JP2015164024A - Prediction system and method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a prediction system capable of calculating a transaction amount for maximizing benefit, in consideration of power generation cost of a power supplier.SOLUTION: Data related to a limitation cost line is calculated by grasping characteristics including a power generation cost for a unit power generation amount, on respective power generation means. Then a transaction amount C is calculated so that difference of a change cost of a power generation cost when a predetermined amount of power transaction calculated from the data related to the limitation cost line and a prediction value N0 of the power demand amount, is performed and transaction balance when a predetermined amount of power transaction calculated based on a transaction price is performed, becomes maximum.

Description

  The present invention relates to a prediction system and a prediction method.

  In recent years, in the electric power market, electric power can be freely bought and sold. When buying and selling electric power, the electric power transaction price is determined for a certain period in the future, and buying and selling of electric power is carried out (for example, buying and selling in units of 30 minutes two days ago).

  From such a background, a method for predicting the amount of power demand on a transaction target date (for example, two days later) has been proposed so that the power supplier can manage risk in the power transaction (see Patent Document 1).

JP 2004-252967 A

  From the background as described above, data related to past power demand is accumulated, and it is possible to predict the power demand at a factory facility or the like to some extent accurately in advance. However, the method as described above does not take into account the power generation cost of the power supplier, so that the power supplier can calculate up to the optimal transaction volume to buy and sell power in order to maximize profits. There wasn't.

  Therefore, an object of the present invention is to propose a prediction system and a prediction method for calculating a transaction amount that maximizes profits in consideration of power generation costs of a power supplier.

  The main present invention that solves the above-described problem is a prediction system that predicts an optimum transaction amount that maximizes a profit value in power trading, and includes a first storage unit that stores a power generation possible amount of a plurality of power generation means, A second storage unit that stores a power generation cost per unit power generation amount of the plurality of power generation means, a third storage unit that stores a predicted value of a power demand amount in a period to be a target of the power transaction, and the unit A fourth storage unit that stores operation priorities for the plurality of power generation units, which is set so that a power generation unit with a low power generation cost per unit of power generation operates preferentially; Based on the fifth storage unit that stores the transaction price per unit power generation amount, the power generation possible amount of the power generation means, the power generation cost per unit power generation amount of the power generation means, and the operation priority for the power generation means, Electric power A power generation schedule calculation unit that calculates data related to the marginal cost line indicating the correspondence between the required amount and the power generation cost, and a predetermined amount of power transaction calculated based on the data related to the marginal cost line and the predicted value of the power demand amount An optimal transaction amount calculation unit for calculating the predetermined amount that maximizes a difference between a generated power change cost and a transaction balance generated by a predetermined amount of power transaction calculated based on the data related to the transaction price; It is the prediction system characterized by having.

  Other features of the present invention will become apparent from the accompanying drawings and the description of this specification.

  According to the present invention, a power supplier can predict a transaction volume that maximizes profits in a power transaction. Further, according to the present invention, even when the power demand amount and the transaction price are predicted values having a probability distribution, it is possible to predict the optimum transaction amount including those risks.

It is a figure which shows the prediction system in embodiment of this invention. It is a figure which shows the hardware constitutions of the prediction apparatus in 1st Embodiment of this invention. It is a figure which shows the hardware constitutions of the transaction information provision apparatus in 1st Embodiment of this invention. It is a figure which shows the data table M1 regarding the electric power generation means in 1st Embodiment of this invention. It is a figure which shows the data table M2 regarding the predicted value of the electric power demand in 1st Embodiment of this invention. It is a figure which shows the data table M3 regarding the transaction information in 1st Embodiment of this invention. It is a figure which shows the function structure of the prediction apparatus in 1st Embodiment of this invention. It is a figure which shows the flow of operation | movement of the prediction system in 1st Embodiment of this invention. It is a figure which shows the data table M4 regarding the operation priority in 1st Embodiment of this invention. It is a figure which shows the relationship between the operation rate and marginal cost in 1st Embodiment of this invention. It is a figure which shows the marginal cost line in 1st Embodiment of this invention. It is a figure which shows the marginal cost line in 1st Embodiment of this invention. It is a figure which shows the marginal cost line in 1st Embodiment of this invention. It is an image figure of the probability distribution of the electric power demand in 2nd Embodiment of this invention. It is an image figure of variable conversion of the probability density function in 2nd Embodiment of this invention. It is a figure which shows the flow of operation | movement of the demand prediction part in 3rd Embodiment of this invention. It is a figure which shows the data table M5 regarding the past power demand in 3rd Embodiment of this invention. It is a figure which shows the data table M6 regarding the past measured air temperature in 3rd Embodiment of this invention.

At least the following matters will become apparent from the description of this specification and the accompanying drawings.
<First Embodiment>
=== About the prediction system ===
In this embodiment, for each power generation means, grasp characteristics of power generation cost per unit power generation amount, etc., and based on those characteristics and power transaction transaction information, the transaction amount that maximizes the profit value in power transaction is calculated. It is to be predicted.

  The power generation cost varies variously depending on whether or not it is a masstran power supply, the operating rate of the power generation means, the fuel cost required for power generation at that time, and the like. Therefore, the present embodiment is based on the understanding that in order to maximize the profit value in power trading, it is indispensable to grasp these characteristics. Hereinafter, the power generation cost required per unit power generation amount (for example, 1 MWh / h) is referred to as “marginal cost”. In addition, the transaction volume that maximizes the profit value in power trading is called “optimum transaction volume”.

  In FIG. 1, an example of the prediction system which implement | achieves prediction of the optimal transaction amount in the case of electric power transaction in this embodiment is shown. The prediction system according to the present embodiment includes a prediction device 100, a transaction information providing device 200, and the like. Both devices transmit and receive data using a communication network 300 such as a LAN connection.

  The prediction device 100 is a computer that is operated by a user. The transaction information providing apparatus 200 is a computer that transmits data in response to a request from the prediction apparatus 100. The prediction device 100 according to the present embodiment is configured to predict a profit value by acquiring transaction information relating to a transaction price or the like from the transaction information providing device 200.

  FIG. 2A shows a hardware configuration of the prediction apparatus 100 of the present embodiment.

