Power interchange system

Abstract

To provide a power interchange system for transmitting electricity generated by a power generation system consisting of a solar battery between locations via a power transmission network capable of accurately estimating the fluctuation range of the power generation amount of a solar battery at the time of transmission.SOLUTION: A disclosed power interchange system estimates the weather classification by using the estimation model by inputting the predicted solar radiation value, and estimates the range of solar radiation fluctuations by using the internal variables of the estimation model.SELECTED DRAWING: Figure 8

Description

[Technical field]

[0001] The present invention relates to a technique for transmitting electric power generated by a power generation system including solar cells between bases via a power transmission network. [Background technology]

[0002] Self-dispatch is when a business operator with power generation facilities uses the power grid owned by the power company to transmit the electricity generated by the power generation facilities between bases. When implementing self-dispatch, it is necessary to submit a transmission plan to the operating organization (e.g. Organization for Cross-regional Coordination of Transmission Operators: OCCTO) before starting the dispatch (e.g. the day before). Furthermore, while implementing self-dispatch, it is necessary to transmit the electricity as planned at specified time intervals (e.g. 30 minutes). If the actual transmitted power deviates from the planned power (imbalance), a penalty is generally imposed.

[0003] The patent document 1 listed below aims to "provide a technology that can accurately estimate the amount of power generated by a solar cell by accurately estimating the amount of solar radiation on the solar cell," and describes the technology that "the power generation prediction system according to the present invention learns the correlation between predicted data on the amount of solar radiation based on meteorological information and the amount of solar radiation estimated from the output of the solar cell, and predicts the amount of solar radiation and the amount of power generated based on this" (see abstract).

[0004] Japanese Patent Application No. 2022-144964 describes a technology that assumes that a power generation system that generates power to be transmitted by self-consignment is composed of solar cells and storage batteries. In this document, the power to be charged and discharged by the storage battery is calculated based on the difference between the planned power that was scheduled to be transmitted by the power transmission network and the actual power that was actually transmitted, and the power that needs to be generated by the solar cell is also calculated.

[0005] Japanese Patent Application No. 2022-144965 also describes a technology assuming that a power generation system that generates power to be transmitted by self-consignment is composed of solar cells and a storage battery. In this document, for a power transmission period in which weather with the largest fluctuation range and frequency of fluctuation in solar radiation is predicted, even if the actual power generation amount of the solar cells is less than the predicted power generation amount, the charge state of the storage battery is determined so that the shortfall can be compensated for by discharging from the storage battery. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2023-023134 A Summary of the Invention [Problem to be solved by the invention]

[0007] Consider a case where a power generation system that generates power to be transmitted by self-dispatch is composed of, for example, a solar cell and a storage battery. In order to transmit power in compliance with a pre-planned plan while performing self-dispatch, when the solar cell generates power in excess of the planned transmission power, it is necessary to suppress the amount of power generation to be less than the maximum power point and to use the surplus power generation to charge the storage battery. In other words, when the amount of power generation from the power generation system exceeds the planned transmission power as planned in advance, the solar cell is instructed to suppress the amount of power generation to be less than the maximum power point and the storage battery is instructed to perform a charging operation. Conversely, when the amount of power generation from the solar cell is less than the planned transmission power, the storage battery is discharged.

[0008] Consider the case where electricity is transmitted from multiple power generation bases to a demand base. In this case, typically, one of the power generation bases becomes a parent base, and the other power generation bases become sub-bases, and the parent base controls all of the power generation bases. In this case, the parent base predicts the amount of electricity generated from the solar cells at each power generation base in advance, and determines the amount of charging and discharging from the storage battery according to the predicted amount of electricity generated. Therefore, in order to comply with the scheduled power to be sent by charging and discharging the storage battery, it is necessary to accurately predict the amount of electricity generated by the solar cells at each power generation base.

[0009] Since the amount of power generated by a solar cell varies over time, when predicting the amount of power generated by the solar cell, it is necessary to predict the variation over time as well. In conventional techniques such as Patent Document 1, the amount of power generated by a solar cell can be predicted based on the predicted amount of solar radiation, but the range of variation in the amount of power generated is not necessarily fully considered.

[0010] The present invention has been made in consideration of the above-mentioned problems, and aims to accurately estimate the fluctuation range of the power generation amount of solar cells at the time of transmission in a power interchange system in which electricity generated by a power generation system composed of solar cells is transmitted between base stations via a power transmission network. [Means for solving the problem]

[0011] The power interchange system according to the present invention estimates weather classification using an estimation model that estimates weather classification by providing a predicted solar radiation value as an input, and estimates the solar radiation fluctuation range using internal variables of the estimation model. Effect of the Invention

[0012] According to the power interchange system of the present invention, it is possible to accurately estimate the fluctuation range of the amount of power generated by the solar cell at the time of power transmission. Problems, configurations, effects, etc. other than those described above will become apparent from the description of the following embodiments. [Brief description of the drawings]

