Control device and program

Abstract

To quickly control increasing and decreasing of power consumption depending on a request associated with increasing and decreasing of power consumption.SOLUTION: A control device that controls power consumption in a service provision system in which services are provided by servers provided at each of a plurality of sites that are geographically dispersed, comprises: a target power setting unit that sets a target power value for the site at which the server is provided on the basis of any one or some of a request associated with increasing and decreasing of power consumption at the site, electric charge at the site, and an amount of power generation at the site; and a load balancing setting unit that performs load transfer among the plurality of servers by live migration on the basis of the target power value.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a technique for performing load transfer between servers at multiple sites.

Background Art

[0002] Conventionally, a website has been constructed using multiple servers, and requests have been distributed to the multiple servers by a load balancer (hereinafter referred to as LB). This makes it possible to easily expand when capacity is insufficient (scalability) and to prevent the entire service from stopping when some servers fail (availability).

[0003] In addition, global server load balancing (GSLB), which realizes the function of LB between multiple sites, is also used.

[0004] On the other hand, at sites such as data centers and communication buildings, in addition to receiving power from commercial power through a power distribution network and supplying power to servers and the like, a power generation unit using renewable energy such as photovoltaic power generation (PV) is provided, and power generated by the power generation unit has also been used.

[0005] Note that Non-Patent Document 1 discloses performing power optimization with QoS as a constraint condition in a distributed web server.

Prior Art Documents

Non-Patent Documents

[0006]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0007] In future electricity supply and demand adjustment markets, there is a need for Virtual Power Plants (VPPs) that can rapidly increase or decrease large amounts of electricity, but conventional technologies are unable to meet these requirements in terms of both scale and response speed. Furthermore, in order to self-consume renewable energy sources with unstable output that are expected to become even cheaper and be introduced on a large scale, there will be a need to match electricity consumption to the amount of electricity generated.

[0008] The present invention has been made in view of the above points, and aims to provide a technology that enables rapid control of power consumption increases and decreases in response to requests regarding increases and decreases in power consumption in a service provision system that provides services using servers installed at multiple locations. [Means for solving the problem]

[0009] According to the disclosed technology, a control device for controlling power consumption in a service delivery system that provides services using servers located at multiple geographically dispersed locations, The aforementioned server is provided For each of the multiple locations, A target power setting unit sets a target power value for a site based on one or more of the following: requests regarding increases or decreases in power consumption at the site, electricity charges at the site, and the amount of power generated at the site. The aforementioned target power value This includes information on the correspondence between load and power consumption, and measured load values ​​for each server. Based on this, a load balancing setting unit performs load transfer between multiple servers. A control device is provided that includes the following. [Effects of the Invention]

[0010] According to the disclosed technology, a technology is provided that enables rapid control of power consumption increases and decreases in response to requests regarding increases or decreases in power consumption in a service delivery system that provides services using servers located at multiple sites. [Brief explanation of the drawing]

[0011] [Figure 1] This is an overall system configuration diagram in an embodiment of the present invention. [Figure 2] This is a diagram illustrating an example of wide-area load balancing control. [Figure 3] This is a diagram illustrating the overview of the control in this embodiment. [Figure 4] This diagram shows an example of a base configuration. [Figure 5] This is a diagram illustrating the configuration of a load control device. [Figure 6] This figure shows an example of the device's hardware configuration. [Figure 7] This is a flowchart illustrating an example of the operation of a load control device. [Figure 8] This figure shows an example of a load-power consumption correspondence table. [Modes for carrying out the invention]

[0012] Hereinafter, embodiments of the present invention (this embodiment) will be described with reference to the drawings. The embodiments described below are merely examples, and the embodiments to which the present invention is applied are not limited to the embodiments described below.

[0013] (System Configuration) Figure 1 shows an example of the overall system configuration in an embodiment of the present invention. As shown in Figure 1, the system is equipped with a load control device 100 and a GSLB device 200, which can communicate with each other via a network 300. In addition, there are multiple geographically dispersed locations (locations A to Z in the example of Figure 1), and servers and the like at each location can communicate with the load control device 100 via the network 300.

