Device, method, optimal placement determination device, optimal placement determination method, and program

Abstract

An optimum arrangement determination device according to one embodiment of the present disclosure is for determining the optimum arrangement of ICT loads that can be arranged at a plurality of bases constituting a subject network, the optimum arrangement determination device having: a pre-processing unit configured to offset, for each of the bases where an electricity supply generated by renewable energy is usable, an electricity demand demanded by the corresponding ICT load arranged at the base against the electricity supply; a main processing unit configured to, by using the electricity supply and the electricity demand having been offset by the pre-processing unit, determine as an optimum arrangement, an arrangement that can minimize, throughout the entirety of the plurality of bases, a cost required for purchasing the amount of electricity that is, of an electricity demand demanded by a ICT load when the ICT load is arranged in a base, an amount exceeding the electricity supply usable in the base; a post-processing unit configured to, by using the electricity supply and the electricity demand having been offset by the pre-processing unit, offset the electricity demand of the ICT load after the optimum arrangement determined by the main processing unit against the electricity supply usable in the base where the ICT load is arranged; and an output unit configured to, when all the electricity demands and the electricity supply can be offset by the post-processing unit and the electricity supply after the offset is greater than 0, output the electricity supply after the offset as amount of selling electricity.

Description

Technical Field

[0001] The present disclosure relates to Device, method, an optimal placement determination device, an optimal placement determination method, and a program.

Background Art

[0002] In recent years, for the purpose of reducing environmental impact and the like, the movement to introduce renewable energy has been promoted worldwide. For this reason, in data centers as well, operations using renewable energy have been advanced. On the other hand, renewable energy has large fluctuations in power generation output due to weather changes and the like, and there may be a surplus or a shortage in the supplied power of renewable energy. In contrast, Non-Patent Document 1 discloses a method of changing the placement of ICT (Information and Communication Technology) loads within a data center network where renewable energy power generation facilities are installed, and effectively utilizing the supplied power by renewable energy throughout the data center network.

Prior Art Documents

Non-Patent Documents

[0003]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the method described in Non-Patent Document 1, the purchase of the insufficient power and the sale of the surplus power after changing the placement of the ICT load are not considered. For this reason, for example, although the insufficient power has decreased throughout the data center network due to the change in the placement of the ICT load, the cost required for purchasing the insufficient power may conversely increase.

[0005] The present disclosure has been made in view of the above points, and an object thereof is to provide a technique for determining an optimal load placement of renewable energy power while considering the buying and selling of surplus or deficit power.

Means for Solving the Problems

[0006] An optimal placement determination device according to an aspect of the present disclosure is an optimal placement determination device that determines an optimal placement of ICT loads that can be placed at a plurality of bases constituting a target network, and for each base that can utilize the amount of power generated by renewable energy, a preprocessing unit configured to offset the power demand required by the ICT load placed at the base with the power supply amount; a main processing unit configured to determine, as the optimal placement, a placement that minimizes, for the entire plurality of bases, the cost required to purchase the amount of power that exceeds the power supply amount available at the base among the power demands required by the ICT load when the ICT load is placed at the base, using the power supply amount and power demand after offset by the preprocessing unit; a postprocessing unit configured to offset the power demand of the ICT load after the optimal placement determined by the main processing unit with the power supply amount available at the base where the ICT load is placed, using the power supply amount and power demand after offset by the preprocessing unit; and an output unit configured to output the power supply amount after offset as the amount of power for sale when all the power demands can be offset with the power supply amount by the postprocessing unit and the power supply amount after offset is greater than 0.

Advantages of the Invention

[0007] A technique for determining an optimal load placement of renewable energy power while considering the buying and selling of surplus or deficit power is provided.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Mode for Carrying Out the Invention

[0009] Hereinafter, an embodiment of the present invention will be described. In the following embodiments, an optimal placement determination device 10 that can determine the optimal placement of ICT loads across the entire data center network where renewable energy power generation facilities are installed will be described, taking into account the sale of surplus power and the purchase of deficit power.

