Dynamic temperature control system for high-density server room based on temperature-humidity-airflow velocity cooperative control

Abstract

The application provides a high-density server room dynamic temperature control system based on temperature-humidity-airflow velocity cooperative control, comprising a heat distribution map construction module, which is used for periodically collecting temperature correlation data in the server room, and generating a dynamic heat distribution map of the server room based on the collected temperature correlation data and a physical model of the server room; the temperature correlation data comprises real-time temperature data, relative humidity data and airflow velocity data; a risk area analysis and identification module, which is used for comparing and analyzing the three-dimensional dynamic heat distribution map of the server room with a preset temperature safety threshold, and obtaining two-level heat density risk areas; a region determination and factor calculation module, which calculates a heat density risk influence factor of a region needing intervention adjustment for eliminating the identified risks and preventing potential risks. The application uses a ladder type adjustment mechanism combined with closed-loop feedback control, avoids excessive adjustment and system oscillation, and further optimizes energy consumption performance.

Description

High-density server room dynamic temperature control system based on temperature-humidity-airflow velocity coordinated control Technical Field

[0001] This invention relates to the field of data center thermal management technology, specifically to a high-density server room dynamic temperature control system based on temperature-humidity-airflow velocity coordinated control. Background Technology

[0002] With the rapid development of cloud computing, artificial intelligence, and big data technologies, modern data centers are evolving towards higher density, larger scale, and greater integration. The increasing integration of server equipment and the significant increase in power per rack have led to a sharp rise in heat load within data centers, with localized overheating and heat accumulation becoming increasingly prominent. This has become a key bottleneck affecting the reliable operation and energy efficiency optimization of data centers.

[0003] Traditional data center temperature control systems often employ control strategies based on fixed thresholds or regional average temperatures, typically relying on centrally located air conditioning (CRAC) units for global unified air supply and cooling regulation. This approach struggles to perceive real-time differences in temperature, humidity, and airflow distribution within the three-dimensional space of the data center, failing to accurately identify localized hotspots and potential heat risk areas, easily leading to either "overcooling" or "undercooling." On one hand, to ensure the safety of equipment in hotspot areas, it is often necessary to lower the overall supply air temperature, resulting in persistently high overall energy consumption. On the other hand, due to a lack of in-depth understanding of the coupling relationship between airflow organization and heat density, traditional systems struggle to implement timely and targeted interventions, exhibiting significant problems of response lag and coarse-grained regulation. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a high-density server room dynamic temperature control system based on temperature-humidity-airflow velocity coordinated control, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a high-density server room dynamic temperature control system based on temperature-humidity-airflow velocity coordinated control, comprising:

[0006] The heat distribution map construction module is used to periodically collect temperature correlation data inside the computer room and generate a dynamic heat distribution map of the computer room based on the collected temperature correlation data and the physical model of the computer room.

[0007] The temperature-related data includes real-time temperature data, relative humidity data, and airflow velocity data;

[0008] The risk zone analysis and identification module is used to compare and analyze the three-dimensional dynamic heat distribution map of the computer room with the preset temperature safety threshold to obtain two levels of heat density risk zones.

[0009] The region identification and factor calculation module calculates the heat density risk impact factor of the region that needs intervention and adjustment to prevent potential risks and eliminate identified risks based on the two-level heat density risk region.

[0010] The strategy generation and execution module generates adjustment strategies based on the calculated heat density risk impact factors and sends the adjustment strategies to the corresponding execution devices for execution.

[0011] The adjustment strategy is primarily based on regulating airflow speed, with fine-tuning achieved by adjusting supply air temperature.

[0012] As a preferred embodiment, the heat distribution map construction module includes:

[0013] Data acquisition units are evenly deployed throughout the computer room to periodically collect real-time temperature data, relative humidity data, and airflow velocity data.