[0014] Each site has one or more servers, and the one or more servers provide services to a large number of client terminals. The services include, for example, but are not limited to, providing an online shopping site, video distribution, cloud infrastructure, etc. A system consisting of these multiple servers may be referred to as a service providing system. Also, a system consisting of multiple sites with servers may be referred to as a service providing system.

[0015] Each site is assumed to be a building such as a communication building or a data center, but such an assumption is just an example. A "site" may be something in a smaller range than a building (e.g., one floor, one room, etc.), or a "site" may be something in a larger range than a building (e.g., a group of buildings, a town, a city, a prefecture, a region, etc.).

[0016] Based on the DR requests at each site, the target power value of each site based on the power generation amount (such as solar radiation amount), etc., the load control device 100 controls the power consumption so that the power consumption of each site approaches the target power value by moving the load of the servers between sites. Note that the load control device may also be referred to as a power consumption control device or a control device.

[0017] In this embodiment, as an example of the means for moving the load of the servers between sites, the GSLB device 200 is used. However, the means for moving the load of the servers between sites is not limited to this. For example, live migration can also be used as the means for moving the load of the servers between sites.

[0018] (Overview of operation) First, the overview of the operation of the GSLB device 200 as the means for moving the load of the servers between sites will be described with reference to FIG. 2. Note that the "GSLB device 200" is not limited to being physically composed of one device, and may also be a system composed of multiple devices.

[0019] In the example shown in Figure 2, there are geographically dispersed locations A through C, and each location has two servers (server 2A, server 2B, and server 2C). This example describes how a GSLB device 200 distributes connection requests (e.g., HTTP requests, hereinafter referred to as "requests") from client terminals 400 to one of servers 2A, 2B, or 2C.

[0020] In step S0 (Step 0), the GSLB device 200 periodically performs health checks on each server. For example, if it detects a faulty server, it prevents access to that server.

[0021] Furthermore, the GSLB device 200 has a setting parameter that assigns weights, for example, 3:2:1, to the three distribution destinations: Server 2A, Server 2B, and Server 2C. In this case, of all access to the services provided by "Server 2A, Server 2B, and Server 2C," 3 / 6 are connected to Server 2A, 2 / 6 to Server 2B, and 1 / 6 to Server 2C.

[0022] In S1, client terminal 400 sends a DNS request to GSLB device 200 specifying the domain name of the service. In S2, GSLB device 200 returns, for example, the IP address of server 2A to client terminal 400 based on the weights mentioned above. In this case, in S3, client terminal 400 sends a request to server 2A.

[0023] In reality, there are many client terminals, and requests from each client terminal are distributed to either Server 2A, Server 2B, or Server 2C, thereby achieving load balancing across locations based on the weights mentioned above.

[0024] Referring to Figure 3, an example of power consumption control between site A and site B, which is achieved by the load balancing control 100 in this embodiment, will be explained.

[0025] In the example shown in Figure 3, site A is equipped with redundant servers 2A-1 and 2A-2, and site B is equipped with redundant servers 2B-1 and 2B-2. Furthermore, GSLB device 200-1 performs load balancing control for servers 2A-1 and 2B-1, and GSLB device 200-2 performs load balancing control for servers 2A-2 and 2B-2.

[0026] Figure 3(a) shows the normal state, in which GSLB devices 200-1 and 200-2 are operating so that requests are distributed 50 / 50 between site A and site B.

[0027] Subsequently, if a request to reduce power consumption is made at site B, the load control device 100 will change the settings of GSLB devices 200-1 and 200-2 to increase the proportion of load distribution to servers 2A-1 and 2A-2 and decrease the proportion of load distribution to servers 2B-1 and 2B-2. In other words, the load is shifted to servers 2A-1 and 2A-2, reducing the load on servers 2B-1 and 2B-2. This reduces the power consumption at site B.

[0028] Requests for increases or decreases in power consumption at each site could include, for example, requests related to improving the utilization rate of renewable energy, requests related to responding to upward / downward demand response (DR) requests from power companies, and requests related to minimizing the electricity purchase price when dynamic pricing is implemented.

[0029] One requirement related to improving the utilization rate of renewable energy is, for example, that at a site equipped with solar power generation equipment, if the weather is good and a large amount of electricity can be generated by solar power, there is a requirement to increase the power consumption of the servers at that site in order to make effective use of it. Another requirement related to improving the utilization rate of renewable energy is to stabilize the grid by making electricity demand follow the output of renewable energy, such as solar and wind power, under unstable renewable energy output conditions.