[0010] Here, the data center network is a network composed of data centers (DCs: Data Centers) where ICT loads can be placed, nodes that transfer communications, and links that connect them to each other. Also, under the nodes, there are a plurality of user terminals that use the services provided by the data center network. Note that it is assumed that the data center network is a wide-area network such as a core network spanning the whole country, for example.

[0011] Hereinafter, as an example, the ICT load is a virtual machine (VM), and it is assumed that solar cells are arranged as power generation facilities using renewable energy in at least one or more data centers within the data center network. However, the ICT load is not limited to virtual machines, and any ICT load that can be arranged on the data center and whose arrangement can be changed or moved can be adopted. Also, the power generation facilities using renewable energy are not limited to solar cells, and other power generation facilities using renewable energy (for example, wind power generation facilities, hydroelectric power generation facilities, geothermal power generation facilities, biomass power generation facilities, etc.) may be used.

[0012] Also, the data center is just an example and is not necessarily limited to data centers. Any facility can be used as long as it is a base where ICT loads can be arranged.

[0013] <Preparation of symbols> Prepare some symbols used in this embodiment.

[0014] Assume that there are multiple data centers in the data center network, and let A be the set of data centers j with power demand. Also, let V(j) be the set of virtual machines (more precisely, virtual machines arranged on the physical servers within data center j) in data center j. Furthermore, let B be the set of data centers j to which the solar cells supply power.

[0015] The power demand of the virtual machine, the power supply of the solar cell, and the power purchase cost per unit power of data center j are represented as follows.

[0016] a jk : Power demand of virtual machine k ∈ V(j) in data center j ∈ A b j : Power supply by the solar cells in data center j ∈ B c j : Power purchase cost per unit power of data center j ∈ A Note that the data center where the virtual machines are deployed can be dynamically changed at predetermined time intervals ΔT (for example, ΔT = 30 minutes, 1 hour, etc.). Therefore, if a certain time is t, more precisely, it is expressed as A = A(t) and V(j) = V(t; j). Similarly, since the power demand, power supply, and power purchase cost can also change depending on the time t, more precisely, a jk = a jk (t), b j = b j (t), c j = c j (t). Although the renewable energy power generation facilities are not frequently installed (or removed), considering the new installation or removal of the renewable energy power generation facilities, since the data center supplied with power by solar cells can also change over time, similarly, it can be expressed as B = B(t). However, hereinafter, a certain specific time is fixed for consideration, and as long as there is no misunderstanding, the time t is not explicitly shown in any case.

[0017] <Hardware Configuration Example of Optimal Placement Determination Device 10> A hardware configuration example of the optimal placement determination device 10 according to this embodiment is shown in FIG. 1. As shown in FIG. 1, the optimal placement determination device 10 according to this embodiment includes an input device 101, a display device 102, an external I / F 103, a communication I / F 104, a RAM (Random Access Memory) 105, a ROM (Read Only Memory) 106, an auxiliary storage device 107, and a processor 108. These hardware components are communicably connected to each other via a bus 109.

[0018] The input device 101 is, for example, a keyboard, a mouse, a touch panel, a physical button, etc. The display device 102 is, for example, a display, a display panel, etc. Note that the optimal placement determination device 10 may not have at least one of the input device 101 and the display device 102, for example.

[0019] The external I / F 103 is an interface with an external device such as a recording medium 103a. The optimal placement determination device 10 can read from and write to the recording medium 103a via the external I / F 103. Examples of the recording medium 103a include a flexible disk, a CD (Compact Disc), a DVD (Digital Versatile Disk), an SD memory card (Secure Digital memory card), a USB (Universal Serial Bus) memory card, and the like.

[0020] The communication I / F 104 is an interface for the optimal placement determination device 10 to communicate with other devices and equipment. The RAM 105 is a volatile semiconductor memory (storage device) that temporarily holds programs and data. The ROM 106 is a non-volatile semiconductor memory (storage device) that can hold programs and data even when the power is turned off. The auxiliary storage device 107 is a storage device (storage device) such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or a flash memory, for example. The processor 108 is an arithmetic device such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), for example.

