WO2011114752A1 - 発電量予測装置とその方法及びプログラム - Google Patents
発電量予測装置とその方法及びプログラム Download PDFInfo
- Publication number
- WO2011114752A1 WO2011114752A1 PCT/JP2011/001648 JP2011001648W WO2011114752A1 WO 2011114752 A1 WO2011114752 A1 WO 2011114752A1 JP 2011001648 W JP2011001648 W JP 2011001648W WO 2011114752 A1 WO2011114752 A1 WO 2011114752A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- power generation
- generation amount
- data
- past
- prediction
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2260/00—Function
- F05B2260/82—Forecasts
- F05B2260/821—Parameter estimation or prediction
-
- 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
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/76—Power conversion electric or electronic aspects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
- Y04S40/20—Information technology specific aspects, e.g. CAD, simulation, modelling, system security
Definitions
- Embodiments of the present invention relate to a power generation amount prediction apparatus, a method and a program for predicting a power generation amount of a generator using natural energy such as wind power generation and solar power generation.
- the power system becomes unstable, for example, the frequency fluctuates from a predetermined value. For this reason, when power generation using natural energy is introduced, special care is required in managing the power system.
- FIG. 16 shows the wind speed at a certain point in Tokyo every hour in August of a certain year.
- FIG. 17 shows the wind direction at the same point every hour. In displaying the wind direction of FIG. 17, the direction is quantified as shown in FIG.
- the amount of power generated by photovoltaic power generation can be almost predicted if the location, the generator installation method, and the amount of solar radiation are determined.
- FIG. 19 shows the amount of solar radiation at a certain point in Tokyo in December of a certain year.
- FIG. 19 also shows that the amount of solar radiation is not random at all, and there are many data close to a certain curve, and there is a characteristic that the amount of solar radiation in the afternoon is small when the amount of solar radiation in the morning is small.
- Both wind and solar power generators are affected by weather conditions, so the power generation of the generators in the same place is similar, but the power generation of the generators in the distance shows a completely different pattern . If it is about several kilometers, the weather conditions are considered to be similar, and thus the power generation pattern should be similar. This is called position correlation. Even if these generators are installed in adjacent locations, the wind speed and the amount of solar radiation are not exactly the same, so it is necessary to consider positional correlation.
- the present invention has been proposed in order to solve the above-described problems of the prior art, and the object of the present invention is to provide a statistical correlation even in the case of a generator whose power generation amount fluctuates uncertainly.
- it is an object to provide a power generation amount prediction apparatus capable of predicting a power generation amount, a method thereof, and a program thereof.
- the power generation amount prediction device for obtaining a predicted value related to the power generation amount of one or more generators whose power generation amount fluctuates uncertainly, the following past data It has a memory
- the predicted value calculation unit calculates a predicted value of the past data related to the power generation amount of the generator based on a statistical correlation between different times in the past data or a statistical correlation between different generator positions. Is calculated as time series data.
- it can also be grasped as a method and a program for realizing the functions of the above-described units by a computer.
- the block diagram which shows one Embodiment of an electric power generation amount prediction apparatus
- a flowchart showing processing for predicting the amount of wind power generation based on wind speed / wind direction data.
- Explanatory drawing which shows an example of the power generation amount data of the past similar day of photovoltaic power generation
- Explanatory drawing which shows an example which overwritten the power generation amount data of FIG.
- Explanatory drawing which shows the simulation result of the electric power generation amount predicted value of photovoltaic power generation based on the electric power generation amount data of FIG.
- Explanatory drawing which shows an example of the correlation coefficient matrix of FIG.
- Explanatory drawing which shows the sum total of the electric power generation amount of FIG.11 (b) and FIG.11 (c)
- Conceptual diagram showing an example of a conventional prediction model Conceptual diagram showing an example in which the embodiment of FIG. 1 is applied to a conventional prediction model
- Explanatory drawing showing an example of August wind speed data for Tokyo in a certain year
- Explanatory diagram showing an example of wind direction data for August in Tokyo in a certain year
- Explanatory drawing showing an example of conversion table of wind direction data Explanatory diagram showing an example of the amount of sunshine in December of Tokyo in a certain year
- the power generation amount prediction apparatus 1 of the present embodiment can be realized by controlling a general-purpose computer such as a personal computer or a server apparatus with a predetermined program.
- the program in this case realizes the processing of each unit as described below by physically utilizing the hardware of the computer, and the method for performing such processing, the program, and the recording medium on which the program is recorded are independent.
- it is one embodiment of the present invention.
- the power generation amount prediction device 1 includes a prediction processing unit 10, a storage unit 20, an input unit 30, an output unit 40, and the like.
- the prediction processing unit 10 includes a similar date selection unit 11, a time series data generation unit 12, a predicted value calculation unit 13, a power generation amount total unit 14, and the like that function by the function of the program as described above.
- the similar date selection unit 11 determines the forecast target date based on the weather forecast data of the forecast target date and the past data (wind speed / wind direction data, meteorological data such as solar radiation data, and power generation amount data of each generator). It is a processing part which selects the day similar to.
- the time series data generation unit 12 is a processing unit that extracts data on each selected similar date in time series.
- the predicted value calculation unit 13 is a processing unit that calculates a predicted value of the power generation amount of each generator.
- the power generation amount totaling unit 14 is a processing unit that calculates a predicted value of the total power generation amount based on the predicted value of the power generation amount of each generator.
- the predicted value calculation unit 13 includes a variance-covariance matrix creation unit 131, a random number generation unit 132, and a power generation amount calculation unit 133.
- the variance-covariance matrix creation unit 131 is a processing unit that creates a variance-covariance matrix based on the extracted time-series data.
- the random number generation unit 132 is a processing unit that generates a predicted value (wind speed / wind direction data, power generation amount data, solar radiation amount data, etc.) by generating random numbers according to a probability distribution based on the created variance-covariance matrix. is there.
- the power generation amount calculation unit 133 is a processing unit that calculates a predicted value of the power generation amount of each generator based on a predicted value (wind speed / wind direction data, solar radiation amount data, etc.).
- the storage unit 20 is a configuration unit that stores various types of information such as data necessary for processing in the prediction processing unit 10 and calculated prediction values. These pieces of information are input from the following input unit 30 or input from the outside via a communication network and stored.