[0013] [Figure 1A]1 is a configuration example of a power generation system provided by a business operator that performs self-wheeling. [Figure 1B] 1 is a configuration example of a power generation system provided by a business operator that performs self-wheeling. [Diagram 2] FIG. 1 is a schematic diagram showing a state in which a power interchange system performs self-transfer between bases. [Diagram 3] FIG. 1 is a diagram illustrating an imbalance in transmitted power. [Figure 4] Here are some examples of weather codes provided by weather information providers: [Figure 5A] FIG. 1 is a diagram comparing the actually measured amount of solar radiation and the predicted amount of solar radiation data on a certain day. [Figure 5B] FIG. 11 is a diagram comparing the actually measured amount of solar radiation and the predicted amount of solar radiation data on another day. [Figure 6] 4 is a schematic diagram showing a procedure in which the power control device 1 learns detailed weather classifications. FIG. [Figure 7] FIG. 7 is a diagram illustrating a procedure for estimating a detailed weather classification using the results of learning according to the procedure in FIG. 6. [Figure 8] 7 is a diagram illustrating an example of a relationship between an output value of a hidden layer neuron in the neural network of FIG. 6 and a wheeling imbalance amount. [Figure 9A] An example of predicted solar radiation values ​​for four days is shown below. [Figure 9B] An example of estimating the range of fluctuations in solar radiation from the output of hidden layer neurons is shown below. [Figure 10A] This shows the power generated by the solar cell on DAY 1 or the fluctuation over time of its predicted value. [Figure 10B] This shows the rate of change in the power generated by the solar cell on DAY1 or its predicted value. [Figure 10C] The results of FIG. 10B being replaced with the rate of change every 5 minutes are shown. [Figure 10D] An example of the expected imbalance shortfall [%] against the rated value (100%) is calculated for each predicted amount of solar radiation. [Figure 11A] 11A to 11D show the results of calculating the power change rate and the shortage imbalance on DAY2 in the same manner as in FIGS. 10A to 10D. [Figure 11B] 11A to 11D show the results of calculating the power change rate and the shortage imbalance on DAY2 in the same manner as in FIGS. 10A to 10D. [Figure 11C] 11A to 11D show the results of calculating the power change rate and the shortage imbalance on DAY2 in the same manner as in FIGS. 10A to 10D. [Figure 11D] 11A to 11D show the results of calculating the power change rate and the shortage imbalance on DAY2 in the same manner as in FIGS. 10A to 10D. [Figure 12A] 12A to 12D show the results of calculating the power change rate and the power shortage imbalance on DAY3 in the same manner as in FIGS. 10A to 10D. [Figure 12B] 12A to 12D show the results of calculating the power change rate and the power shortage imbalance on DAY3 in the same manner as in FIGS. 10A to 10D. [Figure 12C] 12A to 12D show the results of calculating the power change rate and the power shortage imbalance on DAY3 in the same manner as in FIGS. 10A to 10D. [Figure 12D] 12A to 12D show the results of calculating the power change rate and the shortage imbalance on DAY3 in the same manner as in FIGS. 10A to 10D. [Figure 13A] 13A to 13D show the results of calculating the power change rate and the power shortage imbalance on DAY 4 in the same manner as in FIGS. 10A to 10D. [Figure 13B] 13A to 13D show the results of calculating the power change rate and the shortage imbalance on DAY 4 in the same manner as in FIGS. 10A to 10D. [Figure 13C] 13A to 13D show the results of calculating the power change rate and the shortage imbalance on DAY 4 in the same manner as in FIGS. 10A to 10D. [Figure 13D] 13A to 13D show the results of calculating the power change rate and the power shortage imbalance on DAY 4 in the same manner as in FIGS. 10A to 10D. [Figure 14] 4 is a process flow diagram illustrating an outline of a procedure for the power control device 1 to calculate the wheeling planned power. FIG. [Figure 15A]1 is a flowchart illustrating a procedure in which a power interchange system determines power to be transmitted to a demand base. [Figure 15B] 1 is a flowchart illustrating a procedure in which a power interchange system determines power to be transmitted to a demand base. [Figure 16] 3 is an example of a user interface provided by the calculation unit 11. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] 1A and 1B show an example of the configuration of a power generation system provided by a business operator that performs self-wheeling. The power generation system is composed of a solar cell (PV) and a storage battery. The solar cell is connected to a power grid via a DCDC converter and a DCAC converter. The storage battery is connected in the same way. A power control device 1 controls the operation of the solar cell and the storage battery by transmitting operation commands to a drive device for the solar cell and a drive device for the storage battery (each of which is composed of the above converter). There may be multiple solar cells and multiple storage batteries installed.

[0015] Figure 2 is a schematic diagram showing how an electric power interchange system performs self-transfer between bases. Base 1 is equipped with the power generation system described in Figure 1. Bases 2 and 3 are equipped with the power generation system described in Figure 1, excluding storage batteries. This difference is due to, for example, the fact that legal regulations limit the bases where storage batteries can be installed.

[0016] Power generated at bases 1 to 3 is transmitted to bases A and B via a power grid. Bases A and B are demand bases. The power control device 1 controls the transmitted power based on demand forecast data and measurement data of each facility in accordance with a procedure to be described later. The power control device 1 includes a calculation unit 11 and a storage unit 12. These will be described later.

[0017] Of the power generation bases, base 1 that has a storage battery is considered to be the parent base, and the other power generation bases are considered to be small bases. It is assumed that the small bases do not have storage batteries installed. The parent base formulates a power interchange plan for the entire power generation base. Therefore, the power control device 1 is installed at the parent base. The power control device 1 executes charge and discharge commands to the storage battery at the parent base (if the other bases are equipped with storage batteries, it issues charge and discharge commands to those batteries) and output commands to the solar cells at each base. In this way, the power interchange system shown in Figure 2 controls the power transmitted to the demand base.