[0014] The data processing unit is used to clean the collected real-time temperature data, relative humidity data, and airflow velocity data, remove outliers and fill in missing values ​​to obtain preprocessed data.

[0015] The distribution map construction unit utilizes preprocessed data and a physical model of the data center to generate a detailed three-dimensional dynamic heat distribution map of the data center through a spatial interpolation algorithm.

[0016] As a preferred embodiment, the specific process by which the distribution map construction unit generates a detailed three-dimensional dynamic thermal distribution map of the computer room includes:

[0017] The preprocessed data is aligned according to the timestamp, and the physical location of the sensor corresponding to each data point is mapped to a specific coordinate point in a three-dimensional coordinate system.

[0018] The computer room space is logically divided into a three-dimensional grid. Using the spatial difference algorithm and the values ​​of known sensor points in the surrounding area, the estimated temperature value at each grid point is calculated.

[0019] In this context, each grid point of the three-dimensional grid represents a location where the temperature needs to be estimated;

[0020] The temperature estimates at all grid points are combined into a three-dimensional numerical matrix, and a three-dimensional dynamic heat distribution map is generated based on the three-dimensional numerical matrix.

[0021] As a preferred embodiment, the process by which the risk zone analysis and identification module obtains two levels of thermal density risk zones specifically includes:

[0022] By comparing and analyzing the dynamic heat distribution map with preset multi-level temperature thresholds, and using image recognition and clustering algorithms, the heat density risk areas where the current temperature has exceeded the warning threshold, as well as potential hotspot areas with drastic temperature gradient changes and overheating trends, are accurately identified.

[0023] As a preferred embodiment, the region determination and factor calculation module includes:

[0024] The adjustment demand determination unit is used to comprehensively analyze the current heat distribution map, real-time temperature correlation data of each area, and the set temperature and humidity target range to determine whether there are any heat risk areas in the computer room that require intervention.

[0025] If the identified thermal risk area persists or expands, it is determined that active temperature control is required, and the target area requiring intervention is identified.

[0026] The impact factor calculation unit calculates the heat density risk impact factor for each target area determined by the adjustment demand determination unit.

[0027] As a preferred embodiment, the risk zone determination unit assigns a weight to each sub-indicator according to the specific strategy and needs of the computer room, and combines the weighted sub-indicators to calculate the final thermal impact factor.

[0028] The formula for calculating the heat density risk impact factor is as follows:

[0029] ;

[0030] in, Indicates the degree of temperature deviation. Indicates the degree of trend of change. Indicates the thermal density index, Let represent the heat dissipation efficiency index, represent the weighting coefficient, and the sum of all weighting coefficients is 1.

[0031] As a preferred embodiment, the specific process of the adjustment strategy generation module generating an adjustment strategy based on the calculated heat density risk impact factor includes:

[0032] S1: Obtain the heat density risk impact factors for all target areas and sort them by size;

[0033] S2: For each target area, calculate the theoretically required airflow velocity increment and supply air temperature increment proportionally based on its heat density risk impact factor value.

[0034] It should be noted that the calculation follows the principle that "the greater the heat density risk impact factor, the greater the adjustment force", but it must not exceed the preset maximum allowable limit;

[0035] S3: Decompose the theoretical adjustment amount of airflow velocity increment and supply air temperature increment into at least one set of smaller step sizes;

[0036] Each step corresponds to an adjustment cycle, meaning that the theoretical adjustment amount is adjusted by only one step in each cycle.

[0037] S4: Send the calculated incremental airflow velocity and supply air temperature of the stepped adjustment for this cycle to the corresponding execution equipment for execution;

[0038] S5: After executing one cycle, acquire new temperature correlation data, generate a new heat distribution map, and calculate a new heat density risk impact factor value;

[0039] S6: Based on the new heat density risk impact factor value, repeat steps S1-S4 to carry out the next round of step adjustment until the temperature of all regions returns to the equilibrium range.

