Cloud platform-based water cooling system intelligent operation and maintenance management system

Abstract

This invention relates to the field of system management technology, specifically to an intelligent operation and maintenance management system for a cloud-based water-cooling system. The system includes a processor and a memory. The processor executes a computer program stored in the memory to perform the following steps: acquiring the coefficient adjustment factor of fluctuating data to be analyzed and the first coefficient of the data to be analyzed; obtaining the second coefficient of each data in the data sequence to be analyzed based on the first coefficient and the coefficient adjustment factor of the fluctuating data; obtaining the predicted coolant temperature data of the water-cooling equipment at future monitoring times based on the second coefficients of the data to be analyzed and a prediction model; and adjusting the operating power of the water-cooling equipment in the water-cooling system based on the predicted coolant temperature data. This invention ensures the reliability and effectiveness of subsequent adjustments to the operating power of the water-cooling equipment, that is, it enables reliable and effective intelligent operation and maintenance management of the water-cooling system.

Description

Technical Field

[0001] This invention relates to the field of system management, specifically to an intelligent operation and maintenance management system for water cooling systems based on a cloud platform. Background Technology

[0002] Water cooling systems achieve cooling or heat dissipation by absorbing heat through circulating fluid. Intelligent operation and maintenance management of water cooling systems is crucial for improving equipment performance, reducing energy consumption, minimizing failures and maintenance costs, and enhancing operational efficiency. Therefore, intelligent operation and maintenance management of water cooling systems is necessary during their operation.

[0003] However, in existing technologies, future data prediction is generally based on the collected coolant temperature sequence in the water-cooling equipment. The operating power of the water-cooling equipment is adjusted according to the predicted future data and the currently collected real-time coolant temperature. Furthermore, the collected coolant temperature data is transmitted to a cloud platform, which is also used for the operation and maintenance management of the water-cooling system. Adjusting the operating power of the water-cooling equipment based on the predicted future data and the currently collected real-time coolant temperature is one aspect of the operation and maintenance management of the water-cooling system. A typical water-cooling system consists of a cooling tower, a cooling water circulation pump, and a centrifugal chiller unit. However, when acquiring the coolant temperature sequence, uneven flow in the coolant piping can lead to some large fluctuations in the acquired coolant temperature sequence. When data exhibits significant fluctuations due to uneven flow, the reliability of subsequent predictions of coolant temperature sequences for future monitoring moments becomes low. Consequently, adjustments to the cooling system's power output based on these predictions are unreliable or ineffective, hindering reliable or efficient intelligent operation and maintenance management of the cooling system. This could potentially increase energy consumption. Therefore, improving the reliability of coolant temperature predictions for future monitoring to ensure reliable and effective intelligent operation and maintenance management of the cooling system is a pressing issue. Summary of the Invention

[0004] To address the aforementioned problems, this invention provides an intelligent operation and maintenance management system for water-cooled systems based on a cloud platform. The specific technical solution adopted is as follows:

[0005] One embodiment of the present invention provides an intelligent operation and maintenance management system for a cloud-based water cooling system, including a processor and a memory. The processor executes a computer program stored in the memory to perform the following steps:

[0006] During the current monitoring period, acquire the temperature data sequence corresponding to each set of water cooling equipment in the water cooling system, wherein the temperature data in the temperature data sequence is the water coolant temperature data;

[0007] Based on the time-series decomposition results of the temperature data sequence, suspected fluctuating temperature data in the temperature data sequence are obtained. Based on the suspected fluctuating temperature data adjacent to the suspected fluctuating temperature data and the temperature data within the neighborhood of the suspected fluctuating temperature data, the target fluctuation characterization value of the suspected fluctuating temperature data is obtained. Based on the target fluctuation characterization value, the data sequence to be analyzed and the fluctuating data to be analyzed in the data sequence to be analyzed are obtained.

[0008] Based on the order of each data to be analyzed in the data sequence to be analyzed and the fluctuating data to be analyzed in the data sequence to be analyzed, the coefficient adjustment factor of the fluctuating data to be analyzed is obtained.

[0009] Obtain the first coefficient of each data point in the data sequence to be analyzed, and obtain the second coefficient of each data point in the data sequence to be analyzed based on the first coefficient of each data point and the coefficient adjustment factor of the fluctuating data to be analyzed; obtain the predicted coolant temperature data of the water cooling equipment at future monitoring times based on the second coefficient of the data to be analyzed and the prediction model.