[0021] By having the hardware configuration shown in FIG. 1, the optimal placement determination device 10 according to the present embodiment can realize the optimal placement determination process described later. Note that the hardware configuration shown in FIG. 1 is an example, and the hardware configuration of the optimal placement determination device 10 is not limited thereto. For example, the optimal placement determination device 10 may have a plurality of auxiliary storage devices 107 and a plurality of processors 108, may not have a part of the illustrated hardware, or may have various hardware other than the illustrated hardware.

[0022] <Example of the functional configuration of the optimal placement determination device 10> A functional configuration example of the optimal placement determination device 10 according to this embodiment is shown in FIG. 2. As shown in FIG. 2, the optimal placement determination device 10 according to this embodiment includes an input unit 201, a preprocessing unit 202, a main processing unit 203, a postprocessing unit 204, and an output unit 205. Each of these units is realized, for example, by processing that causes one or more programs installed in the optimal placement determination device 10 to be executed by the processor 108.

[0023] The input unit 201 inputs information such as a set A of data centers with power demand, a set V(j) of virtual machines in each data center j∈A, the power demand a of each virtual machine k∈V(j) in each data center j∈A jk , the power supply amount b by the solar cell of each data center j j , and the power purchase cost c per unit power of each data center j. j Note that such information is generally collected and managed by an EMS (Energy Management System), an NMS (Network Management System), etc. that manage the data center network. Therefore, the input unit 201 may obtain and input such information from the EMS, the NMS, etc., for example.

[0024] The preprocessing unit 202 subtracts the power demand a of the virtual machine k∈V(j) from the power supply amount b of the solar cell within each data center j∈A∩B, and cancels out the power supply amount b j and the power demand a as much as possible. Hereinafter, canceling out the power supply amount b jk and the power demand a will be referred to as power cancellation. j and the power demand a jk . Hereinafter, canceling out the power supply amount b j and the power demand a jk will be referred to as power cancellation.

[0025] The main processing unit 203 uses the power demand a jk and the power supply amount b after power cancellation j to balance the power supply amount b j and the power demand a between data centers jkDetermine the placement of virtual machines that cancels out as much as possible. At this time, the main processing unit 203 reduces it to a multiple knapsack problem (see, for example, Reference 1) and calculates the optimal placement of virtual machines (in other words, the optimal destination for moving virtual machines) as its solution. Hereinafter, the "optimal placement of virtual machines" obtained as the solution to the multiple knapsack problem will be referred to as the "optimal VM placement".

[0026] The post-processing unit 204 cancels out the power supply amount b and the power demand amount a within each data center j ∈ A ∩ B after the optimal VM placement, and calculates the surplus power amount or the shortage power amount if there is surplus power or shortage power. As a result of this power cancellation, if there is remaining power supply amount, the surplus power amount is obtained, and if there is remaining power demand amount, the shortage power amount is obtained. j and the power demand amount a jk and calculates the surplus power amount or the shortage power amount if there is surplus power or shortage power. As a result of this power cancellation, if there is remaining power supply amount, the surplus power amount is obtained, and if there is remaining power demand amount, the shortage power amount is obtained.

[0027] The output unit 205 outputs the optimal VM placement to a predetermined output destination. Further, when the surplus power amount is obtained, the output unit 205 outputs it as the sold power amount to a predetermined output destination, and when the shortage power amount is obtained, it outputs it as the purchased power amount to a predetermined output destination. Here, examples of the output destination of the optimal VM placement include a virtual machine control device that controls the placement of virtual machines. Also, examples of the output destination of the sold power amount and the purchased power amount include a power control device that controls the sale and purchase of power.

[0028] <Optimal Placement Determination Process> Hereinafter, the optimal placement determination process according to the present embodiment will be described with reference to FIG. 3. Here, the following steps S101 to S105 are repeatedly executed, for example, every predetermined time interval ΔT (for example, ΔT = 30 minutes, 1 hour, etc.). Hereinafter, steps S101 to S105 at a certain time will be described.

