A fan strategy adjustment method based on an optimization algorithm

Abstract

The application belongs to the technical field of server fan speed regulation, and particularly relates to a fan strategy regulation method based on an optimization algorithm, a heat dissipation mixed strategy model is created, there is one or more fans and a plurality of hot spots in the system, and each fan is responsible for heat dissipation of a group of hot spots; a fan speed mixed strategy matrix is constructed, each row in the fan speed strategy matrix corresponds to a strategy distribution; based on the optimization algorithm, a scene in which a plurality of fans cover a plurality of hot spots is simulated, an optimal solution of the heat dissipation mixed strategy model is solved in the system environment, and heat dissipation strategy deployment is realized based on the optimal solution. By establishing a model in which heat dissipation effects influence each other, the problem of maximizing heat dissipation energy efficiency under limited power consumption is converted into the problem of solving an optimal solution in an optimization model, and through a mixed integer linear programming formula, an optimal strategy and maximum energy efficiency of the multi-fan heat dissipation strategy are obtained, so that the fans in the equipment can work with the optimal strategy and the maximum energy efficiency.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of server fan speed regulation, and particularly relates to a fan strategy regulation method based on an optimization algorithm. BACKGROUND

[0002] The development of electronic technology enables the control of fans through electronic circuits, providing more precise speed control. The widespread use of microcontrollers provides an intelligent control core for fan speed regulation. Sensing technologies such as temperature sensors and speed sensors can monitor environmental parameters in real time, providing a basis for speed regulation. With the increasing awareness of energy conservation, energy saving through speed regulation has become an important focus. In electronic devices, good heat dissipation is crucial for performance and lifespan, so optimizing server fan speed can optimize heat dissipation and prolong server lifespan. Different speeds meet users' needs for air volume and noise, improving server user experience. Intelligent control enables automatic fan speed regulation, dynamically adjusting to actual conditions. Environmental requirements reduce energy consumption and environmental impact through speed regulation. System integration requires fan speed regulation to work in coordination with other system components.

[0003] The purpose of intelligent fan speed regulation strategies is to meet cooling needs while minimizing fan noise and energy consumption. Here are some common intelligent fan speed regulation strategies:

[0004] Temperature sensing speed regulation: Temperature sensors monitor environmental or device temperature, automatically adjusting fan speed based on temperature changes. When temperature rises, fan speed increases to provide more cooling; when temperature drops, fan speed decreases to reduce noise and energy consumption. However, temperature sensors may be affected by factors such as line resistance, external electromagnetic fields, and other interference factors, resulting in large measurement errors. Temperature sensors have a long response time and may not meet the requirements of actual applications. Environmentally sensitive, temperature sensors may be affected by environmental temperature changes, humidity, vibration, and other factors, resulting in unstable measurement signals.

[0005] Pulse width modulation (PWM) speed regulation: PWM speed regulation controls fan speed by changing the duty cycle of the fan's power supply. The higher the duty cycle, the faster the fan speed; the lower the duty cycle, the slower the fan speed. PWM speed regulation can achieve fine speed control and is relatively efficient. The design and implementation of PWM speed regulation systems are relatively complex, requiring precise time control and filter design to process PWM signals to reduce output ripple and electromagnetic interference. This increases system complexity and maintenance difficulty, and requires special control circuits and high-speed switches, resulting in higher hardware costs. High-frequency pulse signals generated by PWM technology can cause electromagnetic interference and noise, especially in low-frequency PWM signals, which may produce audio noise, affecting the normal operation of electronic devices.

[0006] Fuzzy control speed regulation: based on fuzzy logic algorithm, adjusting fan speed according to temperature, humidity, passenger flow and other factors. Fuzzy control speed regulation can better adapt to complex environmental conditions, but requires more sensors and computing power consumption.

[0007] The above-mentioned fan adjustment strategies are generally "single temperature single control" and "multiple fans single control", that is, the fan is adjusted according to a certain hot spot, or multiple fans are adjusted by the same strategy, and the strategy distribution is controlled according to temperature, and the adjustment factor is single, and the mutual influence between adjacent fans is not considered.

