicted model and the predicted power generation amount (s + 1) is sequentially performed. The power generation amount for each period in the prediction target period is predicted, and the prediction result of the power generation amount based on the prediction is output.
　本開示の一態様によれば、プログラムは、コンピュータに、所定の期間（ｔ）に水力発電設備が発電する発電量を発電量（ｔ）とし、前記期間（ｔ）に続く同じ長さの期間を期間（ｔ＋１）、前記期間（ｔ＋１）における前記発電量を発電量（ｔ＋１）としたときに、前記発電量（ｔ）を説明変数に含み、発電量（ｔ＋１）を目的変数とする予測モデルを用いて、所定の予測対象期間を前記期間ごとに分割した場合の最初の前記期間を期間（ｓ）、前記期間（ｓ）における前記発電量を発電量（ｓ）とし、前記期間（ｓ）に続く期間（ｓ＋１）における前記発電量を発電量（ｓ＋１）とし、前記期間（ｓ＋１）に続く期間（ｓ＋２）における前記発電量を発電量（ｓ＋２）としたときに、前記予測モデルと前記発電量（ｓ）の実績値に基づいて、前記発電量（ｓ＋１）を予測し、前記予測モデルと予測した前記発電量（ｓ＋１）に基づいて、前記発電量（ｓ＋２）を予測する、という処理を逐次的に実行し、前記予測対象期間における前記期間ごとの前記発電量を予測し、前記予測による前記発電量の予測結果を出力する処理を実行させる。 According to one aspect of the present disclosure, the program sets the amount of power generated by the hydroelectric power generation facility to the computer in a predetermined period (t) as the amount of power generation (t), and the period of the same length following the period (t). Is a period (t + 1), and when the power generation amount in the period (t + 1) is the power generation amount (t + 1), the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable. When the predetermined prediction target period is divided into the periods, the first period is defined as the period (s), the power generation amount in the period (s) is defined as the power generation amount (s), and the period (s) is used. The prediction model and the power generation when the power generation amount in the period (s + 1) following the period (s + 1) is the power generation amount (s + 1) and the power generation amount in the period (s + 2) following the period (s + 1) is the power generation amount (s + 2). The process of predicting the power generation amount (s + 1) based on the actual value of the amount (s) and predicting the power generation amount (s + 2) based on the power generation amount (s + 1) predicted by the prediction model. It is sequentially executed to predict the power generation amount for each period in the prediction target period, and execute a process of outputting the prediction result of the power generation amount by the prediction.
　上記した予測システム、予測方法およびプログラムによれば、水力発電設備による発電量を予測することができる。 According to the above-mentioned prediction system, prediction method and program, it is possible to predict the amount of power generated by the hydroelectric power generation facility.
実施形態に係る予測システムの構成例を示す機能ブロック図である。It is a functional block diagram which shows the structural example of the prediction system which concerns on embodiment. 実施形態に係る発電量の予測モデルの概要を示す図である。It is a figure which shows the outline of the prediction model of the power generation amount which concerns on embodiment. 実施形態に係る予測モデルの説明変数の一例を示す図である。It is a figure which shows an example of the explanatory variable of the prediction model which concerns on embodiment. 実施形態に係る予測モデルの作成処理の一例を示すフローチャートである。It is a flowchart which shows an example of the creation process of the prediction model which concerns on embodiment. 実施形態に係る発電量の予測処理の一例を示すフローチャートである。It is a flowchart which shows an example of the prediction processing of the power generation amount which concerns on embodiment. 実施形態に係る発電量の予測処理の説明に用いる図である。It is a figure used for the explanation of the power generation amount prediction processing which concerns on embodiment. 実施形態に係る予測システムのハードウェア構成の一例を示す図である。It is a figure which shows an example of the hardware composition of the prediction system which concerns on embodiment.
＜実施形態＞
　以下、実施形態に係る予測システムについて、図１～図７を参照しながら詳しく説明する。
（構成）
　図１は、実施形態に係る予測システムの構成例を示す機能ブロック図である。
　予測システム１０は、水力発電設備が発電できる発電量を予測するシステムである。予測システム１０は、予測対象日直前の所定期間における発電量などに基づいて、予測対象日の発電量を予測する。以下で説明するように、予測システム１０を用いて、逐次的に予測を行うことにより、１カ月先、半年先等の遠い将来までの日々の発電量予測や、１時間ごと、３０分ごと等の発電量予測が可能となる。 <Embodiment>
Hereinafter, the prediction system according to the embodiment will be described in detail with reference to FIGS. 1 to 7.
(Constitution)
FIG. 1 is a functional block diagram showing a configuration example of a prediction system according to an embodiment.
The prediction system 10 is a system that predicts the amount of power that can be generated by a hydroelectric power generation facility. The prediction system 10 predicts the power generation amount on the prediction target day based on the power generation amount in the predetermined period immediately before the prediction target date. As explained below, by sequentially making predictions using the prediction system 10, daily power generation forecasts up to the distant future such as one month ahead, half a year ahead, etc., every hour, every 30 minutes, etc. It is possible to predict the amount of power generation.
　図示するように予測システム１０は、データ取得部１１と、予測モデル作成部１２と、予測部１３と、記憶部１４と、出力部１５と、を備える。
　データ取得部１１は、発電量の予測に必要なパラメータ、発電量を予測する予測モデルの作成に必要なデータなどを取得する。
　予測モデル作成部１２は、予測モデルの作成に必要なデータを加工して学習データを作成し、学習データを用いた機械学習等によって予測モデル１４１を作成する。
　予測部１３は、予測対象期間における単位期間ごとの水力発電設備による発電量を予測する。
　記憶部１４は、データ取得部１１が取得したパラメータや学習データ、予測モデル１４１などを記憶する。
　出力部１５は、予測部１３が予測した発電量の予測結果を電子ファイル等へ出力する。 As shown in the figure, the prediction system 10 includes a data acquisition unit 11, a prediction model creation unit 12, a prediction unit 13, a storage unit 14, and an output unit 15.
The data acquisition unit 11 acquires parameters necessary for predicting the amount of power generation, data necessary for creating a prediction model for predicting the amount of power generation, and the like.
The prediction model creation unit 12 processes the data necessary for creating the prediction model to create training data, and creates the prediction model 141 by machine learning or the like using the training data.
The prediction unit 13 predicts the amount of power generated by the hydroelectric power generation facility for each unit period in the prediction target period.
The storage unit 14 stores parameters, learning data, prediction model 141, and the like acquired by the data acquisition unit 11.
The output unit 15 outputs the prediction result of the amount of power generation predicted by the prediction unit 13 to an electronic file or the like.
　次に、図２、図３を用いて、予測モデル１４１について説明する。
　図２に予測モデル１４１の概要を示す。予測モデル１４１は、予測対象日（ｔ＋１）等の天気情報と、予測対象日（ｔ＋１）等の運転計画と、予測対象日前日（ｔ）等の発電量を説明変数とし、水力発電設備による予測対象日（ｔ＋１）の発電量を目的変数として、説明変数と目的変数の関係を学習して作成される予測モデルである。図２のｔは日を表している。換言すれば、予測モデル１４１に予測対象日の天気情報と運転計画、予測対象日前日の発電量を入力すると、予測モデル１４１は、予測対象日に水力発電設備が発電する発電量の予測値を出力する。発明者は、取水式の水力発電設備において前日と当日での発電量の変動がほとんどないとの知見を得た。発明者は、予測精度を確保するために、前日の発電量（ｔ）に加え、説明変数に天気情報（ｔ＋１）と運転計画（ｔ＋１）等を追加して、図２のような予測モデル１４１を構想した。発明者は、説明変数の発電量（ｔ）を予測した発電量（ｔ＋１）に置き換えて、予測モデル１４１によって発電量を予測することで、予測対象日（ｔ＋１）の翌日（ｔ＋２）の発電量（ｔ＋２）を精度よく予測できることを確認した。つまり、予測モデル１４１によれば、例えば、昨日の発電量の実績に基づいて、当日の発電量予測を行い、当日の発電量予測を用いて、翌日の発電量予測を行い、さらに翌日の発電量予測に基づいて２日後の発電量予測を行うといった逐次的な予測が可能になる。予測システム１０を用いて、逐次的に発電量の予測を行うことにより、１カ月先、半年先等の遠い将来までの発電量予測が可能である。 Next, the prediction model 141 will be described with reference to FIGS. 2 and 3.