[0018] FIG. 3 is a diagram for explaining the imbalance of transmitted power. Before carrying out self-transmission (for example, the day before), the business operator submits to the power management organization a transmission plan that describes the scheduled transmission power, for example, in 30-minute units. The scheduled transmission power is calculated, for example, by subtracting the demand forecast from the power generation amount forecast by the power generation system, and multiplying the result by a coefficient (≦1.0). This coefficient is a coefficient for giving the power generation system an operating margin, and in this embodiment, this will be called the likelihood. By instructing the solar cell to generate power based on the result multiplied by the likelihood, the solar cell will operate at an operating point that outputs power smaller than the maximum power point.

[0019] When the actual generated power exceeds the scheduled power to be sent, the excess is balanced by suppressing the output power of the solar cell below the maximum power point and charging the storage battery. When the actual generated power is short of the scheduled power to be sent, the shortfall is made up by discharging from the storage battery.

[0020] When calculating the scheduled power to be entrusted, it is necessary to predict the power generated by the solar cells and also to predict the power demand. The remainder obtained by subtracting the demand forecast from the power generation forecast is transmitted between bases as the entrusted power. If the power generation forecast falls short of the demand forecast, the shortfall must be made up by discharging from the storage battery. Therefore, the storage battery must be maintained in a charged state sufficient to ensure the scheduled power to be entrusted during the period in which the entrustment is carried out.

[0021] However, the amount of power generated by a solar cell varies depending on the weather, with some varying significantly and others remaining relatively stable. Therefore, in the present invention, solar radiation forecast data for the period during which the vehicle is being transported is obtained from a weather information provider or the like, and the weather during the period during which the vehicle is being transported is forecast using this data.

[0022] Figure 4 shows examples of weather codes provided by weather information providers. Weather codes are generally provided in broad categories such as 10 to 50 as shown in Figure 4. In the present invention, this is taken a step further and weather is classified into more detailed categories. For example, sunny weather is classified into two detailed weather codes, 11 and 12.

[0023] Figure 5A is a graph comparing the measured solar radiation amount and the predicted solar radiation amount data on a certain day. This graph shows an example of a day with a weather code of 10 (sunny). In this example, it can be seen that the measured solar radiation amount and the predicted solar radiation amount data match relatively well.

[0024] FIG. 5B is a diagram comparing the measured solar radiation amount and the predicted solar radiation amount data on another day. This graph shows an example of another day where the weather code is 10 (clear). In this example, the weather code is the same 10 (clear) as in FIG. 5A, but it can be seen that there is a large deviation between the measured solar radiation amount and the predicted solar radiation amount data. In this way, even with the same weather code, the solar radiation amount may deviate significantly from the predicted data.

[0025] 6 is a schematic diagram showing a procedure for the power control device 1 to learn detailed weather classifications. The power control device 1 can learn the correlation between solar radiation forecast data and detailed weather classifications using a learning device constructed by, for example, a neural network. Here, a neural network is illustrated in which the input layer receives solar radiation forecast values ​​for 12 hours, the intermediate layer (hidden layer) is composed of three neurons, and the output layer is composed of two neurons.

[0026] This neural network is constructed to further classify weather code 10 into two detailed weather categories 11 and 12. If the outputs from the two neurons in the output layer are "1" and "0", respectively, it means that the input solar radiation forecast value is for weather code 11. If the outputs from the two neurons in the output layer are "0" and "1", respectively, it means that the input solar radiation forecast value is for weather code 12.

[0027] The predicted solar radiation for 12 hours on the first day (DAY1) is input to the first neuron in the hidden layer. In this example, the correct detailed weather classification for DAY1 is weather code 11 (output layer "1" "0"). The first neuron in the hidden layer has a weighting matrix made up of 12 elements that are multiplied with each of the 12 elements of the matrix describing the predicted solar radiation. The result of multiplying both matrices is substituted into the sigmoid function represented by the first formula in the lower part of Figure 6. The threshold of the first neuron in the hidden layer is specified as 15.02. The output y of the first neuron in the hidden layer is calculated by the above procedure.

[0028] The predicted solar radiation amount for 12 hours on the second day (DAY2) is input to the second neuron in the hidden layer. The same is true for the third and subsequent days, which are input to the corresponding neurons in the hidden layer. The output y of each hidden layer is calculated in the same way. For ease of description, solar radiation amount prediction data up to the third day is used in this example, but the same is true for the fourth and subsequent days.

[0029] The output y of the first neuron in the hidden layer is input to the first neuron in the output layer. The first neuron in the output layer has a weight matrix consisting of three elements that are multiplied by the outputs y of the first to third neurons in the hidden layer. The result of multiplying these two matrices is substituted into the sigmoid function represented by the second formula in the lower part of Figure 6. The threshold of the first neuron in the output layer is specified as 19.84. The output z of the first neuron in the output layer is calculated by the above procedure. The same is true for the second neuron in the output layer.

[0030] From the above calculations, the output of the first neuron in the output layer is 1.00, and the output of the second neuron in the output layer is 0.33. On the other hand, since the correct answers for the weather code on DAY1 are "1" and "0", the error Q between the output from the output layer and the correct answer can be calculated using the third formula in the lower part of Figure 10A. The same calculations are performed for DAY2 to DAY3. Learning is completed by optimizing the matrix elements and thresholds of each layer so that the error Q is minimized. Methods for optimizing neural networks are well known, such as backpropagation, so a description of these will be omitted.