[0030] Minimizing electricity purchase costs when dynamic pricing is implemented means controlling the server load so that, for example, electricity consumption increases at locations with lower electricity rates and decreases at locations with higher electricity rates, when electricity rates vary depending on geographical location, time of day, etc.

[0031] Since there is a positive correlation between server load and power consumption, power consumption can be controlled by utilizing the GSLB device 200 to control the load on specific servers. Furthermore, this control can be implemented quickly.

[0032] Furthermore, by also controlling ancillary equipment such as air conditioning and server room lighting at the site, it is possible to cause larger-scale energy increases or decreases, although the response speed may be slightly slower.

[0033] The configuration and operation of this system will be explained in more detail below.

[0034] (Example of base configuration) Figure 4 shows an example of the configuration of base A in this embodiment. Although Figure 4 shows base A as an example, other bases have a similar configuration. However, there may be bases that do not have a power generation unit 1.

[0035] As shown in Figure 4, site A includes a power generation unit 1A that generates electricity using renewable energy such as solar power, a server 2A that provides services, a power distribution unit 3A that is connected to a power distribution network 10A provided by a power company, ancillary equipment 4A such as air conditioning and lighting for the server room, and a monitoring and control device 5A.

[0036] Note that "Server 2A" may be a single physical server or a group of multiple servers. Furthermore, "Server 2A" may be a virtual function such as a container. However, even if it is a virtual function like a container, it actually operates on a computer (physical server) that consumes power.

[0037] Although Figure 4 shows a server as the device for providing the service, the system may also include communication devices such as routers and switches, and these communication devices may also be subject to power consumption control in this embodiment. Furthermore, the communication devices may also be assumed to be implemented by the server. The server and communication devices may be collectively referred to as power-consuming devices.

[0038] The power distribution unit 3A supplies power received from the power distribution network 10 to the server 2A and ancillary equipment 4A. However, when the power generation unit 1A is generating sufficient power (when the voltage is high), power is supplied to the server 2A by the power generation unit 1A. In addition, the power distribution unit 3A can, if necessary, share any surplus power generated by the power generation unit 1A with other locations.

[0039] The monitoring and control device 5A can communicate with each unit via the on-site communication network. Furthermore, the monitoring and control device 5A is connected to the load control device 100 via the network 300.

[0040] For example, the monitoring and control device 5A can obtain information about the load on server 2A (e.g., number of requests, number of simultaneous connections, CPU usage, memory usage, etc.) from server 2A and notify the load control device 100 of this information.

[0041] Furthermore, the monitoring and control device 5A can control the auxiliary equipment 4A based on commands from, for example, the load control device 100. Examples of such control include turning lights on and off, and changing the temperature settings of the air conditioning.

[0042] (Example of load control device configuration) Figure 5 shows an example configuration of the load control device 100. As shown in Figure 5, the load control device 100 includes a target power setting unit 110, a service load prediction unit 120, a load balance setting unit 130, a load-power consumption correspondence table storage unit 140, and a service load measurement unit 150. The operation of each unit will be described later. The load control device 100 may be a single physical device (computer) or a system composed of multiple devices.

[0043] <Example Hardware Configuration> The load control device 100 in this embodiment can be implemented, for example, by having a computer execute a program that describes the processing content described in this embodiment. This "computer" may be a physical machine or a virtual machine on the cloud. When a virtual machine is used, the "hardware" described here is virtual hardware.

[0044] The above program can be recorded on a computer-readable storage medium (such as portable memory), saved, and distributed. It can also be provided via a network, such as the internet or email.

[0045] Figure 6 shows an example of the hardware configuration of the computer described above. The computer in Figure 6 has a drive device 1000, an auxiliary storage device 1002, a memory device 1003, a CPU 1004, an interface device 1005, a display device 1006, an input device 1007, an output device 1008, etc., all of which are interconnected by a bus BS.

[0046] The program that enables processing on the computer is provided, for example, on a recording medium 1001 such as a CD-ROM or memory card. When the recording medium 1001 containing the program is set in the drive device 1000, the program is installed from the recording medium 1001 to the auxiliary storage device 1002 via the drive device 1000. However, the program does not necessarily have to be installed from the recording medium 1001; it may also be downloaded from another computer via a network. The auxiliary storage device 1002 stores the installed program as well as necessary files and data.