[0040] As a preferred embodiment, the formula for calculating the theoretical adjustment target quantity is:

[0041] Airflow velocity target adjustment amount: ;

[0042] Supply air temperature target adjustment amount: ;

[0043] in, The target change in airflow velocity calculated for region k. This represents the thermal influence factor of region k. This indicates the preset maximum thermal influence factor. This indicates the maximum permissible change in airflow velocity. This represents the target change in supply air temperature calculated for region k; the negative sign indicates cooling. This indicates the maximum permissible variation in supply air temperature.

[0044] As a preferred embodiment, the formula for calculating the airflow velocity increment of the stepped adjustment amount in S3 is: ;

[0045] ;

[0046] in, This represents the actual change in airflow velocity in region k during this round. Represents the inertial filter coefficients. N represents the adjustment amount in the previous round for region k, and N represents the total adjustment step size.

[0047] The formula for calculating the supply air temperature increment of the stepped adjustment is as follows: ;

[0048] ;

[0049] in, This represents the actual change in supply air temperature in region k during this round.

[0050] This invention provides a high-density server room dynamic temperature control system based on temperature-humidity-airflow velocity coordinated control, which has the following beneficial effects:

[0051] By constructing a three-dimensional dynamic heat distribution map, the system achieves refined perception and visual monitoring of the data center's thermal environment. Combined with a two-level thermal risk area identification mechanism, it can identify actual overheated areas and potential hotspots at an early stage, significantly improving thermal risk early warning capabilities. By introducing heat density risk influencing factors as the basis for regulation, the system has achieved a shift from a coarse-to-precise, and from passive response to proactive prevention regulation mode. This effectively avoids equipment failure or performance degradation caused by localized overheating, extends server lifespan, and improves the overall operational stability of the data center. Furthermore, the system prioritizes adjusting airflow speed and fine-tunes supply air temperature, quickly suppressing hotspots through dynamic airflow control, avoiding global temperature and humidity fluctuations and additional cooling energy consumption caused by frequent adjustments to supply air temperature. This achieves a significant reduction in air conditioning system energy consumption while ensuring effective heat dissipation, improving overall energy utilization efficiency. The use of a stepped adjustment mechanism combined with closed-loop feedback control avoids over-adjustment and system oscillation, further optimizing energy consumption performance.

[0052] This system, through the application of multi-parameter collaboration and spatial interpolation algorithms, can achieve high-precision thermal field reconstruction and risk assessment even with limited sensor deployment density, thus reducing implementation and maintenance costs. While improving the thermal safety level of the computer room and ensuring the reliable operation of critical equipment, the system effectively unifies energy conservation and intelligent operation and maintenance, demonstrating high engineering application value and promising market prospects. Attached Figure Description

[0053] Figure 1 is a block diagram of the high-density server room dynamic temperature control system based on temperature-humidity-airflow velocity coordinated control of the present invention.

[0054] Figure 2 is a flowchart of the method for generating and adjusting the calculated heat density risk impact factor according to an embodiment of the present invention. Detailed Implementation

[0055] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0056] The following disclosure provides many different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the invention. Furthermore, reference numerals and / or letters may be repeated in different examples; such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. In addition, examples of various specific processes and materials are provided in this invention, but those skilled in the art will recognize the application of other processes and / or the use of other materials.

[0057] As shown in Figure 1, this embodiment of the invention provides a high-density server room dynamic temperature control system based on temperature-humidity-airflow velocity coordinated control, including:

[0058] The heat distribution map construction module is used to periodically collect temperature correlation data inside the computer room and generate a dynamic heat distribution map of the computer room based on the collected temperature correlation data and the physical model of the computer room.

[0059] The temperature-related data includes real-time temperature data, relative humidity data, and airflow velocity data;

[0060] The risk zone analysis and identification module is used to compare and analyze the three-dimensional dynamic heat distribution map of the computer room with the preset temperature safety threshold to obtain two levels of heat density risk zones.