FIG. 2 shows an outline of the prediction model 141. The forecast model 141 uses weather information such as the forecast target date (t + 1), an operation plan such as the forecast target date (t + 1), and the amount of power generation such as the day before the forecast target date (t) as explanatory variables, and forecasts by the hydroelectric power generation facility. This is a prediction model created by learning the relationship between the explanatory variables and the objective variables with the amount of power generation on the target day (t + 1) as the objective variable. In FIG. 2, t represents a day. In other words, when the weather information and operation plan of the forecast target day and the power generation amount of the day before the forecast target date are input to the forecast model 141, the forecast model 141 calculates the predicted value of the power generation amount generated by the hydroelectric power generation facility on the forecast target day. Output. The inventor has obtained the finding that there is almost no change in the amount of power generated between the previous day and the day of the intake type hydroelectric power generation facility. In order to ensure the prediction accuracy, the inventor added the weather information (t + 1), the operation plan (t + 1), etc. to the explanatory variables in addition to the power generation amount (t) of the previous day, and the prediction model 141 as shown in FIG. I envisioned. The inventor replaces the power generation amount (t) of the explanatory variable with the predicted power generation amount (t + 1), and predicts the power generation amount by the prediction model 141, so that the power generation amount on the next day (t + 2) of the prediction target day (t + 1) It was confirmed that (t + 2) can be predicted accurately. That is, according to the prediction model 141, for example, the power generation amount of the current day is predicted based on the actual power generation amount of yesterday, the power generation amount prediction of the current day is used to predict the power generation amount of the next day, and the power generation of the next day is further performed. It is possible to make sequential predictions such as predicting the amount of power generation two days later based on the amount prediction. By sequentially predicting the amount of power generation using the prediction system 10, it is possible to predict the amount of power generation up to the distant future such as one month ahead, half a year ahead, and the like.
　次に図３を参照して、説明変数の詳細について説明する。図３に示すように予測モデル１４１の説明変数は、天気情報と、運転計画と、発電量とに大別することができる。
　天気情報とは、例えば、雨量である。水力発電による発電量は、取水先の河川の水量に関係する為、説明変数に雨量を用いる。河川の水量の変化は、降雨から遅れが生じる為、予測対象日から過去の数日間の雨量や雨量の合計を説明変数として用いることで予測精度を向上させる。説明変数の天気情報として、（１）予測対象日および数日前からの各日の雨量と、（２）予測対象日の前日～数日前の合計雨量と、を用いる。例えば、当日の発電量を予測する場合、過去数日間の雨量の実績値を用いる。例えば、１週間後の発電量を予測する場合、１週間後から遡る数日間における雨量の予測値を用いる。雨量の実績値および予測値は、気象庁や天気予報情報を提供する企業などから入手することができる。例えば、水力発電設備が所在する位置周辺の複数個所の観測所で観測された雨量の実績値や予測値に基づいて、説明変数として入力する雨量を算出してもよい。 Next, the details of the explanatory variables will be described with reference to FIG. As shown in FIG. 3, the explanatory variables of the prediction model 141 can be roughly classified into weather information, an operation plan, and a power generation amount.
The weather information is, for example, the amount of rainfall. Since the amount of power generated by hydroelectric power generation is related to the amount of water in the river at the intake destination, the amount of rainfall is used as the explanatory variable. Since changes in river water volume are delayed from rainfall, the prediction accuracy is improved by using the total rainfall and rainfall for the past few days from the forecast target date as explanatory variables. As the weather information of the explanatory variables, (1) the rainfall of each day from the forecast target day and several days ago, and (2) the total rainfall from the day before to several days before the forecast target day are used. For example, when predicting the amount of power generation on the day, the actual value of rainfall for the past several days is used. For example, when predicting the amount of power generation after one week, the predicted value of the amount of rainfall in several days going back from one week is used. Actual and predicted rainfall values can be obtained from the Japan Meteorological Agency and companies that provide weather forecast information. For example, the amount of rainfall to be input as an explanatory variable may be calculated based on the actual value or the predicted value of the amount of rainfall observed at a plurality of observation stations around the position where the hydroelectric power generation facility is located.
　運転計画とは、例えば、水力発電設備の運転時間である。水力発電による発電量は、運転時間に関係する為、説明変数に運転時間を用いる。説明変数の運転計画情報として、（１）予測対象日および数日前からの各日の運転時間と、（２）予測対象日の前日～数日前の合計運転時間と、を用いる。過去の運転時間は、水力発電設備が保有する運転の実績データから把握することができ、将来の運転時間は、水力発電設備の運転計画から把握することができる。数日前からの運転時間の合計を用いることにより、当日の運転時間だけを用いるよりも運転計画の傾向を含めて予測することができ、予測精度を向上することができる。 The operation plan is, for example, the operating time of a hydroelectric power generation facility. Since the amount of power generated by hydroelectric power generation is related to the operating time, the operating time is used as an explanatory variable. As the operation plan information of the explanatory variables, (1) the operation time of each day from the prediction target day and several days ago, and (2) the total operation time from the day before to several days before the prediction target day are used. The past operating hours can be grasped from the actual operation data owned by the hydroelectric power generation equipment, and the future operating hours can be grasped from the operation plan of the hydroelectric power generation equipment. By using the total of the operation time from several days ago, it is possible to make a prediction including the tendency of the operation plan as compared with using only the operation time of the day, and the prediction accuracy can be improved.
　運転計画とは、水力発電設備が運転する暦の情報である。水力発電は季節の影響を受けるため、月や曜日など暦の情報を説明変数として用いる。 The operation plan is the calendar information that the hydroelectric power generation facility operates. Since hydroelectric power generation is affected by the seasons, calendar information such as months and days of the week is used as an explanatory variable.
　発電量は、水力発電設備で発電した発電量の実績値または予測モデル１４１を用いて予測した発電量予測値である。説明変数の発電量として、（１）予測対象日の前日～数日前の各日の発電量（実績値または予測値）と、（２）予測対象日の前日～数日前の合計発電量と、を用いる。過去の発電量の実績値は、水力発電設備が保有する発電量の実績データから把握することができ、将来の発電量は、予測モデル１４１を用いて逐次的に予測することにより得ることができる。 The amount of power generation is the actual value of the amount of power generated by the hydroelectric power generation facility or the predicted value of the amount of power generation predicted using the prediction model 141. The power generation amount of the explanatory variables is (1) the power generation amount (actual value or predicted value) of each day from the day before the prediction target day to several days before, and (2) the total power generation amount from the day before to several days before the prediction target day. Is used. The actual value of the past power generation amount can be grasped from the actual power generation amount data owned by the hydroelectric power generation facility, and the future power generation amount can be obtained by sequentially predicting using the prediction model 141. ..
　上記説明では、発電量予測の単位期間を１日として説明を行ったが、例えば、単位期間の長さは、１時間や３０分などでもよい。つまり、例えば、予測モデル１４１は、予測対象日（ｔ＋１）における３０分ごとの発電量の予測値を出力するように作成されてもよい。その場合、例えば、説明変数は、以下のようであってもよい。
　天気情報は、（１）予測対象日および数日前からの各日の３０分ごとの雨量と、（２）予測対象日の前日～数日前の合計雨量と、を用いる。運転計画の情報として、（１）予測対象日および数日前からの各日の３０分ごとの運転時間と、（２）予測対象日の前日～数日前の合計運転時間と、（３）暦の情報と、を用いる。発電量は、（１）予測対象日における３０分前～数日前の各日の３０分ごとの発電量（実績値または予測値）と、（２）予測対象日における３０分前～数日前の合計発電量と、を用いる。そして、次の３０分の発電量を予測する場合は、直前の３０分の発電量予測値を用いて予測する。 In the above description, the unit period for predicting the amount of power generation is set to one day, but for example, the length of the unit period may be one hour or 30 minutes. That is, for example, the prediction model 141 may be created to output the predicted value of the power generation amount every 30 minutes on the prediction target day (t + 1). In that case, for example, the explanatory variables may be as follows.
As the weather information, (1) rainfall every 30 minutes from the forecast target day and several days before, and (2) total rainfall from the day before to several days before the forecast target day are used. As information on the operation plan, (1) the operation time every 30 minutes from the day before the prediction target day and several days before, (2) the total operation time from the day before to several days before the prediction target day, and (3) the calendar. Use information and. The amount of power generation is (1) the amount of power generation (actual value or predicted value) every 30 minutes on each day from 30 minutes before to several days before the forecast target date, and (2) 30 minutes before to several days before the forecast target date. The total amount of power generation and is used. Then, when predicting the power generation amount for the next 30 minutes, the power generation amount predicted value for the immediately preceding 30 minutes is used for the prediction.