  The prediction device 100 includes a control unit 100A, a storage unit 100B, a communication unit 100C, an input unit 100D, and a display unit 100E.

  The control unit 100A is a CPU or the like, and is connected to the storage unit 100B, the communication unit 100C, the input unit 100D, and the display unit 100E via a bus or the like. Then, the control unit 100A performs data communication with the storage unit 100B, the communication unit 100C, the input unit 100D, and the display unit 100E based on the computer program stored in the storage unit 100B, and controls their operations.

  The storage unit 100B includes a volatile memory (RAM), a nonvolatile memory (flash memory), and the like. The storage unit 100B stores a computer program for controlling the prediction device 100, data M1 related to power generation unit (to be described later), data M2 related to the predicted power demand amount, and the like. The storage unit 100B also includes a storage unit (not shown) that stores a regression model, which will be described later, intermediate data calculated by each functional unit, final data, acquired analysis target data, and the like.

  The communication unit 100C is a communication controller or the like, and transmits / receives data to / from the transaction information providing apparatus 200 using a communication network 300 or the like by wired or wireless LAN connection.

  The input unit 100 </ b> D is a switch, a touch panel, or the like, and receives a user operation instruction for the prediction device 100.

  The display unit 100E is a liquid crystal display or the like that displays various types of information, and displays a probability distribution or the like of a predicted temperature described later.

  FIG. 2B shows a hardware configuration of the transaction information providing apparatus 200 of the present embodiment.

  The transaction information providing apparatus 200 includes a control unit 200A, a storage unit 200B, and a communication unit 200C.

  The control unit 200A is a CPU or the like, and is connected to the storage unit 200B and the communication unit 200C via a bus or the like. Then, the control unit 200A performs data communication with the communication unit 200C and the storage unit 200B based on the computer program stored in the storage unit 200B, and controls their operation.

  The storage unit 200B includes a volatile memory (RAM), a nonvolatile memory (flash memory), and the like. And the memory | storage means 200B has memorize | stored the computer program for controlling the transaction information provision apparatus 200, the data regarding the transaction information mentioned later, etc.

  The communication unit 200C is a communication controller or the like, and transmits and receives data to and from the prediction device 100 using the communication network 300 or the like by wired or wireless LAN connection.

  FIG. 3A shows an example of the data table M1 related to the power generation means stored in the storage means 100B of the prediction device 100 of the present embodiment.

  The data relating to the power generation means includes a minimum power generation amount, a power generation possible amount, and a marginal cost for a plurality of power generation means possessed by the power supplier.

  The power supplier has a plurality of power generation means such as hydroelectric power generation, solar power generation, nuclear power generation, and thermal power generation. The marginal cost, the amount of power generation, and the like vary depending on the type of power generation means and the performance such as power generation efficiency. For example, since it is difficult to stop the operation of nuclear power generation, it is planned as a power generation means that is always operated. On the other hand, in the case of thermal power generation, the marginal cost may rise depending on the fuel price or the like. In addition, hydroelectric power generation also has a feature that the marginal cost is cheaper than other power generation means.

  The power generation means A, B, C... Shown in FIG. 3A represents one of those power generation means. In addition, the minimum power generation amount (for example, 1 MWh / h) is a Mastran power supply (power generation means that is difficult to stop in operation from the viewpoint of power generation costs, as in the case of the above-mentioned nuclear power generation, and that needs to be operated constantly). The amount of power generated by The power generation possible amount (for example, 1 MWh / h) is a limit value of the power generation capacity of each of the power generation means. The marginal cost represents the power generation cost required per unit power generation amount (for example, 1 MWh) when operating the power generation means.

  Here, the marginal cost also differs depending on the operating rate, that is, the power generation capacity that is being exhibited among the power generation capacity limit values of the power generation means. Specifically, the marginal cost of the power generation means increases as the operating rate increases. Therefore, in order to maximize the profit, it is better to store the marginal cost corresponding to the change in the operating rate in the data table M1. In the data table of FIG. 3A, the marginal costs of power generation means A, B, C,... Are described as A (x1), B (x2), C (x3). The marginal cost function corresponding to the operating rates x1, x2, x3. The storage format may be a table format or the like.

  FIG. 3B shows an example of the data table M2 related to the predicted power demand stored in the storage unit 100B of the prediction device 100 of the present embodiment.

  The data relating to the predicted demand is data relating to a predicted value (for example, 100 MWh) of the electric power demand that needs to be supplied in a predetermined time zone by the power supplier who is the user of the prediction device 100. The said electric power demand amount changes with time zones. For example, since the factory facilities are operating in the daytime, a large amount of power demand is predicted. However, since the factory facilities are not operated at night, the power demand is predicted to decrease. As this data, for example, data calculated based on the required power demand amount on the same day in the past is used. The past similar conditions are conditions relating to time, season, day of the week, weather, and the like.

  The data table M2 stores the power demand estimated every hour.

  FIG. 3C shows an example of a data table M3 related to transaction information stored in the storage unit 200B of the transaction information providing apparatus 200 of the present embodiment.

  The data related to the transaction information is data related to the transaction price per unit power generation amount (for example, 1 MWh / h) in a predetermined time zone (for example, 11:00 to 12:00) that is the object of the transaction, and data related to the transaction possible amount. Here, the data relating to the transaction information may be a confirmed value or a predicted value. The electric power transaction is performed based on the transaction price. Specifically, when a power supplier sells a predetermined amount of power, based on the transaction price, the power supplier earns the sold amount instead of supplying additional power. Can be obtained as Similarly, when a power supplier purchases a predetermined amount of power, based on the transaction price, the power supplier receives the power supply for the purchase instead of receiving the power supply from the transaction target. This is a mode of paying an amount. Further, the tradeable amount represents an upper limit value at which the power supplier can trade in the power trade.

  The data table M3 stores a transaction price and a tradeable amount every hour.

  Further, the data relating to the tradeable amount may be set for the convenience of operation of the power generation means of the power supplier. For example, as described above, it is assumed that the Mastran power supply is always operated, and therefore, the electric power generated by the operation of the Mastran power supply may be set as inoperable. Moreover, the data regarding the tradeable amount may not necessarily be set.

  In FIG. 4, an example of a function structure of the prediction apparatus 100 of this embodiment is shown.

