Wind turbine location optimization device, wind turbine location optimization method, and program

Abstract

To provide a windmill arrangement optimization device which can derive a proper arrangement spot of a windmill in a short time.SOLUTION: A windmill arrangement optimization device according to one embodiment includes a simulation unit, a prediction model construction unit, a windmill arrangement determination unit, and a determination unit. The simulation unit simulates a speed of wind received by the windmill when the windmill is arranged in an area. The prediction model construction unit calculates, based on the wind speed, an amount of electric power generated by the windmill and an extreme value wind speed by regression analysis and creates a relational expression between a position coordinate of the windmill and at least one of the amount of generated electric power and the extreme value wind speed as a prediction model. The windmill arrangement determination unit determines a position coordinate, at which the amount of generated electric power is larger than a value of a preset amount of generated electric power, as an arrangement candidate spot based on the predication model. The determination unit determines that a spot, where the amount of generated electric power is maximum and the extreme value wind speed is smaller than a threshold value, among the arrangement candidate spots is proper.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] An embodiment of the present invention relates to a wind turbine location optimization device, a wind turbine location optimization method, and a program. [Background technology]

[0002] Wind turbine generators (WTG) using wind turbines are generally known to be cost-effective in eliminating fossil fuels and reducing CO2 emissions. For this reason, wind power generation facilities are increasing in number, from a few wind turbines to large wind farms (WF) consisting of dozens or more wind turbines.

[0003] In wind power generation facilities, the placement of wind turbines is important to ensure their sound operation. The placement of wind turbines is subject to various constraints, such as wind conditions. Therefore, when considering where to place a wind turbine, these constraints must also be taken into account. As a result, determining the optimal placement location for a wind turbine is laborious and takes a lot of time. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 5186691 [Patent Document 2] Japanese Patent Application Publication No. 2019-15236 Summary of the Invention [Problem to be solved by the invention]

[0005] The problem to be solved by the present invention is to provide a wind turbine location optimization device, a wind turbine location optimization method, and a program that are capable of deriving an appropriate wind turbine location point in a short period of time. [Means for solving the problem]

[0006] A wind turbine location optimization device according to one embodiment includes a simulation unit that simulates wind conditions within an area where wind turbine location is being considered; a prediction model construction unit that uses the simulation results of the simulation unit to create a prediction model based on wind conditions for wind turbine location; a wind turbine location determination unit that determines at least one wind turbine location candidate site based on the prediction model; and a determination unit that determines whether the candidate site is appropriate. The simulation unit simulates the wind speed that the wind turbine would experience if it were to be located within the area. The prediction model construction unit calculates the amount of power generated by the wind turbine and extreme wind speeds based on the wind speeds using regression analysis, and creates a prediction model that represents a relationship between the position coordinates of the wind turbine and at least one of the amount of power generated and the extreme wind speed. The wind turbine location determination unit determines, based on the prediction model, as a candidate site for location, a location coordinate where the amount of power generated is greater than a predetermined value. The determination unit determines as appropriate a site among the candidate sites where the amount of power generated is maximum and the extreme wind speed is smaller than a threshold. [Effects of the Invention]

[0007] According to one embodiment, it is possible to derive an appropriate location for the wind turbine in a short time. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a block diagram showing the configuration of a wind turbine location optimization device according to a first embodiment. FIG. [Figure 2] FIG. 2 is a diagram illustrating an example of a wind condition simulation model used in a simulation unit. [Figure 3] FIG. 1 is a diagram illustrating an example of a governing equation. [Figure 4] FIG. 1 is a diagram illustrating an example of a wind turbine. [Figure 5] 3 is an example of a flowchart of a calculation process executed by the wind-turbine placement optimization device according to the first embodiment. [Figure 6] FIG. 4 is a diagram illustrating an example of wind condition data. [Figure 7]FIG. 1 is a diagram showing an example of the distribution of AEP and extreme wind speeds created using a wind condition prediction model. [Figure 8] FIG. 10 is a block diagram showing the configuration of a wind turbine location optimization device according to a second embodiment. [Figure 9] 10 is an example of a flowchart of a calculation process executed by the wind-turbine location optimization device according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Note that the embodiments described below are merely examples of embodiments of the present invention, and the present invention should not be construed as being limited to these embodiments. Furthermore, in the drawings referred to in this embodiment, identical or similar reference numerals are used to designate identical parts or parts having similar functions, and repeated explanations thereof may be omitted. Furthermore, for convenience of explanation, the dimensional ratios of the drawings may differ from the actual ratios, and some components may be omitted from the drawings.