　上記説明では、予測モデル１４１は、予測対象日の発電量を予測するとしたが、予測モデル１４１は、予測対象日の発電量とその前日の発電量との差を出力するように作成されていてもよい。つまり、目的変数を、予測対象日の発電量（ｔ＋１）－前日の発電量（ｔ）として予測モデルを作成してもよい。図３において数日前という記載があるが、例えば、雨量の欄の上段（各日の雨量）の数日前と、下段（合計雨量）の数日前が示す期間は異なっていてもよい。運転時間、発電量の数日前についても同様である。雨量、運転時間、発電量の上段に記載された数日前が示す期間は互いに異なっていてもよい。下段に記載された数日前についても同様である。 In the above explanation, the prediction model 141 predicts the power generation amount on the prediction target day, but the prediction model 141 is created to output the difference between the power generation amount on the prediction target day and the power generation amount on the previous day. May be good. That is, the prediction model may be created with the objective variable as the power generation amount (t + 1) on the prediction target day-the power generation amount (t) on the previous day. Although there is a description of several days before in FIG. 3, for example, the period indicated by a few days before the upper row (rainfall of each day) and a few days before the lower row (total rainfall) may be different. The same applies to the operating hours and several days before the amount of power generation. The periods indicated by the rainfall, operating time, and power generation amount shown in the upper part of the previous few days may be different from each other. The same applies to a few days ago described in the lower row.
（動作）
　次に図４、図５を参照して予測システム１０の動作について説明する。
（予測モデルの作成処理）
　まず、予測モデルの作成処理について説明する。
　図４は、実施形態に係る予測モデルの作成処理の一例を示すフローチャートである。
　まず、データ取得部１１が、予測モデル１４１作成用のデータを取得する（ステップＳ１）。例えば、データ取得部１１は、過去の所定期間における日ごとの雨量、運転時間、発電量を取得する。データ取得部１１は、これらのデータを記憶部１４に記録する。
　次に予測モデル作成部１２は、前処理を行って学習データを作成する（ステップＳ２）。例えば、予測モデル作成部１２は、ステップＳ１で取得されたデータの中から、過去のある日“Ｄ１”を予測対象日として、予測対象日Ｄ１およびＤ１の数日前からの各日の雨量のデータを抽出し、これらを予測対象日Ｄ１用の説明変数として設定する。予測モデル作成部１２は、予測対象日Ｄ１の前日から数日前の雨量の合計を計算し、計算した合計値を予測対象日Ｄ１用の説明変数として設定する。予測モデル作成部１２は、予測対象日Ｄ１およびＤ１の数日前からの各日の運転時間および発電量を抽出し、さらに予測対象日Ｄ１の前日から数日前の運転時間の合計および発電量の合計を計算し、これらを予測対象日Ｄ１用の説明変数として設定する。予測モデル作成部１２は、予測対象日Ｄ１の暦の情報（月と曜日）を予測対象日Ｄ１用の説明変数として設定する。予測モデル作成部１２は、ステップＳ１で取得されたデータの中から予測対象日Ｄ１の発電量を抽出し、この値を予測対象日Ｄ１用の目的変数として設定する。予測モデル作成部１２は、予測対象日Ｄ１を変化させながら、説明変数と目的変数の組み合せ、つまり学習データを多数作成する。予測モデル作成部１２は、作成した多数の学習データを記憶部１４に書き込んで保存する。 (motion)
Next, the operation of the prediction system 10 will be described with reference to FIGS. 4 and 5.
(Prophecy model creation process)
First, the process of creating a prediction model will be described.
FIG. 4 is a flowchart showing an example of a prediction model creation process according to an embodiment.
First, the data acquisition unit 11 acquires data for creating the prediction model 141 (step S1). For example, the data acquisition unit 11 acquires the daily rainfall, operating time, and power generation amount in the past predetermined period. The data acquisition unit 11 records these data in the storage unit 14.
Next, the prediction model creation unit 12 performs preprocessing to create learning data (step S2). For example, the prediction model creation unit 12 sets the prediction target day “D1” as the prediction target day from the data acquired in step S1, and the data of the rainfall amount of each day from several days before the prediction target days D1 and D1. Are extracted and these are set as explanatory variables for the prediction target date D1. The prediction model creation unit 12 calculates the total amount of rainfall from the day before the prediction target day D1 to several days before, and sets the calculated total value as an explanatory variable for the prediction target day D1. The prediction model creation unit 12 extracts the operation time and the amount of power generation of each day from several days before the prediction target day D1 and D1, and further, the total of the operation time and the total amount of power generation from the day before the prediction target day D1 to several days before. Are calculated and these are set as explanatory variables for the prediction target date D1. The prediction model creation unit 12 sets the calendar information (month and day of the week) of the prediction target day D1 as an explanatory variable for the prediction target day D1. The prediction model creation unit 12 extracts the amount of power generation on the prediction target day D1 from the data acquired in step S1 and sets this value as the objective variable for the prediction target day D1. The prediction model creation unit 12 creates a combination of explanatory variables and objective variables, that is, a large number of learning data, while changing the prediction target date D1. The prediction model creation unit 12 writes and stores a large number of created learning data in the storage unit 14.
　次に予測モデル作成部１２は、予測モデル１４１を作成する（ステップＳ３）。予測モデル作成部１２は、ステップＳ１２で作成した学習データを用いて、ランダムフォレストなどの方法により、説明変数と目的変数の関係を学習して予測モデル１４１を作成する。予測モデル作成部１２は、予測モデル１４１を記憶部１４に書き込んで保存する。予測モデル１４１を構築する方法は、ランダムフォレストに限らず、回帰分析や他の機械学習による方法であってもよい。 Next, the predictive model creation unit 12 creates the predictive model 141 (step S3). The prediction model creation unit 12 learns the relationship between the explanatory variable and the objective variable by a method such as a random forest using the training data created in step S12, and creates the prediction model 141. The prediction model creation unit 12 writes and stores the prediction model 141 in the storage unit 14. The method for constructing the prediction model 141 is not limited to the random forest, and may be a method by regression analysis or other machine learning.
（発電量の予測処理）
　次に予測処理の流れについて説明する。
　図５は、実施形態に係る発電量の予測処理の一例を示すフローチャートである。
　まず、データ取得部１１が、予測対象期間と単位期間の設定を受け付ける（ステップＳ１１）。予測対象期間は、発電量を予測する期間の最初から最後までを示し、単位期間は、予測対象期間においてどの程度の長さの期間ごとの発電量を予測するかを意味する。例えば、ユーザが、予測対象期間として、予測日（予測を実行する日）当日から３日後まで、単位期間として１日ごとの発電量を予測すること指示する情報を予測システム１０へ入力する。データ取得部１１は、予測対象期間として“当日～３日後”、単位期間として“１日”という設定を記憶部１４に記録する。 (Prediction processing of power generation)
Next, the flow of prediction processing will be described.
FIG. 5 is a flowchart showing an example of the power generation amount prediction process according to the embodiment.
First, the data acquisition unit 11 accepts the setting of the prediction target period and the unit period (step S11). The forecast target period indicates from the beginning to the end of the period for predicting the power generation amount, and the unit period means how long the power generation amount is predicted for each period in the forecast target period. For example, the user inputs to the prediction system 10 information instructing that the power generation amount for each day is predicted as a unit period from the day of the prediction date (the day when the prediction is executed) to 3 days after the prediction target period. The data acquisition unit 11 records in the storage unit 14 the setting of "current day to 3 days later" as the prediction target period and "1 day" as the unit period.
