Fan efficiency control method and server

Abstract

A fan efficiency control method is used for a server, the server comprises a plurality of fans and at least one sensor, and the fan efficiency control method comprises the following steps: obtaining a plurality of system parameters of the plurality of fans of the server; obtaining a current temperature through the at least one sensor, and obtaining a temperature parameter corresponding to a main heat source of the server according to the current temperature; calculating a rotating speed weight corresponding to each of the fans according to the system parameters, a modulation function and the temperature parameter; and adjusting the rotating speed corresponding to one of the fans according to the rotating speed weight.

Description

Technical Field

[0001] The present invention relates to a fan efficiency control method and a server, and in particular to a fan efficiency control method and a server for dynamically adjusting fan speed weight according to a modulation function. Background Art

[0002] Server rooms are high-energy-consuming equipment. Especially driven by popular technologies such as artificial intelligence (AI), cloud services (Cloud Service), 5G networks and the Internet of Things (IOT), the huge demand for servers has brought considerable power consumption. Therefore, "power efficiency" has become an important consideration in server design. A server is usually equipped with 4 to 10 cooling fans, and the maximum power consumption of each cooling fan can be as high as 100W or more. The power consumption of the fan increases almost to the third power as the speed increases, so when the fan speed is too high, the overall energy consumption of the server will increase significantly.

[0003] In this case, how to dynamically adjust the fan speed of the server and operate it at a better efficiency has become one of the goals that the industry is working hard on. Summary of the invention

[0004] One of the main purposes of the present invention is to provide a fan efficiency control method and a server to solve the above problems.

[0005] The present invention provides a fan efficiency control method for a server, wherein the server comprises a plurality of fans and at least one sensor. The fan efficiency control method comprises obtaining a plurality of system parameters of the plurality of fans of the server; obtaining a current temperature through the at least one sensor, and obtaining a temperature parameter corresponding to a main heat source of the server according to the current temperature; calculating a rotation speed weight corresponding to each of the fans according to the system parameters, a modulation function and the temperature parameter; and adjusting the rotation speed of one of the corresponding fans according to the rotation speed weight.

[0006] The present invention provides a server, comprising a plurality of fans; at least one sensor; a plurality of PID (Proportional-Integral-Derivative) controllers coupled to the fans; and a processor coupled to the sensors and the PID controllers for executing a fan efficiency control method. The fan efficiency control method comprises obtaining a plurality of system parameters of the fans of the server; obtaining a current temperature through the at least one sensor, and obtaining a temperature parameter corresponding to a main heat source of the server according to the current temperature; calculating a rotation speed weight corresponding to each of the fans according to the system parameters, a modulation function and the temperature parameter; and adjusting the rotation speed of one of the corresponding fans through the PID controllers according to the rotation speed weight. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1A A schematic diagram of a server according to an embodiment of the present invention;

[0008] Figure 1B A schematic diagram of the layout inside the server casing;

[0009] Figure 2 A schematic diagram of a fan efficiency control method flow chart according to an embodiment of the present invention;

[0010] Figure 3 A schematic diagram of a server according to an embodiment of the present invention;

[0011] Figure 4 is a schematic diagram of a modulation function according to an embodiment of the present invention;

[0012] Figure 5 A schematic diagram of a graphical model of a fan efficiency control method according to an embodiment of the present invention;

[0013] FIG. 6A to FIG. 6C A schematic diagram showing the power consumption of multiple fans in conventional technology;

[0014] FIG. 7A to FIG. 7C FIG. 4 is a schematic diagram of the power consumption of multiple fans according to an embodiment of the present invention.

[0015] Explanation of symbols

[0016] 1,3: Server

[0017] 2: Process

[0018] 10: Processor CPU1, CPU2: Central Processing Unit

[0019] D1: Memory

[0020] S200, S202, S204, S206: Steps

[0021] 20, S1~S3: Sensor

[0022] 40, F1~F6: Fan

[0023] 30, PID1~PID3: PID controller

[0024] E: Temperature error vector

[0025] e1, e2, e3: temperature error

[0026] U: Required speed vector

[0027] u1,u2,u3: required speed

[0028] W: speed weight vector DETAILED DESCRIPTION

[0029] Certain words are used in the specification and subsequent patent applications to refer to specific components. A person with ordinary knowledge in the field should understand that hardware manufacturers may use different terms to refer to the same component. This specification and subsequent patent applications do not use differences in names as a way to distinguish components, but use differences in the functions of components as the criteria for distinction. The term "including" mentioned throughout the specification and subsequent patent applications is an open term and should be interpreted as "including but not limited to". In addition, the term "coupled" here includes any direct and indirect electrical connection means. Therefore, if the text describes a first device coupled to a second device, it means that the first device can be directly electrically connected to the second device, or indirectly electrically connected to the second device through other devices or connection means.