[0047] The memory device 1003 reads and stores a program from the auxiliary storage device 1002 when a program startup command is received. The CPU 1004 implements the functions related to the load control device 100 according to the program stored in the memory device 1003. The interface device 1005 is used as an interface for connecting to a network. The display device 1006 displays a GUI (Graphical User Interface) or the like, generated by a program. The input device 1007 consists of a keyboard and mouse, buttons, or a touch panel, and is used to input various operation commands. The output device 1008 outputs the calculation results.

[0048] (Example of load control device operation) Next, we will explain an example of the operation of the load control device 100 following the steps in the flowchart shown in Figure 7. In the following explanation, we will use the case where the target service is provided by server 2A at site A, server 2B at site B, and server 2C at site C as an example.

[0049] <s101> In S101, the service load prediction unit 120 predicts the future load of the target service based on information such as the past load of the target service. More specifically, the service load prediction unit 120 predicts the number of requests per unit time to the target service at a certain time t in the future.

[0050] For example, if the target service is provided by server 2A at site A, server 2B at site B, and server 2C at site C, the service load prediction unit 120 predicts the number of requests per unit time to servers 2A, server 2B, and server 2C at a certain time t in the future.

[0051] If the time from the current time until the transfer of server load (number of requests) to each location is completed by the control of S101 to S103 is T seconds, then time t is the current time plus T seconds. However, time t is not limited to this.

[0052] Note that using the number of requests as a measure of load is just one example. For example, the number of concurrent users or the overall CPU usage of the servers related to the service could also be used as the load. Furthermore, there is no limit to the method used to predict the load, but for example, the ARIMA model or regression analysis can be used to predict the load.

[0053] <s102> In S102, the target power setting unit 110 sets (determines) the target power value (target power consumption) for each site at time t, and notifies the load balance setting unit 130 of the target power value.

[0054] For example, if the target service is provided by server 2A at site A, server 2B at site B, and server 2C at site C, the target power setting unit 110 sets target power values ​​for each of the sites A, B, and C. It is not mandatory to set target power values ​​for all sites that have servers providing the target service. For example, target power values ​​may be set only for the sites where power consumption needs to be increased or decreased. Examples of what constitutes a "target power value" are explained below.

[0055] The target power setting unit 110 periodically collects information from the monitoring and control devices 5 at each site, such as the current power consumption of each consuming device (servers, ancillary equipment, etc.), DR requests from the power company, electricity charges when dynamic pricing is implemented, and the status of renewable energy (weather, wind power, etc.). From this current information, the information at time t can be estimated.

[0056] The target power setting unit 110 uses the above information to set target power values ​​for each site at time t. For example, suppose the target service is provided by server 2A at site A, server 2B at site B, and server 2C at site C, and the target power setting unit 110 detects that there is a 50kW reduction DR request at site A, and that site B, which has solar power generation equipment as power generation unit 1B, has changed from bad weather to sunny weather. Also, suppose the current power consumption (total power consumption within all sites) is site A = 500kW, site B = 500kW, and site C = 500kW.

[0057] The target power setting unit 110 sets the target power value for site A to 450kW based on the request for reduced demand response (DR). The target power setting unit 110 also recognizes that site B generates 50kW on a clear day and determines its target power value to be 550kW. For site C, the target power value remains unchanged at 500kW. Regarding this method of setting target power values, service load prediction is not considered at this point; therefore, the actual power consumption after load balancing may differ from the target power value.

[0058] Furthermore, for example, if electricity rates differ between locations during a given time t, the target power values ​​may be set so that the power consumption of the location with the lowest electricity rate is higher, that is, so that the overall electricity rate approaches the lowest possible value. For example, if the electricity rates are "Location A = Location B > Location C", the target power values ​​may be set as "Location A = 30%, Location B = 30%, Location C = 40%" when the total power consumption of locations A to C providing the target service is set to 100%, so that the power consumption at location C is higher.

[0059] Furthermore, target power values ​​may be set using vague information such as "large" or "small." For example, in the above situation (site A = request for reduced DR, site B = clear weather), the target power values ​​could be set as "small" (reduce power consumption) for site A and "large" (increase power consumption) for site B.