[0008] Therefore, the present application considers the influence of the heat dissipation effect of multiple heat dissipation fans in the same device on each other, and accordingly establishes a model of maximizing heat dissipation energy efficiency under rated power consumption. Since the model considers the mutual influence between fan heat dissipation strategies, a hybrid strategy is used to represent and calculate the optimal heat dissipation strategy of each fan. SUMMARY

[0009] The purpose of the present application is to provide a fan strategy adjustment method based on optimization algorithm, which considers the influence of the heat dissipation effect of multiple heat dissipation fans in the same device on each other, and accordingly establishes a model of maximizing heat dissipation energy efficiency under rated power consumption. Since the model considers the mutual influence between fan heat dissipation strategies, a hybrid strategy is used to represent and calculate the optimal heat dissipation strategy of each fan.

[0010] To solve the above technical problems, the technical scheme adopted by the present application is as follows:

[0011] A fan strategy adjustment method based on optimization algorithm, comprising the following steps:

[0012] S1: creating a heat dissipation hybrid strategy model, the system has one or more fans and a plurality of hot spots, and each fan i is responsible for heat dissipation of a group of hot spots;

[0013] S2: constructing a fan speed hybrid strategy matrix, each row of the fan speed strategy matrix corresponds to a strategy distribution;

[0014] S3: based on the optimal algorithm, simulating the scene of multiple fans covering multiple hot spots, solving the optimal solution of the heat dissipation hybrid strategy model in the system environment, and realizing the deployment of heat dissipation strategy based on the optimal solution.

[0015] Preferably, the specific process in step S1 is as follows:

[0016] S11: creating a heat dissipation hybrid strategy model, the heat dissipation hybrid strategy model has one or more fans I, I = {1, 2, 3, ···, n} and a plurality of hot spots;

[0017] S12: each fan i a group of hot spots responsible for heat dissipation T i , , and , i.e. the number of hot spots covered by each fan ≥ 1.

[0018] Preferably, the specific process of constructing the fan speed hybrid strategy matrix in step S2 is as follows:

[0019] S21: set the corresponding heat dissipation strategy for each hot spot to which the strategy is distributed, and use probability to represent the heat dissipation strategy of fan i to hot spot;

[0020] S22: the strategy of fan i to all hot spots covered by it is represented by a hybrid strategy matrix Q , , and , the temperature reduction value of hot spot v is represented by j . j

[0021] Among them,

[0022] .

[0023] Preferably, in step S2, the fan speed hybrid strategy matrix introduces the correlation degree between fans , and the specific process is as follows:

[0024] Let fan A cover a specified number of hot spots. Due to the proximity of the hot spots or the coverage of the air duct, other hot spots will be affected by the heat dissipation effect of fan A, to some extent, expanding the heat dissipation effect of fan A. After allocating heat dissipation power to fan A and improving the heat dissipation energy efficiency of fan A, the heat dissipation energy efficiency of other hot spots associated with the hot spot is indirectly increased. The indirect influence of indirectly increasing the heat dissipation energy efficiency of other hot spots associated with the hot spot is transmitted by the correlation degree , and is used to represent the correlation degree between the current hot spot j and the associated hot spot .

[0025] Preferably, in step S2, the fan speed hybrid strategy matrix introduces heat dissipation power c , and the specific process is as follows:

[0026] The power consumption of the fan is calculated by , and all the total heat dissipation power consumption is C , wherein the power consumption required for fan i to cover hot spots is C .i , , and total heat dissipation cost C Also meet: .