[0010] (First embodiment) Fig. 1 is a block diagram showing the configuration of a wind turbine location optimization device according to a first embodiment. The wind turbine location optimization device 1 shown in Fig. 1 is a device that calculates and outputs an optimal location for a wind turbine based on wind conditions, land conditions, and social conditions. Here, wind conditions include, for example, the annual energy production (AEP) obtained from the wind turbine, extreme wind speed V ref , V e50 These include the index I indicating the state of turbulence, the wind upflow angle of the wind flowing into the wind turbine, an index indicating the change in wind speed in the vertical direction during a storm, and the wake effect on the wind turbine on the downwind side from the wind turbine on the upwind side. Land conditions also include constraints such as distance from buildings, roads, rivers, etc., restrictions on light and sound pollution, restrictions on construction such as slopes and ground conditions, and constraints such as land rights. Social conditions also include constraints such as flora and fauna protection areas, scenic protection areas, and cultural heritage protection areas.

[0011] As shown in Fig. 1, the wind turbine location optimization device 1 according to this embodiment is configured to include a wind turbine location calculation unit 10, an input unit 20, and a display unit 30. The wind turbine location calculation unit 10 calculates the location of wind turbines. The detailed configuration of the wind turbine location calculation unit 10 will be described later.

[0012] The input unit 20 is realized by a mouse, keyboard, trackball, switches, buttons, joystick, etc. that accepts various input operations from the operator and outputs the accepted input information to the wind turbine placement calculation unit 10. The input unit 20 accepts input operations such as topographical data, designation of the area for which wind turbine placement is being considered, wind inflow conditions such as wind direction, wind speed, and turbulence intensity, information about the wind turbines such as the wind turbine shape and the number of wind turbines to be installed, and social conditions.

[0013] The display unit 30 is configured by a liquid crystal display, a CRT (Cathode Ray Tube) display, etc. that displays various information. The display unit 30 displays an image showing the wind turbine arrangement calculated by the wind turbine arrangement calculation unit 10, for example.

[0014] The detailed configuration of the wind turbine placement calculation unit 10 will be described below. The wind turbine placement calculation unit 10 has a calculation processing unit 102, a determination unit 103, and a storage unit 104. The calculation processing unit 102 further has a simulation unit 102a, a prediction model construction unit 102b, and a wind turbine placement determination unit 102c. In this embodiment, the processing functions performed by the simulation unit 102a, the prediction model construction unit 102b, and the wind turbine placement determination unit 102c are stored in the storage unit 104 in the form of programs executable by a computer.

[0015] The arithmetic processing unit 102 is a processor that reads out programs from the storage unit 104 and executes them to realize functions corresponding to the programs. In other words, the processing circuit in the state in which each program has been read out has each function shown in the arithmetic processing unit 102. Here, the term "processor" refers to circuits such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)).

[0016] The simulation unit 102a simulates wind conditions in an area where the placement of wind turbines is being considered using, for example, MASCOT or RIAM-COMPACT (registered trademark). At this time, the simulation unit 102a samples the position coordinates for placing multiple wind turbines using random numbers (quasi-random numbers). Furthermore, for any given wind turbine type, the simulation unit 102a samples a wind turbine placement that has a relatively large total amount of power generation using a greedy algorithm or the like, or samples a position from the sampled wind turbine placements that is the shortest distance from the current optimal placement.

[0017] FIG. 2 is a diagram illustrating an example of a wind simulation model used by the simulation unit 102a. The wind simulation model 40 shown in FIG. 2 includes an inflow wind 50, an analysis center 41, a minimum analysis grid range 42, a target region 43, an analysis region 44, an additional region 45, an upstream buffer region 46, a downstream buffer region 47, and a side buffer region 48. The inflow wind 50 is wind flowing in from the upwind side of the wind turbine. The analysis center 41 is the central position of the analysis of the wind model and corresponds to the wind turbine position 60. The minimum analysis grid range 42 is the smallest constituent unit of the target region 43 of the wind simulation. The analysis region 44 is a region that entirely surrounds the target region 43. The additional region 45 is a region added to the upwind side of the analysis region 44. The upstream buffer region 46 is a region adjacent to the additional region 45 on the upwind side. The downstream buffer region 47 is a region adjacent to the analysis region 44 on the downwind side. The side buffer areas 48 are areas adjacent to the sides of the analysis area 44 and the additional area 45. Each area of ​​the wind condition simulation model 40 reflects the topographical data received by the input unit 20 and the area designation for considering wind turbine placement. In addition, wind inflow conditions such as wind direction, wind speed, and turbulence intensity received by the input unit 20 are used in the analysis.