- the storage unit 20 can be configured by various built-in or externally connected memories, a hard disk, an optical disk, or the like, but any storage medium that can be used at present or in the future can be used.
- the input unit 30 is a configuration unit that inputs information necessary for the power generation amount prediction processing device 1 and inputs processing selections and instructions.
- this input unit 30 for example, a keyboard, a mouse, a touch panel (including one configured in a display device), and the like are conceivable. However, all input devices available now or in the future are included. Therefore, a voice input device for inputting by voice is also included. Also, a simple switch or the like may be used.
- the output unit 40 is a means for outputting various data, calculated predicted values, etc. so that a user including an administrator, an operator, etc. can recognize the data.
- Examples of the output unit 40 include a display device and a printer. However, any output device available now or in the future is included. Therefore, a voice output device that outputs by voice is also included.
- weather data or power generation amount data is modeled using a multidimensional normal distribution, and a plurality of random numbers according to the multidimensional normal distribution are generated using a variance-covariance matrix.
- the predicted value is calculated by generating a set of time series data.
- FIG. 2 is a flowchart showing a procedure and data flow for predicting wind speed / wind direction data and calculating a predicted power generation amount from the predicted wind speed / wind direction data.
- the similar date selection unit 11 selects a date on which the prediction target date and the weather data are similar based on the weather prediction data on the prediction target date and the past weather data (D1-1) at the position of each generator.
- Select N days (N is an arbitrary integer greater than or equal to 2) (step 101).
- a method for selecting a day in which the corresponding day and weather data are similar from past data is not limited to a specific one.
- a simple method of selecting a day on which certain information in the weather data matches such as a day when the morning is clear and the afternoon is cloudy can be considered.
- a method of selecting a day that approximates certain numerical information in weather data such as a clear sky index and a cloud amount can be used.
- the time series data generation unit 12 uses the similar date as the time series data (D1-2) at the time K of the generators for M units (M is an arbitrary integer equal to or greater than 1) on the selected N days of similar days.
- Two types of data sets (time point K, N days, M units) of wind speed and direction are generated from the wind speed / wind direction data included in the weather data (D1-1) (step 102).
- the variance-covariance matrix creation unit 131 creates a variance-covariance matrix of (2 ⁇ K ⁇ M) rows (2 ⁇ K ⁇ M) columns from these time series data (D1-2) (step 103).
- the random number generator 132 generates (2 ⁇ K ⁇ M) random number sets (L is an arbitrary integer equal to or greater than 2) using the variance-covariance matrix, thereby generating each wind power generation.
- Two types of predicted values (D1-3) of wind direction and wind speed at the position of the machine are created as L sets of data (K time, M units, L ways) (step 104). The details of the process for creating the variance-covariance matrix and the random number generation process will be described later.
- the power generation amount calculation unit 133 uses the wind speed and wind direction prediction values (D1-3) to generate L sets (K points, M units) of the power generation amount prediction values (D1-4) of the generators at the time K. Generate (step 105).
- the L sets of data are data having the same time correlation and position correlation as the original N days of data, and correspond to the prediction result of the power generation amount. Therefore, the power generation amount totaling unit 14 adds up the predicted power generation amount values (D1-4) of the respective generators to obtain the predicted power generation amount value (D1-5) of the entire power generation (step 106).
- the similar date selection unit 11 uses the same method as the above-described similar day (for example, the same method as the above-mentioned similar date) based on the weather forecast data of the prediction target date and the past weather data (D1-1). ) Is selected for N days (step 201).
- the time series data generation unit 12 generates each generator from the power generation amount data (D2-1) of the selected N days of similar days as time series data (D2-2) of the selected N days of similar days.
- a set of power generation amount data (time point K, N days, M units) is extracted (step 202).
- the variance-covariance matrix creation unit 131 statistically analyzes the time series data (D2-2) and creates a variance-covariance matrix (step 203).
- the random number generation unit 132 generates L sets of random numbers using the variance-covariance matrix, thereby obtaining a predicted value (D2-3) of the power generation amount of each generator (step 204). Further, the power generation amount totaling unit 14 obtains the predicted value (D2-4) of the total power generation amount by summing the predicted values (D2-3) of the power generation amount of the respective generators (step 205).
- FIG. 3 shows a case of a wind power generator, the same applies to a case of a solar power generator.
- data ⁇ xi ⁇ obtained by collecting power generation amount data for each time from a plurality of days is stored in the storage unit 20 in advance.
- the similar date selection unit 11 selects a similar date by using, for example, a classification algorithm.
- the time series data generation unit 12 decomposes the power generation amount on the selected similar day into the power generation amount xi at time i every hour, and creates time series data which is a vector in which the power generation amounts are arranged from x1 to x24.
- the variance-covariance matrix creation unit 131 creates a variance-covariance matrix having 24 ⁇ 24 components such as [Equation 1] in order to consider the relationship between the power generation amounts between times.
- var (xi) is the variance of ⁇ xi ⁇
- cov (xi, xj) is the covariance of ⁇ xi ⁇ and ⁇ xj ⁇ .
- at least two days or more are required for obtaining power generation amount data.
- the number of days for acquiring the power generation amount data may be two days, but the prediction accuracy increases as the number of days increases.
- the random number generation unit 132 generates a large number of 24-dimensional random numbers based on the variance-covariance matrix and creates the predicted value 24 of the power generation amount.
- Power generation data for one day can be regarded as a 24-dimensional vector x.
- this is called a power generation scenario.
- An arbitrary number of power generation scenarios can be created by generating a large number of sets of 24 random numbers according to the probability distribution of [Equation 2]. This power generation scenario reproduces the statistical nature of past power generation data.
- the fluctuation range at each time is reproduced by the variance of each time, and the correlation between the times is also reproduced by the covariance.
- the past power generation amount data is only for two days, for example, one million power generation amount scenarios can be created.
- the distribution of past data is obtained for each time, and L random numbers are generated according to the distribution.
- An example of the simplest method of generating random numbers according to a specific distribution is by the rejection method. This is a method of generating a uniform random number in an area defined by a domain and a range of a distribution function, and rejecting those that exceed the value of the distribution function.
- This method can be used for any distribution function, but it is not always efficient. In addition, it is difficult to apply even when the definition area is not a finite area. If an inverse function of a specific distribution exists, a random number according to the specific distribution can be easily created from a uniform random number. This is repeated at each time of 24 hours.