[0031] FIG. 7 is a diagram explaining the procedure for estimating a detailed weather classification using the results of learning according to the procedure in FIG. 6. The power control device 1 inputs solar radiation forecast data to the neural network constructed according to FIG. 6. The output from each neuron in the output layer is obtained using the same procedure as during learning. For example, if the output from the first neuron in the output layer is equal to or greater than the threshold and the output from the second neuron is less than the threshold, the estimation result by the neural network is "1" or "0", i.e., weather code 11. This results in an estimation result of the detailed weather classification.

[0032] The power control device 1 learns in advance the correlation between the expected solar radiation and the solar radiation forecast data for each detailed weather classification. The power control device 1 estimates the solar radiation for the solar cell using the correlation corresponding to the estimated detailed weather classification. The power control device 1 can predict the power generation amount of the solar cell using the estimated solar radiation. The expected solar radiation can be estimated using the output current and output voltage of the solar cell. Any publicly known technology can be used as the estimation method, and examples include those described in Patent Application No. 2020-127908 and Patent Application No. 2021-128374.

[0033] FIG. 8 is a diagram illustrating the relationship between the output value of the hidden layer neuron in the neural network of FIG. 6 and the wheeling imbalance amount. The hidden layer neuron calculates the output value using a sigmoid function. The output value is shown on the vertical axis of the upper graph of FIG. 8. The inventors have found that this sigmoid function value correlates with the fluctuation range of the amount of solar radiation in one day. In the present invention, this correlation is utilized to estimate the fluctuation range of the amount of solar radiation from the neural network of FIG. 6.

[0034] The larger the sigmoid function value of the hidden layer neuron, the larger the fluctuation range of the solar radiation on that day. The fluctuation range here is either (a) the largest absolute difference between the solar radiation forecast value and the solar radiation actual value at each time, or (b) the sum of the absolute differences between the solar radiation forecast value and the solar radiation actual value at each time for all times. However, since both have almost the same tendency, and on days when (a) is large, (b) is generally also large, either (a) or (b) may be used.

[0035] On a day when the fluctuation range of the amount of solar radiation is large, the difference between the power that was scheduled to be dispatched (planned transmission power) and the power that was actually dispatched (actual transmission power), i.e., the transmission imbalance, is also large, and the imbalance power amount, which is the time integral of the difference, is also large. Therefore, the sigmoid function value of the hidden layer neuron is correlated with the fluctuation range of the amount of solar radiation on that day, and the fluctuation range of the amount of solar radiation is further correlated with the imbalance power amount. This makes it possible to estimate the imbalance power amount on that day using the sigmoid function value of the hidden layer neuron. The relationship between the sigmoid function value and the imbalance power amount is set, for example, by previously associating the maximum value of the sigmoid function value (vertical axis 1.0 in the upper part of Figure 8) with the maximum value of the imbalance power amount (horizontal axis 2.0) based on actual values, etc.

[0036] Point (1) in the upper graph of Figure 8 is the sigmoid function value on a day with a moderate fluctuation in solar radiation. Therefore, the difference between the solar cell's predicted power generation value (power generation plan) and the actual power generation value also fluctuates moderately from hour to hour. The middle graph of Figure 8 shows this situation. The imbalance power amount on this day is estimated to be 1.15 [kWh] from the horizontal axis of the graph. Point (2) in the upper graph of Figure 8 is the sigmoid function value on a day with a large fluctuation in solar radiation, and the lower graph of Figure 8 shows the power generation plan and actual power generation on this day. Similarly, the imbalance power amount on this day is estimated to be 1.47 [kWh] from the horizontal axis of the graph.

[0037] We will now add a bit more about the fact that the output values ​​of hidden layer (intermediate layer) neurons are correlated with the range of fluctuations in insolation. For example, on a clear day, the fluctuations in insolation are relatively small, whereas on a clear to cloudy day, the fluctuations in insolation are relatively large. When a weather code is determined based on the value input from the intermediate layer to the output layer, the output from the intermediate layer is considered to reflect this fluctuation in insolation. In other words, in the process of training a neural network to estimate a weather code, the output value of the intermediate layer is considered to be correlated with the range of fluctuations in insolation via the weather code. In the present invention, we have focused on this point and confirmed that the output of hidden layer neurons is actually configured in this way. Figure 8 is based on this idea.

[0038] The relationship between the sigmoid function, the fluctuation range, and the imbalance amount is considered to differ for each weather code. Therefore, a data table or the like that defines the relationship between them may be prepared in advance, and the insolation fluctuation range and the imbalance amount may be estimated by referring to the data table. For example, this data table may be prepared in advance for each insolation fluctuation pattern (i.e., detailed weather code) such as DAY1 to DAY4 described later, and the insolation fluctuation range and the imbalance amount may be estimated by referring to the data table corresponding to the estimated weather code. This data table may be used in combination with a neural network as an estimation model for the weather code and insolation fluctuation range.

[0039] 9A shows an example of predicted values ​​of solar radiation for four days. In the following, an example of predicting the range of fluctuation in solar radiation for each day will be described using this predicted value of solar radiation as an example.

[0040] FIG. 9B shows an example of estimating the insolation fluctuation range from the output of hidden layer neurons. The neural network described in FIG. 6-FIG. 7 outputs detailed weather classification for each day (DAY1-DAY4 in FIG. 9A). In addition, the hidden layer neurons of the same neural network represent the insolation fluctuation range for each day as described in FIG. 8. The power control device 1 uses this to estimate the insolation fluctuation range for each of DAY1-DAY4. Furthermore, the imbalance power amount is estimated from the insolation fluctuation range. In the example described in FIG. 8, the larger the sigmoid function value, the smaller the insolation fluctuation. Therefore, even if the weather code is the same for a day, the larger the output value of the hidden layer neurons, the larger the insolation fluctuation.