[0029] The input unit 201 receives the set A of data centers with power demand, the set V(j) of virtual machines in each data center j ∈ A, and the power demand amount a of each virtual machine k ∈ V(j) in each data center j ∈ A jk, the amount of power supplied by the solar cells of each data center j is b j , and the power purchase cost per unit of power for each data center j, c j The above information is input (step S101).

[0030] Next, the preprocessing unit 202 calculates the power supply amount b j From the power demand a of virtual machine k ∈ V(j) jk Subtract the power supply amount b j and electricity demand a jk In other words, the preprocessing unit 202 performs power cancellation for each data center j∈A∩B in accordance with the following steps 1-1 and 1-2.

[0031] Step 1-1:b j ≧a jk' (k'∈V(j)) jk' Then, determine whether b exists. j ≧a jk' (k'∈V(j)) jk' If exists, execute steps 1-2. On the other hand, if b j ≧a jk' meet a jk' If does not exist (i.e., b j jk (∀k∈V(j)) or V(j)=φ), power cancellation is terminated.

[0032] Step 1-2:b j ←b j -a jk' And set V(j)←V(j)\{k'}, and return to step 1-1.

[0033] In addition, in step 1-1 above, j ≧a jk' (k'∈V(j)) jk' Therefore, in step 1-2 above, jk' Which of the a jk' A j ​It can be determined in various ways whether to subtract from. For example, as one idea, among a plurality of a jk' the a with the largest value jk' is considered to be subtracted from b j . This is a measure for preferentially canceling out power because it is difficult to change the placement of virtual machines with a large power demand. As another idea, for example, it is considered to evaluate the difficulty of changing the placement of virtual machines from the perspective of location or function, and preferentially cancel out the power demand of virtual machines with a high evaluation value. This is also a measure for preferentially canceling out the power demand of virtual machines whose placement is difficult to change.

[0034] An example of power cancellation in step S102 described above is shown in FIG. 4. The example shown in FIG. 4 is an example of power cancellation in a certain data center j where there are power demands a j1 , a j2 and a j3 and a power supply amount b j . In this example, as a result of power cancellation, finally, the power supply amount becomes b j ←b j -a j1 -a j2 , and the power demand a j3 (>b j ) remains.

[0035] Another example of power cancellation in step S102 described above is shown in FIG. 5. The example shown in FIG. 5 is an example of power cancellation in a certain data center j where there are power demands a j1 and a j2 and a power supply amount b j . In this example, as a result of power cancellation, finally, the power supply amount becomes b j ←b j -a j1 -a j2 , and there is no remaining power demand.

[0036] Next, the main processing unit 203 uses the power demand a jk and the power supply amount b j after power cancellation in step S102 described above to supply the power supply amount b jand power demand a jk Determine an optimal VM allocation that cancels out as much as possible (step S103). At this time, the main processing unit 203 reduces the problem to a multiple knapsack problem and calculates the optimal VM allocation as its solution.

[0037] Variable x of the multiple knapsack problem ijk is defined as follows.

[0038] x ijk : If the virtual machine k∈V(j) is moved from data center j∈A to data center i∈A∪B, then x ijk = 1; otherwise, x ijk = 0 At this time, the multiple knapsack problem for optimizing the allocation of virtual machines is formulated as follows.

[0039]

Equation

[0040] The multiple knapsack problem shown in Equation 1 above means that for virtual machines that were not moved so that power can be supplied by solar cells, their power demand is covered by power purchase, and it is optimized to minimize the cost required for that power purchase.

[0041] An example of the optimal VM allocation in step S103 above is shown in FIG. 6. The example shown in FIG. 6 shows the case where the power supply amount b j exists in a certain data center j, the power demand a j'1 and a j'2 exist in a certain data center j', respectively, and the virtual machine corresponding to the power demand a j'1 and the virtual machine corresponding to the power demand a j'2 are moved (allocated) to the data center j. Note that b j - a j'1-a j'2 ≧0 indicates that the second constraint condition of the multiple knapsack problem shown in Equation 1 above is satisfied.