- L random numbers are created for 24 hours.
- the set of random numbers at each time has no correlation with the set of random numbers at other times and is independent of each other.
- random numbers generated by ordinary algorithms are pseudo-random numbers, and even if they intend to create independent random numbers, they may actually be correlated. Therefore, it is converted into a set of independent random numbers by principal component analysis as necessary.
- the correlation coefficient matrix is obtained by normalizing the variance-covariance matrix ⁇ .
- the standard deviation matrix S of 24 rows by 24 columns (24 ⁇ 24) in which the standard deviation at each time is placed on a diagonal line and the other components are 0 is multiplied from the right, and the average vector ⁇ is arranged in L rows.
- An average matrix A having 24 rows (L ⁇ 24) is added.
- G ′′ having a mean, variance, and correlation finally obtained is obtained.
- G ′′ G ′S + A This matrix G ′′ is the prediction result itself, and each N row vector (1 row, 24 columns) of G ′′ corresponds to each prediction result.
- FIG. 5 shows the data of FIG. 4 overwritten.
- FIG. 6 shows a power generation amount scenario generated by the method of this embodiment.
- the number of predictions need not be limited to 50.
- FIG. 7 shows a correlation coefficient matrix in this example. This is a standardized variance covariance matrix.
- FIG. 8 shows an example in which the wind speed and the wind direction are predicted in order to predict the power generation amount of wind power generation.
- (a) is an example of past wind speed data
- (b) is an example of corresponding wind direction data.
- the wind direction is quantified.
- the corresponding data is formally arranged to create time series data. Since there are 24 points of data for both wind speed and direction, this wind force data is a time series consisting of 48 time points. In FIG. 8C, five such time series are superimposed and plotted.
- the variance of data at each time point and the covariance between different time points can be calculated to create a 48 ⁇ 48 variance covariance matrix.
- An arbitrary number of time series having a length of 48 time points can be generated by generating random numbers according to a 48-dimensional normal distribution using the variance-covariance matrix.
- FIG. 9A shows time series data generated in this way.
- Each one of this time series has information on both the wind speed and direction, has the same variance as the original data at each time point, and the covariance between the time points reproduces the information of the original data. Yes. That is, for example, the prediction result takes into account the correlation between the wind speed at 13:00 and the wind direction at 18:00.
- FIG. 9B and FIG. 9C are plots of the wind speed and direction at each time by separating the time series of FIG. 9A at the center.
- FIG. 10 is a plot of power generation at two solar power plants.
- the sunlight data 1 in FIG. 10 (a) and the sunlight data 2 in FIG. 10 (b) are data measured at the time 24 times a day in the past, and 10 days are overwritten. Each of these data has a correlation.
- FIG. 10 (c) shows the data of the same day connected formally and plotted as time series data of 48 time points.
- FIG. 11 shows time series data generated by creating a 48-by-48 distributed covariance matrix from the data shown in FIG. 10C in the same manner as described above, generating random numbers, and generating random numbers.
- FIG. 11A shows the calculation result, and 50 time series are displayed. What separated this is FIG.11 (b) and FIG.11 (c), and has shown the predicted value of the electric power generation amount of the photovoltaic power plant 1 and the photovoltaic power plant 2, respectively.
- FIG. 12 (a) shows the frequency distribution of the power generation output at 12:00 in the photovoltaic power generation 1 of FIG. 11 (b).
- the frequency is calculated based on 1000 pieces of time series data.
- FIG. 12B shows the probability density distribution. Expected values and occurrence probabilities of prediction results can be calculated from this probability density distribution.
- the power generation output can be predicted to be between 4 kW and 4.9 kW with a probability of 95%.
- FIGS. 12C and 12D show the frequency distribution and probability density distribution of the output at 15:00 in the solar power plant 2 of FIG. 11C.
- the fluctuation of the power generation amount in FIG. 11 (b) and the power generation amount in FIG. 11 (c) are not independent, and when the R-th time-series data is realized in the solar power plant 1, the R in the solar power plant 2 is also R. It means that the second time series data is realized. Therefore, it is easy to obtain the total power generation amount of the solar power plant 1 and the solar power plant 2, and the sum may be calculated for each time with the corresponding time series data.
- FIG. 13 shows the total amount of power generated by the two solar power plants described above. From this figure, you can see how much the total power generation changes. This fluctuation amount cannot be obtained simply by adding the prediction errors of the power generation amount in the conventional prediction model.
- This variation is a variation that is actually given to the system, and is a variation that should be taken into account in supply and demand control and load frequency control.
- the frequency fluctuation range is proportional to the fluctuation range of the power generation amount by natural energy if the power generation amount of the load and other generators is constant.
- the proportionality constant at this time is a load frequency constant. Therefore, the frequency calculation unit provided in the prediction processing unit 10 in FIG. 1 divides the fluctuation range in FIG. 13 by the total power generation amount of the system and multiplies the inverse of the load frequency constant to obtain the frequency fluctuation rate. Can do.
- the number of solar power generators is two in the example of FIG. 13, a similar method can be used when the number of power generators is large.
- the predicted value is calculated with respect to the past data related to the power generation amount in consideration of the statistical correlation between different times, so the power generation amount of a specific generator can be accurately predicted. can do.
- the predicted value is calculated in consideration of the statistical correlation between the positions of different generators, the power generation amount of the plurality of generators can be predicted with high accuracy. That is, considering the statistical correlation of power generation between different times in weather data and power generation data, or the statistical correlation of power generation at the same time of power generation of generators with different positions, The quantity can be predicted as a set of a plurality of time series data to which the occurrence probability is given. Therefore, even in a power plant or power system having a generator whose power generation amount fluctuates uncertainly, the power generation amount can be accurately predicted by using a statistical probability method.
- the power generation amount of a large number of generators is predicted at the same time, it is possible to make a prediction in consideration of time correlation and position correlation. Furthermore, when there are a plurality of generators and power generation plants, it is possible to predict the total power generation amount by summing those power generation amounts (or in a specific group unit). Furthermore, the fluctuation amount of the power generation amount of the system can be evaluated from the prediction result of the total power generation amount of many generators, and the frequency fluctuation of the system can be evaluated.