[0018] The simulation unit 102a generates a wind condition simulation model 40 as shown in Fig. 2. More specifically, the simulation unit 102a generates the wind condition simulation model 40 for calculating physical quantities based on the Navier-Stokes equations, which are governing equations according to this embodiment. Here, the governing equations are mathematical equations that express the physical laws within the mesh model.

[0019] Figure 3 shows an example of the governing equations. As shown in Figure 3, the governing equations are the Navier-Stokes equations. In the equations shown in Figure 3, ρ represents the density of the fluid, ν represents the dynamic viscosity of the fluid, and μ represents the viscosity of the fluid. The Navier-Stokes equations also include an external force term F, which is the force acting from the wind turbine rotor (described below). The external force term F includes external forces Fx, Fy, and Fz in the x, y, and z directions. The x direction is parallel to the wind direction, the y direction is perpendicular to the x direction, and the z direction is the vertical direction perpendicular to the x and y directions.

[0020] FIG. 4 is a diagram showing an example of a wind turbine. The wind turbine 200 shown in FIG. 4 has multiple blades 200a, a nacelle 200b, a tower 200c, and a hub 200d. The multiple blades 200a are mounted on the hub 200d at intervals in the rotational direction. The nacelle 200b is mounted on top of the tower 200c. The tower 200c extends in the vertical direction (z direction) at wind turbine position 60. The hub 200d is attached to the front of the nacelle 200b. In the wind turbine 200 configured in this manner, when each blade 200a rotates due to wind force, the rotational force causes a generator provided in the nacelle 200b to generate electricity.

[0021] The prediction model construction unit 102b constructs a prediction model for wind conditions using Gaussian process regression, neural network, random forest, support vector regression, etc. The wind condition parameters of this prediction model are a model in which the position coordinates of one wind turbine are used as explanatory variables, and for example, the above-mentioned AEP, extreme wind speed V ref , V e50 The model includes wind conditions such as the index I indicating the state of turbulence, the upflow angle, an index indicating the change in wind speed in the vertical direction during a storm, and the wake effect on the downwind wind turbine from the upwind wind turbine. The wake effect is modeled using the position coordinates of the downwind wind turbine and the distance and angle between the downwind wind turbine and the nearest wind turbine as explanatory variables.

[0022] The wind turbine location determination unit 102c discretizes the position coordinates of the wind turbines using random numbers (quasi-random numbers), arbitrary grid points, or points parallel to the contour lines of the terrain, and formulates the problem as an integer linear programming problem in the discretized space to determine the position coordinates of multiple wind turbines. Specifically, the design variables are 0-1 variables that indicate whether or not wind turbines at multiple candidate coordinates are to be used. The AEP and V of the candidate coordinates are ref , V e50 is calculated using a prediction model. This allows for more coordinates to be considered as candidates than the number of wind turbine coordinates simulated, making it possible to determine a wind turbine location that produces the greatest amount of power generation with fewer simulations. Alternatively, the wind turbine location determination unit 102c can solve the problem using a greedy method. Specifically, a search is performed by selecting one wind turbine at a time from the wind turbine location, changing only the selected wind turbine coordinates so that the total AEP increases, while leaving the other wind turbine coordinates unchanged, until the wind turbine location no longer requires updating. Furthermore, it is also possible to solve the problem using a gradient method or the like without discretizing the problem. For example, an AEP prediction model can calculate the gradient (the amount of change in AEP when the wind turbine position coordinates move slightly), so the wind turbine location that produces the greatest AEP can be determined using a gradient method using this gradient. While the gradient cannot be calculated in simulations, the gradient method can be used by using a prediction model, making it possible to use the gradient method, thereby more quickly determining a wind turbine location that produces the greatest amount of power generation.

[0023] The determination unit 103 determines whether the wind turbine layout determined by the calculation processing unit 102 is an appropriate layout.