  The prediction device 100 includes an acquisition unit 101, a power generation schedule calculation unit 102, an optimum transaction amount calculation unit 103, and a presentation described below, based on the computer program stored in the storage unit 100B and the hardware configuration (100A to 100E) described above. The function of the unit 104 is realized.

  The acquisition unit 101 acquires data by performing data communication with another device. In the present embodiment, data related to transaction information is acquired from the transaction information providing apparatus 200.

  The power generation schedule calculation unit 102 determines the marginal cost based on the data M1 regarding the power generation means (data regarding the power generation possible amount of the power generation means, data regarding the marginal cost of the power generation means) and the operation priorities for the plurality of power generation means set. Calculate data about the line. The data related to the marginal cost line is data that specifies how to operate the power generation means in order to compensate for the power generation amount in correspondence with the required power generation amount (power demand amount). Data corresponding to the line F (W).

The optimum transaction amount calculation unit 103 uses the data related to the calculated marginal cost line, the change cost of the power generation cost when performing a predetermined amount of power transaction calculated based on the predicted value of the power demand amount, and the data related to the transaction information. The transaction amount when the difference from the transaction balance when performing a predetermined amount of power transaction calculated based on the maximum is calculated as the optimum transaction amount.
=== About the operation of the prediction system ===
Next, an example of the operation of the prediction system will be described.

  FIG. 5 shows a flowchart of the present embodiment.

  (S1) is a step in which the user of the prediction device 100 inputs a prediction target period (for example, 2013/2/1 from 7:00 to 8:00). At this time, the user of the prediction device 100 sets the operation priority of the power generation means in consideration of the status of each power generation means.

  FIG. 6 shows a data table M4 regarding the priority related to the mass-tran power supply and the priority related to the marginal cost in the present embodiment. The power generation schedule calculation unit 102 calculates data related to the marginal cost line so as to operate in order from the power generation means with the highest operation priority. In addition, the priority regarding the mastrun power supply is set higher than the priority regarding the marginal cost.

  Here, the priority related to the marginal cost set for each power generation means may be set so as to vary according to the operating rate of the power generation means. This is based on the understanding that the power generation efficiency of the power generation means varies depending on the operating rate, and the marginal cost also varies accordingly. FIG. 7 shows an example of the marginal cost according to the operating rate of each power generation means. As shown in FIG. 7, the power generation efficiency of many power generation means decreases according to the operation rate, and the marginal cost increases. From this, it is good also as what changes a priority at the intersection of the relationship line of the operation rate of each electric power generation means and a marginal cost.

  (S2) is a step in which the prediction device 100 acquires acquisition information from the transaction information providing device 200. Specifically, the acquisition unit 101 of the prediction device 100 requests the transaction information providing device 200 for an acquisition price and a transaction possible amount related to a prediction target period. And the transaction information provision apparatus 200 receives the said request, and transmits the acquisition price and transaction possible quantity regarding the period of prediction object to the prediction apparatus 100 from the data table M3 regarding transaction information.

  (S3) is how the power generation schedule calculation unit 102 operates a plurality of power generation means in a period subject to a power transaction based on the data M1 related to the power generation means and the data M4 related to the operation priority. This is a process of calculating data related to the marginal cost line. The data related to the marginal cost line is data that specifies how to operate the power generation means in order to compensate for the power generation amount in correspondence with the required power generation amount (power demand amount). Data corresponding to F (W). The data related to the marginal cost line may be any data that associates the power generation amount with the power generation cost, and is not limited to a function expression, but is stored in a table format corresponding to the power generation amount and the power generation cost. It may be.

  Hereinafter, the data related to the marginal cost line calculated in (S3) will be described with reference to FIGS. 8A to 8C which are graphed.

  FIG. 8A is a marginal cost line calculated from the data M1 regarding the power generation means and the data M2 regarding the operation priority of the power generation means. The horizontal axis represents the required power generation amount (power demand), and the vertical axis represents the marginal cost of each power generation means. The further to the right, the greater the amount of power generation (power demand), and the more upward, the greater the marginal cost. The section below the marginal cost line represents the difference in power generation means to be operated (the same applies to FIGS. 8B and 8C). Here, since the priority related to the mastrun power supply is set as a higher priority than the priority related to the marginal cost, the marginal cost line is composed of two areas, a masstran power supply priority area A and a marginal cost priority area B. Yes. In other words, it represents that the marginal cost of the power generation means A, B, C is operated before the lowest power generation means D.

  (S4) is a step in which the optimum transaction amount calculation unit 103 calculates the change cost of the power generation cost when the predetermined amount C of power transaction is performed.

  Here, with reference to FIG. 8B and FIG. 8C, the change cost of the power generation cost when a power transaction of a predetermined amount C is performed will be described. FIG. 8B shows the power generation cost required when the power demand is N0. When the predicted power demand is N0, the total value of the areas indicated by the oblique lines in FIG. 8B is the necessary power generation cost. At this time, the power generation cost can be expressed by equation (1).

ここで、Ｆ（Ｗ）は、発電量と対応した限界費用を示す限界費用線に関するデータを表す。上述したとおり、Ｆ（Ｗ）は、各発電手段の稼働率と限界費用に関するデータＡ（ｘ１）、Ｂ（ｘ２）、Ｃ（ｘ３）・・、稼働優先度、発電可能量等に基づいて算出される（ｘ１、ｘ２・・・は、稼働率を表す）。

Here, F (W) represents data related to the marginal cost line indicating the marginal cost corresponding to the power generation amount. As described above, F (W) is calculated on the basis of data A (x1), B (x2), C (x3),. (X1, x2,... Represent operating rates).

  FIG. 8C shows an example of the change cost (decrease) in the power generation cost when a transaction with the transaction amount C (electric power purchase) is performed during the period of power transaction. From FIG. 8C, the change cost of the power generation cost when the power purchase of the transaction amount C is performed is an area in which F (W) is surrounded by the demand predicted value N0 and the post-transaction N0-C on the W axis. Specifically, the change cost of the power generation cost can be expressed by Expression (2).