[0010] Based on the predicted coolant temperature data, the operating power of the water-cooling equipment in the water-cooling system is adjusted.

[0011] Beneficial Effects: This invention first acquires the temperature data sequence corresponding to each set of water-cooling equipment in the water-cooling system; then, based on the time-series decomposition results of the temperature data sequence, it obtains the suspected fluctuating temperature data in the temperature data sequence, and based on the suspected fluctuating temperature data adjacent to the suspected fluctuating temperature data and the temperature data within the neighborhood of the suspected fluctuating temperature data, it obtains the target fluctuation characterization value of the suspected fluctuating temperature data; based on the target fluctuation characterization value, it obtains the data sequence to be analyzed in the temperature data sequence and the fluctuating data to be analyzed in the data sequence to be analyzed; then, based on the order of each data to be analyzed in the data sequence to be analyzed and the fluctuating data to be analyzed in the data sequence to be analyzed, it obtains the coefficient adjustment factor of the fluctuating data to be analyzed; next, it acquires the first coefficient of each data to be analyzed in the data sequence to be analyzed, and based on the first coefficient of each data to be analyzed and the coefficient adjustment factor of the fluctuating data to be analyzed, it obtains the second coefficient of each data to be analyzed in the data sequence to be analyzed; based on the second coefficient of the data to be analyzed and the prediction model, it obtains the predicted coolant temperature data of the water-cooling equipment at the future monitoring time; finally, based on the predicted coolant temperature data, it adjusts the working power of the water-cooling equipment in the water-cooling system. Furthermore, this invention adjusts the first coefficient based on the coefficient adjustment factor, and then the second coefficient obtained by the adjustment can improve the reliability of the prediction results, thereby ensuring the reliability or effectiveness of subsequent adjustment of the working power of the water-cooled equipment, that is, it can reliably and effectively carry out intelligent operation and maintenance management of the water-cooled system. Attached Figure Description

[0012] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of an intelligent operation and maintenance management method for a water-cooled system based on a cloud platform, according to the present invention. Detailed Implementation

[0014] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention are within the protection scope of the embodiments of the present invention.

[0015] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art.

[0016] This embodiment provides a cloud-based intelligent operation and maintenance management system for a water-cooling system, including a processor and a memory. The processor executes a computer program stored in the memory to implement an artificial intelligence-based monitoring method for the intestinal-friendly pet food processing technology. Figure 1 As shown, this cloud-based intelligent operation and maintenance management method for water-cooled systems includes the following steps:

[0017] Step S001: During the current monitoring period, acquire the temperature data sequence of each water-cooling device in the water-cooling system.

[0018] This embodiment primarily focuses on water-cooling systems applied in large-scale demand scenarios, such as factory workshops and data centers. To ensure the effectiveness of water-cooling systems in large-scale demand scenarios, it is generally required that multiple sets of water-cooling equipment be designed into such systems. That is, water-cooling systems applied in large-scale demand scenarios include multiple sets of water-cooling equipment. Each set of water-cooling equipment consists of a cooling tower, a cooling water circulation pump, and a centrifugal chiller unit. For ease of analysis, this embodiment will use a water-cooling system applied to any large-scale demand scenario as an example for subsequent analysis. For instance, a water-cooling system applied to a data center can be used as an example for analysis. In other words, all water-cooling systems mentioned in this embodiment refer to the same water-cooling system, and the water-cooling equipment mentioned refers to the equipment within that system. Furthermore, the number of water-cooling equipment in the water-cooling system in this embodiment needs to be determined by the implementer based on the application scenario. If the application scenario or location is large, a larger number of sets of water-cooling equipment can be selected.

[0019] Since this embodiment requires data prediction later, it first needs to obtain the temperature data sequence corresponding to each set of water-cooling equipment in the water-cooling system during the current monitoring period. The temperature data in the temperature data sequence is the water coolant temperature data. The temperature data sequence is mainly used for data prediction, and the specific method for obtaining the temperature data sequence corresponding to each set of water-cooling equipment is as follows:

[0020] At each monitoring moment within the current monitoring period, the temperature of the coolant in each set of water-cooled equipment is obtained. The time sequence of all coolant temperatures in the same set of water-cooled equipment obtained within the current monitoring period is recorded as the temperature data sequence corresponding to the water-cooled equipment. That is, the temperature data sequence corresponding to any water-cooled equipment is composed of all coolant temperatures in that water-cooled equipment obtained within the current monitoring period. The coolant temperature in the water-cooled equipment refers to the temperature of the coolant in the centrifugal chiller unit in the corresponding water-cooled equipment.