[0030] Please refer to Figure 1A , Figure 1AIt is a schematic diagram of a server 1 according to an embodiment of the present invention. The server 1 includes a processor 10, at least one sensor 20, a plurality of PID (Proportional-Integral-Derivative) controllers 30, and a plurality of fans 40. The processor 10 is coupled to at least one sensor 20 and a plurality of PID controllers 30, and is used to execute a fan efficiency control method to dynamically adjust the fan speeds of the plurality of fans 40 in the server 1 and enable the plurality of fans 40 to operate at optimal efficiency. It should be noted that the server 1 only represents the necessary components required to execute the fan efficiency control method, and its basic architecture is well known in the art, so it will not be repeated. A person with ordinary knowledge in the art can appropriately add other components as needed, such as a motherboard, power supply, memory, CPU (Central Processing Unit), GPU (Graphics Processing Unit), etc., but is not limited thereto, or implement the server 1 with appropriate devices or equipment. For example, please refer to Figure 1B , Figure 1B Schematic diagram of the layout inside the casing of server 1. Server 1 includes dual CPUs (CPU1, CPU2), memory D1, six fans (F1-F6) and at least one sensor (not shown). Figure 1B Specifically, when the server 1 is operating, the dual CPUs (CPU1, CPU2) and the memory D1 may generate a large amount of heat energy, and the processor 10 executes the fan efficiency control method to dynamically adjust the fan speeds of the six fans (F1~F6) and make the six fans (F1~F6) operate at the best efficiency respectively.

[0031] The fan efficiency control method executed by the processor 10 can be summarized into a process 2, such as Figure 2 Process 2 includes the following steps:

[0032] Step S200: obtaining a plurality of system parameters of a plurality of fans of the server.

[0033] Step S202: Obtain a current temperature through at least one sensor, and obtain a temperature parameter corresponding to a main heat source of the server according to the current temperature.

[0034] Step S204: Calculate a speed weight corresponding to each fan according to a plurality of system parameters, the modulation function and the temperature parameter.

[0035] Step S206: adjusting the speed of one of the corresponding plurality of fans according to the speed weight.

[0036] According to process 2, in step S200, the processor 10 obtains a plurality of system parameters of a plurality of fans 40 of the server. The plurality of system parameters may include, but are not limited to, the number of fans, a distance between each fan, etc. For example, please refer to Figure 3 , Figure 3 It is a schematic diagram of a server 3 according to an embodiment of the present invention. The server 3 includes a plurality of fans F1 to F6 and a plurality of sensors S1 to S3. The plurality of sensors S1 to S3 correspond to the plurality of main heat sources of the server 3, such as, but not limited to, a central processing unit (CPU), a dual in-line memory (DIMM) and a graphics processing unit (GPU). In addition, the processor 10 can dynamically adjust the fan speed of the plurality of fans 40 for the plurality of main heat sources and make them operate at a better efficiency. It should be noted that FIG. 3 is only an embodiment of the present invention. A person with ordinary knowledge in the field can appropriately adjust the number of fans and sensors according to the needs of the system. For the convenience of explanation, the following uses a main heat source of the server and its corresponding sensor S2 to illustrate the concept of the present invention.

[0037] In one embodiment, the number of fans of the server 3 is equal to 6. The processor 10 determines a fan anchor point and the number of fan anchor points based on the distance between the sensor S2 and each fan F1~F6. For example, the distance between the sensor S2 and the fan F4 is the shortest, and the processor 10 can determine that the fan F4 is the fan anchor point. Furthermore, the number of fan anchor points can be set to 2, so the processor 10 determines that the fan F5 below the fan F4 is also a fan anchor point. In other words, for the heat dissipation of the main heat source, the fan F4 and the fan F5 are the two main fans, and the fans F1~F3 and F6 are the four secondary fans. It should be noted that the number of fan anchor points is related to the computing power of the processor 10, and those with ordinary knowledge in this field can appropriately increase the number of fan anchor points as needed.