　次に、データ取得部１１が、予測に必要なデータを取得する（ステップＳ１２）。ここで図６を参照する。予測を行う当日が１０月３１日、図３を用いて説明した“数日前”が一律３日前であるとする。すると、予測対象期間の最初の日である１０月３１日の予測に必要なデータは、１０月２８日～１０月３０日の発電量、天気情報、運転計画の実績値（白丸印）と、１０月３１日の天気情報、運転計画の予測値（黒丸印）である。一方、予測対象期間の最終日である１１月３日の予測に必要なデータは、１０月３１日～１１月２日の発電量の予測値（黒丸印）、１０月３１日～１１月３日の天気情報および運転計画の予測値（黒丸印）である。ユーザは、１０月２８日～１０月３０日の発電量、天気情報、運転計画の実績値と、１０月３１日～１１月３日の天気情報、運転計画の予測値を予測システム１０へ入力する。データ取得部１１は、これらのデータを、予測に必要なデータとして取得し、記憶部１４に記録する。１０月３１日～１１月２日の発電量の予測値については、以降の処理によって算出する。 Next, the data acquisition unit 11 acquires the data necessary for prediction (step S12). Now refer to FIG. It is assumed that the day when the prediction is made is October 31, and the "several days ago" explained using FIG. 3 is uniformly 3 days ago. Then, the data required for the forecast on October 31, which is the first day of the forecast period, is the amount of power generated from October 28 to October 30, the weather information, the actual value of the operation plan (white circle), and The weather information for October 31 and the predicted value of the operation plan (black circles). On the other hand, the data required for the forecast of November 3, which is the final day of the forecast period, is the forecast value of the amount of power generation from October 31 to November 2 (black circle), and from October 31 to November 3. It is the weather information of the day and the predicted value of the operation plan (black circle). The user inputs the amount of power generated from October 28 to October 30, the weather information, the actual value of the operation plan, the weather information from October 31 to November 3, and the forecast value of the operation plan into the prediction system 10. do. The data acquisition unit 11 acquires these data as data necessary for prediction and records them in the storage unit 14. The predicted value of the amount of power generation from October 31st to November 2nd will be calculated by the following processing.
　次に予測部１３が、変数ｍ、ｔに初期値を設定する（ステップＳ１３）。ここで、ｍは、予測日（＝当日）から予測対象日の差、ｔは予測日当日を示す。今回の例では、予測開始日が予測日当日なので、予測部１３は、ｍ＝０、ｔ＝予測日当日（１０月３１日）を設定する。
　次に予測部１３が、予測対象期間の最初の予測対象期間における発電量Ｙ（ｔ＋ｍ）を予測する（ステップＳ１４）。今回の例の場合、予測部１３は、発電量Ｙ（１０月３１日）を予測する。予測部１３は、１０月２８日～１０月３０日の発電量、天気情報、運転計画の実績値と、１０月３１日の天気情報、運転計画の予測値を予測モデル１４１に入力する。予測モデル１４１は、１０月３１日の発電量を出力する。予測モデル１４１が出力した発電量が発電量Ｙ（１０月３１日）である。予測部１３は、発電量Ｙ（ｔ＋ｍ）を記憶部１４に記録する。 Next, the prediction unit 13 sets initial values for the variables m and t (step S13). Here, m indicates the difference between the predicted date (= the current day) and the predicted target date, and t indicates the predicted date. In this example, since the prediction start date is the prediction date day, the prediction unit 13 sets m = 0 and t = the prediction date day (October 31).
Next, the prediction unit 13 predicts the power generation amount Y (t + m) in the first prediction target period of the prediction target period (step S14). In the case of this example, the prediction unit 13 predicts the power generation amount Y (October 31). The forecasting unit 13 inputs the power generation amount from October 28 to October 30, the actual value of the weather information and the operation plan, and the weather information of October 31 and the predicted value of the operation plan into the prediction model 141. The prediction model 141 outputs the amount of power generation on October 31st. The amount of power generated by the prediction model 141 is the amount of power generation Y (October 31). The prediction unit 13 records the power generation amount Y (t + m) in the storage unit 14.
　次に予測部１３が、変数ｍに１を加算する（ステップＳ１５）。今回の例の場合、ｍ＝０＋１＝１となる。次に予測部１３が、発電量の予測値、発電量Ｙ（ｔ＋ｍ－１）を用いて、発電量Ｙ（ｔ＋ｍ）を予測する（ステップＳ１６）。つまり、１つ前の単位期間（１０月３１日）での発電量の予測値を用いて、次の単位期間（１１月１日）の発電量を予測する。予測部１３は、１０月２９日～１０月３１日の天気情報、運転計画の実績値と、１１月１日の天気情報、運転計画の予測値、１０月２９日～１０月３０日の発電量の実績値と、１０月３１日の発電量の予測値を予測モデル１４１に入力する。予測モデル１４１は、１１月１日の発電量を出力する。予測モデル１４１が出力した発電量が発電量Ｙ（ｔ＋ｍ＝１１月１日）である。予測部１３は、発電量Ｙ（ｔ＋ｍ－１）を記憶部１４に記録する。 Next, the prediction unit 13 adds 1 to the variable m (step S15). In the case of this example, m = 0 + 1 = 1. Next, the prediction unit 13 predicts the power generation amount Y (t + m) using the predicted value of the power generation amount and the power generation amount Y (t + m-1) (step S16). That is, the power generation amount in the next unit period (November 1st) is predicted by using the predicted value of the power generation amount in the previous unit period (October 31st). The prediction unit 13 has weather information from October 29th to October 31st, actual values of the operation plan, weather information of November 1st, predicted values of the operation plan, and power generation from October 29th to October 30th. The actual value of the amount and the predicted value of the amount of power generation on October 31 are input to the prediction model 141. The prediction model 141 outputs the amount of power generation on November 1. The power generation amount output by the prediction model 141 is the power generation amount Y (t + m = November 1st). The prediction unit 13 records the power generation amount Y (t + m-1) in the storage unit 14.
　次に、予測部１３は、ｍがＮ以上となったか否かを判定する（ステップＳ１７）。ここでＮとは、予測対象期間に含まれる単位期間の数から１を減算した値である。今回の例の場合、Ｎ＝３である。ｍがＮ未満の場合（ステップＳ１７；Ｎｏ）、予測部１３は、ステップＳ１５以降の処理を繰り返す。例えば、今回の例の場合、ｍ＝１であれば、予測部１３は、１０月３０日の発電量の実績値と１０月３１日～１１月１日の発電量の予測値などを用いて、１１月２日の発電量の予測を行う。さらに次のループでは、予測部１３は、１０月３１日～１１月２日の発電量の予測値などを用いて、１１月３日の発電量の予測を行う。このように予測部１３は、１つ前の単位期間に対する予測結果を用いて次の単位期間の予測を行う処理を逐次的に繰り返し実行する。 Next, the prediction unit 13 determines whether or not m is N or more (step S17). Here, N is a value obtained by subtracting 1 from the number of unit periods included in the prediction target period. In the case of this example, N = 3. When m is less than N (step S17; No), the prediction unit 13 repeats the processes after step S15. For example, in the case of this example, if m = 1, the prediction unit 13 uses the actual value of the power generation amount on October 30 and the predicted value of the power generation amount from October 31st to November 1st. , Predict the amount of power generation on November 2nd. Further, in the next loop, the prediction unit 13 predicts the power generation amount on November 3 using the predicted value of the power generation amount from October 31st to November 2nd. In this way, the prediction unit 13 sequentially and repeatedly executes the process of predicting the next unit period using the prediction result for the previous unit period.
　ｍがＮ以上となると（ステップＳ１７；Ｙｅｓ）、出力部１５が予測対象期間における単位期間ごとの発電量の予測値を出力する（ステップＳ１８）。例えば、出力部１５は、１０月３１日～１１月３日までの１日ごとの水力発電設備による発電量の予測値を表示装置や電子ファイル等へ出力する。 When m is N or more (step S17; Yes), the output unit 15 outputs the predicted value of the power generation amount for each unit period in the prediction target period (step S18). For example, the output unit 15 outputs the predicted value of the amount of power generated by the daily hydroelectric power generation facility from October 31st to November 3rd to a display device, an electronic file, or the like.
　以上の説明では１日ごとの発電量を４日間にわたって予測する例を挙げたが、例えば、３０分ごとの発電量予測値を出力するように作成された予測モデル１４１を用いて、３日先までの３０分ごとの発電量予測を行ってもよいし、１カ月先までの１日ごとの発電量予測を行ってもよい。 In the above explanation, an example of predicting the amount of power generation per day for 4 days is given. For example, using the prediction model 141 created to output the predicted value of the amount of power generation every 30 minutes, 3 days ahead. The power generation amount may be predicted every 30 minutes up to, or the daily power generation amount may be predicted up to one month ahead.
（効果）
　以上説明したように、予測システム１０によれば、水力発電設備が計測できるデータ（過去の発電量および運転時間の実績値と未来の運転計画）と、市場で入手可能な天気情報（実績値および予測値）と、予測モデル１４１によって、水力発電設備が供給可能な発電量を精度よく予測することができる。逐次的な予測を行うことにより、長期的な発電量の予測を行うことができる。これにより、水力発電設備で発電した電力を売電するような場合、高精度な発電量予測に基づいて、売電する発電量を取り決めることができ、約束した電力量を供給できなかった場合のペナルティを受けるリスクを低減することができる。本実施形態の発電量予測では、電力需要量予測などを必要とせず、実績に基づく、自設備の能力に応じた発電量を予測することができる。例えば、発明者が予測モデル１４１を構築し、図５のフローチャートによる逐次予測を行って結果を評価したところ、数日先の予測では９５％程度、１月先で９０％程度の精度で発電量を予測できることが確認できた。 (effect)