[0027] Preferably, in step S2, the fan speed mixing strategy matrix introduces an effective coefficient s And the utility, the specific process is as follows:

[0028] The parameter s j reacts the effectiveness of the fan on the hot spot j , reacts the effectiveness of the fan on the hot spot j , and s j is expressed as the effective coefficient of the covered hot spot j , when fan A only covers hot spot j , s j The value of 1; s j The value of s j 0 means that the heat dissipation of fan A on the hot spot is completely ineffective;

[0029] The heat dissipation power consumption of hot spot j will cause power consumption C j The heat dissipation of fan A only on hot spot , the generated utility is recorded as U i,j , v j Indicates the temperature drop value of hot spot j ;

[0030] Let the heat dissipation energy efficiency only depend on the temperature drop value of hot spot j v j And the heat dissipation strategy of the hot spot, the heat dissipation of fan i on hot spot j will consume heat dissipation power consumption c i,j Hot spot j Due to the proximity to hot spot Distance or share the same air duct, generate hitchhiking effect, the size of the hitchhiking effect is determined by the correlation degree ; Now the fan dissipates heat on hot spot Based on the hitchhiking effect, the total utility value of the fan at this time will be expressed as:

[0031] .​

[0032] Preferably, the specific process of step S3 is as follows:

[0033] S31: Express the total heat dissipation available for the heat dissipation hotspot matrix T as C , and give the initial heat dissipation strategy matrix satisfying uniform distribution , and the initial heat dissipation strategy size is ;

[0034] S32: According to the initial heat dissipation strategy matrix , assign the heat dissipation power of the fan to the hotspot j , and the specific formula is as follows:

[0035] ;

[0036] Through the heat dissipation power formula of the fan assigned to the hotspot j , the initial heat dissipation matrix is obtained.

[0037] S33: Establish the initial heat dissipation matrix of all hotspots , and then calculate the initial heat dissipation efficiency matrix by the formula ;

[0038] S34: Set the effective coefficient matrix S j , and based on the initial heat dissipation matrix , the initial heat dissipation efficiency matrix , and the effective coefficient matrix S j , calculate the new heat dissipation strategy of each hotspot q j , q j The specific calculation formula is as follows:

[0039] ;

[0040] Wherein, ;

[0041] S35: Obtain the new heat dissipation strategy matrix Q , and then obtain the new heat dissipation matrix by c , and calculate the new heat dissipation efficiency matrix by U , and output the results Q , U .

[0042] The beneficial effects of the present application include:

[0043] The application provides a fan strategy adjustment method based on an optimization algorithm, creates a heat dissipation mixed strategy model, and the system has one or more fans and a plurality of hot spots, and each fan is responsible for dissipating heat of a group of hot spots; a fan speed mixed strategy matrix is constructed, each row in the fan speed strategy matrix corresponds to a strategy distribution; based on an optimization algorithm, a scene in which a plurality of fans cover a plurality of hot spots is simulated, an optimal solution of the heat dissipation mixed strategy model is solved in a system environment, and heat dissipation strategy deployment is realized based on the optimal solution. By establishing a model in which heat dissipation effects influence each other, the problem of maximizing heat dissipation energy efficiency under limited power consumption is converted into the problem of solving an optimal solution in an optimization model, and the optimal strategy and the maximum energy efficiency of the multi-fan heat dissipation strategy are solved through a mixed integer linear programming formula, so that the fans in the equipment can work with the optimal strategy and the maximum energy efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 It is a heat dissipation strategy diagram of the application.

[0045] Figure 2 It is a parameter value diagram of the application.

[0046] Figure 3 It is a hot spot value, correlation and initial strategy distribution diagram of the application.

[0047] Figure 4 It is a heat dissipation energy efficiency growth rate diagram of the application.

[0048] Figure 5 It is a total heat dissipation energy efficiency comparison diagram considering correlation or not under different heat dissipation power consumptions of the application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings Figures 1-5 The application will be further described in detail:

[0050] Example 1

[0051] A fan strategy adjustment method based on an optimization algorithm, comprising the following steps:

[0052] S1: creating a heat dissipation mixed strategy model, the system has one or more fans and a plurality of hot spots, and each fan is responsible for dissipating heat of a group of hot spots; i

[0053] S2: constructing a fan speed mixed strategy matrix, each row in the fan speed strategy matrix corresponds to a strategy distribution;