[0021] In addition, in specific applications, implementers need to set the time interval between the current monitoring time period and adjacent monitoring times according to the actual situation. For example, in this embodiment, the current monitoring time period can be set to one hour before the current monitoring time, and the current monitoring time period must include the current monitoring time. The time interval between adjacent monitoring times can be set to 1 second or 0.1 seconds, etc. It should also be noted that in this embodiment, each water-cooling device in the water-cooling system can be adjusted independently. Moreover, this embodiment uses temperature sensors to collect the temperature of the coolant in the centrifugal chiller unit, and the collected data will be remotely transmitted to the water-cooling system operation and maintenance management cloud platform. After receiving the data, the cloud platform will store it in the data sequence corresponding to each water-cooling device.

[0022] Therefore, this embodiment obtains the temperature data sequence corresponding to each set of water-cooling equipment in the water-cooling system through the above process.

[0023] Step S002: Based on the time-series decomposition results of the temperature data sequence, obtain the suspected fluctuating temperature data in the temperature data sequence; and based on the suspected fluctuating temperature data adjacent to the suspected fluctuating temperature data and the temperature data within the neighborhood of the suspected fluctuating temperature data, obtain the target fluctuation characterization value of the suspected fluctuating temperature data; and based on the target fluctuation characterization value, obtain the data sequence to be analyzed and the fluctuating data to be analyzed in the temperature data sequence.

[0024] When acquiring temperature data sequences for water-cooled equipment, uneven flow in the coolant piping can cause significant fluctuations in the acquired data. This fluctuation leads to unreliable predictions of future coolant temperatures, resulting in poor performance when using the data sequence to forecast future temperatures. Consequently, adjustments to the water-cooled equipment's power output based on these predictions are also unreliable or ineffective. Therefore, this embodiment aims to improve the reliability of predictions to ensure the reliability and effectiveness of power adjustments for the water-cooled equipment. The main purpose of this embodiment is to improve the reliability of predicting the coolant temperature at future monitoring times. It is known that large fluctuations caused by uneven local flow in the coolant pipeline are the main reason for unreliable prediction results. Therefore, this embodiment will reduce the impact of this type of data on the prediction results. Specifically, this embodiment will first identify the data with large fluctuations in the temperature data sequence caused by uneven local flow in the coolant pipeline, which is the fluctuating data to be analyzed. Then, by analyzing whether the fluctuations in the data to be analyzed are caused by uneven local flow in the coolant pipeline or by a sudden temperature rise in the heat source itself, the coefficients of the fluctuating data to be analyzed will be adjusted accordingly to improve the reliability of the prediction.

[0025] Therefore, based on the above analysis, this embodiment needs to first obtain the fluctuation data to be analyzed. Before obtaining the fluctuation data to be analyzed, it is necessary to perform time-series decomposition on the temperature data sequence corresponding to each set of water-cooling equipment. Then, based on the time-series decomposition results of the temperature data sequence corresponding to each set of water-cooling equipment, the suspected fluctuation temperature data in the temperature data sequence corresponding to each set of water-cooling equipment is obtained. Subsequently, based on the known suspected fluctuation temperature data, further analysis is performed to determine the fluctuation data to be analyzed, that is, the noise temperature data in the suspected fluctuation temperature data is screened to further determine the fluctuation data to be analyzed. Therefore, in this embodiment, the specific process of obtaining the suspected fluctuation temperature data in the temperature data sequence corresponding to each set of water-cooling equipment is as follows:

[0026] First, STL time-series decomposition is performed on the temperature data sequence corresponding to each set of water-cooling equipment to obtain the residuals of each temperature data in the temperature data sequence corresponding to each set of water-cooling equipment, which are the residual terms. The process of performing time-series decomposition to obtain trend terms, periodic terms and residual terms is a well-known technique, so it will not be described in detail. Then, a first mapping coordinate system is constructed, where the horizontal axis of the first mapping coordinate system represents time and the vertical axis represents the residuals of the temperature data. Then, the acquisition time and residuals of each temperature data in the temperature data sequence corresponding to each set of water-cooling equipment are mapped to the constructed first mapping coordinate system to obtain the residual points corresponding to each temperature data in the temperature data sequence corresponding to each set of water-cooling equipment. The vertical axis of the residual point corresponding to the temperature data is the residual of the corresponding temperature data, and the horizontal axis is the acquisition time of the corresponding temperature data.