As described above, according to the prediction system 10, data that can be measured by hydroelectric power generation facilities (actual values of past power generation and operating hours and future operating plans) and weather information available in the market (actual values and actual values and future operation plans) The predicted value) and the prediction model 141 can accurately predict the amount of power that can be supplied by the hydroelectric power generation facility. By making sequential predictions, it is possible to predict the amount of power generation over the long term. As a result, when selling the power generated by the hydroelectric power generation facility, the amount of power to be sold can be decided based on the highly accurate power generation amount prediction, and the promised amount of power cannot be supplied. The risk of being penalized can be reduced. The power generation amount prediction of the present embodiment does not require power demand prediction or the like, and can predict the power generation amount according to the capacity of the own facility based on the actual results. For example, when the inventor constructed a prediction model 141 and evaluated the results by performing sequential prediction using the flowchart of FIG. 5, the amount of power generation was estimated to be about 95% in the prediction several days ahead and about 90% in January. It was confirmed that it can be predicted.
　図７は、実施形態に係る予測システムのハードウェア構成の一例を示す図である。
　コンピュータ９００は、ＣＰＵ９０１、主記憶装置９０２、補助記憶装置９０３、入出力インタフェース９０４、通信インタフェース９０５を備える。
　上述の予測システム１０は、コンピュータ９００に実装される。そして、上述した各機能は、プログラムの形式で補助記憶装置９０３に記憶されている。ＣＰＵ９０１は、プログラムを補助記憶装置９０３から読み出して主記憶装置９０２に展開し、当該プログラムに従って上記処理を実行する。ＣＰＵ９０１は、プログラムに従って、記憶領域を主記憶装置９０２に確保する。ＣＰＵ９０１は、プログラムに従って、処理中のデータを記憶する記憶領域を補助記憶装置９０３に確保する。 FIG. 7 is a diagram showing an example of the hardware configuration of the prediction system according to the embodiment.
The computer 900 includes a CPU 901, a main storage device 902, an auxiliary storage device 903, an input / output interface 904, and a communication interface 905.
The prediction system 10 described above is mounted on the computer 900. Each of the above-mentioned functions is stored in the auxiliary storage device 903 in the form of a program. The CPU 901 reads a program from the auxiliary storage device 903, expands it to the main storage device 902, and executes the above processing according to the program. The CPU 901 reserves a storage area in the main storage device 902 according to the program. The CPU 901 secures a storage area for storing the data being processed in the auxiliary storage device 903 according to the program.
　予測システム１０の全部または一部の機能を実現するためのプログラムをコンピュータ読み取り可能な記録媒体に記録して、この記録媒体に記録されたプログラムをコンピュータシステムに読み込ませ、実行することにより各機能部による処理を行ってもよい。ここでいう「コンピュータシステム」とは、ＯＳや周辺機器等のハードウェアを含むものとする。「コンピュータシステム」は、ＷＷＷシステムを利用している場合であれば、ホームページ提供環境（あるいは表示環境）も含むものとする。「コンピュータ読み取り可能な記録媒体」とは、ＣＤ、ＤＶＤ、ＵＳＢ等の可搬媒体、コンピュータシステムに内蔵されるハードディスク等の記憶装置のことをいう。このプログラムが通信回線によってコンピュータ９００に配信される場合、配信を受けたコンピュータ９００が当該プログラムを主記憶装置９０２に展開し、上記処理を実行しても良い。上記プログラムは、前述した機能の一部を実現するためのものであっても良く、さらに前述した機能をコンピュータシステムにすでに記録されているプログラムとの組み合わせで実現できるものであってもよい。予測システム１０は、複数のコンピュータ９００によって構成されていても良い。 A program for realizing all or a part of the functions of the prediction system 10 is recorded on a computer-readable recording medium, and the program recorded on the recording medium is read into the computer system and executed. May be processed by. The term "computer system" as used herein includes hardware such as an OS and peripheral devices. The "computer system" shall include the homepage providing environment (or display environment) if the WWW system is used. The "computer-readable recording medium" refers to a portable medium such as a CD, DVD, or USB, or a storage device such as a hard disk built in a computer system. When this program is distributed to the computer 900 by a communication line, the distributed computer 900 may expand the program to the main storage device 902 and execute the above processing. The above program may be for realizing a part of the above-mentioned functions, and may be further realized for realizing the above-mentioned functions in combination with a program already recorded in the computer system. The prediction system 10 may be composed of a plurality of computers 900.
　以上のとおり、本開示に係るいくつかの実施形態を説明したが、これら全ての実施形態は、例として提示したものであり、発明の範囲を限定することを意図していない。これらの実施形態は、その他の様々な形態で実施されることが可能であり、発明の要旨を逸脱しない範囲で種々の省略、置き換え、変更を行うことができる。これらの実施形態及びその変形は、発明の範囲や要旨に含まれると同様に、特許請求の範囲に記載された発明とその均等の範囲に含まれる。 As described above, some embodiments according to the present disclosure have been described, but all of these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and variations thereof are included in the scope of the invention described in the claims and the equivalent scope thereof, as are included in the scope and gist of the invention.
＜付記＞
　実施形態に記載の予測システム１０、予測方法およびプログラムは、例えば以下のように把握される。 <Additional Notes>
The prediction system 10, the prediction method and the program according to the embodiment are grasped as follows, for example.
（１）第１の態様に係る予測システム１０は、所定の期間（ｔ）に水力発電設備が発電する発電量を発電量（ｔ）とし、前記期間（ｔ）に続く同じ長さの期間を期間（ｔ＋１）、前記期間（ｔ＋１）における前記発電量を発電量（ｔ＋１）としたときに、前記発電量（ｔ）を説明変数に含み、発電量（ｔ＋１）を目的変数とする予測モデル１４１と、所定の予測対象期間を前記期間ごとに分割した場合の最初の前記期間を期間（ｓ）、前記期間（ｓ）における前記発電量を発電量（ｓ）とし、前記期間（ｓ）に続く期間（ｓ＋１）における前記発電量を発電量（ｓ＋１）とし、前記期間（ｓ＋１）に続く期間（ｓ＋２）における前記発電量を発電量（ｓ＋２）としたときに、前記予測モデルと前記発電量（ｓ）の実績値に基づいて、前記発電量（ｓ＋１）を予測し、前記予測モデルと予測した前記発電量（ｓ＋１）に基づいて、前記発電量（ｓ＋２）を予測する、という処理を逐次的に実行し、前記予測対象期間における前記期間ごとの前記発電量を予測する予測部１３と、前記予測部による前記発電量の予測結果を出力する出力部１５と、を備える。
　取水式の水力発電設備では、例えば、前日と当日で発電可能な発電量が大きく変動しないという知見を得た。この知見に基づいて作成された、発電量（ｔ）を説明変数、発電量（ｔ＋１）を目的変数とする予測モデルとこの予測モデルによる予測値を用いると、期間（ｓ）の発電量（ｓ）から期間（ｓ＋１）の発電量（ｓ＋１）を予測し、発電量（ｓ＋１）から期間（ｓ＋２）の発電量（ｓ＋２）を予測し、といったように逐次的に次の期間の発電量を予測することで予測対象期間の最後の期間である期間（ｓ＋Ｎ）までの単位期間ごとの発電量を予測することができる。これにより、電力需要などに関係なく、自設備の実績・能力に応じた供給可能な発電量を予測することができる。 (1) In the prediction system 10 according to the first aspect, the amount of power generated by the hydroelectric power generation facility in a predetermined period (t) is set as the amount of power generation (t), and a period of the same length following the period (t) is set. Prediction model 141 in which the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable when the power generation amount in the period (t + 1) and the period (t + 1) is the power generation amount (t + 1). When the predetermined prediction target period is divided into the periods, the first period is the period (s), the power generation amount in the period (s) is the power generation amount (s), and the period (s) is continued. When the power generation amount in the period (s + 1) is the power generation amount (s + 1) and the power generation amount in the period (s + 2) following the period (s + 1) is the power generation amount (s + 2), the prediction model and the power generation amount ( The process of predicting the power generation amount (s + 1) based on the actual value of s) and predicting the power generation amount (s + 2) based on the predicted model and the predicted power generation amount (s + 1) is sequentially performed. It is provided with a prediction unit 13 for predicting the power generation amount for each period in the prediction target period, and an output unit 15 for outputting the prediction result of the power generation amount by the prediction unit.
It was found that, for example, in the intake type hydroelectric power generation facility, the amount of power that can be generated does not fluctuate significantly between the day before and the day. Using the prediction model created based on this finding, with the power generation amount (t) as the explanatory variable and the power generation amount (t + 1) as the objective variable, and the predicted value by this prediction model, the power generation amount (s) in the period (s). ) Predicts the amount of power generation (s + 1) in the period (s + 1), predicts the amount of power generation (s + 2) in the period (s + 2) from the amount of power generation (s + 1), and so on. By doing so, it is possible to predict the amount of power generation for each unit period up to the period (s + N), which is the last period of the prediction target period. This makes it possible to predict the amount of power generation that can be supplied according to the actual performance and capacity of the own equipment, regardless of the power demand.
（２）第２の態様に係る予測システム１０は、（１）の予測システム１０であって、前記予測モデル１４１の説明変数は、前記発電量（ｔ）に加え、前記期間（ｔ）における前記水力発電設備の周辺の所定範囲における雨量と、前記期間（ｔ）における前記水力発電設備の運転時間と、を含む（図２）。