- the power generation amount when predicting the power generation amount of wind power generation, the power generation amount can be evaluated by predicting the wind direction and speed, or the power generation amount can be predicted directly.
- the power generation amount of solar power generation it can be used to predict the amount of sunlight, but the power generation amount can also be predicted directly. For this reason, it is also possible to obtain a predicted value of wind direction and wind speed and a predicted value of solar radiation amount in the process of power generation amount prediction.
- a series of events that occur simultaneously in the world can be considered as a scenario.
- the solar power generation scenario, the wind power generation scenario, and the load scenario that belong to the same scenario are scenarios that are highly likely to occur at the same time, and from these, it is possible to evaluate the amount of power generation that needs to be generated at a normal power plant. Along with this, the necessary cost, the amount of fuel, etc. can be evaluated including fluctuations. Therefore, the expected cost value can be evaluated from these.
- the present invention is not limited to the embodiment as described above.
- the specific contents and values of various information used in the present invention are free, and are not limited to specific contents and numerical values.
- “Predicted value relating to power generation amount” and “past data relating to power generation amount” in the present specification are broad concepts including various types of information relating to power generation amount, such as weather data, power generation amount data, and error data (described later).
- random numbers according to a multidimensional normal distribution are used.
- the probability distribution need not be limited to the normal distribution.
- weather data or power generation data is modeled using the distribution as described above, and a large number of random numbers according to the distribution are generated using the variance-covariance matrix, thereby providing a plurality of time series to which occurrence probabilities are given.
- generating a data set is also contained in this invention.
- FIG. 14 is a conceptual diagram showing a conventional prediction model. Many models for predicting the future, not limited to photovoltaic power generation, have been proposed. All of these predict future values from information obtained to date.
- various models such as regression models and neural networks are used.
- the relationship between past weather information and the amount of power generation is usually modeled.
- past actual values actual weather data, power generation amount data, etc.
- normally past predicted values predicted values such as weather data, power generation amount data, etc.
- error bars, standard deviations, and the like are used to evaluate future predicted value errors and fluctuations.
- FIG. 15 is an example of a model in which the method of the above embodiment is applied to a conventional prediction method.
- a conventional prediction method typically only the past predicted value and the past actual value are used.
- some kind of prediction model A has been used in the past, but any method may be used in the present invention for the method of this prediction model (prediction in the above embodiment). Model).
- the past error data can be obtained from the difference between the past actual value and the past predicted value.
- This error data can be calculated by, for example, an error data calculation unit provided in the prediction processing unit 10.
- error data input from the outside via the input unit 30 or the communication network and stored in the storage unit 20 can be used.
- the error data is generated by the time series data generation unit 12 as a set of time series of error data.
- a time series set of error data is obtained for the number of days, weeks, or months in which data is calculated at regular intervals such as the past day, week, or month. It is assumed that there are K time series sets of error data (K ⁇ 2).
- the predicted value in the future is predicted by any of the above-described prediction models A.
- the error of the future prediction result is evaluated using the time series set of the error data. can do. That is, the variance-covariance matrix creation unit 131 creates a variance-covariance matrix from a set of K error data time series by the above-described method, and the random number generation unit 132 corresponds to a predicted value of the error data. L sets are generated. This is a predicted value of an error expected when a specific prediction model A is used.