[0042] In the multiple knapsack problem shown in Equation 1 above, it is optimized to minimize the cost required for power purchase to cover the power demand of the virtual machines that have not been moved. For this reason, the optimal placement of virtual machines is determined considering the power purchase cost as well. For example, as shown in FIG. 7, the power supply amount b j exists in a certain data center j, the power demand a j'1 and a j'2 exist in a certain data center j', and the power demand a j''1 and a j''2 exist in a certain data center j''. At this time, when c j' >c j'' (that is, when the power purchase cost of data center j' is greater than that of data center j''), in order to minimize the total power purchase cost required to cover the power demand of the unmoved virtual machines, the virtual machines corresponding to the power demand a j'1 and the virtual machines corresponding to the power demand a j'2 are preferentially moved.

[0043] Next, the post-processing unit 204 offsets the power supply amount b j and the power demand a jk in each data center j∈A∩B after the optimal VM placement determined in step S103 above, and calculates the surplus power or deficit power if there is surplus power or deficit power (step S104). That is, the post-processing unit 204 performs power offset and calculation of surplus power amount or deficit power amount for each data center j∈A∩B according to the following procedures 2-1 to 2-4.

[0044] Procedure 2-1: Determine whether there exists an a j ≧a jk' (k'∈V(j)) that satisfies the condition. And determine whether there exists an a jk' such that b j ≧a jk' (k'∈V(j)) and a jk'If it exists, execute Step 2-2. On the other hand, if b j ≥a jk' satisfies for a jk' and it does not exist (that is, when b j <a jk (∀k∈V(j)) or V(j)=φ), execute Step 2-3.

[0045] Step 2-2: b j ←b j -a jk' And set V(j)←V(j)\{k'}, then return to Step 2-1.

[0046] Step 2-3: Determine whether b j =0. If b j =0, since neither surplus power nor deficit power is generated, end the process. On the other hand, if b j ≠0, execute Step 2-4.

[0047] Step 2-4: a jk (>b j ) does not exist (that is, when V(j)=φ), set b j as the surplus power amount. On the other hand, if a jk (>b j ) exists (that is, when V(j)≠φ), Σ k∈V(j) a jk -b j is set as the deficit power amount.

[0048] An example of the calculation of the surplus power amount and the deficit power amount in the above Step S104 is shown in FIG. 8. In the example shown in FIG. 8, when V(j)=φ, the power supply amount b j is directly used as the surplus power amount, and when V(j)≠φ, a j1 -b j is used as the deficit power amount. In the example shown in FIG. 8, it is assumed that when V(j)≠φ, V(j)={1}.

[0049] Finally, the output unit 205 outputs the optimal VM allocation determined in step S103 above to a predetermined output destination (e.g., a virtual machine control device, etc.), and when surplus power is obtained in a certain data center in step S104 above, it outputs it as the sold power amount, and when a shortage power amount is obtained, it outputs it as the purchased power amount to a predetermined output destination (e.g., a power control device, etc.) (step S105). As a result, the allocation of virtual machines is changed to the optimal VM allocation by a virtual machine control device or the like. Also, when surplus power or shortage power occurs in a certain data center, the surplus power is sold and the shortage power is purchased by a power control device or the like.

[0050] <Summary> As described above, the optimal allocation determination device 10 according to the present embodiment determines the optimal virtual machine allocation through three stages of processing: preprocessing, main processing, and postprocessing. As a result, considering the power supply and demand balance, the power demand of as many virtual machines as possible is covered by the power supply from solar cells, and the cost required for power purchase can be minimized. Also, on the other hand, when there is a surplus in the power supply amount from solar cells after covering the power demand of virtual machines, the surplus can be used as the sold power amount.