（Ｓ５）は、最適取引量算出部１０３が、取引情報に関するデータＭ３に基づいて、電力取引の対象となる期間に所定量の取引を行った場合の取引収支を算出する工程である。具体的には、電力取引の対象となる期間の取引価格が一定値Ｒである場合、所定量Ｃの取引（電力買い）を行った場合の取引収支（支払額）は、式（３）より表すことができる。

(S5) is a step in which the optimal transaction amount calculation unit 103 calculates a transaction balance when a predetermined amount of transaction is performed during a period subject to power transaction based on the data M3 related to transaction information. Specifically, when the transaction price for a period subject to power trading is a constant value R, the transaction balance (payment amount) when a transaction of a predetermined amount C (power purchase) is performed is given by Equation (3) Can be represented.

（Ｓ６）は、最適取引量算出部１０３が、（Ｓ４）において算出した所定量の取引を行った場合の発電費用の変化費用と、（Ｓ５）において算出した所定量の取引を行った場合の取引収支の差に基づいて、最適取引量を算出する工程である。具体的には、電力買いの場合、発電費用の変化費用（減少）から取引収支（支払額）を減じた差分が大きくなるほど、電力供給者にとって最大利益となる。

(S6) is a case where the optimal transaction amount calculation unit 103 performs a predetermined amount of transaction calculated in (S4) and a change amount of power generation cost when the predetermined amount of transaction calculated in (S5) is performed. This is a process of calculating the optimum transaction volume based on the difference in transaction balance. Specifically, in the case of power purchase, the larger the difference obtained by subtracting the transaction balance (payment amount) from the change cost (decrease) in power generation cost, the maximum profit is for the power supplier.

  That is, the profit amount Y of the power supplier can be expressed as Expression (4) in the case of purchasing power from Expression (2) and Expression (3).

ここで、Ｙが最大となるＣ’が最適取引量となる。例えば、最適取引量Ｃ’は、Ｃに係る微分方程式により算出することができる。尚、（Ｓ４）、（Ｓ５）の工程は、実質的に（Ｓ６）の工程に集約されるから省略してもよい。

Here, C ′ that maximizes Y is the optimum transaction amount. For example, the optimal transaction amount C ′ can be calculated by a differential equation relating to C. Note that the steps (S4) and (S5) may be omitted because they are substantially integrated into the step (S6).

  Note that the optimal transaction amount calculation unit 103 sets the maximum C ′ in the direction in which the difference Y obtained by subtracting the transaction balance (payment amount) from the change cost (decrease) in the power generation cost becomes a positive amount for the power supplier. Select as the optimal trading volume.

  Moreover, when the transaction possible quantity is set as transaction information, the optimal transaction quantity is calculated by using the transaction possible quantity as an upper limit value.

  Thus, the optimum transaction amount calculation unit 103 calculates the optimum transaction amount so that the power supplier can obtain the maximum profit regarding the power purchase of the power transaction.

  (S7) is a step in which the presentation unit 104 performs predetermined image processing and presents the optimum transaction amount in the power transaction calculated in (S5) so that the user of the prediction device 100 can recognize it. For example, the presentation unit 104 outputs the power generation means, the operation rate, and the optimum transaction amount in the time zone of the transaction target as text data.

  Thus, according to the present embodiment, it is possible to calculate the optimum transaction amount of the power transaction that maximizes the profit value in consideration of the power generation cost.

  In the above embodiment, the case of purchasing power has been described, but the same applies to the case of selling power. That is, in the case of power sales, when the difference obtained by subtracting the change cost (increased) of the power generation cost from the transaction balance (income) is maximized, the profit is maximized for the power supplier. At this time, the profit amount Y can be expressed as Equation (5). Then, C ′ that maximizes Y can be calculated as the optimum transaction amount.

尚、本実施形態では、電力買い、電力売りの一方のみ可能な場合について説明したが、電力買い、電力売りのいずれも可能である場合には、電力買い、電力売りのいずれについてもＹを算出し、Ｙが最大となるときのＣ’を最適取引量とすればよい。

In this embodiment, the case where only one of power purchase and power sale is possible has been described. However, when both power purchase and power sale are possible, Y is calculated for both power purchase and power sale. Then, C ′ when Y is maximized may be set as the optimum transaction amount.

  In the above-described embodiment, the data regarding the priority of each power generation means is set by the user of the prediction device 100 in consideration of the status of each power generation means. The power generation schedule calculation unit 102 may set the value each time when the value is calculated, or may be stored in the data table M4 in advance.

  Moreover, in the said embodiment, although the priority regarding a mass run power supply and the priority regarding a marginal cost were described as data regarding a priority, the aspect which sets only the priority regarding a marginal cost may be sufficient. In addition to those priorities, data regarding other priorities may be set. For example, when there is a request to reduce the amount of power supplied by nuclear power generation, the power generation means related to nuclear power generation sets data on the use refusal level as another item so as to lower the priority.

  In the above embodiment, the case where the transaction price R is constant regardless of the transaction amount C has been described. However, the transaction price R may vary depending on the transaction amount C. In that case, R in Equation (4) can be expressed as a function R (C) of C. Then, the optimum transaction amount calculation unit 103 calculates the optimum transaction amount C ′ that maximizes Y in a manner in which the equation (4) is replaced with the function R (C).

  In the above embodiment, the prediction system calculates the profit amount Y. However, as long as the data is related to the profit value, the prediction system is not limited to the profit amount and may be a predetermined point or the like.

Note that, due to the influence of lightning or the like, the predetermined power generation means may stop and it may not be possible to supply power. In this case, the marginal cost line calculated by the power generation schedule calculation unit 102 varies. Therefore, in (S3), in consideration of such fluctuation factors, the respective power generation possible amounts on the marginal cost line may be calculated as expected values considering the possibility of dropping out. In this case, data relating to the probability distribution relating to dropout is stored in the predetermined power generation means of the data table M1. Then, an expected value of the power generation possible amount of the power generation means is calculated based on the data relating to the probability distribution regarding the dropout of the predetermined power generation means and the power generation possible amount of the power generation means. Then, the power generation schedule calculation unit 102 can reflect the risk of power loss by calculating data related to the marginal cost line based on the expected value of the power generation possible amount of the power generation means. Further, instead of changing the marginal cost line, assuming that the demand forecast value N has virtually increased, the expected value due to the dropout of each power generation means is added to the demand forecast value N, and the subsequent processing is executed. Good.
Second Embodiment
The present embodiment is different from the first embodiment in that when the predicted value of the power demand is calculated as a probability distribution, data relating to the probability distribution of the profit amount is calculated together with the optimal transaction amount. In the first embodiment, the case where the power demand amount is a constant predicted value has been described, but in reality, the predicted power demand amount has a probability distribution that varies within a certain range. For example, the power demand amount used in a factory facility or the like can be predicted in advance, but it is difficult to predict the power demand amount caused by the cooling / heating demand due to temperature fluctuations in advance.