- the correction unit provided in the prediction processing unit 10 performs correction by adding this time series to the prediction result of the specific prediction model A, a prediction result with a high probability of realization can be obtained.
- the specific prediction model A has a strong tendency to produce a prediction result that is smaller than the actual value, there is a tendency that the error time-series data also becomes negative.
- the time series data of the prediction results reflect such characteristics.
- any specific prediction model may be used. Although it is desirable that the accuracy of the prediction model is high, the accuracy is improved by using the prediction value of the error data as described above even if the accuracy of the prediction model is poor. Prediction models generally have poor accuracy over time, but using the prediction value of error data as described above also has the advantage that the same prediction model can be used for a long time.
- time series data that is the subject of the present invention is not limited to solar power generation and wind power generation. Geothermal power generation, wave power generation, tidal power generation, and other natural energy generation, as well as demand data for a specific region can be predicted. Of course, these error time series may be used. Furthermore, even when it is difficult to predict from meteorological data such as tidal power generation, the fluctuation amount of the power generation amount can be predicted only from the past actual power generation amount data.
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
Description
[1.実施形態の構成]
まず、本実施形態の構成を説明する。すなわち、図1に示すように、本実施形態の発電量予測装置1は、パーソナルコンピュータやサーバ装置のような汎用のコンピュータを、所定のプログラムで制御することによって実現できる。この場合のプログラムは、コンピュータのハードウェアを物理的に活用することで、以下に述べるような各部の処理を実現するものであり、かかる処理を行う方法、プログラム及びプログラムを記録した記録媒体は単独でも本発明の一態様である。
[2-1.処理の概要]
本実施形態は、気象データ若しくは発電量データを、多次元正規分布を用いてモデル化し、分散共分散行列を用いて多次元正規分布に従う乱数を多数発生させることで、発生確率が付与された複数の時系列データの組を生成することにより、予測値を算出するものである。
次に、本実施形態の作用を説明する。まず、風速・風向データに基づいて、風力発電の発電機の発電量を予測する一例を、図2を参照して説明する。なお、図2は、風速・風向データを予測し、予測した風速・風向データから、発電量の予測値を計算する手順とデータの流れを示すフローチャートである。
本実施形態では、風向・風速データの代わりに、日射量データを用いて、太陽光発電の発電機の発電量を予測することもできる。その手順は、基本的には、上記と同様である。すなわち、気象予報データと過去の気象データに基づく類似日の選択、選択された類似日の気象データに含まれる日射量データに基づく日射量の時系列データの生成、分散共分散行列の作成、乱数の発生が行われる。
さらに、上記の例では、風向・風速の予測値や日射量の予測値を、発電量の予測値へ変換(発電量計算部133による発電量の予測値の計算)する処理が行われていた。しかし、このような変換処理は、必ずしも必要ではない。すなわち、本実施形態においては、過去の発電量データに基づいて、発電量の予測値を求めることもできる。
次に、分散共分散行列の作成と乱数の発生の手法を、太陽光発電機の発電量の予測を一例として説明する。ここでは、K時点を、1時間ごとの24点とし、1台の発電機(M=1)の発電量を、時刻相関を考慮して予測する手法を例にとって説明する。
R=TUTL
その後、正規乱数行列Gに上三角行列TUを右から掛けることで、相関を持った正規乱数行列が作成できる。
G’=GTU
G”=G’S+A
この行列G”が予測結果そのものであり、G”のN個の各行ベクトル(1行24列)が、各予測結果に相当する。
次に、本実施形態による予測処理を、具体的な事例に適用した結果について説明する。
[3-1.太陽光発電の発電量予測]
図4は、過去の太陽光発電の発電量をプロットした例である。この場合、2時間ごと、7日分のデータが示されている。すなわち、K=12、N=7である。ここでは、類似日選択処理により、すでに同様な気象条件の日が選択されているものとする。同じ気象条件でも、わずかな気温の違いや雲の量の違いから発電量が変動する場合がある。図5は、図4のデータを重ね書きしたものである。
図8は、風力発電の発電量を予測するために、風速と風向を予測する場合の例である。図8において、(a)は過去の風速データの例であり、(b)は対応する風向データの例である。ここでは、図17と同様に、風向が数値化されている。
次に、自然エネルギーによる発電機が複数ある場合の予測処理を、太陽光発電を一例として説明する。複数の太陽光発電機の発電量が、互いに相関がない場合、これらの発電量を独立に予測することができる。しかし、複数の太陽光発電機の発電量は気象データを通じて相互に相関があるのが普通である。複数の太陽光発電機の発電量を合計すると変動が小さくなることが知られている。この場合、相関が小さければ変動が平滑化される可能性が高いが、正の相関が強ければ変動は平滑化されない。
以上のような本実施形態によれば、発電量に関する過去データについて、異なる時刻の間の統計的相関を考慮して、予測値を算出するので、特定の発電機の発電量を、精度よく予測することができる。また、異なる発電機の位置の間の統計的相関を考慮して、予測値を算出するので、複数台の発電機の発電量を、精度よく予測することができる。すなわち、気象データや発電量データの異なる時刻の間の発電量の統計的相関、あるいは位置が異なる発電機の発電量の同時刻の発電量の統計的相関を考慮して、各発電機の発電量を発生確率が付与された複数の時系列データの組として予測することができる。したがって、発電量が不確実に変動する発電機を持つ発電プラントや電力系統であっても、統計確率的な手法を用いることにより、発電量を正確に予測することができる。
本発明は、上記のような実施形態に限定されるものではない。例えば、本発明で用いられる各種の情報の具体的な内容、値は自由であり、特定の内容、数値には限定されない。本明細書中の「発電量に関する予測値」、「発電量に関する過去データ」は、気象データ、発電量データ、誤差データ(後述)等、発電量に関する各種の情報を含む広い概念である。
Claims (10)
- 発電量が不確実に変動する1台以上の発電機の発電量に関する予測値を求める発電量予測装置において、
少なくとも一つの発電機の過去の発電量に関する過去データとして、各日の複数時点の情報を含む過去データを記憶する過去データ記憶部と、
前記過去データにおける異なる時刻の間の統計的相関若しくは異なる発電機の位置の間の統計的相関に基づいて、発電機の発電量に関する当該過去データの予測値を、発生確率を含む時系列データとして算出する予測値算出部と、
を有することを特徴とする発電量予測装置。 - 前記過去データは、発電量データであることを特徴とする請求項1記載の発電量予測装置。
- 前記過去データは、発電量に影響を与える気象データであり、
前記予測値算出部は、気象データの予測値を、発電量に換算する発電量計算部を有することを特徴とする請求項1記載の発電量予測装置。 - 前記予測値算出部は、
前記過去データに基づいて、分散共分散行列を作成する分散共分散行列作成部と、
前記分散共分散行列に基づいて、確率分布に従う乱数を発生させる乱数発生部と、
を有することを特徴とする請求項1記載の発電量予測装置。 - 複数の発電機における発電量の予測値に基づいて、複数を合計した発電量の予測値を算出する発電量合計部を有することを特徴とする請求項1記載の発電量予測装置。
- 前記合計した発電量の予測値に基づいて、周波数の変動率を演算する周波数演算部を有することを特徴とする請求項5記載の発電量予測装置。
- 前記予測値算出部は、前記過去データとして記憶された過去の実績値とそれから得られる過去の誤差付き予測値との誤差を、当該過去データの誤差データの予測値として算出するように構成されたことを特徴とする請求項1記載の発電量予測装置。
- 前記過去の誤差付き予測値として得られる気象データの誤差付き予測値若しくは発電量データの誤差付き予測値を、前記誤差データの予測値によって補正する補正部を有することを特徴とする請求項7記載の発電量予測装置。
- コンピュータにより発電量が不確実に変動する1台以上の発電機の発電量を予測する発電量予測方法において、
前記コンピュータは、過去データ記憶部と予測値算出部とを有し、
前記過去データ記憶部が、少なくとも一つの発電機の過去の発電量に関する過去データとして、各日の複数時点の情報を含む過去データを記憶する処理と、