[0051] Therefore, even when the power supply amount of renewable energy fluctuates due to weather changes or the like, the power supply amount can be utilized efficiently and effectively. That is, through the above three stages of processing, the power demand of the ICT load is covered as much as possible by the power supply amount of renewable energy so that the total power purchase cost of the shortage is minimized, and thus the power supply amount can be utilized efficiently. Also, even when a surplus occurs in the power supply amount of renewable energy, the surplus can be used as the sold power amount, so the surplus can be utilized effectively.

[0052] The present invention is not limited to the specifically disclosed above embodiments, and various modifications, changes, combinations with known technologies, etc. are possible without departing from the description of the claims.

[0053] References Reference 1: Applied Mathematical Planning Handbook, by Mikio Kubo et al., Asakura Shoten, 2002, pp240 - 241.

Explanation of Symbols

[0054] 10 Optimal Placement Determination Device 101 Input Device 102 Display Device 103 External I / F 103a Recording Medium 104 Communication I / F 105 RAM 106 ROM 107 Auxiliary Storage Device 108 Processor 109 Bus 201 Input Section 202 Pre - processing Section 203 Main - processing Section 204 Post - processing Section 205 Output Section

Claims

1. An apparatus for determining an optimal placement of ICT loads, comprising: For each base where the power supply amount is available, using the power demand amount required by the ICT loads arranged at the base, among the power demand amounts required by the ICT loads when the ICT loads are arranged at the base, the cost required for purchasing the amount of power exceeding the power supply amount available at the base is minimized for the entire base, and the placement is determined as the optimal placement.

2. For each base where the power supply amount is available, it is configured to offset the power demand amount required by the ICT loads arranged at the base with the power supply amount, Using the power supply amount and power demand amount after the offset, all the power demand amounts of the ICT loads after the optimal placement are configured to offset with the power supply amount available at the base where the ICT loads are arranged, When the power supply amount after the offset is greater than a predetermined value, the power supply amount after the offset is output as the surplus power amount of the sold power, and when the power demand amount after the offset is greater than a predetermined value, it is output as the shortage power amount. The apparatus according to claim 1, characterized in that.

3. When at least part of the power demand amount cannot be offset with the power supply amount, it is configured to output the amount of power obtained by subtracting the power supply amount after the offset from the power demand amount that could not be offset as the purchased power amount. The apparatus according to claim 2.

4. The problem of obtaining the optimal placement is formulated as a multiple knapsack problem, and the optimal placement is determined by solving the multiple knapsack problem. The apparatus according to any one of claims 1 to 3.

5. Regarding the ICT loads whose placement has not been changed, the multiple knapsack problem is formulated as a problem of minimizing the sum of the costs required for purchasing the amount of power exceeding the power supply amount available at the base where the ICT loads are arranged among the power demand amounts required by the ICT loads. In the multi-knapsack problem, the apparatus according to claim 4 includes a first constraint condition indicating that each ICT load is arranged at any one of the bases, and a second constraint condition indicating that the total power demand required by the ICT loads arranged at each base is equal to or less than the power supply amount available at the base.

6. The apparatus according to claim 5, wherein the second constraint condition is a constraint condition to be satisfied on a best-effort basis.

7. An apparatus for determining an optimal arrangement of ICT loads, For each base with available power supply amount, using the power demand required by the ICT loads arranged at the base, among the power demands required by the ICT loads when the ICT loads are arranged at the base, the cost required for purchasing the amount of power exceeding the available power supply amount at the base is minimized for the entire base, and the determined arrangement is defined as the optimal arrangement.

8. In an apparatus for determining an optimal arrangement of ICT loads, For each base with available power supply amount, using the power demand required by the ICT loads arranged at the base, among the power demands required by the ICT loads when the ICT loads are arranged at the base, the cost required for purchasing the amount of power exceeding the available power supply amount at the base is minimized for the entire base, and a program for determining the determined arrangement as the optimal arrangement.