[0061] The region identification and factor calculation module calculates the heat density risk impact factor of the region that needs intervention and adjustment to prevent potential risks and eliminate identified risks based on the two-level heat density risk region.

[0062] The strategy generation and execution module generates adjustment strategies based on the calculated heat density risk impact factors and sends the adjustment strategies to the corresponding execution devices for execution.

[0063] The adjustment strategy is primarily based on regulating airflow speed, with fine-tuning achieved by adjusting supply air temperature.

[0064] In this embodiment, the heat distribution map construction module includes:

[0065] Data acquisition units are evenly deployed throughout the computer room to periodically collect real-time temperature data, relative humidity data, and airflow velocity data.

[0066] The data processing unit is used to clean the collected real-time temperature data, relative humidity data, and airflow velocity data, remove outliers and fill in missing values ​​to obtain preprocessed data.

[0067] The distribution map construction unit utilizes preprocessed data and a physical model of the data center to generate a detailed three-dimensional dynamic heat distribution map of the data center through a spatial interpolation algorithm.

[0068] Among them, the dynamic heat distribution map displays the temperature field, humidity field and airflow field of the entire computer room in real time in a visual form.

[0069] Specifically, the process of generating a detailed 3D dynamic thermal distribution map of the computer room using the distribution map construction unit includes:

[0070] The preprocessed data is aligned according to the timestamp, and the physical location of the sensor corresponding to each data point is mapped to a specific coordinate point in a three-dimensional coordinate system.

[0071] The computer room space is logically divided into a three-dimensional grid. Using the spatial difference algorithm and the values ​​of known sensor points in the surrounding area, the estimated temperature value at each grid point is calculated.

[0072] In this context, each grid point of the three-dimensional grid represents a location where the temperature needs to be estimated;

[0073] The temperature estimates at all grid points are combined into a three-dimensional numerical matrix, and a three-dimensional dynamic heat distribution map is generated based on the three-dimensional numerical matrix.

[0074] In this embodiment, the three-dimensional numerical matrix is ​​the digital representation of the heat distribution map. The value of each element in the matrix represents the temperature of a small area, and its coordinates correspond to the actual spatial location.

[0075] Specifically, the three-dimensional numerical matrix is ​​passed to the visualization engine. Based on the range of temperature values, a custom color mapping table can be used: for example, blue for low temperatures, green for medium temperatures, and red for high temperatures. The temperature value of each point in the matrix is ​​mapped to the corresponding color and rendered on the floor plan or three-dimensional model of the computer room, ultimately forming the dynamic heat distribution map that we can see.

[0076] The formula for calculating the temperature estimate at each grid point, using the spatial interpolation algorithm and the values ​​from known surrounding sensor points, is as follows:

[0077] ;

[0078] in, Indicates the point to be estimated. The predicted temperature value, where n represents the number of known sensor points used for interpolation calculations. This represents the weight of the i-th known sensor point. This represents the temperature measurement value of the i-th known sensor point;

[0079] It should be noted that weight The following formula can be used to calculate it:

[0080] ;

[0081] in, This represents the weight of the j-th known sensor point. Indicates known sensor points and The semivariance between them Indicates known sensor points and points to be estimated The semivariance between them Represents the Lagrange multiplier. , This represents the spatial coordinates of known sensor points i and j.

[0082] In this embodiment, the process by which the risk area analysis and identification module obtains two levels of heat density risk areas specifically includes:

[0083] By comparing and analyzing the dynamic heat distribution map with preset multi-level temperature thresholds, and using image recognition and clustering algorithms, the heat density risk areas where the current temperature has exceeded the warning threshold, as well as potential hotspot areas with drastic temperature gradient changes and overheating trends, are accurately identified.

[0084] Understandably, the two-tiered heat density risk areas include heat density risk areas that have exceeded the warning threshold and potential hotspot areas.