[0024] The storage unit 104 is realized by, for example, a semiconductor memory device such as RAM (Random Access Memory), flash memory, a hard disk, an optical disk, etc. The storage unit 104 has a wind condition data storage unit 104a, a land condition data storage unit 104b, a social condition data storage unit 104c, and a setting value storage unit 104d. The storage unit 104 also stores various programs.

[0025] The wind condition data storage unit 104a stores wind condition data showing the results of the simulation by the simulation unit 102a. The land condition data storage unit 104b stores data related to the land conditions described above in advance. The social condition data storage unit 104c stores data related to the social conditions described above in advance. The set value storage unit 104d stores various values ​​input through operations on the input unit 20.

[0026] 5 is an example of a flowchart of the calculation process executed by the wind turbine location optimization device 1. The calculation process of the wind turbine location optimization device 1 will be described below.

[0027] 5, first, the operator operates input unit 20 to input wind turbine information to be used in the calculation process, the area for which the placement of wind turbines 200 is being considered, the number of wind turbines to be considered, the extreme wind speed threshold value, etc. (Step S100). Here, the wind turbine information includes, for example, the height of hub 200d of wind turbine 200 and the diameter of the rotor surface formed by combining blades 200a and hub 200d. The values ​​input to input unit 20 are saved in set value storage unit 104d.

[0028] Next, the simulation unit 102a executes the wind condition simulation model 40 based on the conditions set in step S100 (step S101). The wind condition data obtained by the wind condition simulation model 40 is stored in the wind condition data storage unit 104a.

[0029] Fig. 6 is a diagram showing an example of wind condition data. The wind condition data shown in Fig. 6 shows wind speed V by wind direction and altitude at a certain point in the area considered for placement of wind turbines 200, which is divided into a grid by the minimum analytical grid range 42. In this embodiment, the simulation unit 102a creates wind condition data for each position coordinate of the analysis center 41 of the minimum analytical grid range 42.

[0030] After the simulation by the simulation unit 102a is completed, the prediction model construction unit 102b processes the wind condition data read from the wind condition data storage unit 104a using a regression analysis method such as Gaussian process regression to create a prediction model of wind conditions (step S102).

[0031] In step S102, the prediction model construction unit 102b creates a relational expression between the position coordinates of the analysis center 41 in the minimum analysis grid range 42, in other words, the coordinates of the wind turbine position 60, and the AEP or extreme wind speed.

[0032] FIG. 7 is a diagram showing an example of the distribution of AEP and extreme wind speed created using a wind condition prediction model. In FIG. 7, the AEP and extreme wind speed within the consideration area are shown in association with the coordinates of wind turbine positions 60. FIG. 7 also shows the magnitude of the AEP and extreme wind speed at wind turbine positions 60. The AEP and extreme wind speed are calculated by the prediction model construction unit 102b using wind condition data stored in the wind condition data storage unit 104a. In this case, the prediction model construction unit 102b may calculate either the AEP or the extreme wind speed, rather than both. Furthermore, the prediction model construction unit 102b may calculate not only the AEP and extreme wind speed, but also, for example, an index I indicating the state of turbulence, based on the wind condition data.

[0033] Once the prediction model construction unit 102b has finished constructing the prediction model, the wind turbine placement determination unit 102c then uses the prediction model to determine at least one or more wind turbine placement candidate sites within the placement consideration area (step S103). In step S103, the wind turbine placement determination unit 102c determines, for example, points within the placement consideration area where the AEP is greater than a preset lower limit value as wind turbine placement candidate sites.

[0034] Next, the determining unit 103 determines whether or not there is a point among the wind turbine location candidate points that satisfies the conditions that the AEP is maximum and the extreme wind speed is smaller than the threshold set in step S100 (step S104).

[0035] If a wind turbine installation candidate site exists that satisfies the above conditions, the wind turbine installation determination unit 102c determines that site as the wind turbine installation site based on the wind conditions (step S105). Note that multiple wind turbine installation sites may be determined in step S105. On the other hand, if no wind turbine installation candidate site exists that satisfies the above conditions in step S104, the wind turbine installation determination unit 102c returns to step S103. In this case, the conditions for determining wind turbine installation candidate sites and the conditions for wind turbine installation sites may be relaxed.