[0060] Alternatively, you could set target power values ​​as increases or decreases, such as reducing power consumption by 20kW at site A or increasing power consumption by 20kW at site B. Or, you could set target power consumption (kWh) for each site as the target power value.

[0061] The target power setting unit 110 notifies the load balance setting unit 130 of the target power value set as described above.

[0062] <s103> In S103, the load balance setting unit 130 calculates the parameters (load balance) to be set in the GSLB device 200 based on the predicted service load at time t predicted by the service prediction load unit 120, the target power value set by the target power setting unit 110, the load-power consumption correspondence table stored in the load-power consumption correspondence table storage unit 140, and information from the service load measurement unit 150, and sets the calculated parameters in the GSLB device 200.

[0063] The load-power consumption correspondence table records information on the correspondence between the load (e.g., the number of requests to the server per unit time) and the power consumption of the server, as shown in Figure 8, for example. The load may also be, for example, CPU usage. The service load measurement unit 150 measures the load for each server (e.g., the number of requests per unit time) and notifies the load balance setting unit 130 of this.

[0064] For example, suppose the load balancing setting unit 130 receives target power values ​​from the target power setting unit 110, such as reducing power consumption by 20kW for site A and increasing power consumption by 20kW for site B, and also receives "200" as the service load at time t from the service load prediction unit 120. Furthermore, suppose the current load received from the service load measurement unit 150 is "Server 2A at site A = 60, Server 2B at site B = 60, Server 2C at site C = 60".

[0065] In this case, the load balancing setting unit 130, by referring to the load-power consumption correspondence table, determines that in order to reduce the power consumption of site A by 20kW, the load of site A (server 2A) needs to be reduced from 60 to 20, and in order to increase the power consumption of site B by 20kW, the load of site B (server 2B) needs to be increased from 60 to 100.

[0066] Furthermore, since the predicted load for the entire service is 200, the load balancing setting unit 130 determines that the load on site C (server 2C) needs to be set to 200-20-100=80. In other words, the ratio of the number of requests from sites A, B, and C will be site A:site B:site C = 20:100:80 = 1:5:4.

[0067] Therefore, the load balancing setting unit 130 calculates "Site A:Site B:Site C = 1:5:4" as the parameter (request weight) to be set in the GSLB device 200, and sets this in the GSLB device 200. The GSLB device 200, upon receiving the setting, performs request distribution according to the setting.

[0068] Furthermore, it is also possible to omit any or all of the service load prediction values, load-power consumption correspondence table, and current service load values. In other words, it is also possible to omit any or all of the service load prediction unit 120, load-power consumption correspondence table storage unit 140, and service load measurement unit 150.

[0069] When the service load prediction values, load-power consumption correspondence table, and current service load values ​​are not used, for example, if the load balancing setting unit 130 sets the target power values ​​to "small" (reduce power consumption) for site A and "large" (increase power consumption) for site B, it changes the parameter values ​​set in the GSLB device 200 by a predetermined value. For example, if the weights before the change were "Site A:Site B:Site C = 3:3:4", the weights after the change would be "Site A:Site B:Site C = 2:4:4".

[0070] Alternatively, the load balancing setting unit 130 may be used to input the service requirements (SLA, SLO, etc.) of the target service, and the load balancing setting unit 130 may use the service requirements as constraints to calculate the parameters to be set in the GSLB device 200. For example, if the weights are "Site A:Site B:Site C = 0:2:3" when no service requirement constraints are used, and the service requirements stipulate that at least Site A and Site B must be included in the distribution destinations from the standpoint of availability or reliability, the load balancing setting unit 130 may set the weights to, for example, "Site A:Site B:Site C = 1:1:3".

[0071] In the example above, the GSLB device 200 is used to transfer the load between servers in the form of request distribution control, but the method of load transfer is not limited to this. For example, if it is desired to transfer the load from server 2A to server 2B, the load balancing setting unit 130 may instruct server 2A and server 2B to move the virtual machines running on server 2A to server 2B via live migration.

[0072] Furthermore, while the above example only performs load control on the server, it is also possible to perform power control on the ancillary equipment 4 (air conditioning, lighting, etc.) in conjunction with the server control.