  Therefore, in this embodiment, based on the data related to the probability distribution of power demand, the data related to the probability distribution of profits is calculated together with the optimal transaction amount.

  Hereinafter, aspects of the present embodiment will be described. In the present embodiment, only the configuration of the optimum transaction amount calculation unit 103 ′ is different from that of the first embodiment, and thus the description of other configurations is omitted.

  In the present embodiment, the optimal transaction amount calculation unit 103 ′ calculates the optimal transaction amount based on the probability distribution of power demand and calculates data related to the probability distribution of profit amount.

  Note that the data relating to the probability distribution in the present embodiment (hereinafter referred to as “probability distribution data”) indicates a variation in the value that can be realized from the predicted value, and is, for example, a predetermined time zone in the future (for example, 2013). This means the amount of power demand and the amount of profit (confidence interval) that can be realized with a probability of 95% at 7 o'clock of 1/2/1. In addition, the probability distribution may be data representing a probability density function related to a predicted value, data indicating a correspondence relationship between a probability that can be realized and a width of the predicted value, a dispersion coefficient, or the like.

  As an example, the optimum transaction amount calculation unit 103 ′ calculates the expected value N1 of the power demand amount based on the probability distribution of the power demand amount, and uses the expected value N1 as the predicted value of the power demand amount as an optimum transaction. The optimal transaction amount and the probability distribution data of the profit amount are calculated by the step of calculating the amount and the step of reflecting the probability distribution of the power demand amount with respect to the profit value for the optimal transaction amount.

  Specifically, based on the probability distribution of the power demand, the step of calculating the expected value N1 of the power demand is based on the probability distribution of the power demand by the probability density function f ( N), it can be calculated from equation (6).

当該期待値Ｎ１を電力需要量の予測値として、最適取引量を算出する工程は、図５の（Ｓ４）〜（Ｓ６）に示すとおりである。すなわち、最適取引量算出部１０３’は、電力需要量の予測値を期待値Ｎ１として、限界費用線に関するデータに基づいて、所定の取引量Ｃの電力取引を行った場合の発電費用の変化費用を算出する（Ｓ４）。そして、最適取引量算出部１０３’は、取引情報に関するデータＭ３に基づいて、電力取引の対象となる期間に所定量の取引を行った場合の取引収支を算出する（Ｓ５）。そして、最適取引量算出部１０３’は、（Ｓ４）において算出した所定量の取引を行った場合の発電費用の変化費用と、（Ｓ５）において算出した所定量の取引を行った場合の取引収支の差が最大となるように、最適取引量Ｃ’を算出する（Ｓ６）。

The process of calculating the optimum transaction amount using the expected value N1 as the predicted value of the power demand is as shown in (S4) to (S6) of FIG. In other words, the optimal transaction amount calculation unit 103 ′ sets the predicted value of the power demand amount as the expected value N1, and changes the power generation cost when performing a power transaction for a predetermined transaction amount C based on the data on the marginal cost line. Is calculated (S4). And optimal transaction amount calculation part 103 'calculates the transaction balance at the time of performing a predetermined amount of transaction in the period used as the object of electric power transaction based on the data M3 regarding transaction information (S5). Then, the optimal transaction amount calculation unit 103 ′ performs the change in power generation cost when the predetermined amount of transaction calculated in (S4) is performed, and the transaction balance when the predetermined amount of transaction calculated in (S5) is performed. The optimal transaction amount C ′ is calculated so that the difference between the two is maximized (S6).

  The step of reflecting the probability distribution of the power demand amount with respect to the profit value for the optimum transaction amount calculates the confidence interval of the profit amount based on the confidence interval of the power demand amount, for example. The confidence interval of the profit amount can be calculated by substituting the upper limit value N2 and the lower limit value N3 of the confidence interval of the power demand amount N into the equation (4) (the function equation (4) of the profit amount Y is It is a monotonically increasing function with respect to power demand N when C is constant). In addition, by selecting 5 points included in the confidence interval of the power demand amount and calculating the profit amount Y corresponding to each, it is a method of imitating the upper limit value and lower limit value of the confidence interval of the profit amount. Also good.

  The confidence interval means a numerical range that can actually occur within a certain probability range. FIG. 9 represents a confidence interval that falls within a range of 68.3% when the probability density function f (Nf) of the power demand is a normal distribution of N (N1, σ).

  As described above, according to the present embodiment, the probability distribution of the profit amount can be calculated by using the probability distribution of the power demand amount N, and the power transaction can be performed while considering the risk.

  In the above embodiment, a predetermined point in the confidence interval of the power demand N is sampled and converted into the confidence interval of the profit amount Y. The probability distribution of the profit amount Y is a probability density function of f (Nf). May be converted into variables and expressed as a probability density function of the profit amount Y.

  FIG. 10 is an image diagram of variable conversion of the probability density function. When converting the probability density function f (N) of the power demand N into the probability density function g (Y) of the profit amount Y, the probability density function g (Y) of Y is obtained by modifying the formula (7). It can be expressed as (8).

これによって、最適取引量算出部１０３’は、電力需要量Ｎの確率密度関数ｆ（Ｎ）を、利益額の確率密度関数ｇ（Ｙ）に変数変換することができる。

As a result, the optimum transaction amount calculation unit 103 ′ can variable-convert the probability density function f (N) of the power demand amount N into the probability density function g (Y) of the profit amount.

  Thus, according to the present embodiment, it is possible to calculate the optimum transaction amount of the power transaction that maximizes the profit value in consideration of the probability distribution of the power demand amount.

  In the above embodiment, the method for calculating the optimum transaction amount based on the expected value N1 of the probability distribution of the power demand amount has been described. However, the optimum transaction amount is calculated based on the average value instead of the expected value. It may be a method.