[0041] 10A shows the fluctuation over time of the power generated by the solar cell on DAY 1 or its predicted value. Here, the actual value of the solar cell installed in one of the power generation bases is shown. The same applies to the following examples.

[0042] Figure 10B shows the rate of change in the power generated by the solar cell on DAY 1 or its predicted value. The fluctuation range of the power generated at the current time compared to the power generated at the previous time was calculated every minute. The rated output of the solar cell was set to 100%, and this fluctuation range was normalized to obtain the rate of change. At each time, the rate of change was within 10%.

[0043] Figure 10C shows the result of replacing Figure 10B with the rate of change every 5 minutes. For example, the rate of change every 5 minutes can be calculated by averaging the rate of change every 1 minute over 5 minutes.

[0044] FIG. 10D shows an example of the expected shortage imbalance [%] against the rated power (100%) calculated for each predicted solar radiation amount. The data points are plots of the shortage imbalance at each time. The imbalance in the amount of power transmitted to a demand base is represented by the difference between the transmission planned power and the transmission actual power. The transmission planned power can be calculated based on the power generation forecast of the solar cell and the demand forecast at the demand base. The power control device 1 uses these to calculate the shortage amount of the transmission actual power against the transmission planned power. The calculation result is calculated as a percentage of the solar cell rated power. In the example shown in FIG. 10D, like the solar radiation fluctuation range, the shortage imbalance was within 10% of the rated power at all times.

[0045] The horizontal axis of Fig. 10D shows the solar radiation forecast. The shortage imbalance is correlated with the forecast solar radiation, and in some cases the relationship between the two is expressed by a function, as in DAY 4 described below. Therefore, the solar radiation forecast is taken as the horizontal axis of Fig. 10D, and the shortage imbalance is plotted for each solar radiation forecast at each time. However, as shown in the figure, for DAYS 1 to 3, the upper limit of the shortage imbalance can be considered to be a constant value regardless of fluctuations in the forecast solar radiation.

[0046] As shown in Figure 10D, the upper limit of the shortage imbalance at each time is 10% of the rated output of the solar cell. This is used as the imbalance threshold described later, and when the storage battery discharges beyond this threshold, it is determined that the output of the solar cell has dropped below the standard. The imbalance threshold is in units of [kWh], since it is compared with the discharge amount of the storage battery. In this example, the shortage imbalance is calculated every 5 minutes, so 10% of the rated [kW] × (1 / 12) [h] is defined as the imbalance threshold [kWh] on DAY1. Specific applications of the imbalance threshold will be described later.

[0047] 11A to 11D show the results of calculating the power change rate and the power shortage imbalance on DAY2 in the same manner as in FIG. 10A to FIG. 10D. Both the power change rate and the power shortage imbalance were within 20% of the rated output of the solar cell. Therefore, 20% of the rated output [kW] × (1 / 12) [h] is defined as the imbalance threshold [kWh] on DAY2.

[0048] 12A to 12D show the results of calculating the power change rate and the power imbalance on DAY3 in the same manner as in FIG. 10A to FIG. 10D. Both the power change rate and the power imbalance were within 8% of the rated output of the solar cell. Therefore, 8% of the rated output [kW] × (1 / 12) [h] is defined as the imbalance threshold [kWh] on DAY3.

[0049] 13A to 13D show the results of calculating the power change rate and the shortage imbalance for DAY4 in the same manner as in FIG. 10A to FIG. 10D. As shown in FIG. 13A to FIG. 13B, the range of fluctuations in the amount of solar radiation and the range of fluctuations in the power generation are the largest on DAY4 compared to DAY1 to DAY3, and these values ​​vary greatly from time to time. However, as shown in FIG. 13C, the rate of power change tends to peak at a certain time and then decrease linearly. Therefore, the relationship of the shortage imbalance to the solar radiation forecast can also be expressed by a linear function. In the example shown in FIG. 13D, this is expressed by a function that approximates the plot of the shortage imbalance at each time. Here, an example is shown in which a linear function of imbalance threshold=42.86×(forecasted solar radiation)+5.8 is derived. As in this example, for a weather code in which the range of fluctuations in solar radiation is larger than other weather codes, the imbalance threshold can be expressed as a function of the solar radiation forecast (typically a linear function).

[0050] As shown in Fig. 13D, the weather code with the largest fluctuation range of the insolation has a linear function relationship between the insolation prediction and the imbalance deficiency. For other weather codes, the upper limit of the imbalance deficiency can be considered to be a constant value, as explained in Figs. 10A to 12D. In other words, for weather codes with an insolation fluctuation range less than the threshold, the imbalance threshold (second reference value: corresponding to the imbalance amount threshold in S1512 described later) can be considered to be constant, and for weather codes with an insolation fluctuation range equal to or greater than the threshold, the imbalance threshold can be found based on the relationship as shown in Fig. 13D.

[0051] 14 is a process flow diagram for explaining an outline of a procedure for calculating the wheeling planned power by the power control device 1. Since the same calculation procedure is performed for each power generation base, the parent base will be explained below.

[0052] The power control device 1 estimates the fluctuation range of the amount of solar radiation at the site 1 and the fluctuation range of the power generated by the solar cell based on the fluctuation range on the day when power is scheduled to be transmitted to the demand site, using the method described in Fig. 8. Furthermore, using the procedure described in Figs. 10A to 10D, etc., it calculates the fluctuation range of the power generated by the solar cell for every 5 minutes. Based on this, it calculates the imbalance threshold value for every 5 minutes. In addition, the power control device 1 calculates the planned amount of power to be sent for every 30 minutes based on the predicted amount of power generated by the solar cell and the predicted power demand at the demand site.