[0085] Specifically, the region determination and factor calculation module includes:

[0086] The adjustment demand determination unit is used to comprehensively analyze the current heat distribution map, real-time temperature correlation data of each area, and the set temperature and humidity target range to determine whether there are any heat risk areas in the computer room that require intervention.

[0087] If the identified thermal risk area persists or expands, it is determined that active temperature control is required, and the target area requiring intervention is identified.

[0088] It should be noted that the target area refers to the thermal risk area itself and the adjacent areas that may be affected.

[0089] In this embodiment, each two-level heat density risk zone is defined as an assessment unit;

[0090] For each evaluation unit, core parameters are extracted or calculated from its corresponding heat map region;

[0091] The core parameters include: average temperature, maximum temperature, temperature gradient, heat density, and average airflow velocity.

[0092] Using the extracted parameters, sub-indicators representing different risk dimensions are calculated respectively.

[0093] It should be noted that these sub-indicators should be normalized to eliminate the influence of dimensions, so that their values ​​are within the range of 0-1 or 0-100, which facilitates comprehensive analysis.

[0094] The impact factor calculation unit calculates the heat density risk impact factor for each target area determined by the adjustment demand determination unit.

[0095] Specifically, the risk zone determination unit assigns a weight to each sub-indicator based on the specific strategies and needs of the data center, and combines the weighted sub-indicators to calculate the final thermal impact factor.

[0096] The formula for calculating the heat density risk impact factor is as follows:

[0097] ;

[0098] in, Indicates the degree of temperature deviation. Indicates the degree of trend of change. Indicates the thermal density index, Let represent the heat dissipation efficiency index, represent the weighting coefficient, and the sum of all weighting coefficients is 1.

[0099] Understandably, a higher heat density risk impact factor value indicates a higher thermal risk in the region, a higher priority in temperature control, and a greater need for control measures. The heat density risk impact factor value is output to the control strategy generation module for formulating coordinated control strategies.

[0100] As shown in Figure 2, the specific process of the adjustment strategy generation module generating adjustment strategies based on the calculated heat density risk impact factor includes:

[0101] S1: Obtain the heat density risk impact factors for all target areas and sort them by size;

[0102] S2: For each target area, calculate the theoretically required airflow velocity increment and supply air temperature increment proportionally based on its heat density risk impact factor value.

[0103] It should be noted that the calculation follows the principle that "the greater the heat density risk impact factor, the greater the adjustment force", but it must not exceed the preset maximum allowable limit;

[0104] S3: Decompose the theoretical adjustment amount of airflow velocity increment and supply air temperature increment into at least one set of smaller step sizes;

[0105] Each step corresponds to an adjustment cycle, meaning that the theoretical adjustment amount is adjusted by only one step in each cycle.

[0106] S4: Send the calculated incremental airflow velocity and supply air temperature of the stepped adjustment for this cycle to the corresponding execution equipment for execution;

[0107] S5: After executing one cycle, acquire new temperature correlation data, generate a new heat distribution map, and calculate a new heat density risk impact factor value;

[0108] S6: Based on the new heat density risk impact factor value, repeat steps S1-S4 to carry out the next round of step adjustment until the temperature of all regions returns to the equilibrium range.

[0109] Specifically, the primary approach is to adjust the airflow speed, while fine-tuning involves adjusting the supply air temperature. The priority is to quickly suppress hot spots by increasing the air volume, avoiding easy changes in the supply air temperature that could cause fluctuations in overall humidity.

[0110] In this embodiment, the formula for calculating the theoretical adjustment target quantity is:

[0111] Airflow velocity target adjustment amount: ;

[0112] Supply air temperature target adjustment amount: ;

[0113] in, The target change in airflow velocity calculated for region k. This represents the thermal influence factor of region k. This indicates the preset maximum thermal influence factor. This indicates the maximum permissible change in airflow velocity. This represents the target change in supply air temperature calculated for region k; the negative sign indicates cooling. This indicates the maximum permissible variation in supply air temperature.