  Further, instead of the method of variable-converting the probability density function f (N) of the power demand amount N into the probability density function g (Y) of the profit amount, the variance coefficient of the power demand amount N is changed to the variance coefficient of the profit amount. A variable conversion method may be used.

Further, the above embodiment is not limited to the case where the probability density function f (N) of the power demand N is a normal distribution, and can be applied to an arbitrary distribution function such as a t distribution, a χ ² distribution, an F distribution, or the like. .

In the above embodiment, the case where the power demand is calculated as a probability distribution has been described. However, even when the transaction price is calculated as a probability distribution, the profit probability distribution can be calculated by performing variable conversion in the same manner as described above. In addition, when both the power demand and the transaction price are calculated as probability distributions, a known two-dimensional variable conversion may be performed.
<Third Embodiment>
The present embodiment is different from the above embodiment in that the prediction device 100 further includes a demand prediction unit 105 (not shown) that calculates a probability distribution of power demand. Hereinafter, aspects of the present embodiment will be described. In addition, about the structure which is common in 1st Embodiment, it abbreviate | omits.

  In the present embodiment, based on the understanding that the actual power demand varies from the predicted value of the power demand, there is a fluctuation in the cooling / heating demand due to the temperature fluctuation, the power demand is predicted. Do. That is, the probability distribution of power demand is calculated from the probability distribution of predicted temperature calculated by a known method. In the present embodiment, the demand prediction unit 105 calculates a relational expression between the temperature and the electric power demand based on the past actual measurement value of the air temperature and the actual measurement value of the electric power demand, and the probability of the predicted air temperature from the relational expression. Reflect the distribution in the probability distribution of power demand.

  FIG. 11 shows an example of a flowchart of the present embodiment.

  In the present embodiment, the prediction device 100 uses the demand information providing device 400, the weather information providing device 500, and the communication network 300 by LAN connection or the like (not shown in FIG. 1), The power demand is predicted by transmitting and receiving past data related to the power demand at that time. The demand information providing device 400 and the weather information providing device 500 are computers that transmit data in response to a request from the prediction device 100. Further, the demand information providing apparatus 400 and the weather information providing apparatus 500 have the same hardware configuration as the transaction information providing apparatus 200 shown in FIG. 2B.

  FIG. 12A shows an example of the data table M5 related to the power demand amount measured in the past, stored in the storage unit of the demand information providing apparatus 400. In the data table M5, the power demand (W) in a predetermined time zone is stored in units of one hour in association with the date and time.

  FIG. 12B shows an example of the data table M6 related to the temperature actually measured in the past, stored in the storage unit of the weather information providing apparatus 500. In this data table M6, the measured value of the temperature in a predetermined time zone is associated with the date and time and stored in units of one hour.

  (S41) in FIG. 11 is a step in which the acquisition unit 101 of the prediction device 100 requests the demand information providing device 400 for a past power demand amount related to a future predetermined time zone P.

  (S42) is a step in which the demand information providing apparatus 400 receives the request, acquires the power demand from the data table M5 related to the past power demand, and transmits the data to the prediction apparatus 100. It is.

  As an example, when the predetermined time zone P in the future is 7 o'clock, the acquisition unit 101 acquires data from 7 o'clock to 8 o'clock in the data M <b> 5 related to the power demand in the past (the same month last year).

  (S43) is a step in which the acquisition unit 101 of the prediction device 100 requests the weather information providing device 500 for an actual measured value of the past temperature related to the time of the power demand acquired in (S42).

  (S44) is a process in which the weather information providing apparatus 500 receives the request, acquires an actual measurement value from the data table M6 related to the past measured temperature, and transmits the data to the prediction apparatus 100. .

  As an example, when the time zone of the power demand acquired in (S42) is from 7:00 to 8:00, the acquisition unit 101 acquires data at 7:00 or 8:00 of the data M6 related to the measured temperature.

  (S45) is a step in which the demand prediction unit 105 of the prediction device 100 calculates a demand prediction formula based on the acquired past data. Specifically, the prediction device 100 performs regression analysis for calculating a relational expression between the electric power demand amount and the air temperature based on the measured value T1 of the air temperature in the predetermined time zone acquired in (S44) and the electric power demand amount N1. I do.

  In the regression analysis, for example, for the regression model of Equation (9), the power demand amount N is an objective variable, the difference between the standard temperature 18 ° C. and the measured value, and the square of the difference between the standard temperature 18 ° C. and the measured value is the explanatory variable. The least squares method is used.

（γ₀、δ₀は母切片、γ₁、γ₂、δ₁、δ₂は母回帰係数、Ｅ_iは誤差項を表す。また、各変数の末尾のｉは、各観測点ｉを表し、サンプルとして取得した過去のデータの各実測値Ｔ１、電力需要量Ｎ１を表す。）
ここで、標準気温１８℃と実測値の差を説明変数としているのは、冷暖房需要による電力需要量の変動量は、標準気温１８℃のときには、冷暖房需要は実質的に０であるとみなせるためである。また、標準気温１８℃と実測値の差の二乗を説明変数とすることによって、冷暖房の需要は、気温が標準気温１８℃から離れるにつれて、急激に増加するという一般的社会現象をより正確に反映させることができる。

(Γ ₀ , δ ₀ are population intercepts, γ ₁ , γ ₂ , δ ₁ , δ ₂ are population regression coefficients, E _i is an error term, and i at the end of each variable represents each observation point i. , Each measured value T1 of the past data acquired as a sample, and power demand amount N1 are represented.)
Here, the difference between the standard temperature 18 ° C. and the measured value is used as an explanatory variable because the fluctuation amount of the power demand due to the cooling / heating demand can be regarded as substantially zero when the standard temperature 18 ° C. It is. In addition, by using the square of the difference between the standard temperature of 18 ° C and the measured value as an explanatory variable, the demand for air conditioning will more accurately reflect the general social phenomenon that the temperature rapidly increases as the temperature departs from the standard temperature of 18 ° C. Can be made.

  Further, the equation (9) divides the equation into two depending on whether it is 18 ° C. or higher and 18 ° C. or lower, and separates the cooling demand from the heating demand. Although omitted in equation (9), regression analysis may be performed by adding explanatory variables such as weather information and day information.