　これにより、発電量の予測精度を向上することができる。 (2) The prediction system 10 according to the second aspect is the prediction system 10 of (1), and the explanatory variables of the prediction model 141 are the said in the period (t) in addition to the power generation amount (t). It includes the amount of rainfall in a predetermined range around the hydroelectric power generation facility and the operating time of the hydroelectric power generation facility during the period (t) (FIG. 2).
This makes it possible to improve the accuracy of predicting the amount of power generation.
（３）第３の態様に係る予測システム１０は、（１）～（２）の予測システム１０であって、前記予測モデル１４１の説明変数は、前記発電量（ｔ）に加え、前記期間（ｔ）を含む前記期間（ｔ）以前の所定期間における前記期間ごとの前記発電量と、前記期間（ｔ）を含む前記期間（ｔ）以前の所定期間における前記発電量の合計と、前記期間（ｔ）を含む前記期間（ｔ）以前の所定期間における前記期間ごとの前記水力発電設備周辺の所定範囲における雨量および前記期間（ｔ＋１）における前記雨量と、前記期間（ｔ）を含む前記期間（ｔ）以前の所定期間における前記雨量の合計と、前記期間（ｔ）を含む前記期間（ｔ）以前の所定期間における前記期間ごとの前記水力発電設備の運転時間および前記期間（ｔ＋１）における前記運転時間と、前記期間（ｔ）を含む前記期間（ｔ）以前の所定期間における前記運転時間の合計と、前記期間（ｔ＋１）の月および曜日の情報と、を含む（図３）。
　これにより、発電量の予測精度を向上することができる。 (3) The prediction system 10 according to the third aspect is the prediction system 10 of (1) to (2), and the explanatory variables of the prediction model 141 are the period (t) in addition to the power generation amount (t). The total of the power generation amount for each period in the predetermined period before the period (t) including t), the power generation amount in the predetermined period before the period (t) including the period (t), and the period (t). The rainfall in a predetermined range around the hydroelectric power generation facility for each period in the predetermined period before the period (t) including t), the rainfall in the period (t + 1), and the period (t) including the period (t). ) The total amount of the rainfall in the previous predetermined period, the operation time of the hydroelectric power generation facility for each period in the predetermined period before the period (t) including the period (t), and the operation time in the period (t + 1). And, the total of the operation time in the predetermined period before the period (t) including the period (t), and the information of the month and the day of the period (t + 1) are included (FIG. 3).
This makes it possible to improve the accuracy of predicting the amount of power generation.
（４）第４の態様に係る予測システム１０は、（１）～（３）の予測システム１０であって、前記説明変数と前記目的変数との関係を学習することによって、前記予測モデルを作成する予測モデル作成部、をさらに備える。
　これにより、予測モデル１４１を作成することができる。 (4) The prediction system 10 according to the fourth aspect is the prediction system 10 of (1) to (3), and creates the prediction model by learning the relationship between the explanatory variable and the objective variable. It also has a predictive model creation unit.
As a result, the prediction model 141 can be created.
（５）第５の態様に係る予測システム１０は、（１）～（４）の予測システム１０であって、前記予測モデル１４１の前記目的変数が、前記発電量（ｔ＋１）に替えて、前記発電量（ｔ）と前記発電量（ｔ＋１）の差である。
　目的変数を発電量（ｔ）と発電量（ｔ＋１）の差とおくことによっても、予測モデル１４１を作成することができる。 (5) The prediction system 10 according to the fifth aspect is the prediction system 10 of (1) to (4), in which the objective variable of the prediction model 141 is replaced with the power generation amount (t + 1). It is the difference between the power generation amount (t) and the power generation amount (t + 1).
The prediction model 141 can also be created by setting the objective variable as the difference between the power generation amount (t) and the power generation amount (t + 1).
（６）第６の態様に係る予測方法は、所定の期間（ｔ）に水力発電設備が発電する発電量を発電量（ｔ）とし、前記期間（ｔ）に続く同じ長さの期間を期間（ｔ＋１）、前記期間（ｔ＋１）における前記発電量を発電量（ｔ＋１）としたときに、前記発電量（ｔ）を説明変数に含み、発電量（ｔ＋１）を目的変数とする予測モデルを用いて、所定の予測対象期間を前記期間ごとに分割した場合の最初の前記期間を期間（ｓ）、前記期間（ｓ）における前記発電量を発電量（ｓ）とし、前記期間（ｓ）に続く期間（ｓ＋１）における前記発電量を発電量（ｓ＋１）とし、前記期間（ｓ＋１）に続く期間（ｓ＋２）における前記発電量を発電量（ｓ＋２）としたときに、前記予測モデルと前記発電量（ｓ）の実績値に基づいて、前記発電量（ｓ＋１）を予測し、前記予測モデルと予測した前記発電量（ｓ＋１）に基づいて、前記発電量（ｓ＋２）を予測する、という処理を逐次的に実行し、前記予測対象期間における前記期間ごとの前記発電量を予測し、前記予測による前記発電量の予測結果を出力する。 (6) In the prediction method according to the sixth aspect, the amount of power generated by the hydroelectric power generation facility in a predetermined period (t) is defined as the amount of power generation (t), and the period of the same length following the period (t) is a period. (T + 1), when the power generation amount in the period (t + 1) is the power generation amount (t + 1), a prediction model is used in which the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable. The first period when the predetermined prediction target period is divided into each period is defined as the period (s), the power generation amount in the period (s) is defined as the power generation amount (s), and the period (s) is continued. When the power generation amount in the period (s + 1) is the power generation amount (s + 1) and the power generation amount in the period (s + 2) following the period (s + 1) is the power generation amount (s + 2), the prediction model and the power generation amount ( The process of predicting the power generation amount (s + 1) based on the actual value of s) and predicting the power generation amount (s + 2) based on the predicted model and the predicted power generation amount (s + 1) is sequentially performed. The power generation amount for each period in the prediction target period is predicted, and the prediction result of the power generation amount based on the prediction is output.
（７）第７の態様に係るプログラムは、コンピュータに、所定の期間（ｔ）に水力発電設備が発電する発電量を発電量（ｔ）とし、前記期間（ｔ）に続く同じ長さの期間を期間（ｔ＋１）、前記期間（ｔ＋１）における前記発電量を発電量（ｔ＋１）としたときに、前記発電量（ｔ）を説明変数に含み、発電量（ｔ＋１）を目的変数とする予測モデルを用いて、所定の予測対象期間を前記期間ごとに分割した場合の最初の前記期間を期間（ｓ）、前記期間（ｓ）における前記発電量を発電量（ｓ）とし、前記期間（ｓ）に続く期間（ｓ＋１）における前記発電量を発電量（ｓ＋１）とし、前記期間（ｓ＋１）に続く期間（ｓ＋２）における前記発電量を発電量（ｓ＋２）としたときに、前記予測モデルと前記発電量（ｓ）の実績値に基づいて、前記発電量（ｓ＋１）を予測し、前記予測モデルと予測した前記発電量（ｓ＋１）に基づいて、前記発電量（ｓ＋２）を予測する、という処理を逐次的に実行し、前記予測対象期間における前記期間ごとの前記発電量を予測し、前記予測による前記発電量の予測結果を出力する処理を実行させる。 (7) In the program according to the seventh aspect, the amount of power generated by the hydroelectric power generation facility in a predetermined period (t) is set as the power generation amount (t), and the period of the same length following the period (t) is set. Is a period (t + 1), and when the power generation amount in the period (t + 1) is the power generation amount (t + 1), the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable. When the predetermined prediction target period is divided into the periods, the first period is defined as the period (s), the power generation amount in the period (s) is defined as the power generation amount (s), and the period (s) is used. The prediction model and the power generation when the power generation amount in the period (s + 1) following the period (s + 1) is the power generation amount (s + 1) and the power generation amount in the period (s + 2) following the period (s + 1) is the power generation amount (s + 2). The process of predicting the power generation amount (s + 1) based on the actual value of the amount (s) and predicting the power generation amount (s + 2) based on the power generation amount (s + 1) predicted by the prediction model. It is sequentially executed to predict the power generation amount for each period in the prediction target period, and execute a process of outputting the prediction result of the power generation amount by the prediction.
　上記した予測システム、予測方法およびプログラムによれば、水力発電設備による発電量を予測することができる。 According to the above-mentioned prediction system, prediction method and program, it is possible to predict the amount of power generated by the hydroelectric power generation facility.
１０・・・予測システム
１１・・・データ取得部
１２・・・予測モデル作成部
１３・・・予測部
１４・・・記憶部
１４１・・・予測モデル
１５・・・出力部
９００・・・コンピュータ
９０１・・・ＣＰＵ
９０２・・・主記憶装置
９０３・・・補助記憶装置
９０４・・・入出力インタフェース
９０５・・・通信インタフェース 10 ... Predictive system 11 ... Data acquisition unit 12 ... Predictive model creation unit 13 ... Predictive unit 14 ... Storage unit 141 ... Predictive model 15 ... Output unit 900 ... Computer 901 ... CPU
902 ... Main storage device 903 ... Auxiliary storage device 904 ... Input / output interface 905 ... Communication interface