[0038] In step S202, the processor 10 obtains a temperature parameter corresponding to a main heat source of the server. Specifically, the sensor S2 can sense a current temperature of the main heat source, so that the processor 10 can determine the temperature parameter of the main heat source according to the current temperature and a set temperature corresponding to the main heat source. For example, the temperature parameter is the difference between the set temperature and the current temperature, that is, the temperature error. The set temperature is, for example, defined in a thermal table.

[0039] In step S204, the processor 10 may set a plurality of initial weights corresponding to the plurality of fans F1-F6. In this way, the processor 10 may calculate a plurality of speed weights corresponding to the plurality of fans F1-F6 according to a plurality of system parameters, a modulation function and a temperature parameter. The modulation function is a modulation function for modifying a fan speed vector (fan vector). The modulation function may be customized by a designer and stored in the server 1. Please refer to Figure 4 , Figure 4 FIG. 1 is a schematic diagram of a modulation function according to an embodiment of the present invention. Figure 4 As shown, when the temperature error is 2 to 6 degrees, the temperature error is linearly related to the reduction in the speed weight. For example, when the temperature error is 6, the processor 10 can reduce the speed weight by 0.01, that is, 1%. It should be noted that Figure 4 The modulation function is an embodiment of the present invention, and those skilled in the art may make different modifications thereto, without limitation thereto. Further, for heat dissipation of the main heat source, fan F4 and fan F5 are two main fans, so the processor 10 decides to maintain the initial weights of fan F4 and fan F5. On the other hand, the processor 10 adjusts the speed weights of the secondary fans (fans F1 to F3 and fan F6) according to the modulation function and the temperature error. For example, most of the initial weights of the majority of fans F1 to F6 are 1, which can be expressed as an initial weight vector W0 = [1, 1, 1, 1, 1], and the adjusted speed weight vector W1 can be expressed as W1 = [w1, w2, w3, 1, 1, w6]. In other words, after adjustment, the speed weights of fans F4 and F5 are still maintained at the initial weights equal to 1. In this way, the processor 10 can dynamically reduce the speed weights of the secondary fans so that most of the fans F1 to F6 operate at optimal efficiency. It should be noted that the plurality of fans F1 to F6 in the above embodiment have a one-to-one relationship with the plurality of speed weights, and a person skilled in the art may make different modifications accordingly without being limited thereto. For example, fans F1 and F2 correspond to a first speed weight, fans F3 and F4 correspond to a second speed weight, and fans F5 and F6 correspond to a third speed weight.

[0040] In step S206, the processor 10 adjusts the speed of one of the corresponding plurality of fans through a plurality of PID controllers 30 according to a plurality of speed weights. In detail, after the processor 10 obtains the temperature parameter or calculates the temperature error, the PID controller 30 can obtain a required speed according to the temperature error. In this way, the processor 10 can dynamically adjust the speeds of the plurality of fans F1 to F6 according to the required speed and the adjusted speed weight vector W1. For example, the processor 10 obtains the temperature error e2 from the sensor S2 corresponding to the main heat source and calculates the speed weight vector W1 = [w1, w2, w3, 1, 1, w6]. The plurality of PID controllers 30 calculate the required speed u2 according to the temperature error e2. In this way, the processor 10 can adjust the speeds of the plurality of fans F1 to F6 to u2*W1 through the plurality of PID controllers 30 so that they operate at the best efficiency.

[0041] In one embodiment, please refer to Figure 5 , Figure 5 Schematic diagram of a graphical model of the fan efficiency control method according to an embodiment of the present invention. Specifically, the server 3 includes three sensors S1-S3 corresponding to the three main heat sources of the server, the processor 10 obtains temperature errors e1, e2, e3 from the sensors S1-S3, the PID controllers PID1-PID3 calculate the required speeds u1, u2, u3 according to the temperature errors e1, e2, e3 and express them as the required speed vector U=[u1,u2,u3], the processor 10 can adjust the speeds of the plurality of fans F1-F6 to U*W1 respectively, so that they operate at the best efficiency.