[0053] The power control device 1 calculates the following by adding up the values ​​calculated as above for each base for all bases. (a) The sum of the fluctuation range of solar cell power generation every 5 minutes for all power generation bases is set as the fluctuation range threshold of solar cell output every 5 minutes in the power interchange system. (b) The sum of the imbalance thresholds every 5 minutes for all power generation bases is set as the imbalance threshold for every 5 minutes in the power interchange system. (c) The sum of the planned transmission power amount every 30 minutes for all power generation bases is set as the planned transmission power amount every 30 minutes in the power interchange system.

[0054] 15A and 15B are flowcharts illustrating a procedure for determining the power to be transmitted to a demand base by the power interchange system. This flowchart is executed by the power control device 1. Each step in FIG. 15 will be described below.

[0055] (FIG. 15A: Step S1501) The calculation unit 11 acquires the scheduled transmission power for every 30 minutes for all the power generation bases and sums them up. This value corresponds to (c) described in FIG.

[0056] (FIG. 15A: Step S1502) The calculation unit 11 calculates the scheduled transmission power for each hour by doubling the scheduled transmission power acquired in S1501. The calculation unit 11 further multiplies the value by the likelihood c (<1). This allows the power interchange system to operate with a surplus in the transmission capacity.

[0057] (FIG. 15A: Step S1503) The calculation unit 11 obtains the sum of the power generated by the solar cells for each power generation base. The power generation output in this step is a value per minute. The calculation unit 11 further obtains the sum of the power demand at the demand base.

[0058] (FIG. 15A: Step S1504) The calculation unit 11 calculates the wheeling performance for each time interval (i.e., one minute) of S1503 based on the data acquired in S1503. Specifically, the wheeled power can be calculated by subtracting the power demand for that time interval from the sum of the solar cell output at each power generation base acquired in S1503.

[0059] (FIG. 15A: Step S1505) The calculation unit 11 compares the planned transmission power calculated in S1502 with the actual transmission power calculated in S1504. If the planned transmission power is greater, the process proceeds to S1506, otherwise the process proceeds to S1507.

[0060] (FIG. 15A: Step S1506: Part 1) The calculation unit 11 determines the result of subtracting the actual transmission power from the planned transmission power as the power to be discharged from the storage battery. In this way, the shortage of power actually generated by the solar cell is compensated for by discharging from the storage battery.

[0061] (FIG. 15A: Step S1506: Part 2) The calculation unit 11 specifies the sum of the scheduled transmission power and the power demand as the power to be generated by the solar cells. The calculation unit 11 allocates the calculated power to each power generation base. Specifically, the total rated output of the solar cells in the entire power interchange system is used as a standard, and the power to be generated by each power generation base is apportioned based on the rated output of the solar cells at each base.

[0062] (FIG. 15A: Step S1507) In this step, the actual transmission power is greater than the scheduled transmission power, that is, the output power of the solar cell has a margin. This corresponds to the solar cell operating at an output power lower than the maximum power point. Therefore, the calculation unit 11 calculates the output power (hereinafter referred to as potential power) that is assumed to be possible to output by the solar cell operating at the maximum power point. The potential power can be calculated by determining the maximum power point of the solar cell.

[0063] (FIG. 15A: Step S1508: Part 1) The calculation unit 11 subtracts the planned power to be wheeled from the actual power to be wheeled, and adds the potential power to the result to determine the power to be charged to the storage battery. A predetermined coefficient may be further multiplied. This allows the surplus power actually generated by the solar cell to be consumed by charging the storage battery.

[0064] (FIG. 15A: Step S1508: Part 2) The calculation unit 11 determines the output power of the solar cell. In this step, since the solar cell may have a power generation surplus, the output power is determined taking that surplus into consideration. In order to comply with the scheduled transmission power, it is necessary to specify at least the result of adding the demand to the scheduled transmission power as the solar cell output. The calculation unit 11 allocates the calculated output power to each power generation base. Specifically, it is sufficient to allocate it based on the rated output, as in S1506.

[0065] (FIG. 15A: Step S1509) The calculation unit 11 instructs the output power determined in S1506 or S1508 as a command value to the driving device of the solar cell (a device constituted by a converter in the example of Figs. 1A-1B). The calculation unit 11 further instructs the charging / discharging power determined in S1506 or S1508 as a charge / discharge command value to the driving device of the storage battery (a device constituted by a converter in the example of Figs. 1A-1B).

[0066] (FIG. 15A: Step S1510) The calculation unit 11 performs steps S1502 to S1509 for five minutes. After each five minutes, the process proceeds to step S1511 and onward.

[0067] (FIG. 15B: Step S1511) The calculation unit 11 calculates the actual value of the output fluctuation [kW] of the solar cell every 5 minutes. The output here is the total sum of the solar cell output at all power generation sites. The calculation unit 11 also obtains the actual value of the discharge capacity [kWh] of the storage battery every 5 minutes.

[0068] (FIG. 15B: Step S1512) The calculation unit 11 judges whether or not the power demand at the demand base is fluctuating significantly. There are two judgment conditions as follows. If both conditions 1 and 2 are satisfied, it is judged that the power demand at the demand base is fluctuating significantly. If both conditions 1 and 2 are satisfied, the process proceeds to S1513, and otherwise the process proceeds to S1514.