[0036] After determining the wind turbine placement sites based on wind conditions, the wind turbine placement determination unit 102c uses the land condition data stored in advance in the land condition data storage unit 104b and the social condition data stored in advance in the social condition data storage unit 104c to calculate the degree of influence of constraints due to land conditions and social conditions within the wind turbine placement consideration area set in step S100 (step S106). In step S106, for example, the land condition data and social condition data have constraints that are quantified in advance according to their content, and the wind turbine placement determination unit 102c calculates the degree of influence by calculating the numerical values ​​of the land condition data and social condition data (for example, by determining whether installation is possible by referencing flags assigned to coordinates, setting limits on the number of units that can be installed in a partial area, setting distance constraints from buildings and roads, etc.).

[0037] Next, the wind turbine placement determination unit 102c determines at least one or more candidate wind turbine placement sites taking into account land conditions and social conditions (step S107). In step S107, for example, the wind turbine placement determination unit 102c determines, within the wind turbine placement consideration area, points where the influence calculated in step S106 is smaller than a preset reference value as candidate wind turbine placement sites taking into account land conditions and social conditions.

[0038] Next, the determination unit 103 determines whether the wind turbine installation site determined in step S105 is appropriate for the wind turbine installation site candidate determined in step S107 (step S108). In step S108, if the wind turbine installation site determined in step S105 also corresponds to the wind turbine installation site candidate determined in step S107, the determination unit 103 determines that the wind turbine installation site determined in step S105 is a site that also satisfies the land conditions and social conditions. On the other hand, if the wind turbine installation site determined in step S105 does not correspond to the wind turbine installation site candidate determined in step S107, the determination unit 103 determines that the wind turbine installation site determined in step S105 is a site that does not satisfy the land conditions or the social conditions.

[0039] In step S108, if the wind turbine placement site determined based on the wind conditions also satisfies the land and social conditions, the display unit 30 performs a display operation that allows the operator to confirm that the wind turbine placement site is an appropriate placement site within the wind turbine placement consideration area. For example, the display unit 30 displays sites within the wind turbine placement consideration area that satisfy the wind, land, and social conditions in a different color from the other sites.

[0040] According to the present embodiment described above, the prediction model construction unit 102b constructs a prediction model based on wind conditions, which saves the effort of considering an appropriate location for the wind turbine. This makes it possible to derive an appropriate location for the wind turbine in a short amount of time.

[0041] Furthermore, in this embodiment, the wind turbine placement determination unit 102c determines candidate locations for wind turbine placement using land condition data and social condition data stored in the storage unit 104. This allows for more appropriate placement of wind turbines, as it takes into account not only wind conditions but also constraints that must be considered when actually placing a wind turbine, such as land conditions and social conditions.

[0042] In this embodiment, the wind turbine placement determination unit 102c determines a wind turbine placement site that satisfies the wind conditions within the wind turbine placement consideration area, and then determines a wind turbine placement site that satisfies the land and social conditions. However, the wind turbine placement determination unit 102c may determine a wind turbine placement site that satisfies the wind conditions after determining a wind turbine placement site that satisfies the land and social conditions. That is, in the flowchart shown in FIG. 5, the operations of steps S106 to S108 may be executed between steps S100 and S101. In this case, too, the wind turbine placement can be more optimal because it takes into account not only wind conditions but also constraints that must be considered when actually placing a wind turbine, such as land and social conditions.

[0043] (Second embodiment) 8 is a block diagram showing the configuration of a wind turbine location optimization device according to the second embodiment. The same components as those in the wind turbine location optimization device 1 according to the first embodiment described above are given the same reference numerals, and detailed explanations will be omitted.

[0044] In the wind turbine location optimization device 2 shown in Fig. 8, in addition to the components of the wind turbine location optimization device 1 according to the first embodiment, a cost data storage unit 104e is newly provided in the storage unit 104. The cost data storage unit 104e stores cost data required for installing and operating the wind turbine 200. The cost data indicates, for example, the material costs, construction costs, transportation costs, operating costs, etc. of the wind turbine 200.

[0045] 9 is an example of a flowchart of the calculation process executed by the wind turbine location optimization device 2. The calculation process of the wind turbine location optimization device 2 will be described below.

[0046] In this embodiment, first, the operations of steps S100 to S103 described in the first embodiment are executed. That is, various values ​​are input by the operator to the input unit 20, then the simulation unit 102a executes a wind condition simulation, then the prediction model construction unit 102b constructs a prediction model of wind conditions, and then the wind turbine placement determination unit 102c determines candidate wind turbine placement sites based on the wind conditions. In step S103, the wind turbine placement determination unit 102c can use, for example, NSGA-II. By solving a two-objective optimization problem of AEP and cost, it is possible to output multiple wind turbine placements that have a trade-off between AEP and cost. This installation cost can be derived based on cost data stored in the cost data storage unit 104e. The wind turbine placement determination unit 102c can also calculate the installation cost using a branch-and-bound method, Prim's method, or Esau-Williams method.