[0027] Next, in the first mapping coordinate system, a straight line with all ordinate values ​​of 0 is obtained and denoted as the first straight line, meaning that the residual of all points on the first straight line is 0. Then, based on the residual points corresponding to each temperature data in the temperature data sequence corresponding to each set of water-cooling equipment and the first straight line, the initial fluctuation index value of each temperature data in the temperature data sequence corresponding to each set of water-cooling equipment is obtained. After that, based on the initial fluctuation index value of each temperature data in the temperature data sequence, the suspected fluctuating temperature data in the temperature data sequence corresponding to each set of water-cooling equipment is obtained.

[0028] In this embodiment, for ease of understanding, the specific process of obtaining the initial fluctuation index value of any temperature data a in the temperature data sequence A corresponding to any set of water-cooling equipment is described as an example. That is, the specific process of obtaining the initial fluctuation index value of temperature data a is as follows:

[0029] First, obtain the set of residual points corresponding to all temperature data except temperature data a in the temperature data sequence A, and denote it as the first set. Then, in the first set, obtain the residual point closest to the residual point corresponding to temperature data a, and denote it as the nearest neighbor point corresponding to temperature data a. Next, obtain the Euclidean distance between the residual point corresponding to temperature data a and the nearest neighbor point corresponding to temperature data a, and denote it as the first distance. Obtain the distance between the residual point corresponding to temperature data a and the first straight line, and denote it as the second distance. Finally, obtain the normalized value of the result obtained by adding the first distance and the second distance, and denote it as the initial fluctuation index value of temperature data a.

[0030] Furthermore, the specific expression for obtaining the initial fluctuation index value of temperature data 'a' is as follows:

[0031]

[0032] in, Let D1 be the initial fluctuation index value of temperature data 'a', D2 be the first distance, and norm() be the normalization function. A larger D1 or D2 indicates that temperature data 'a' deviates more from trends and periodicity, and that the outlier of temperature data 'a' is more pronounced. A more pronounced outlier suggests that temperature data 'a' is more likely caused by uneven local flow in the coolant piping, external noise, or sudden temperature rises from the heat source itself. Furthermore, larger D1 and D2 values ​​indicate... The larger the value, the better. The larger the value of , the more likely the temperature data 'a' is caused by uneven local flow in the coolant piping, external noise, or a sudden temperature rise from the heat source itself. In other words, when the temperature data 'a' is noise temperature data, The value will also be relatively large, so when When the value is large, it only indicates that the temperature data 'a' is more likely to be suspected fluctuating temperature data; conversely, when the value is small... When the value is large, it indicates that the temperature data 'a' is less likely to be fluctuating temperature data, meaning that the initial fluctuation index value cannot specifically determine the cause of the large data fluctuation.

[0033] In this embodiment, the specific process for obtaining suspected fluctuating temperature data in the temperature data sequence is as follows: For temperature data a, if the initial fluctuation characterization value of temperature data a is not less than the preset first fluctuation threshold, then temperature data a is determined to be suspected fluctuating temperature data, that is, temperature data a is recorded as suspected fluctuating temperature data; and in specific applications, the implementer needs to set the preset first fluctuation threshold according to the actual situation and mathematical experimental statistics. For example, in this embodiment, the preset first fluctuation threshold can be set to 0.7.

[0034] Therefore, this embodiment can obtain the suspected fluctuating temperature data in the temperature data sequence corresponding to each set of water-cooling equipment through the above process. Since the suspected fluctuating temperature data may not only be caused by uneven local flow in the coolant pipeline, but also by noise data or sudden temperature rise of the heat source itself, after obtaining the suspected fluctuating temperature data, this embodiment also needs to obtain the target fluctuation characterization value of each suspected fluctuating temperature data in the temperature data sequence based on the suspected fluctuating temperature data adjacent to the suspected fluctuating temperature data and the temperature data within the neighborhood of the suspected fluctuating temperature data. The target fluctuation characterization value is an important parameter for screening out noise temperature data and determining the fluctuating data to be analyzed, and it is determined in this embodiment. In addition, for ease of understanding, this embodiment will subsequently describe the process of obtaining the target fluctuation characterization value of any suspected fluctuating temperature data b in the temperature data sequence B corresponding to any water-cooling equipment as an example, that is, the process of obtaining the target fluctuation characterization value of suspected fluctuating temperature data b is as follows:

[0035] First, in temperature data sequence B, a sequence consisting of a predetermined number of consecutive temperature data points adjacent to and to the left of suspected fluctuating temperature data point b is obtained and denoted as the left-side adjacent sequence of suspected fluctuating temperature data point b. Then, a sequence consisting of a predetermined number of consecutive temperature data points adjacent to and to the right of suspected fluctuating temperature data point b is obtained and denoted as the right-side adjacent sequence of suspected fluctuating temperature data point b. Next, the difference sequence of the left-side adjacent sequence of suspected fluctuating temperature data point b is obtained, and the variance of the difference sequence of the left-side adjacent sequence is denoted as the first variance of suspected fluctuating temperature data point b. Finally, the difference sequence of the right-side adjacent sequence of suspected fluctuating temperature data point b is obtained, and the variance of the difference sequence of the right-side adjacent sequence is denoted as the second variance of suspected fluctuating temperature data point b. In specific applications, the implementer needs to set the value of the predetermined number based on the actual situation and mathematical experimental statistics. For example, in this embodiment, the value of the predetermined number can be set to 10.

[0036] Furthermore, in this embodiment, there may be cases where the number of data points to the left or right of the suspected temperature fluctuation data point b is less than a preset number. When the number of data points to the left of the suspected temperature fluctuation data point b is less than the preset number, the sequence consisting of all data points to the left of the suspected temperature fluctuation data point b is recorded as the left adjacent sequence of the suspected temperature fluctuation data point b. Similarly, when the number of data points to the right of the suspected temperature fluctuation data point b is less than the preset number, the sequence consisting of all data points to the right of the suspected temperature fluctuation data point b is recorded as the right adjacent sequence of the suspected temperature fluctuation data point b. It should also be noted that although the first and last data points in the temperature data sequence B are almost impossible to be suspected temperature fluctuation data points... However, to prevent special cases, it is still necessary to specify the specific values ​​of the first and second variances of the suspected temperature fluctuation data b when it is the first and last data in the temperature data sequence B. That is, when the suspected temperature fluctuation data b is the first data in the temperature data sequence B, there is no data to the left of the suspected temperature fluctuation data b, so the first variance of the suspected temperature fluctuation data b is recorded as 0. When the suspected temperature fluctuation data b is the last data in the temperature data sequence B, there is no data to the right of the suspected temperature fluctuation data b, so the second variance of the suspected temperature fluctuation data b is recorded as 0.

[0037] Then, a second mapping coordinate system is constructed, with the horizontal axis representing time and the vertical axis representing temperature data. Each temperature data point in the temperature data sequence B and the acquisition time of each temperature data point are mapped to the constructed second mapping coordinate system. The data points obtained by mapping are recorded as the temperature data points corresponding to each temperature data point in the temperature data sequence B, with the horizontal axis value being the acquisition time of the corresponding temperature data and the vertical axis value being the corresponding temperature data.

[0038] After obtaining the temperature data points corresponding to the temperature data, the nearest suspected data points and feature set of the suspected fluctuating temperature data b are obtained based on the temperature data points corresponding to each temperature data in the temperature data sequence B. Then, based on the first variance, second variance, nearest suspected data points, and feature set of the suspected fluctuating temperature data b, the target fluctuation characterization value of the suspected fluctuating temperature data b is obtained.

[0039] In this embodiment, the specific process of obtaining the nearest neighbor suspected data points and feature set of suspected fluctuating temperature data b based on the temperature data points corresponding to each temperature data in the temperature data sequence B is as follows:

[0040] First, in the temperature data sequence B, all temperature data points corresponding to suspected fluctuating temperature data (excluding suspected fluctuating temperature data b) are recorded as suspected data points, and the temperature data point corresponding to suspected fluctuating temperature data b is recorded as the first data point. Then, in the second mapping coordinate system, the suspected data point located to the left of the first data point and closest to the first data point is obtained and recorded as the left nearest suspected data point of suspected fluctuating temperature data b. The suspected data point located to the right of the first data point and closest to the first data point is obtained and recorded as the right nearest suspected data point of suspected fluctuating temperature data b. That is, the nearest suspected data point includes the left nearest suspected data point and the right nearest suspected data point.