[0054] S3: based on an optimization algorithm, a scene in which a plurality of fans cover a plurality of hot spots is simulated, an optimal solution of the heat dissipation mixed strategy model is solved in a system environment, and heat dissipation strategy deployment is realized based on the optimal solution. ​

[0055] In this embodiment, the optimization algorithm is applied to the study of fan cooling speed regulation strategy, a multi-fan and multi-hot spot cooling model is established, and the temperature values of multiple hot spots in the system, the mutual influence of fan cooling effect, fan power consumption and other factors are combined to maximize the cooling energy efficiency. When only one fan operates in the system, it will have different cooling effects on different hot spots. Similarly, when multiple fans operate in the system, they will also affect each other, which is called "neighbor effect".

[0056] The established cooling hybrid strategy model is basically a negative feedback control according to the temperature value of the hot spot, but it additionally considers the influence of "neighbor effect" on fan cooling. Due to the fan cooling effect, the design of the air duct, or the mutual promotion or mutual offset, the positive superposition of the cooling effect is similar to "hitchhiking", and the negative mutual offset will waste the actual energy efficiency of the fan. Under the given total power consumption, a reasonable cooling strategy is established for the hot spot according to the energy efficiency of the fan cooling. The overall cooling energy efficiency of the system is optimized or maximized. According to this point, the problem is converted into the calculation of the optimal solution in the optimization model.

[0057] Embodiment 2

[0058] On the basis of embodiment 1, the specific process in step S1 is as follows:

[0059] S11: Create a cooling hybrid strategy model, which has one or more fans I, I = {1, 2, 3, ···, n} and several hot spots;

[0060] S12: Each fan i is responsible for cooling a group of hot spots T i , , and , that is, the number of hot spots covered by each fan ≥ 1.

[0061] In this embodiment, the specific process of constructing the fan speed hybrid strategy matrix in step S2 is as follows:

[0062] S21: Set the corresponding cooling strategy for each hot spot distributed by the strategy to the probability representing the cooling strategy of fan i for the hot spot;

[0063] S22: The strategy of fan i for all the hot spots it covers is represented by a hybrid strategy matrix Q , , and , the fan speed is adjusted v j indicates the hotspot j temperature reduction value

[0064] wherein,

[0065] .

[0066] In step S2, the fan speed mixed strategy matrix introduces the correlation degree between fans The specific process is as follows:

[0067] Let fan A cover a specified number of hotspots. Due to the proximity of the hotspots or the coverage of the air duct, other hotspots will be affected by the heat dissipation effect of fan A, to some extent, expanding the heat dissipation effect of fan A. After allocating the heat dissipation power consumption to fan A and improving the heat dissipation energy efficiency of fan A, the heat dissipation energy efficiency of other hotspots associated with the hotspot is indirectly increased. The indirect influence of indirectly increasing the heat dissipation energy efficiency of other hotspots associated with the hotspot is transmitted by the correlation degree , wherein indicates the current hotspot j and the correlation degree between the associated hotspots .

[0068] In step S2, the fan speed mixed strategy matrix introduces the heat dissipation power consumption c The specific process is as follows:

[0069] The power consumption of the fan is calculated by The total heat dissipation power consumption is C , wherein the fan i covers the hotspots and needs to consume power C i , , and the total heat dissipation cost C also satisfies: .

[0070] In step S2, the fan speed mixed strategy matrix introduces the effective coefficient s and the utility, and the specific process is as follows:

[0071] The parameter s j reacts the effectiveness of the fan on the hotspot j , s j ∈[0, 1], and s j indicates the effective coefficient of the covered hotspot j , when fan A only covers the hotspot j , s j , the value of s is 1.j The value of defines the actual effective degree of heat dissipation of the fan to the hotspot, s j When the value is 0, it means that the heat dissipation of fan A to the hotspot is completely ineffective.