[0047] Next, in this embodiment, the determination unit 103 determines whether or not there is a location among the candidate wind turbine installation locations that satisfies the conditions that the AEP is maximum, the extreme wind speed is smaller than the threshold value set in step S100, and the installation cost of the wind turbine 200 is minimum (step S104).

[0048] After step S104, the operations of steps S105 to S108 described in the first embodiment are executed. That is, after the wind turbine location determination unit 102c determines a wind turbine location site based on wind conditions, it determines candidate wind turbine location sites based on land conditions and social conditions, and the determination unit 103 determines whether the wind turbine location site is appropriate as the candidate wind turbine location site. Finally, the display unit 30 displays the wind turbine location site that satisfies all of the wind conditions, land conditions, and social conditions.

[0049] In the present embodiment described above, as in the first embodiment, the prediction model construction unit 102b constructs a prediction model based on wind conditions, which saves the effort of considering an appropriate location for the wind turbine. This makes it possible to derive an appropriate location for the wind turbine in a short amount of time. Furthermore, in this embodiment, the wind turbine location determination unit 102c determines candidate locations for wind turbine locations based on the cost data stored in the cost data storage unit 104e. This makes it possible to optimize wind turbine location from the perspective of the entire business, taking into account not only soundness in terms of wind conditions, land conditions, and social conditions, but also profitability.

[0050] In this embodiment, there is no restriction on the order in which wind turbine installation sites that satisfy wind conditions and wind turbine installation sites that satisfy land and social conditions are determined. Therefore, the wind turbine installation determination unit 102c may determine wind turbine installation sites that satisfy wind conditions after determining wind turbine installation sites that satisfy land and social conditions.

[0051] (Third embodiment) The third embodiment will now be described. The configuration of the wind turbine placement optimization device according to this embodiment is the same as the wind turbine placement optimization device 1 according to the first embodiment or the wind turbine placement optimization device 2 according to the second embodiment, and therefore a description thereof will be omitted.

[0052] When the land conditions and social conditions described in the first embodiment change, the land condition data stored in land condition data storage unit 104b is updated, and the social condition data stored in social condition data storage unit 104c is updated. After the data is updated, executing steps S100 to S108 of the flowchart shown in Figure 5 or 9 makes it possible to optimize the placement of wind turbines 200 based on the latest land conditions and social conditions.

[0053] However, land conditions and social conditions may change frequently. Therefore, if all of the operations in steps S100 to S108 of the flowchart shown in FIG. 5 or 9 were to be repeated every time the land conditions and social conditions changed, the calculation process would take a long time and the processing load would increase. On the other hand, there are cases where changes in land conditions and social conditions do not affect the results of the simulation performed by the simulation unit 102a in step S101. In this case, the wind condition prediction model created by the prediction model creation unit 102b in step S102 is also not affected by changes in land conditions and social conditions.

[0054] Therefore, in the above case, in this embodiment, when the land condition data stored in land condition data storage unit 104b and the social condition data stored in social condition data storage unit 104c are updated in accordance with changes in the land conditions and social conditions, the wind turbine location optimization device skips steps S100 to S105 and starts operation from step S106. In other words, the wind conditions simulation is not performed, and the wind turbine location site based on the wind conditions is determined using the already created prediction model.

[0055] According to the present embodiment described above, even if land and social conditions change frequently, it is possible to shorten the time required for the calculation processing to optimize the placement of wind turbines and reduce the processing load.

[0056] In the first to third embodiments described above, a wind turbine location optimization device for appropriately locating wind turbines 200 on land has been described, but the wind turbine location optimization device according to each embodiment can also be applied to appropriately locating wind turbines 200 offshore. When wind turbines 200 are located offshore, the land conditions and social conditions will be offshore-related, such as fishing rights.