[0069] (FIG. 15B: Step S1512: Condition 1) The calculation unit 11 judges whether or not the output fluctuation of the solar cell calculated in S1511 exceeds the fluctuation width threshold of the solar cell output described in Fig. 14. If it exceeds the threshold, the condition 1 is satisfied.

[0070] (FIG. 15B: Step S1512: Condition 2) The calculation unit 11 judges whether or not the actual value of the discharge capacity of the storage battery calculated in S1511 exceeds the imbalance amount threshold value described with reference to Fig. 14. If it exceeds the imbalance amount threshold value, the second condition is satisfied.

[0071] (Figure 15B: Step S1512: Supplementary Note 1) In this flowchart, the process proceeds to S1513 only when both conditions 1 and 2 are satisfied, but the process may proceed to S1513 if at least either condition 1 or 2 is satisfied. This is because both of these conditions indicate that the solar cell output is insufficient. On the other hand, if both conditions 1 and 2 are satisfied, it is more likely that there is an output shortage, so if the criteria are to be applied strictly, the process may proceed to S1513 only if both conditions are satisfied.

[0072] (Figure 15B: Step S1512: Supplementary Note 2) As described in Fig. 10A to Fig. 13D, the fluctuation range threshold and imbalance amount threshold in this step are set to different values ​​for each estimated weather code. Furthermore, the set fluctuation range threshold and imbalance amount threshold are used to set the likelihood c (i.e., to control the power transmitted to the demand base). Therefore, in this step, the imbalance is estimated using the weather code and fluctuation range estimated using a neural network, and the transmission power is calculated using the estimated imbalance.

[0073] (FIG. 15B: Step S1513) The calculation unit 11 resets the likelihood c based on the ratio of the discharge capacity result to the imbalance threshold (discharge result / imbalance threshold), as necessary. In this step, the discharge result is greater than the imbalance threshold (S1512: Yes), so the likelihood c is reset to a larger value in this step. By increasing the likelihood c, the scheduled power to be sent in S1502 is increased, so the system is controlled to increase the amount of discharge from the storage battery in S1505-S1506 (or, instead of or in combination with this, increase the solar cell output). This prevents the amount of discharge from exceeding the imbalance threshold at a later time. The likelihood c is assumed to be 1.0 or less, but may temporarily exceed 1.0.

[0074] (FIG. 15B: Step S1514) The calculation unit 11 maintains the likelihood c at the current setting value. This is because, when either the condition 1 or the condition 2 in S1512 is not satisfied, it is considered that at least one of the discharge capacity of the storage battery or the output fluctuation of the solar cell still has a margin. In other words, when both the condition 1 and the condition 2 are satisfied, it means that it is considered that the transmission margin of the power interchange system is not sufficient.

[0075] (FIG. 15B: Step S1515) The calculation unit 11 returns to S1501 every 30 minutes to repeat the same process, or alternatively, the process may end at this step and re-execute the process every 30 minutes.

[0076] 16 is an example of a user interface provided by the calculation unit 11. The user interface can be presented, for example, on a display provided in the power control device 1. The user interface can present, for example, an estimated solar radiation fluctuation range, an estimated weather code, a calculated transmission power, a calculated fluctuation range threshold and an imbalance threshold, and the like.

[0077] <Modifications of the present invention> The present invention is not limited to the above-described embodiment, and includes various modified examples. For example, the above-described embodiment has been described in detail to clearly explain the present invention, and is not necessarily limited to those having all of the configurations described. In addition, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. In addition, it is possible to add, delete, or replace a part of the configuration of each embodiment with another configuration.

[0078] In the above embodiment, an example was described in which the output value of the second neuron among the hidden layer neurons 1 to 3 shown in Fig. 9B is used to estimate the solar radiation fluctuation range, but which hidden layer neuron is used can be designed appropriately. Furthermore, the output values ​​of the output layer neurons can be appropriately combined to estimate the solar radiation fluctuation range as necessary.

[0079] In the above embodiment, the imbalance threshold is set only for the shortage imbalance. Since the excess imbalance is assumed to be smaller than the shortage imbalance, it is assumed that if the imbalance threshold for the shortage imbalance is determined, it is also possible to deal with the excess imbalance. However, if necessary, a separate imbalance threshold may also be set for the excess imbalance, and the output excess or shortage of the solar cell may be determined using each of the thresholds for the shortage imbalance and the excess imbalance.

[0080] In the above embodiments, the calculation unit 11 can be configured by hardware such as a circuit device that implements its functions, or can be configured by a calculation device such as a CPU (Central Processing Unit) executing software that implements its functions.

[0081] In the above embodiment, the sigmoid function is used as the output function of the hidden layer neurons (internal variables), but other similar functions may be used. For example, it is possible to use a function other than the sigmoid function, in which the relationship between the input and the output is nonlinear and the output increases monotonically with an increase in the input.