[0072] The heat dissipation of fan A to the hotspot j will cause the consumption of power consumption C j Fan A only dissipates heat to the hotspot j ( j ∈T) and the generated utility is denoted as U i,j The temperature reduction value of the hotspot v j is denoted as j

[0073] Let the heat dissipation energy efficiency only depend on the temperature reduction value of the hotspot j v j and the heat dissipation strategy of the hotspot, the heat dissipation of fan i to the hotspot j will consume heat dissipation power consumption c i,j The hotspot j has a hitchhiking effect with the hotspot due to the proximity of the distance or sharing the same air duct, and the size of the hitchhiking effect is determined by the correlation degree . Now that the fan dissipates heat to the hotspot j , based on the hitchhiking effect, the total utility value of the fan at this time will be represented by the following formula:

[0074] .

[0075] Referring to Figure 1 , the mixed strategy matrix q corresponding thereto is:

[0076] .

[0077] In the strategy matrix, the first m row represents the fan m , and the first n column represents the first n hotspot covered by the fan. Therefore, Figure 1 ​​The corresponding strategy matrix shows that the first fan only covers hot spots 3 and 7 and the heat dissipation strategies are 0.5 and 0.5 respectively; similarly, the second row represents the second fan covering hot spots 1, 4 and 8, and the heat dissipation strategies are 0.333333, 0.333333 and 0.333333 respectively; the third row represents the third fan covering hot spots 2, 5 and 6, and the heat dissipation strategies are 0.333333, 0.333333 and 0.333333 respectively.

[0078] Referring to Figure 2 , there are two hot spots, and it is assumed that there are two fans each dissipating heat for one hot spot, the temperature value of each hot spot is 1 (normalized), the correlation degree with each other is 0.5, and the heat dissipation power is 0.5; it is assumed that the temperature of hot spot 1 decreases from 1 to 0, and the effective coefficient is 0.5; considering the "free ride" effect, it can be obtained from that the heat dissipation energy efficiency of hot spot 1 and hot spot 2 is 1.75 and 2.25 respectively.

[0079] Embodiment 3

[0080] On the basis of the embodiment 1 or the embodiment 2, the specific process of step S3 is as follows:

[0081] S31: the total heat dissipation power available for the heat dissipation hot spot matrix T is expressed as C , and the initial heat dissipation strategy matrix satisfying uniform distribution is given as , and the size of the initial heat dissipation strategy is ;

[0082] S32: according to the initial heat dissipation strategy matrix , the heat dissipation power of the fan is allocated to the hot spot j , and the specific formula is as follows:

[0083] ;

[0084] The initial heat dissipation power matrix j is obtained by the heat dissipation power formula of the fan allocated to the hot spot ;

[0085] S33: the initial heat dissipation power matrix C of all hot spots is established * , and the initial heat dissipation energy efficiency matrix is calculated by formula ;

[0086] S34: the effective coefficient matrix S j is set, and the initial heat dissipation power matrix , the initial heat dissipation energy efficiency matrix , and the effective coefficient matrix S j, calculate the new heat dissipation strategy of each hotspot q j , q j The specific calculation formula is as follows:

[0087] ;

[0088] Among them, ;

[0089] S35: get the new heat dissipation strategy matrix Q After that, through Get the new heat dissipation power matrix c , and Calculate the new heat dissipation energy efficiency matrix U , and output the result Q , U .

[0090] To intuitively express how the above algorithm realizes the heat dissipation strategy deployment in the system environment, the following example is given: assuming that there are 8 hotspots in a server, let the temperature reduction value of each hotspot be v , the correlation degree is represented by r , and the initial heat dissipation strategy is represented by q ; According to the simplified topology structure between computers Figure 3 , the influence between any two fans is represented by the correlation degree r . The total heat dissipation power is C , and the total heat dissipation power C is now limited. Through the optimization algorithm, a reasonable allocation strategy is given to maximize the utility of heat dissipation.

[0091] For convenience of calculation, we take the temperature reduction value of each hotspot as 1, and the correlation degree between hotspots r is uniformly 0.5, and the total heat dissipation cost is given C =4.