Claims (7)

  1. 　所定の期間（ｔ）に水力発電設備が発電する発電量を発電量（ｔ）とし、前記期間（ｔ）に続く同じ長さの期間を期間（ｔ＋１）、前記期間（ｔ＋１）における前記発電量を発電量（ｔ＋１）としたときに、前記発電量（ｔ）を説明変数に含み、発電量（ｔ＋１）を目的変数とする予測モデルと、
    　所定の予測対象期間を前記期間ごとに分割した場合の最初の前記期間を期間（ｓ）、前記期間（ｓ）における前記発電量を発電量（ｓ）とし、前記期間（ｓ）に続く期間（ｓ＋１）における前記発電量を発電量（ｓ＋１）とし、前記期間（ｓ＋１）に続く期間（ｓ＋２）における前記発電量を発電量（ｓ＋２）としたときに、前記予測モデルと前記発電量（ｓ）の実績値に基づいて、前記発電量（ｓ＋１）を予測し、前記予測モデルと予測した前記発電量（ｓ＋１）に基づいて、前記発電量（ｓ＋２）を予測する、という処理を逐次的に実行し、前記予測対象期間における前記期間ごとの前記発電量を予測する予測部と、
    　前記予測部による前記発電量の予測結果を出力する出力部と、
    　を備える予測システム。     The amount of power generated by the hydroelectric power generation facility in a predetermined period (t) is defined as the amount of power generation (t), the period of the same length following the period (t) is the period (t + 1), and the amount of power generated in the period (t + 1). With the power generation amount (t + 1), a prediction model in which the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable.
    When the predetermined prediction target period is divided into the periods, the first period (s) is defined as the period (s), the power generation amount in the period (s) is defined as the power generation amount (s), and the period following the period (s) (s). When the power generation amount in s + 1) is the power generation amount (s + 1) and the power generation amount in the period (s + 2) following the period (s + 1) is the power generation amount (s + 2), the prediction model and the power generation amount (s) The process of predicting the power generation amount (s + 1) based on the actual value of the above and predicting the power generation amount (s + 2) based on the power generation amount (s + 1) predicted by the prediction model is sequentially executed. Then, the prediction unit that predicts the amount of power generation for each period in the prediction target period,
    An output unit that outputs the prediction result of the power generation amount by the prediction unit, and
    Prediction system with.
  2. 　前記予測モデルの説明変数は、前記発電量（ｔ）に加え、
    　前記期間（ｔ）における前記水力発電設備の周辺の所定範囲における雨量と、
    　前記期間（ｔ）における前記水力発電設備の運転時間と、
    　を含む請求項１に記載の予測システム。     The explanatory variables of the prediction model are, in addition to the power generation amount (t),
    The amount of rainfall in a predetermined range around the hydroelectric power generation facility during the period (t), and
    The operating time of the hydroelectric power generation facility in the period (t) and
    The prediction system according to claim 1.
  3. 　前記予測モデルの説明変数は、前記発電量（ｔ）に加え、
    　前記期間（ｔ）を含む前記期間（ｔ）以前の所定期間における前記期間ごとの前記発電量と、
    　前記期間（ｔ）を含む前記期間（ｔ）以前の所定期間における前記発電量の合計と、
    　前記期間（ｔ）を含む前記期間（ｔ）以前の所定期間における前記期間ごとの前記水力発電設備の周辺の所定範囲における雨量および前記期間（ｔ＋１）における前記雨量と、
    　前記期間（ｔ）を含む前記期間（ｔ）以前の所定期間における前記雨量の合計と、
    　前記期間（ｔ）を含む前記期間（ｔ）以前の所定期間における前記期間ごとの前記水力発電設備の運転時間および前記期間（ｔ＋１）における前記運転時間と、
    　前記期間（ｔ）を含む前記期間（ｔ）以前の所定期間における前記運転時間の合計と、
    　前記期間（ｔ＋１）の月および曜日の情報と、
    　を含む請求項１または請求項２に記載の予測システム。     The explanatory variables of the prediction model are, in addition to the power generation amount (t),
    The amount of power generation for each period in a predetermined period before the period (t) including the period (t), and
    The total amount of power generation in the predetermined period before the period (t) including the period (t), and
    The amount of rainfall in a predetermined range around the hydroelectric power generation facility and the amount of rainfall in the period (t + 1) for each period in the predetermined period before the period (t) including the period (t).
    The total amount of rainfall in the predetermined period before the period (t) including the period (t), and
    The operating time of the hydroelectric power generation facility and the operating time in the period (t + 1) for each period in the predetermined period before the period (t) including the period (t).
    The total of the operating hours in the predetermined period before the period (t) including the period (t), and
    Information on the month and day of the week for the period (t + 1),
    The prediction system according to claim 1 or 2.
  4. 　前記説明変数と前記目的変数との関係を学習することによって、前記予測モデルを作成する予測モデル作成部、
    　をさらに備える請求項１から請求項３の何れか１項に記載の予測システム。     A predictive model creation unit that creates a predictive model by learning the relationship between the explanatory variables and the objective variable.
    The prediction system according to any one of claims 1 to 3, further comprising.
  5. 　前記予測モデルの前記目的変数が、前記発電量（ｔ＋１）に替えて、前記発電量（ｔ）と前記発電量（ｔ＋１）の差である、
    　請求項１から請求項４の何れか１項に記載の予測システム。     The objective variable of the prediction model is the difference between the power generation amount (t) and the power generation amount (t + 1) instead of the power generation amount (t + 1).
    The prediction system according to any one of claims 1 to 4.
  6. 　所定の期間（ｔ）に水力発電設備が発電する発電量を発電量（ｔ）とし、前記期間（ｔ）に続く同じ長さの期間を期間（ｔ＋１）、前記期間（ｔ＋１）における前記発電量を発電量（ｔ＋１）としたときに、前記発電量（ｔ）を説明変数に含み、発電量（ｔ＋１）を目的変数とする予測モデルを用いて、
    　所定の予測対象期間を前記期間ごとに分割した場合の最初の前記期間を期間（ｓ）、前記期間（ｓ）における前記発電量を発電量（ｓ）とし、前記期間（ｓ）に続く期間（ｓ＋１）における前記発電量を発電量（ｓ＋１）とし、前記期間（ｓ＋１）に続く期間（ｓ＋２）における前記発電量を発電量（ｓ＋２）としたときに、前記予測モデルと前記発電量（ｓ）の実績値に基づいて、前記発電量（ｓ＋１）を予測し、前記予測モデルと予測した前記発電量（ｓ＋１）に基づいて、前記発電量（ｓ＋２）を予測する、という処理を逐次的に実行し、前記予測対象期間における前記期間ごとの前記発電量を予測し、
    　前記予測による前記発電量の予測結果を出力する、
    　予測方法。     The amount of power generated by the hydroelectric power generation facility in a predetermined period (t) is defined as the amount of power generation (t), the period of the same length following the period (t) is the period (t + 1), and the amount of power generated in the period (t + 1). With the power generation amount (t + 1), a prediction model in which the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable is used.
    When the predetermined prediction target period is divided into the periods, the first period (s) is defined as the period (s), the power generation amount in the period (s) is defined as the power generation amount (s), and the period following the period (s) (s). When the power generation amount in s + 1) is the power generation amount (s + 1) and the power generation amount in the period (s + 2) following the period (s + 1) is the power generation amount (s + 2), the prediction model and the power generation amount (s) The process of predicting the power generation amount (s + 1) based on the actual value of the above and predicting the power generation amount (s + 2) based on the power generation amount (s + 1) predicted by the prediction model is sequentially executed. Then, the amount of power generation for each period in the prediction target period is predicted, and the amount of power generation is predicted.
    Outputs the prediction result of the power generation amount by the prediction.
    Prediction method.
  7. 　コンピュータに、
    　所定の期間（ｔ）に水力発電設備が発電する発電量を発電量（ｔ）とし、前記期間（ｔ）に続く同じ長さの期間を期間（ｔ＋１）、前記期間（ｔ＋１）における前記発電量を発電量（ｔ＋１）としたときに、前記発電量（ｔ）を説明変数に含み、発電量（ｔ＋１）を目的変数とする予測モデルを用いて、
    　所定の予測対象期間を前記期間ごとに分割した場合の最初の前記期間を期間（ｓ）、前記期間（ｓ）における前記発電量を発電量（ｓ）とし、前記期間（ｓ）に続く期間（ｓ＋１）における前記発電量を発電量（ｓ＋１）とし、前記期間（ｓ＋１）に続く期間（ｓ＋２）における前記発電量を発電量（ｓ＋２）としたときに、前記予測モデルと前記発電量（ｓ）の実績値に基づいて、前記発電量（ｓ＋１）を予測し、前記予測モデルと予測した前記発電量（ｓ＋１）に基づいて、前記発電量（ｓ＋２）を予測する、という処理を逐次的に実行し、前記予測対象期間における前記期間ごとの前記発電量を予測し、
    　前記予測による前記発電量の予測結果を出力する処理、
    　を実行させるプログラム。     On the computer
    The amount of power generated by the hydroelectric power generation facility in a predetermined period (t) is defined as the amount of power generation (t), the period of the same length following the period (t) is the period (t + 1), and the amount of power generated in the period (t + 1). With the power generation amount (t + 1), a prediction model in which the power generation amount (t) is included in the explanatory variables and the power generation amount (t + 1) is the objective variable is used.
    When the predetermined prediction target period is divided into the periods, the first period (s) is defined as the period (s), the power generation amount in the period (s) is defined as the power generation amount (s), and the period following the period (s) (s). When the power generation amount in s + 1) is the power generation amount (s + 1) and the power generation amount in the period (s + 2) following the period (s + 1) is the power generation amount (s + 2), the prediction model and the power generation amount (s) The process of predicting the power generation amount (s + 1) based on the actual value of the above and predicting the power generation amount (s + 2) based on the power generation amount (s + 1) predicted by the prediction model is sequentially executed. Then, the amount of power generation for each period in the prediction target period is predicted, and the amount of power generation is predicted.
    Processing to output the prediction result of the power generation amount by the prediction,
    A program to execute.
PCT/JP2021/034895 2020-12-03 2021-09-22 Prediction system, prediction method, and program WO2022118524A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020200853A JP2022088807A (en) 2020-12-03 2020-12-03 Prediction system, prediction method, and program
JP2020-200853 2020-12-03