[0082] In the above embodiment, a neural network is exemplified as an estimation model of the weather code and the insolation fluctuation range, but other estimation models may be used. However, the estimation model must be configured to output the weather code and to have an internal variable that correlates with the insolation fluctuation range (and the imbalance amount). As long as the estimation model is configured in this way, estimation models other than a neural network can be used. [Explanation of symbols]

[0083] 1: Power control device 11: Arithmetic section 12: Storage part

Claims

1. A power interchange system in which power generated by a power generation system composed of solar cells is transmitted between bases via a power transmission network, A calculation unit is provided that estimates a weather classification when the power generation system generates power by using an estimation model that estimates a weather classification by providing a predicted solar radiation value as an input; The estimation model is configured to have, as an internal variable, a variable correlated with a fluctuation range of the amount of solar radiation in one day, The calculation unit calculates transmission power to be transmitted from the power generation system to a demand base using the weather classification estimated using the estimation model and the fluctuation range estimated using the internal variable. The power interchange system is characterized by:

2. The estimation model is an input layer for receiving the solar radiation forecast value; an output layer that outputs the weather classification; an intermediate layer disposed between the output layers; Equipped with The internal variables are configured as variables that the intermediate layer has, The calculation unit estimates the fluctuation range by using the internal variables of the intermediate layer.

2. The power interchange system according to claim 1 .

3. the calculation unit estimates an imbalance between a power generation forecast value and a power generation actual value of the power generation system by using the weather classification estimated by using the estimation model and the fluctuation range estimated by using the internal variable; The calculation unit calculates the transmission power using the estimated imbalance.

2. The power interchange system according to claim 1 .

4. the estimation model is configured such that the value or range of the internal variable in the intermediate layer is different for each weather classification output by the output layer; The calculation unit estimates the fluctuation range corresponding to the weather classification output by the output layer based on the internal variables.

3. The power interchange system according to claim 2.

5. The power generation system further includes a storage battery. The calculation unit acquires a planned power representing power that the power generation system is scheduled to output to the power transmission network during a power transmission period in which the power transmission is performed, The calculation unit acquires actual power representing power output by the power generation system to the power transmission network during the power transmission period; the calculation unit calculates power to be charged or discharged from the storage battery based on a second difference between the planned power and the actual power during the power transmission period; The calculation unit calculates the power that needs to be generated by the solar cell during the power transmission period based on the second difference.

2. The power interchange system according to claim 1 .

6. The calculation unit acquires a power demand during the power transmission period, the calculation unit calculates the actual power by subtracting the power demand from a result of multiplying an output voltage of the solar cell by an output current of the solar cell; When the planned power is greater than the actual power, the calculation unit determines a difference between the planned power and the actual power as power to be discharged from the storage battery; When the planned power is greater than the actual power, the calculation unit calculates a value obtained by proportionally dividing the sum of the planned power and the power demand for each power generation base based on the rated output of the solar cell as the power that needs to be generated by the solar cell at the power generation base.

6. The power interchange system according to claim 5.

7. The calculation unit acquires a power demand during the power transmission period, the calculation unit calculates the actual power by subtracting the power demand from a result of multiplying an output voltage of the solar cell by an output current of the solar cell; When the actual power is equal to or greater than the planned power, the calculation unit determines the power to be charged to the storage battery based on a difference between the actual power and the planned power.

6. The power interchange system according to claim 5.

8. the calculation unit calculates the second difference using a result obtained by multiplying the planned power by a coefficient representing a rate at which a power generation capacity of the solar cell is suppressed; The calculation unit determines whether or not the coefficient needs to be adjusted by using a determination criterion for determining whether or not the amount of power generated by the solar cell is insufficient for the planned power, When the calculation unit determines that the power generation capacity of the solar cell is insufficient based on the determination criterion, the calculation unit adjusts the coefficient so as to increase the capacity of the power generation system to transmit power to the demand base by relaxing the restriction.

6. The power interchange system according to claim 5.

9. The criteria are: whether or not a fluctuation amount per unit time of the power generation amount of the solar cell exceeds a first reference value; whether or not the discharge amount per unit time of the storage battery exceeds a second reference value; It is composed of The calculation unit adjusts the coefficient so as to increase the capacity of the power generation system to transmit power to the demand base when at least one of the following conditions is satisfied: a fluctuation amount per unit time of the power generation amount of the solar cell exceeds the first reference value, or a discharge amount per unit time of the storage battery exceeds the second reference value.

9. The power interchange system according to claim 8.

10. The calculation unit maintains the coefficient without adjusting it when a fluctuation amount of the power generation amount of the solar cell per unit time is equal to or less than the first reference value and a discharge amount of the storage battery per unit time is equal to or less than the second reference value.

10. The power interchange system according to claim 9.

11. The calculation unit divides the discharge amount per unit time of the storage battery by the second reference value, and then multiplies the result by a predetermined adjustment coefficient, thereby adjusting the coefficient so as to increase the capacity of the power generation system to transmit power to the demand base.

10. The power interchange system according to claim 9.

12. The calculation unit sets a constant value regardless of a time period of a day as the second reference value for a first weather classification in which the fluctuation range is less than a threshold value, For a second weather classification in which the fluctuation range is equal to or greater than the threshold value, the calculation unit sets, as the second reference value, a value that changes according to a predicted amount of solar radiation for each time period of a day.

10. The power interchange system according to claim 9.

13. The power generation system includes: A first solar cell provided at the first power generation site; A storage battery provided at the first power generation base; A second solar cell provided at the second power generation site; It is composed of The calculation unit estimates the weather classification and the fluctuation range for each of the first power generation base and the second power generation base, The calculation unit calculates the transmission power based on the results of the estimation at each of the first power generation base and the second power generation base.

2. The power interchange system according to claim 1 .

14. The calculation unit outputs a user interface; The user interface is configured to present the transmission power and the fluctuation range.

2. The power interchange system according to claim 1 .

15. The estimation model is configured to calculate the internal variables according to a nonlinear and monotonically increasing function.

2. The power interchange system according to claim 1 .

Images