[0092] Initial heat dissipation strategy matrix:

[0093] Q *=[0.125, 0.125, 0.125, 0.125, 0.125, 0.125, 0.125, 0.125];

[0094] The total heat dissipation power C , the initial heat dissipation power matrix is obtained by :

[0095] C *=[0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5];

[0096] According to The heat dissipation efficiency matrix of all hotspots is obtained:

[0097] U ini = [3.75, 3.0, 3.0, 4.5, 3.75, 3.0, 2.25, 2.25];

[0098] According to the hotspot reduction value, the effective coefficient matrix is set:

[0099] ;

[0100] The above known conditions are brought into , , and the iteration of the heat dissipation strategy matrix is obtained:

[0101] ;

[0102] After obtaining the heat dissipation strategy matrix, the heat dissipation power consumption matrix is updated according to

[0103] ;

[0104] Finally, the heat dissipation efficiency matrix is updated according to :

[0105] .

[0106] In order to verify the effectiveness of the above optimal algorithm, the same total heat dissipation power C is given, and the calculation results of the optimal algorithm are compared with the results obtained without considering the correlation relationship. When the correlation relationship between hotspots is not considered, the corresponding heat dissipation power is often arranged according to the cooling value of the hotspot; the basic relationship satisfies:

[0107] ;

[0108] Further, the heat dissipation power consumption matrix without considering the correlation relationship is obtained: c

[0109] ;

[0110] When making decisions, the correlation relationship is not considered, but when calculating the heat dissipation efficiency, it needs to be calculated in the actual situation (considering the correlation relationship), so the heat dissipation power C is brought into to obtain the heat dissipation efficiency matrix .

[0111] ​Then, the results under different power consumptions and whether considering the correlation relationship are compared, and the results are as shown in Figure 5 Figure 4 Figure 5 It can be seen that the decision considering the mutual influence of heat dissipation often produces higher utility than the decision without considering the mutual influence relationship, and with the increase of energy consumption, the growth rate of heat dissipation utility is also increasing, provided that the total amount of energy consumption does not exceed the upper limit of fan energy efficiency; this shows that the greater the given power consumption is, the more the mutual influence between fans should be considered, and the algorithm can help to fully consider the mutual influence between fan heat dissipation when adjusting the fan strategy, arrange a reasonable distribution mode for the fan, and ensure the optimal heat dissipation energy efficiency under the rated power consumption.

[0112] In summary, the fan strategy adjustment method based on the optimization algorithm provided in the application creates a heat dissipation mixed strategy model, there is one or more fans and a plurality of hot spots in the system, and each fan is responsible for heat dissipation of a group of hot spots; a fan speed mixed strategy matrix is constructed, each row in the fan speed strategy matrix corresponds to a strategy distribution; based on the optimal algorithm, the scene of multiple fans covering multiple hot spots is simulated, the optimal solution of the heat dissipation mixed strategy model is solved in the system environment, and the heat dissipation strategy deployment is realized based on the optimal solution. By establishing a heat dissipation effect mutual influence model, the problem of maximizing the heat dissipation energy efficiency under limited power consumption is converted into the problem of solving the optimal solution in the optimization model, and the optimal strategy and the maximum energy efficiency of the multi-fan heat dissipation strategy are obtained through the mixed integer linear programming formula, so that the fans in the equipment can work with the optimal strategy and the maximum energy efficiency.​​