[0042] For further information, please refer to Figure 5 , step 204 of process 2 may also include a conditional decision mechanism, which determines whether to adjust the plurality of speed weights corresponding to the plurality of fans by determining whether the temperature parameter and the required speed satisfy an adjustment condition. In one embodiment, the processor 10 may determine whether the temperature parameter is less than a first critical value, and whether the plurality of required speeds are greater than a second critical value. When the temperature parameter is less than the first critical value and the plurality of required speeds are greater than the second critical value, the processor 10 calculates the plurality of speed weights according to the modulation function and the plurality of initial speed weights; and when the temperature parameter is greater than or equal to the first critical value, or the plurality of required speeds are less than or equal to the second critical value, the plurality of speed weights are maintained as the plurality of initial speed weights. For example, when the temperature error e2 is less than 1 degree and the required speed u2 is greater than 50% of the maximum speed, the processor 10 calculates the plurality of speed weights according to the modulation function and the plurality of initial speed weights. In this way, the processor 10 can set the speeds of the plurality of fans according to the adjusted speed weights or the unadjusted initial speed weights when there is a need to reduce the fan efficiency, so that the fans operate at the best efficiency.

[0043] For the power consumption of the plurality of fans F1 to F6 in the server 3 of the present invention, please refer to FIG. 6A to FIG. 6C and FIG. 7A to FIG. 7C , FIG. 6A to FIG. 6C This is a schematic diagram of the power consumption of multiple fans F1 to F6 when using traditional technology. FIG. 7A to FIG. 7C FIG. 2 is a schematic diagram of the power consumption of the plurality of fans F1 to F6 according to an embodiment of the present invention. Specifically, the plurality of fans F1 to F6 in the server 3 can be divided into primary fans and secondary fans. Fig. 6A As shown, in the conventional technology, after the primary fan and the secondary fan are operated in a synchronous manner for a period of time, the temperature error between the primary fan and the secondary fan tends to be stable, so the fan speeds of the primary fan and the secondary fan are stabilized to a duty cycle between 75% and 80%. Figure 6B As shown, in the conventional technology, the speed weights of all fans are 1 and will not change. Therefore, Figure 6C As shown, the power consumption of most fans F1-F6 will be stabilized to 120W. In contrast, the processor 10 of the embodiment of the present invention will adjust the speed weights of the primary fan and the secondary fan so that the primary fan and the secondary fan operate at the best efficiency. For example, FIG. 7A to FIG. 7B As shown, in the embodiment of the present invention, after the server 3 operates for 140 seconds, the speed weight of the secondary fan begins to decrease, and finally the speed of the main fan stabilizes to 70% of the working cycle and the speed of the secondary fan stabilizes to 60% of the working cycle. Figure 7C As shown, the power consumption of most fans F1-F6 is stabilized to 60W, and compared with the traditional technology, the energy saving effect is close to 50%.

[0044] It should be noted that server 1 is an embodiment of the present invention. A person with ordinary knowledge in the art can combine, modify or change the above-mentioned embodiments according to the spirit of the present invention, but is not limited thereto. All the above descriptions, steps, and / or processes (including recommended steps) can be implemented through hardware, software, firmware (i.e., a combination of hardware devices and computer instructions, the data in the hardware devices are read-only software data), electronic systems, or a combination of the above devices. Hardware can include analog, digital and hybrid circuits (i.e., microcircuits, microchips or silicon chips). Electronic systems can include system on chip (SoC), system in package (SiP), computer on module (CoM) and server 1. The process steps and embodiments of the present invention can exist in the form of program code or instructions and be stored in a memory. The memory may be a computer-readable recording medium, and the memory may include a read-only memory (ROM), a flash memory (Flash Memory), or a random-access memory (RAM), but is not limited thereto. The above-mentioned processes and embodiments may be compiled into program codes or instructions and stored in the memory. The processor 10 may be used to read and execute the program codes or instructions stored in the memory to implement all the aforementioned steps and functions.

[0045] In this embodiment, the server of the present invention can be used for artificial intelligence (AI) computing and edge computing, and can also be used as a 5G server, a cloud server, or an Internet of Vehicles server.

[0046] In summary, compared to conventional technologies, the fan efficiency control system of the present invention dynamically adjusts the speed weights of the plurality of fans in the server and replaces the complicated weight table settings in conventional technologies through vector calculations. This not only operates the plurality of fans at optimal efficiency, but also makes the fan efficiency control method easier to implement.

[0047] The above description is only a preferred embodiment of the present invention. All equivalent changes and modifications made according to the scope of the patent application of the present invention should fall within the scope of the present invention.

Claims

1. A fan efficiency control method, characterized in that: For a server, the server includes a plurality of fans and at least one sensor, the fan efficiency control method includes: Obtaining a plurality of system parameters of a plurality of fans of the server; Obtaining a current temperature through the at least one sensor, and obtaining a temperature parameter corresponding to a main heat source of the server according to the current temperature; Obtaining a modulation function; Calculating a rotation speed weight of each of the fans according to the system parameters, the modulation function and the temperature parameter; and According to the rotation speed weight, the rotation speed of a corresponding one of the fans is adjusted.