[0057] Although several embodiments have been described above, these embodiments are presented only as examples and are not intended to limit the scope of the invention. The novel system described in this specification can be embodied in various other forms. Furthermore, various omissions, substitutions, and modifications can be made to the forms of the system described in this specification without departing from the spirit of the invention. The appended claims and their equivalents are intended to cover such forms and modifications that fall within the scope and spirit of the invention. [Explanation of symbols]

[0058] 1, 2: Wind turbine placement optimization device 40: Wind simulation model 102a: Simulation Department 102b: Prediction model construction section 102c: Wind turbine placement determination part 103: Judgment section 200: Windmill

Claims

1. A simulation department that simulates wind conditions within the area where wind turbine placement is being considered; a prediction model construction unit that uses the simulation results of the simulation unit to create a prediction model based on wind conditions related to the arrangement of the wind turbines; and a wind turbine location determination unit that determines at least one candidate location for the wind turbine based on the prediction model; a determination unit that determines whether the placement candidate point is appropriate; Equipped with the simulation unit simulates a wind speed that the wind turbine will experience when the wind turbine is placed within the area; the prediction model construction unit calculates the amount of power generated by the wind turbine and the extreme wind speed by regression analysis based on the wind speed, and creates a relational expression as the prediction model between the position coordinates of the wind turbine and at least one of the amount of power generated and the extreme wind speed; the wind turbine placement determination unit determines, based on the prediction model, the position coordinates at which the amount of power generation is greater than a predetermined value for the amount of power generation, as the placement candidate point; The determination unit determines, among the candidate placement locations, a location where the amount of generated power is maximum and the extreme wind speed is smaller than a threshold value to be appropriate.

2. the simulation unit samples the position coordinates when a plurality of wind turbines are arranged, 2. The wind turbine placement optimization device according to claim 1, wherein the wind turbine placement determination unit discretizes the position coordinates when the plurality of wind turbines are to be placed, and determines the position coordinates when the plurality of wind turbines are to be placed in the discretized virtual space using linear programming.

3. The wind turbine location optimization device according to claim 1 or 2, wherein the wind turbine location determination unit determines the location candidate site based on land conditions, which are land constraints related to the location of the wind turbine, in addition to the wind conditions.

4. 4. The wind turbine location optimization device according to claim 1, wherein the wind turbine location determination unit determines the location candidate site based on social conditions that are social constraints on the location of the wind turbine, in addition to the wind conditions.

5. 5. The wind turbine placement optimization device according to claim 1, wherein when determining the candidate placement sites using NSGA-II, the wind turbine placement determination unit determines the cost associated with installing the wind turbines using one of a branch and bound method, a Prim method, or an Esau-Eilliams method, with multiple wind turbine placements involving trade-offs as a multi-objective optimization problem.

6. The wind turbine location optimization device according to claim 1 , wherein the determination unit determines whether the location candidate site is appropriate based on costs related to installation and operation of the wind turbine.

7. simulating wind conditions in an area where the placement of a wind turbine is being considered, simulating the wind speed that the wind turbine would experience if the wind turbine were to be placed in the area; creating a prediction model based on wind conditions for the arrangement of the wind turbines by regression analysis using the simulation results, calculating the amount of power generated by the wind turbines and extreme wind speeds based on the wind speeds by regression analysis, and creating a relational expression as the prediction model between the position coordinates of the wind turbines and at least one of the amount of power generated and the extreme wind speeds; determining at least one or more candidate locations for the wind turbine based on the prediction model, and determining, based on the prediction model, the position coordinates at which the amount of power generated is greater than a predetermined value for the amount of power generated, as the candidate location; a wind turbine placement optimization method for determining whether the candidate placement sites are appropriate, and determining that a site among the candidate placement sites where the amount of generated power is maximum and the extreme wind speed is smaller than a threshold value is appropriate.

8. simulating wind conditions in an area where the placement of a wind turbine is being considered, simulating the wind speed that the wind turbine would experience if the wind turbine were to be placed in the area; creating a prediction model based on wind conditions for the arrangement of the wind turbines by regression analysis using the simulation results, calculating the amount of power generated by the wind turbines and extreme wind speeds based on the wind speeds by regression analysis, and creating a relational expression as the prediction model between the position coordinates of the wind turbines and at least one of the amount of power generated and the extreme wind speeds; determining at least one or more candidate locations for the wind turbine based on the prediction model, and determining, based on the prediction model, the position coordinates at which the amount of power generated is greater than a predetermined value for the amount of power generated, as the candidate location; A program for causing a computer to execute a process of determining whether the candidate placement site is appropriate, and determining that a site among the candidate placement sites where the amount of generated power is maximum and the extreme wind speed is smaller than a threshold value is appropriate.

Images