[0114] The formula for calculating the airflow velocity increment of the stepped regulation is: ;

[0115] ;

[0116] in, This represents the actual change in airflow velocity in region k during this round. Represents the inertial filter coefficients. N represents the adjustment amount in the previous round for region k, and N represents the total adjustment step size.

[0117] The formula for calculating the supply air temperature increment of the stepped adjustment is: ;

[0118] ;

[0119] in, This represents the actual change in supply air temperature in region k during this round.

[0120] The high-density server room dynamic temperature control system provided by this invention, based on temperature-humidity-airflow velocity coordinated control, achieves refined perception and visual monitoring of the server room's thermal environment by constructing a three-dimensional dynamic heat distribution map. Combined with a two-level thermal risk area identification mechanism, it can identify actual overheated areas and potential hotspots at an early stage, significantly improving thermal risk early warning capabilities. By introducing heat density risk influencing factors as the basis for regulation, the system realizes a shift from a rough to a precise regulation mode, and from passive response to proactive prevention. This effectively avoids equipment failure or performance degradation caused by local overheating, extends server life, and improves the overall operational stability of the server room. Furthermore, the system prioritizes adjusting airflow velocity and fine-tunes supply air temperature, quickly suppressing hotspots through dynamic airflow control. This avoids global temperature and humidity fluctuations and additional cooling energy consumption caused by frequent adjustments to supply air temperature, significantly reducing air conditioning system energy consumption while ensuring heat dissipation and improving overall energy utilization efficiency. Moreover, the stepped adjustment mechanism combined with closed-loop feedback control avoids over-adjustment and system oscillation, further optimizing energy consumption performance.

[0121] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A high-density server room dynamic temperature control system based on temperature-humidity-airflow velocity coordinated control, characterized in that, include: The heat distribution map construction module is used to periodically collect temperature correlation data inside the computer room and generate a dynamic heat distribution map of the computer room based on the collected temperature correlation data and the physical model of the computer room; the temperature correlation data includes real-time temperature data, relative humidity data, and airflow velocity data; The risk zone analysis and identification module is used to compare and analyze the three-dimensional dynamic heat distribution map of the computer room with the preset temperature safety threshold to obtain two levels of heat density risk zones; the area determination and factor calculation module calculates the heat density risk impact factor of the area that needs to be intervened and adjusted to eliminate the identified risks and prevent potential risks based on the two levels of heat density risk zones. Strategy The generation and execution module generates adjustment strategies based on the calculated heat density risk impact factors and sends the adjustment strategies to the corresponding execution devices for execution; the adjustment strategies are mainly based on adjusting airflow speed and fine-tuned by adjusting supply air temperature; The specific process of the adjustment strategy generation module generating the adjustment strategy based on the calculated heat density risk impact factor includes: S1: Obtaining the heat density risk impact factor of all target areas and sorting them by size; S2: For each target area, calculating the theoretically required airflow velocity increment and supply air temperature increment proportionally based on its heat density risk impact factor value; S3: Decomposing the theoretical adjustment amount of airflow velocity increment and supply air temperature increment into at least one set of smaller step sizes; where each step size corresponds to an adjustment cycle, that is, only one step size of the theoretical adjustment amount is adjusted in each cycle; S4: Sending the calculated step adjustment amount of airflow velocity increment and supply air temperature increment for this cycle to the execution equipment in the corresponding area for execution; S5: After executing one cycle, obtaining new temperature correlation data to generate a new heat distribution map and calculating a new heat density risk impact factor value; S6: Based on the new heat density risk impact factor value, repeating steps S1-S4 to perform the next round of step adjustment until the temperature of all areas returns to the equilibrium range; The calculation formula for the theoretical adjustment target amount is: Airflow velocity target adjustment amount: Target adjustment amount for supply air temperature: ;in, The target change in airflow velocity calculated for region k. This represents the thermal influence factor of region k. This indicates the preset maximum thermal influence factor. This indicates the maximum permissible change in airflow velocity. This represents the target change in supply air temperature calculated for region k; the negative sign indicates cooling. This represents the maximum permissible change in supply air temperature; the formula for calculating the airflow velocity increment of the stepped adjustment amount described in S3 is: ； ;in, This represents the actual change in airflow velocity in region k during this round. Represents the inertial filter coefficients. Let N represent the adjustment amount in the previous round for region k, and N represent the total adjustment step size; the formula for calculating the supply air temperature increment of the step adjustment amount is: ； ;in, This represents the actual change in supply air temperature in region k during this round.