9. An optimal arrangement determination apparatus for determining an optimal arrangement of ICT loads that can be arranged at a plurality of bases constituting a target network, A preprocessing unit configured to offset the power demand required by the ICT loads arranged at each base with the power supply amount generated by renewable energy for each base with available power supply amount; A main processing unit configured to use the power supply amount and power demand after offset by the preprocessing unit to minimize, for the entire plurality of bases, the cost required for purchasing the amount of power exceeding the available power supply amount at the base among the power demands required by the ICT loads when the ICT loads are arranged at the base, and determine the determined arrangement as the optimal arrangement. A post-processing unit configured to offset the power demand of the ICT load after the optimal placement determined by the main processing unit with the power supply available at the site where the ICT load is placed, using the power supply amount and power demand amount after offset by the pre-processing unit. An output unit configured to output the power supply amount after offset as the power amount for sale when all the power demand amounts can be offset with the power supply amount by the post-processing unit and the power supply amount after offset is greater than a predetermined value. An optimal placement determination device having the above.

10. The output unit is configured to output, as the power amount to be purchased, the power amount obtained by subtracting the power supply amount after offset by the post-processing unit from the power demand amount that could not be offset when at least part of the power demand amounts could not be offset with the power supply amount by the post-processing unit. The optimal placement determination device according to claim 9.

11. The main processing unit is configured to formulate the problem of obtaining the optimal placement as a multiple knapsack problem and determine the optimal placement by solving the multiple knapsack problem. The optimal placement determination device according to claim 9 or 10.

12. The main processing unit is For the ICT load whose placement has not been changed, formulate the multiple knapsack problem as a problem of minimizing the sum of the costs required to purchase the power amount exceeding the power supply amount available at the site where the ICT load is placed among the power demand amounts required by the ICT load. The multiple knapsack problem includes a first constraint condition indicating that each ICT load is placed at one of the sites, and a second constraint condition indicating that the total power demand amount required by the ICT loads placed at each site is less than or equal to the power supply amount available at the site. The optimal placement determination device according to claim 11.

13. The second constraint condition is a constraint condition to be satisfied by best effort. The optimal placement determination device according to claim 12.

14. An optimal placement determination device that determines the optimal placement of ICT loads that can be placed at a plurality of bases constituting a target network, for each base where the amount of power supplied by renewable energy can be utilized, a preprocessing procedure for offsetting the power demand required by the ICT load placed at the base with the amount of power supplied; Using the amount of power supplied and the power demand after offsetting by the preprocessing procedure, among the power demands required by the ICT load when the ICT load is placed at the base, the cost required to purchase the amount of power exceeding the amount of power supplied available at the base is minimized for the entire plurality of bases, and the placement is determined as the optimal placement in a main processing procedure; Using the amount of power supplied and the power demand after offsetting by the preprocessing procedure, a postprocessing procedure for offsetting the power demand of the ICT load after the optimal placement determined by the main processing procedure with the amount of power supplied available at the base where the ICT load is placed; An output procedure for outputting the amount of power supplied after offsetting as the amount of power sold when all the power demands can be offset with the amount of power supplied by the postprocessing procedure and the amount of power supplied after the offset is greater than a predetermined value; An optimal placement determination method for executing the above.

15. In an optimal placement determination device that determines the optimal placement of ICT loads that can be placed at a plurality of bases constituting a target network, for each base where the amount of power supplied by renewable energy can be utilized, a preprocessing procedure for offsetting the power demand required by the ICT load placed at the base with the amount of power supplied; Using the amount of power supplied and the power demand after offsetting by the preprocessing procedure, among the power demands required by the ICT load when the ICT load is placed at the base, the cost required to purchase the amount of power exceeding the amount of power supplied available at the base is minimized for the entire plurality of bases, and the placement is determined as the optimal placement in a main processing procedure; Using the power supply amount and power demand amount after offsetting by the preprocessing procedure, a postprocessing procedure for offsetting the power demand amount of the ICT load after the optimal placement determined by the main processing procedure with the power supply amount available at the base where the ICT load is placed, An output procedure for outputting the power supply amount after offsetting as the power generation amount for sale when all the power demand amounts can be offset with the power supply amount by the postprocessing procedure and the power supply amount after the offsetting is greater than a predetermined value; A program for executing the above.

Images