From this, γ ₀ , γ ₁ , γ ₂ , δ ₀ , δ ₁ , δ ₂ of the regression model are determined, and the regression equation (10) is calculated as a demand prediction formula.

（Ｓ４６）は、予測装置１００の需要予測部１０５が、上記回帰式（１０）と、予測気温の確率分布データに基づいて、電力需要量の確率分布を算出する工程である。

(S46) is a step in which the demand prediction unit 105 of the prediction device 100 calculates the probability distribution of the power demand based on the regression equation (10) and the probability distribution data of the predicted temperature.

  As an example, when the probability distribution data of the predicted temperature is expressed by the expected value T2 of the predicted temperature and the temperature T2 ± S as the confidence interval of 68.2%, the probability distribution (confidence interval) of the power demand is It becomes as follows.

That is, the expected value of the power demand can be calculated by substituting the expected value T2 of the probability distribution of the predicted temperature with respect to the temperature T in Expression (10). Then, the upper limit value and lower limit value of the confidence interval of the predicted value of the power demand can be calculated by substituting T2 + S and T2-S for equation (10). (Equation (10) can be regarded as a monotonically increasing function for temperature T)
As described above, according to the present embodiment, the probability distribution of the predicted temperature can be reflected in the probability distribution of the power demand, and the probability distribution of the power demand can be calculated with high accuracy.

  In the above embodiment, a regression model is used in which the difference between the standard temperature 18 ° C. and the actual measurement value and the square of the difference between the standard temperature 18 ° C. and the actual measurement value are explanatory variables. However, the regression model need not be limited to the above if the probability distribution of the power demand can be calculated from the probability distribution of the predicted temperature with a certain degree of accuracy. For example, regarding the square of the difference between the standard temperature 18 ° C. and the actual measurement value, an explanatory variable may be omitted, or a normal actual measurement value may be used as the explanatory variable instead of the difference between the standard temperature 18 ° C. and the actual measurement value. Also, the standard temperature may be set to 17 ° C. or 19 ° C. instead of 18 ° C. Further, a predicted maximum temperature, predicted minimum temperature, weather information, regional information, etc. may be added as explanatory variables. Further, in order to stabilize the variance of the sample, a variance stabilization conversion may be performed to apply the regression model.

  Moreover, in the said embodiment, although the process which calculates a demand prediction formula was performed according to the date and time of prediction object being set, a demand prediction formula is produced | generated beforehand and the date and time of prediction object is set. Accordingly, the predicted value of the power demand amount for the corresponding date and time may be calculated.

  Further, in the above embodiment, when calculating the variation in the electric power demand, assuming that the fluctuation in the air conditioning demand due to the temperature fluctuation is the largest factor that causes the actual electric power demand to fluctuate from the predicted value of the electric power demand. The error term in equation (9) is not considered. However, regarding the error term in Equation (9), a standard deviation of the error term may be calculated and taken into consideration when calculating the probability distribution of the power demand. In that case, the standard deviations may be integrated according to the known law of error propagation.

  As described above, according to each of the above embodiments, it is possible to calculate the optimum transaction amount of the power transaction that maximizes the profit value in consideration of the power generation cost.

In each of the above embodiments, the prediction device 100 has the power generation schedule calculation unit 102 and the optimal transaction amount calculation unit 103 as functional units. However, these functional units or a part thereof may be distributed to other devices. Similarly, the storage area of the data stored in each storage means may be an arbitrary place. For example, it may be aggregated in the prediction device 100, or may be configured to be distributed and stored on a cloud system composed of a plurality of computers.
=== Conclusion ===
From the above, the above embodiments can be described as follows.

  Each of the above embodiments is a prediction system that predicts the optimum transaction amount that maximizes the profit value (Y) in power trading, and a first storage unit that stores the power generation possible amount of a plurality of power generation means (the above embodiment) Then, it corresponds to the data table M1), a second storage unit (corresponding to the data table M1 in the above embodiment) that stores the power generation cost per unit power generation amount of a plurality of power generation means, and the target of power transaction A third storage unit (corresponding to the data table M2 in the above embodiment) that stores the predicted value (N) of the power demand amount during the period and power generation means with low power generation cost per unit power generation operate preferentially. A fourth storage unit (in the above embodiment, corresponding to the data table M4) that stores operation priorities for a plurality of power generation means, and a unit power generation amount in a period that is a target of power trading. A fifth storage unit (which corresponds to the data table M3 in the above embodiment), a power generation capability of the power generation means, a power generation cost per unit power generation amount of the power generation means, and an operation priority for the power generation means Based on the power generation schedule calculation unit (102) for calculating data on the marginal cost line indicating the correspondence between the power demand and the power generation cost, and based on the data on the marginal cost line and the predicted value of the power demand The predetermined amount that maximizes the difference between the change cost of the power generation cost caused by the predetermined amount of power transaction (C) and the transaction balance generated by the predetermined amount of power transaction calculated based on the transaction price data is calculated. The prediction system characterized by having the optimal transaction amount calculation part (103, 103 ') to perform is disclosed.

  Thus, the power supplier can calculate the optimum transaction amount of the power transaction that maximizes the profit value in consideration of the power generation cost.

  Here, the power generation cost per unit power generation amount of the plurality of power generation means may be data stored by associating the operation rate of each of the plurality of power generation means with the power generation cost per unit power generation amount.

  As a result, it becomes possible to grasp the power generation cost in detail, and it is possible to calculate the optimal transaction amount of the power transaction that maximizes the profit value more accurately.

  Here, the predicted value of the power demand amount is the probability distribution data of the power demand amount in the period targeted for the power transaction, and the optimum transaction amount calculation unit is based on the probability distribution data of the power demand amount in the power transaction. The probability distribution data of the optimal transaction volume and profit value may be calculated. At this time, the optimal transaction amount calculation unit may calculate the optimal transaction amount in the power transaction based on the expected value of the probability distribution of the power demand amount.

  As a result, in addition to the optimal transaction volume, it is possible to calculate the profit fluctuation (risk) in the power transaction.