2. The fan efficiency control method according to claim 1, characterized in that: The step of obtaining the system parameters of the fans includes: Obtain a fan quantity of the fans; Get the number of anchor points of a fan; and According to the number of the fan anchor points and the main heat source, a part of the fans is defined as a first fan group, and another part of the fans is defined as a second fan group, wherein the number of the first fan group is equal to the number of the fan anchor points.

3. The fan efficiency control method according to claim 2, characterized in that: The step of calculating the rotation speed weight of each of the fans according to the system parameters, the modulation function and the temperature parameter comprises: respectively determining an initial speed weight of each of the fans; Calculate the speed weight corresponding to the second fan group according to the modulation function, the temperature parameter and the initial speed weight of each of the fans; as well as The initial rotation speed weight corresponding to the first fan group is maintained.

4. The fan efficiency control method according to claim 1, characterized in that: The step of obtaining the temperature parameter corresponding to the main heat source of the server comprises: The temperature parameter of the main heat source is obtained according to the current temperature and a set temperature corresponding to the main heat source.

5. The fan efficiency control method according to claim 1, characterized in that: The step of calculating the rotation speed weight of each of the fans according to the system parameters, the modulation function and the temperature parameter comprises: respectively determining an initial speed weight of each of the fans; Calculating a required rotation speed of each of the fans; Determining whether the temperature parameter is less than a first critical value, and whether the required rotation speed of each of the fans is greater than a second critical value; When the temperature parameter is less than the first critical value and the required speed of each of the fans is greater than the second critical value, the speed weight of each of the fans is calculated according to the modulation function and the initial speed weight of each of the fans; as well as When the temperature parameter is greater than or equal to the first critical value, or the required rotational speed is less than or equal to the second critical value, the rotational speed weight is maintained as the initial rotational speed weight.

6. A server comprising: Many fans; at least one sensor; A plurality of proportional-integral-derivative controllers are coupled to the fans; and A processor is coupled to the sensor and the PID controllers, and is used to execute a fan efficiency control method. The fan efficiency control method includes: Obtaining a plurality of system parameters of the fans of the server; Obtaining a current temperature through the at least one sensor, and obtaining a temperature parameter corresponding to a main heat source of the server according to the current temperature; Obtaining a modulation function; Calculating a rotation speed weight of each of the fans according to the system parameters, the modulation function and the temperature parameter; and According to the speed weight, the speed of a corresponding one of the fans is adjusted through the proportional-integral-derivative controllers.

7. The server according to claim 6, characterized in that: The step of obtaining the system parameters of the fans includes: Obtain a fan quantity of the fans; Get the number of anchor points of a fan; and According to the number of the fan anchor points and the main heat source, a part of the fans is defined as a first fan group, and another part of the fans is defined as a second fan group, wherein the number of the first fan group is equal to the number of the fan anchor points.

8. The server according to claim 7, characterized in that: The step of calculating the rotation speed weight of each of the fans according to the system parameters, the modulation function and the temperature parameter comprises: respectively determining an initial speed weight of each of the fans; Calculating the speed weight of the second fan group according to the modulation function, the temperature parameter and the initial speed weight of each of the fans; as well as Maintain the initial speed weight of the first fan group.

9. The server according to claim 6, characterized in that: The step of obtaining the temperature parameter corresponding to the main heat source of the server comprises: The temperature parameter of the main heat source is obtained according to the current temperature and a set temperature corresponding to the main heat source.

10. The server according to claim 6, characterized in that: The step of calculating the rotation speed weight of each of the fans according to the system parameters, the modulation function and the temperature parameter comprises: Determining an initial speed weight corresponding to each of the fans; Calculating the required speed of each of the fans through the proportional-integral-derivative controllers; Determining whether the temperature parameter is less than a first critical value, and whether the required rotation speed of each of the fans is greater than a second critical value; When the temperature parameter is less than the first critical value and the required speed of each of the fans is greater than the second critical value, the speed weight of each of the fans is calculated according to the modulation function and the initial speed weight of each of the fans; as well as When the temperature parameter is greater than or equal to the first critical value, or the required rotational speed is less than or equal to the second critical value, the rotational speed weight is maintained as the initial rotational speed weight.

Images