Publications (1)

Publication Number Publication Date
WO2022118524A1 true WO2022118524A1 (en) 2022-06-09

Family

ID=81852709

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/034895 WO2022118524A1 (en) 2020-12-03 2021-09-22 Prediction system, prediction method, and program

Country Status (2)

Country Link
JP (1) JP2022088807A (en)
WO (1) WO2022118524A1 (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003030621A (en) * 2001-07-13 2003-01-31 Fuji Electric Co Ltd Generated hydraulic power prediction method for run-of- river type dam and neural network therefor
WO2020203854A1 (en) * 2019-03-29 2020-10-08 三菱重工業株式会社 Power generation amount prediction device, power generation amount prediction method, and program

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003030621A (en) * 2001-07-13 2003-01-31 Fuji Electric Co Ltd Generated hydraulic power prediction method for run-of- river type dam and neural network therefor
WO2020203854A1 (en) * 2019-03-29 2020-10-08 三菱重工業株式会社 Power generation amount prediction device, power generation amount prediction method, and program

Also Published As

Publication number Publication date
JP2022088807A (en) 2022-06-15

Similar Documents

Publication Publication Date Title
Green et al. Disruptive innovation, stranded assets and forecasting: the rise and rise of renewable energy
JP6852392B2 (en) Stochastic price and sudden change forecast
Samset Early project appraisal: making the initial choices
Aasgård et al. Hydropower bidding in a multi-market setting
Chazarra et al. Stochastic optimization model for the weekly scheduling of a hydropower system in day-ahead and secondary regulation reserve markets
Block Tailoring seasonal climate forecasts for hydropower operations
WO2011114752A1 (en) Device for prediction of electricity generation amount, method for same, and program for same
US20130268318A1 (en) Systems and Methods for Temporal Reconciliation of Forecast Results
Loureiro et al. Renewable integration through transmission network expansion planning under uncertainty
Göke et al. Adequacy of time-series reduction for renewable energy systems
JP2017011780A (en) Power generation amount prediction control device, power generation amount prediction method and power generation amount prediction program
Gaha et al. Global methodology for electrical utilities maintenance assessment based on risk-informed decision making
Anderson et al. Optimize Deep Decarbonization Pathways in California with Power System Planning Using Surrogate Level-based Lagrangian Relaxation
Lucic et al. Performance of the autoregressive integrated moving average model with exogenous variables statistical model on the intraday market for the Denmark-West bidding area
WO2022118524A1 (en) Prediction system, prediction method, and program
Wheatcroft et al. The scenario culture
Fujimoto et al. Day-Ahead Scheduling of Wind-Hydro Balancing Group Operation to Maximize Expected Revenue Considering Wind Power Output Uncertainty
CN109766541A (en) Marketing strategy identification method, server and computer storage medium
Nandakumar et al. Impact of increased renewables on natural gas markets in eastern United States
Barlow et al. On using simulation to model the installation process logistics for an offshore wind farm
Uyanik et al. How Realistic Are Coal Phase-Out Timeline Targets for Turkey?
Ziel Smoothed bernstein online aggregation for day-ahead electricity demand forecasting
Sun et al. Machine learning derived dynamic operating reserve requirements in high-renewable power systems
WO2021079507A1 (en) Data expansion device, method, and program
Lakshmi et al. Comparative Study on Forecasting of Schedule Generation in Delhi Region for the Resilient Power Grid Using Machine Learning

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: 21900280

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: 21900280

Country of ref document: EP

Kind code of ref document: A1