[0073] For example, if a load reduction request is made to site A, but the load control of server 2A alone is insufficient to reduce power consumption enough to meet the load reduction request, the load balance setting unit 130 instructs the monitoring and control device 5A at site A to raise the set temperature of the server room's air conditioning by a predetermined amount (e.g., 1°C). The monitoring and control device 5A may automatically control the air conditioning according to the instruction, or an operator may manually control the air conditioning by looking at the instruction displayed on the monitoring and control device 5A.

[0074] (Effects of the embodiment) According to the technology of this embodiment, in a service provision system that provides services using servers located at multiple sites, it becomes possible to quickly control the increase or decrease of power consumption in response to requests regarding increases or decreases in power consumption.

[0075] In other words, in this embodiment, for example, a business operator can use a GSLB device to control the server load of users, thereby controlling energy consumption and achieving the generation of negative / positive watts and maximizing the use of renewable energy.

[0076] (Summary of the embodiments) This specification includes control devices, control methods, and programs as described in at least the following sections. (Section 1) A control device for controlling power consumption in a service provision system that provides services using servers located at multiple geographically dispersed locations, A target power setting unit sets a target power value for a location where the server is installed, based on requests regarding increases or decreases in power consumption at that location. Based on the aforementioned target power value, a load balancing setting unit performs load transfer between multiple servers. A control device equipped with the following features. (Section 2) The load balancing setting unit performs the load shift by setting the weights for distribution to the wide-area load balancing device that controls the distribution of requests in the service provision system. The control device described in paragraph 1. (Section 3) In addition to load shifting, the load balancing setting unit also controls the power consumption of ancillary equipment at the base. The control device described in paragraph 1 or 2. (Section 4) The load balancing setting unit uses the service requirements of the service as constraints to perform the load shifting. A control device as described in any one of paragraphs 1 through 3. (Section 5) A control method for controlling power consumption in a service provision system that provides services using servers located at multiple geographically dispersed locations, A target power setting step in which a target power value is set for a site where the server is installed, based on a request regarding an increase or decrease in power consumption at the site, A load balancing setting step that performs load transfer between multiple servers based on the aforementioned target power value. A control method comprising the following features. (Section 6) A program for causing a computer to function as a component of the control device described in any one of paragraphs 1 through 4.

[0077] Although this embodiment has been described above, the present invention is not limited to this specific embodiment, and various modifications and changes are possible within the scope of the gist of the invention as described in the claims. [Explanation of symbols]

[0078] 1A Power Generation Unit 2A, 2B, 2C Servers 3A power distribution section 4A Ancillary Equipment 5A Monitoring and Control System 10A power grid 100 Load control device 110 Target Power Setting Unit 120 Service Load Prediction Unit 130 Load balance setting section 140 Load-Power Consumption Compatible Table Storage Unit 150 Service Load Measurement Unit 200 GSLB device 300 Networks 400 client terminals 1000 drive unit 1001 Recording media 1002 Auxiliary storage device 1003 Memory device 1004 CPU 1005 Interface device 1006 Display device 1007 Input device 1008 Output device

Claims

1. A control device for controlling power consumption in a service provision system that provides services using servers located at multiple geographically dispersed locations, For each of the multiple locations equipped with the aforementioned server, a target power setting unit sets a target power value for the location based on one or more of the following: requests regarding increases or decreases in power consumption at the location, electricity charges at the location, and the amount of power generated at the location. A load balancing setting unit performs load transfer between multiple servers based on the aforementioned target power value, information on the correspondence between load and power consumption, and measured load values ​​for each server. A control device equipped with the following features.

2. The load balancing setting unit calculates the required load for each server at each location based on the predicted load of the service, the target power value, and the corresponding information, and performs load transfer between multiple servers based on the calculated required load. The control device according to claim 1.

3. In order to control power consumption based on the target power value, the load balance setting unit, in addition to the load shifting, issues instructions to the monitoring and control device of the site, thereby controlling the power consumption of the ancillary equipment at that site. The control device according to claim 1 or 2.

4. The load balancing setting unit uses the service requirements of the service as a constraint when performing the load shift based on the target power value. The control device according to claim 1 or 2.

5. A program for causing a computer to function as a component of the control device described in any one of claims 1 to 4.

Images