  Here, the prediction system further includes a sixth storage unit (corresponding to the data table M1 in the above embodiment) that stores probability distribution data of power loss of a predetermined power generation unit, and the power generation schedule calculation unit includes a predetermined power generation unit. Based on the probability distribution data of the power loss of the power generation means and the power generation possible amount of the predetermined power generation means, the expected value of the power generation possible amount of the predetermined power generation means is calculated, and the expected power generation possible amount of the predetermined power generation means is calculated. Based on this, data related to the marginal cost line may be calculated.

  Accordingly, it is possible to calculate the optimal transaction amount of the power transaction that maximizes the profit value in consideration of the risk of power loss.

  Here, the transaction price is the probability distribution data of the transaction price in the target period of the power transaction, and the optimal transaction amount calculation unit is configured to determine the optimal transaction amount in the power transaction based on the probability distribution data of the transaction price, and Probability value probability distribution data may be calculated.

  As a result, in addition to the optimal transaction volume, it is possible to calculate the profit fluctuation (risk) in the power transaction.

  Here, the fourth storage unit further has a priority related to the mastrand power supply, and the operation priority for the plurality of power generation means is a priority related to the mastrand power supply over the power generation means having a low power generation cost per unit power generation amount. It may be data set so that the power generation means for which the degree is set operates preferentially.

  As a result, it becomes possible to grasp the power generation cost in detail, and it is possible to calculate the optimal transaction amount of the power transaction that maximizes the profit value more accurately.

  In addition, each of the above embodiments is a prediction method for predicting a transaction amount that maximizes a profit value in a power transaction, and includes a power generation possible amount of a plurality of power generation means and a power generation cost per unit power generation amount of the plurality of power generation means. And a power generation schedule calculation step for calculating data on marginal cost lines indicating the correspondence between power demand and power generation costs based on operation priorities for a plurality of power generation means, data on marginal cost lines and prediction of power demand A predetermined amount that maximizes the difference between the change in power generation costs caused by a predetermined amount of power transaction calculated based on the value and the transaction balance generated by the predetermined amount of power transaction calculated based on the transaction price data. And an optimal transaction amount calculating step for calculating the transaction amount.

  Thus, the power supplier can calculate the optimum transaction amount of the power transaction that maximizes the profit value in consideration of the power generation cost.

  As mentioned above, although the specific example of this invention was demonstrated in detail, these are only illustrations and do not limit a claim. The technology described in the claims includes various modifications and changes of the specific examples illustrated above.

DESCRIPTION OF SYMBOLS 100 Prediction apparatus 101 Acquisition part 102 Power generation plan calculation part 103 Optimal transaction amount calculation part 104 Presentation part 105 Demand prediction part 200 Transaction information provision apparatus 300 Communication network 400 Demand information provision apparatus 500 Weather information provision apparatus

Claims (8)

A prediction system for predicting an optimal transaction volume that maximizes a profit value in power trading,
A first storage unit for storing the power generation possible amount of the plurality of power generation means;
A second storage unit for storing a power generation cost per unit power generation amount of the plurality of power generation means;
A third storage unit that stores a predicted value of the amount of power demand in the period to be the target of the power transaction;
A fourth storage unit configured to store operation priorities for the plurality of power generation units, the power generation units having a low power generation cost per unit power generation set to operate preferentially;
A fifth storage unit that stores a transaction price per unit power generation amount in a period to be a target of the power transaction;
Based on the power generation possible amount of the power generation means, the power generation cost per unit power generation amount of the power generation means, and the operation priority for the power generation means, data on the marginal cost line indicating the correspondence between the power demand and the power generation cost A power generation schedule calculation unit to calculate,
A predetermined amount of power transaction calculated based on data relating to the marginal cost line and a change cost of power generation cost caused by a predetermined amount of power transaction calculated based on the predicted value of the power demand amount, and data relating to the transaction price An optimal transaction amount calculation unit for calculating the predetermined amount with which the difference from the transaction balance caused by
A prediction system characterized by comprising: The power generation cost per unit power generation amount of the plurality of power generation means is data stored in association with the operation rate of each of the plurality of power generation means and the power generation cost per unit power generation amount. The prediction system according to 1. The predicted value of the power demand amount is probability distribution data of the power demand amount in the period targeted for the power transaction, and the optimum transaction amount calculation unit is configured to generate the power based on the probability distribution data of the power demand amount. The prediction system according to claim 1 or 2, wherein the probability distribution data of the optimal transaction amount and profit value in the transaction is calculated. The said optimal transaction amount calculation part calculates the optimal transaction amount in the said electric power transaction based on the expected value of the probability distribution of the said electric power demand amount. The prediction system of Claim 3 characterized by the above-mentioned. A sixth storage unit for storing probability distribution data of power loss of the predetermined power generation means;
The power generation schedule calculation unit calculates an expected value of the power generation possible amount of the predetermined power generation unit based on probability distribution data of power loss of the predetermined power generation unit and a power generation possible amount of the predetermined power generation unit. The prediction system according to any one of claims 1 to 4, wherein data relating to the marginal cost line is calculated based on an expected value of a power generation possible amount of the predetermined power generation means. The transaction price is probability distribution data of a transaction price in a period to be the target of the power transaction,
The said optimal transaction amount calculation part calculates the optimal transaction amount in the said electric power transaction, and the probability distribution data of profit value based on the probability distribution data of the said transaction price. The prediction system according to item. The fourth storage unit further includes a priority relating to the mass run power supply for the plurality of power generation means,
The operation priority for the plurality of power generation means is data set so that the power generation means for which the priority related to the mass run power supply is set to operate preferentially over the power generation means with a low power generation cost per unit power generation amount. It is these. The prediction system as described in any one of Claims 1 thru | or 6 characterized by the above-mentioned. A prediction method for predicting a transaction volume that maximizes a profit value in power trading,
The correspondence between the power demand and the power generation cost is shown based on the power generation possible amount of the plurality of power generation means, the power generation cost per unit power generation amount of the plurality of power generation means, and the operation priority for the plurality of power generation means. A power generation schedule calculation process for calculating data on marginal cost lines;
According to the predetermined amount of power transaction calculated based on the data related to the marginal cost line and the change cost of the power generation cost caused by the predetermined amount of power transaction calculated based on the predicted value of the power demand amount and the data related to the transaction price An optimal transaction amount calculating step for calculating the predetermined amount with which the difference from the resulting transaction balance is maximized;
The prediction method characterized by having.

Images