前記予測値算出部が、前記過去データにおける異なる時刻の間の統計的相関若しくは異なる発電機の位置の間の統計的相関に基づいて、発電機の発電量に関する当該過去データの予測値を、発生確率を含む時系列データとして算出する処理と、
を実行することを特徴とする発電量予測方法。 - コンピュータにより実行されることにより、発電量が不確実に変動する1台以上の発電機の発電量を予測する発電量予測プログラムにおいて、
前記コンピュータに、
少なくとも一つの発電機の過去の発電量に関する過去データとして、各日の複数時点の情報を含む過去データを記憶する処理と、
前記過去データにおける異なる時刻の間の統計的相関若しくは異なる発電機の位置の間の統計的相関に基づいて、発電機の発電量に関する当該過去データの予測値を、発生確率を含む時系列データとして算出する処理と、
を実行させることを特徴とする発電量予測プログラム。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP11755942.7A EP2549641A4 (en) | 2010-03-19 | 2011-03-18 | DEVICE FOR FORECASTING THE AMOUNT OF A GENERATED CURRENT, METHOD THEREFOR AND PROGRAM THEREFOR |
US13/583,792 US20130013233A1 (en) | 2010-03-19 | 2011-03-18 | Electric-power-generation level predicting apparatus, method and program |
CN201180013084.7A CN102792542B (zh) | 2010-03-19 | 2011-03-18 | 发电量预测装置和其方法及程序 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2010065083A JP5606114B2 (ja) | 2010-03-19 | 2010-03-19 | 発電量予測装置、予測方法及び予測プログラム |
JP2010-065083 | 2010-03-19 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2011114752A1 true WO2011114752A1 (ja) | 2011-09-22 |
Family
ID=44648862
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2011/001648 WO2011114752A1 (ja) | 2010-03-19 | 2011-03-18 | 発電量予測装置とその方法及びプログラム |
Country Status (7)
Country | Link |
---|---|
US (1) | US20130013233A1 (ja) |
EP (1) | EP2549641A4 (ja) |
JP (1) | JP5606114B2 (ja) |
CN (1) | CN102792542B (ja) |
MY (1) | MY156889A (ja) |
TW (1) | TWI533251B (ja) |
WO (1) | WO2011114752A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210222948A1 (en) * | 2020-01-22 | 2021-07-22 | L'air Liquide, Societe Anonyme Pour L'etude Et L?Exploitation Des Procedes Georges Claude | Liquefaction apparatus |
EP4131698A1 (en) * | 2021-08-04 | 2023-02-08 | Toyota Jidosha Kabushiki Kaisha | Power management system, power management server, and power management method |
Families Citing this family (54)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5505191B2 (ja) * | 2010-08-16 | 2014-05-28 | 東京電力株式会社 | 太陽光発電量予測方法および配電系統制御システム |
JP5661594B2 (ja) * | 2011-11-01 | 2015-01-28 | 日本電信電話株式会社 | 予測モデル構築装置、方法、及びプログラム、並びに発電量予測装置、及び方法 |
JP6178045B2 (ja) | 2012-04-16 | 2017-08-09 | 株式会社東芝 | エネルギー管理システム、エネルギー管理方法、プログラムおよびサーバ装置 |
JP5797599B2 (ja) * | 2012-04-19 | 2015-10-21 | 株式会社日立パワーソリューションズ | 発電量予測方法及びそのシステム |
TWI509942B (zh) * | 2012-06-21 | 2015-11-21 | Au Optronics Corp | 多電源供電系統之電力管理方法 |
JP5940922B2 (ja) * | 2012-07-12 | 2016-06-29 | トヨタ自動車株式会社 | 自然エネルギー量予測装置 |
JP2014054048A (ja) * | 2012-09-06 | 2014-03-20 | Toshiba Corp | 電力予測方法、装置、及びプログラム |
JP6054122B2 (ja) | 2012-09-28 | 2016-12-27 | 株式会社東芝 | 鉄道電力管理装置 |
JP5946742B2 (ja) * | 2012-10-16 | 2016-07-06 | 一般財団法人電力中央研究所 | 自然エネルギー型分散電源群の合計出力の変動推定方法、変動推定装置及び変動推定プログラム |
TWI492158B (zh) * | 2012-11-15 | 2015-07-11 | Inventec Corp | 負載預測方法與電子裝置 |
JP6009976B2 (ja) | 2013-03-07 | 2016-10-19 | 株式会社東芝 | エネルギー管理システム、エネルギー管理方法、プログラムおよびサーバ |
JP2014217092A (ja) * | 2013-04-22 | 2014-11-17 | 清水建設株式会社 | 発電電力予測装置、発電電力予測方法及びプログラム |
US20150100386A1 (en) * | 2013-10-04 | 2015-04-09 | International Business Machines Corporation | Digital framework for business model innovation |
KR101575071B1 (ko) | 2013-12-02 | 2015-12-07 | 두산중공업 주식회사 | 풍력 발전 단지의 발전량 제어 방법 |
JP6181589B2 (ja) * | 2014-03-31 | 2017-08-16 | 株式会社Ihi | 計測値解析装置及び計測値解析方法 |
KR101585961B1 (ko) | 2014-04-23 | 2016-02-02 | 전자부품연구원 | 풍력-파력 복합 발전에서의 상태 감시 및 예측 시스템 |
JP6303909B2 (ja) * | 2014-08-11 | 2018-04-04 | 富士通株式会社 | 計画策定方法、計画策定システム及び計画策定プログラム |
JP2016053925A (ja) * | 2014-09-04 | 2016-04-14 | 株式会社東芝 | 電力市場価格予測装置、電力市場価格予測方法およびプログラム |
JP6400403B2 (ja) * | 2014-09-12 | 2018-10-03 | 株式会社東芝 | 契約電力選択装置、契約電力選択方法、及び、契約電力選択プログラム |
JP5937167B2 (ja) * | 2014-10-01 | 2016-06-22 | 中国電力株式会社 | 需要予測装置、需要予測方法、及びプログラム |
JP5989732B2 (ja) * | 2014-10-01 | 2016-09-07 | 中国電力株式会社 | 発電量予測装置、発電量予測方法、及びプログラム |
JP6543028B2 (ja) * | 2014-11-05 | 2019-07-10 | 東芝エネルギーシステムズ株式会社 | 異常診断装置及び異常診断方法 |
JP6582418B2 (ja) * | 2015-01-23 | 2019-10-02 | 中国電力株式会社 | 発電量予測装置、発電量予測方法、及びプログラム |
JPWO2016121202A1 (ja) * | 2015-01-30 | 2017-11-09 | 日本電気株式会社 | 予測装置、予測方法、及び、プログラム |
JP6847343B2 (ja) * | 2015-02-23 | 2021-03-24 | 学校法人沖縄科学技術大学院大学学園 | 再生可能エネルギーの変動に対する予測誤差を決定するシステムおよび方法 |
JP6600516B2 (ja) * | 2015-09-14 | 2019-10-30 | 株式会社東芝 | アグリゲーション管理装置及び方法 |
US9773303B2 (en) * | 2015-11-04 | 2017-09-26 | Institute of Nuclear Energy Research, Atomic Energy Council, Executive Yuan, R.O.C. | Prediction system for short-term solar irradiance and method for operating the same |
TWI642019B (zh) * | 2015-11-17 | 2018-11-21 | 財團法人資訊工業策進會 | 發電系統效能估測方法 |
JP6427090B2 (ja) * | 2015-12-07 | 2018-11-21 | 株式会社日立製作所 | 発電量予測装置、発電量予測方法、系統安定化装置、並びに系統安定化方法 |
CN105515042A (zh) * | 2015-12-08 | 2016-04-20 | 上海电力设计院有限公司 | 风光同场项目光伏接入容量优化算法 |
US10509868B2 (en) * | 2016-01-29 | 2019-12-17 | Fujitsu Limited | Operating a solar power generating system |