2. The high-density server room dynamic temperature control system based on temperature-humidity-airflow velocity coordinated control as described in claim 1, characterized in that, The heat distribution map construction module includes: a data acquisition unit, which is evenly deployed within the computer room to periodically collect real-time temperature data, relative humidity data, and airflow velocity data; a data processing unit, which cleans the collected real-time temperature data, relative humidity data, and airflow velocity data, removes outliers and fills in missing values ​​to obtain preprocessed data; and a heat distribution map construction unit, which uses the preprocessed data and the physical model of the computer room to generate a detailed three-dimensional dynamic heat distribution map of the computer room through a spatial interpolation algorithm.

3. The high-density server room dynamic temperature control system based on temperature-humidity-airflow velocity coordinated control according to claim 2, characterized in that, The specific process of generating a detailed three-dimensional dynamic thermal distribution map of the computer room by the distribution map construction unit includes: aligning the preprocessed data according to the timestamp, and mapping the physical location of the sensor corresponding to each data point to a specific coordinate point in a three-dimensional coordinate system; logically dividing the computer room space into a three-dimensional grid, and calculating the temperature estimate at each grid point using a spatial difference algorithm and the values ​​of known sensor points in the surrounding area; wherein, each grid point in the three-dimensional grid represents a location where the temperature needs to be estimated; combining the temperature estimates at all grid points into a three-dimensional numerical matrix, and generating a three-dimensional dynamic thermal distribution map based on the three-dimensional numerical matrix.

4. The high-density server room dynamic temperature control system based on temperature-humidity-airflow velocity coordinated control according to claim 1, characterized in that, The process of obtaining two levels of heat density risk areas by the risk area analysis and identification module specifically includes: comparing and analyzing the dynamic heat distribution map with preset multi-level temperature thresholds, and accurately identifying heat density risk areas where the current temperature has exceeded the warning threshold, as well as potential hotspot areas with drastic temperature gradient changes and overheating trends through image recognition and clustering algorithms.

5. A high-density server room dynamic temperature control system based on temperature-humidity-airflow velocity coordinated control as described in claim 1, characterized in that, The region determination and factor calculation module includes: a regulation demand determination unit, used to comprehensively analyze the current heat distribution map, real-time temperature correlation data of each region, and the set temperature and humidity target range to determine whether there are heat risk areas in the computer room that require intervention; wherein, if the identified heat risk areas persist or expand, it is determined that active temperature control adjustment is required, and the target areas that need intervention are identified; and an impact factor calculation unit, which calculates the heat density risk impact factor for each target area determined by the regulation demand determination unit.

6. A high-density server room dynamic temperature control system based on temperature-humidity-airflow velocity coordinated control as described in claim 5, characterized in that, The risk zone determination unit assigns a weight to each sub-indicator based on the specific strategies and needs of the computer room, and combines the weighted sub-indicators to calculate the final thermal impact factor; wherein, the calculation formula for the thermal density risk impact factor is: ;in, Indicates the degree of temperature deviation. Indicates the degree of change trend. Indicates the thermal density index, This indicates the heat dissipation efficiency index. 、 、 、 This represents the weighting coefficient, and the sum of all weighting coefficients is 1.

Images