Claims

1. A fan strategy adjustment method based on an optimization algorithm, characterized in that: The following steps are involved: S1: Create a hybrid cooling strategy model. The system has one or more fans and several hotspots. Each fan is responsible for cooling a group of hotspots. S2: Constructing a fan speed control hybrid strategy matrix, where each row in the fan speed control strategy matrix corresponds to a strategy distribution; S3: Based on the optimal algorithm, the system simulates a scenario where multiple fans cover multiple hotspots, finds the optimal solution for the heat dissipation hybrid strategy model in the system environment, and implements the heat dissipation strategy deployment based on the optimal solution. The specific process in step S1 is as follows: S11: creating a heat dissipation hybrid strategy model, wherein the heat dissipation hybrid strategy model includes one or more fans I, where I={1, 2, 3, . . . , n} and a number of hot spots; S12: Each fan i Responsible for cooling a group of hot spots T i , , as well as , that is, the number of hotspots covered by each fan is ≥1; The specific process of constructing the fan speed regulation hybrid strategy matrix in step S2 is as follows: S21: Let the strategy distribution set the corresponding heat dissipation strategy for each hot spot of its heat dissipation, using probability Indicates fan i Cooling strategies for hot spots; S22: Fan i A mixed strategy matrix is ​​used for the strategies of all hot spots it covers Q To express, ,and ,use v j Indicates hotspots j Temperature reduction value; in, ； The specific process of step S3 is as follows: S31: The total heat dissipation power available from the heat dissipation hotspot matrix T is expressed as C , giving the initial heat dissipation strategy matrix that satisfies uniform distribution , the initial cooling strategy size is ; S32: Based on the initial cooling strategy matrix , a hotspot j Allocate the fan's cooling power consumption. The specific formula is as follows: ； By hot spot j The heat dissipation power consumption formula of the fan is used to obtain the initial heat dissipation power consumption matrix ; S33: Establish the initial heat dissipation power consumption matrix of all hot spots Afterwards, by The initial heat dissipation energy efficiency matrix is ​​calculated using the formula ; S34: Set effective coefficient matrix S j , based on the initial heat dissipation matrix , and the initial heat dissipation efficiency matrix , effective coefficient matrix S j , calculate the corresponding new cooling strategy for each hotspot q j , q j The specific calculation formula is as follows: ； in, , ; S35: Get a new cooling strategy matrix Q Afterwards, through Get the new heat dissipation power matrix c , and by Calculate the new heat dissipation energy efficiency matrix U , and the result Q 、 U Output.

2. The fan strategy adjustment method based on the optimization algorithm according to claim 1, characterized in that: In step S2, the fan speed control hybrid strategy matrix introduces the correlation between fans The specific process is as follows: Let fan A cover a specified hotspot. Due to the proximity of the hotspot or the coverage of the air duct, other hotspots will be affected by the cooling effect of fan A, which will amplify the cooling effect of fan A to a certain extent. Allocate cooling power consumption to fan A, improve the cooling energy efficiency of fan A, and indirectly increase the cooling energy efficiency of other hotspots associated with the hotspot. The indirect impact of indirectly increasing the cooling energy efficiency of other hotspots associated with the hotspot is determined by the correlation degree. To pass on, use Indicates the current hot spot j Related hot spots The correlation between them.

3. The fan strategy adjustment method based on the optimization algorithm according to claim 1, characterized in that: In step S2, the fan speed control hybrid strategy matrix introduces the heat dissipation power consumption c The specific process is as follows: The power consumption of the fan is determined by Calculation, the total heat dissipation power consumption is C , where the fan i Covering the hotspot requires power consumption of C i , , and the total cooling cost C Also meets: .

4. The fan strategy adjustment method based on the optimization algorithm according to claim 1, characterized in that: In step S2, the fan speed control hybrid strategy matrix introduces the effective coefficient s The specific process is as follows: Use parameters s j To react to hot spots j effectiveness, To react to hot spots j Validity, will s j Indicates covered hotspots j The effectiveness coefficient is when fan A only covers the hot spot j hour, s j The value of is 1; s j The value of is defined based on the actual effectiveness of the fan in cooling the hot spot. s j When the value is 0, it means that fan A is completely ineffective in cooling the hotspot; Hotspot j Heat dissipation will cause power consumption C j , direct fan A only towards the hot spot The heat dissipation is recorded as U i,j ,use v j Indicates hotspots j Temperature reduction value; Make cooling efficiency depend only on hot spots j Temperature reduction value v j And the heat dissipation strategy for this hot spot, fan i Hotspot j Heat dissipation consumes heat dissipation power c i,j , hot spots j Due to the hot spots The distance between them is close or they share the same wind channel, which results in a hitchhiking effect. The magnitude of the hitchhiking effect is determined by the "correlation OK; now the fan is on the hot spot To dissipate heat, based on the hitchhiking effect, the total utility value of the fan at this time will be expressed as follows: 。

Images