US10714968B2 (en) * | 2016-03-08 | 2020-07-14 | Nec Corporation | Power control apparatus, power control system, and power control method |
US10824119B2 (en) * | 2016-03-29 | 2020-11-03 | International Business Machines Corporation | Intelligent energy switch |
JP6742894B2 (ja) | 2016-06-09 | 2020-08-19 | 株式会社日立製作所 | データ予測システムおよびデータ予測方法 |
WO2017212880A1 (ja) * | 2016-06-09 | 2017-12-14 | 株式会社日立製作所 | データ予測システムおよびデータ予測方法 |
JP6725406B2 (ja) * | 2016-12-12 | 2020-07-15 | 株式会社東芝 | 発電計画策定装置、発電計画策定方法、および発電計画策定プログラム |
US10418822B2 (en) * | 2017-02-14 | 2019-09-17 | Mitsubishi Electric Research Laboratories, Inc. | Energy production and frequency regulation Co-optimization for power generation systems |
TWI623890B (zh) * | 2017-07-04 | 2018-05-11 | 台灣電力股份有限公司 | 由多個類神經網路組成的發電量預測系統與其方法 |
KR102395474B1 (ko) | 2017-08-24 | 2022-05-09 | 삼성전자주식회사 | 반도체 소자의 특성 예측 방법 및 반도체 소자의 특성 예측 장치 |
TWI632516B (zh) * | 2018-01-11 | 2018-08-11 | 國立臺灣師範大學 | 日射量比對系統與方法 |
CN110676868A (zh) * | 2018-07-02 | 2020-01-10 | 赫普科技发展(北京)有限公司 | 一种风光气互补耦合发电系统及方法 |
CN109165777A (zh) * | 2018-08-10 | 2019-01-08 | 广东电网有限责任公司 | 一种居民用电电量预测方法、装置、设备及存储介质 |
KR102534367B1 (ko) * | 2018-10-08 | 2023-05-22 | 한국전력공사 | 전력 시계열 데이터의 전송처리 시스템 및 방법 |
CN109412200B (zh) * | 2018-10-24 | 2021-12-10 | 安徽科达售电有限公司 | 一种可再生能源发电的接入控制系统 |
CN110008981B (zh) * | 2019-01-11 | 2023-08-08 | 国网浙江省电力有限公司 | 基于矢量模糊矩阵模型的电水气用能替代可引导评价方法 |
CN111985673A (zh) * | 2019-05-22 | 2020-11-24 | 三菱重工业株式会社 | 预测装置、预测系统、预测方法以及记录介质 |
US11261846B2 (en) | 2019-11-01 | 2022-03-01 | General Electric Company | System and method for designing and operating a wind turbine power system based on statistical analysis of operational and/or grid data thereof |
US11636390B2 (en) | 2020-03-19 | 2023-04-25 | International Business Machines Corporation | Generating quantitatively assessed synthetic training data |
JP7443173B2 (ja) | 2020-07-08 | 2024-03-05 | 株式会社東芝 | 電力系統状態推定方法、電力系統状態推定プログラム、電力系統状態推定プログラムを記憶した記憶媒体、及び電力系統状態推定装置 |
CN112186761B (zh) * | 2020-09-30 | 2022-03-01 | 山东大学 | 一种基于概率分布的风电功率场景生成方法及系统 |
FR3135798A1 (fr) * | 2022-05-19 | 2023-11-24 | IFP Energies Nouvelles | Procédé de prévision d’une puissance produite par au moins un panneau photovoltaïque |
CN116123028A (zh) * | 2022-12-20 | 2023-05-16 | 中国华能集团清洁能源技术研究院有限公司 | 风电场级mppt预测模型控制方法和装置 |
KR102642564B1 (ko) * | 2023-06-30 | 2024-02-29 | 식스티헤르츠 주식회사 | 재생 에너지 발전기 이상 진단 방법 및 시스템 |
CN117540859A (zh) * | 2023-11-15 | 2024-02-09 | 深圳南控新能源有限公司 | 一种基于神经网络的光伏电站发电量的预估方法及系统 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007233639A (ja) * | 2006-02-28 | 2007-09-13 | Tohoku Electric Power Co Inc | 風力発電出力予測方法、風力発電出力予測装置およびプログラム |
JP2009138523A (ja) * | 2007-12-03 | 2009-06-25 | Mitsubishi Electric Corp | 風力発電出力予測方法 |
JP2009167848A (ja) * | 2008-01-11 | 2009-07-30 | Chugoku Electric Power Co Inc:The | 風力発電量予測システム、方法及びプログラム |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3142489B2 (ja) * | 1996-08-26 | 2001-03-07 | 沖電気工業株式会社 | 目標運動解析方法及び目標運動解析装置 |
JP4574985B2 (ja) * | 2001-09-28 | 2010-11-04 | 三菱電機株式会社 | 電力供給計画立案支援方法 |
JP3994910B2 (ja) * | 2003-05-08 | 2007-10-24 | 株式会社日立製作所 | 電力売買支援システム |
US6966073B2 (en) * | 2003-12-01 | 2005-11-22 | Timothy Lee | Sock |
US20070035135A1 (en) * | 2004-05-07 | 2007-02-15 | Mitsubishi Denki Kabushiki Kaisha | Wind power generation evaluation system and predictive control service system for use with wind power generator |
JP4245583B2 (ja) * | 2005-04-15 | 2009-03-25 | 日本電信電話株式会社 | 分散型エネルギーシステムの制御装置、制御方法、プログラム、および記録媒体 |
JP2007056686A (ja) * | 2005-08-22 | 2007-03-08 | Univ Of Ryukyus | 風速予測に基づく風力発電機の数時間先発電電力予測装置 |
JP2007120362A (ja) * | 2005-10-26 | 2007-05-17 | Toshiba Corp | 発電電力予測装置 |
US7716100B2 (en) * | 2005-12-02 | 2010-05-11 | Kuberre Systems, Inc. | Methods and systems for computing platform |
JP2007281060A (ja) * | 2006-04-04 | 2007-10-25 | Nippon Telegr & Teleph Corp <Ntt> | 太陽光発電システムの発電予測方法、装置、およびプログラム |
EP2136450A4 (en) * | 2007-03-26 | 2013-06-19 | Vpec Inc | FEEDING SYSTEM |
JP5190311B2 (ja) * | 2008-07-09 | 2013-04-24 | 株式会社東芝 | 取引対象物に関する将来需要の予測シナリオ作成方法およびその作成装置 |
KR101075958B1 (ko) * | 2009-11-16 | 2011-10-21 | 일진전기 주식회사 | 분산전원의 전력 거래 시스템 및 거래 방법 |
-
2010
- 2010-03-19 JP JP2010065083A patent/JP5606114B2/ja active Active
-
2011
- 2011-03-18 US US13/583,792 patent/US20130013233A1/en not_active Abandoned
- 2011-03-18 MY MYPI2012700591A patent/MY156889A/en unknown
- 2011-03-18 EP EP11755942.7A patent/EP2549641A4/en not_active Withdrawn
- 2011-03-18 CN CN201180013084.7A patent/CN102792542B/zh not_active Expired - Fee Related
- 2011-03-18 WO PCT/JP2011/001648 patent/WO2011114752A1/ja active Application Filing
- 2011-03-18 TW TW100109378A patent/TWI533251B/zh not_active IP Right Cessation
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007233639A (ja) * | 2006-02-28 | 2007-09-13 | Tohoku Electric Power Co Inc | 風力発電出力予測方法、風力発電出力予測装置およびプログラム |
JP2009138523A (ja) * | 2007-12-03 | 2009-06-25 | Mitsubishi Electric Corp | 風力発電出力予測方法 |
JP2009167848A (ja) * | 2008-01-11 | 2009-07-30 | Chugoku Electric Power Co Inc:The | 風力発電量予測システム、方法及びプログラム |
Non-Patent Citations (2)
Title |
---|
AKINOBU MURATA; HIROSHI YAMAGUCHI; KENJI OHTANI: "Prediction technique of fluctuation in output range in solar power generation with multiple power generators installed at broad regions", THESIS B FOR THE INSTITUTE OF ELECTRICAL ENGINEERING OF JAPAN, vol. 127, 2007, pages 645 - 652 |
See also references of EP2549641A4 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210222948A1 (en) * | 2020-01-22 | 2021-07-22 | L'air Liquide, Societe Anonyme Pour L'etude Et L?Exploitation Des Procedes Georges Claude | Liquefaction apparatus |
US11913719B2 (en) * | 2020-01-22 | 2024-02-27 | L'air Liquide Societe Anonyme Pour L'etude Et L'exploitation Des Procedes Georges Claude | Liquefaction apparatus |
EP4131698A1 (en) * | 2021-08-04 | 2023-02-08 | Toyota Jidosha Kabushiki Kaisha | Power management system, power management server, and power management method |
Also Published As
Publication number | Publication date |
---|---|
MY156889A (en) | 2016-04-15 |
US20130013233A1 (en) | 2013-01-10 |
EP2549641A4 (en) | 2016-11-30 |
CN102792542B (zh) | 2015-01-07 |
EP2549641A1 (en) | 2013-01-23 |
TWI533251B (zh) | 2016-05-11 |
JP5606114B2 (ja) | 2014-10-15 |
JP2011200040A (ja) | 2011-10-06 |
CN102792542A (zh) | 2012-11-21 |
TW201205492A (en) | 2012-02-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5606114B2 (ja) | 発電量予測装置、予測方法及び予測プログラム | |
Ding et al. | A novel adaptive discrete grey model with time-varying parameters for long-term photovoltaic power generation forecasting | |
Behera et al. | Solar photovoltaic power forecasting using optimized modified extreme learning machine technique | |
Pousinho et al. | A risk-averse optimization model for trading wind energy in a market environment under uncertainty | |
Yin et al. | Generation and transmission expansion planning towards a 100% renewable future | |
Gallego-Castillo et al. | On-line quantile regression in the RKHS (Reproducing Kernel Hilbert Space) for operational probabilistic forecasting of wind power | |
Rebennack et al. | Handbook of power systems I | |
JP5248372B2 (ja) | 発電計画作成方法、装置、プログラムおよび記憶装置 | |
Tang et al. | Efficient scenario generation of multiple renewable power plants considering spatial and temporal correlations | |
Acakpovi et al. | Time Series Prediction of Electricity Demand Using Adaptive Neuro‐Fuzzy Inference Systems | |
Muzumdar et al. | Designing a robust and accurate model for consumer-centric short-term load forecasting in microgrid environment | |
Bashari et al. | Forecasting electric load by aggregating meteorological and history-based deep learning modules | |
Kirilenko et al. | A framework for power system operational planning under uncertainty using coherent risk measures | |
WO2022168357A1 (ja) | 発電量管理システム及び発電量管理方法 | |
US20210055700A1 (en) | Hybrid machine learning and simulation based system for forecasting in electricity systems | |
Bødal et al. | Capacity expansion planning with stochastic rolling horizon dispatch | |
Nammouchi et al. | Robust opportunistic optimal energy management of a mixed microgrid under asymmetrical uncertainties | |
Matsuo et al. | Forecasting daily electric load by applying artificial neural network with fourier transformation and principal component analysis technique | |
Abubakar et al. | Intelligent modeling and optimization of solar plant production integration in the smart grid using machine learning models | |
Kronqvist et al. | Alternating mixed-integer programming and neural network training for approximating stochastic two-stage problems | |
Pramanik et al. | An ensemble-based approach for short-term load forecasting for buildings with high proportion of renewable energy sources | |
Dillon et al. | Impact of uncertainty on wind power curtailment estimation | |
Velasco et al. | Hour-ahead electric load forecasting using artificial neural networks | |
Bantugon et al. | Short-and long-term electricity load forecasting using classical and neural network based approach: a case study for the Philippines | |
Dai et al. | Probabilistic model for nondispatchable power resource integration with microgrid and participation in the power market |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201180013084.7 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 11755942 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13583792 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2011755942 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 8824/CHENP/2012 Country of ref document: IN |