[0041] Next, the interval formed by the x-coordinates of the left nearest neighbor suspected data points of the suspected fluctuating temperature data b and the x-coordinate of the first data point is obtained and denoted as the left interval. The interval formed by the x-coordinates of the right nearest neighbor suspected data points of the suspected fluctuating temperature data b and the x-coordinate of the first data point is obtained and denoted as the right interval. The left interval contains the x-coordinates of the left nearest neighbor suspected data points but does not contain the x-coordinate of the first data point, and the right interval contains the x-coordinates of the right nearest neighbor suspected data points but does not contain the x-coordinate of the first data point. Then, in the second mapped coordinate system, all temperature data points whose x-coordinates belong to the left interval are obtained, and the set formed by all temperature data points whose x-coordinates belong to the left interval is denoted as the first feature set. All temperature data points whose x-coordinates belong to the right interval are obtained, and the set formed by all temperature data points whose x-coordinates belong to the right interval is denoted as the second feature set. That is, the feature set includes the first feature set and the second feature set.

[0042] In this embodiment, the specific process of obtaining the target fluctuation characterization value of the suspected fluctuating temperature data b based on the first variance, second variance, nearest neighbor suspected data points, and feature set of the suspected fluctuating temperature data b is as follows:

[0043] First, obtain the sum of the first variance and the second variance of the suspected fluctuating temperature data b, and then perform a negative correlation mapping on the sum of the first variance and the second variance of the suspected fluctuating temperature data b. The mapping result is recorded as the first index value of the suspected fluctuating temperature data b.

[0044] Then, the Euclidean distance between the left nearest neighbor suspected data point of the suspected temperature fluctuation data b and the first data point is obtained and recorded as the left nearest neighbor distance of the suspected temperature fluctuation data b. The Euclidean distance between the right nearest neighbor suspected data point of the suspected temperature fluctuation data b and the first data point is also obtained and recorded as the right nearest neighbor distance of the suspected temperature fluctuation data b. Next, the sum of the left nearest neighbor distance and the right nearest neighbor distance of the suspected temperature fluctuation data b is obtained, and a negative correlation mapping is performed on the sum of the left nearest neighbor distance and the right nearest neighbor distance of the suspected temperature fluctuation data b. The mapping result is recorded as the second index value. It should be noted that the suspected fluctuating temperature data b may not have a left or right neighbor suspected data point. When the suspected fluctuating temperature data b does not have a left neighbor suspected data point, the value after negatively mapping the right neighbor distance of the suspected fluctuating temperature data b is directly recorded as the second index value. When the suspected fluctuating temperature data b does not have a right neighbor suspected data point, the value after negatively mapping the left neighbor distance of the suspected fluctuating temperature data b is directly recorded as the second index value of the suspected fluctuating temperature data b.

[0045] Next, the mean of the ordinate values ​​of all data points in the first feature set of the suspected fluctuating temperature data b is obtained and recorded as the first mean. The absolute value of the difference between the first mean and the ordinate value of the first data point is calculated and recorded as the first difference value of the suspected fluctuating temperature data b. The mean of the ordinate values ​​of all data points in the second feature set of the suspected fluctuating temperature data b is obtained and recorded as the second mean. The absolute value of the difference between the second mean and the ordinate value of the first data point is obtained and recorded as the second difference value of the suspected fluctuating temperature data b. Then, the sum of the first difference value and the second difference value of the suspected fluctuating temperature data b is obtained. Then, a negative correlation mapping is performed on the sum of the first difference value and the second difference value of the suspected fluctuating temperature data b, and the mapping result is recorded as the third index value of the suspected fluctuating temperature data b. It should be noted that the suspected fluctuating temperature data b may not have a first feature set or a second feature set. When the suspected fluctuating temperature data b does not have a first feature set, the result of negatively mapping the second difference value of the suspected fluctuating temperature data b is directly recorded as the third index value of the suspected fluctuating temperature data b. When the suspected fluctuating temperature data b does not have a second feature set, the result of negatively mapping the first difference value of the suspected fluctuating temperature data b is directly recorded as the third index value of the suspected fluctuating temperature data b.

[0046] Finally, the sum of the first, second, and third index values ​​of the suspected fluctuating temperature data b is obtained, and the sum of the first, second, and third index values ​​of the suspected fluctuating temperature data b is normalized. The result of the normalization process is then recorded as the target fluctuation characterization value of the suspected fluctuating temperature data b.

[0047] Furthermore, in this embodiment, the specific expression for obtaining the target fluctuation characterization value of the suspected fluctuating temperature data b is as follows:

[0048]

[0049] in, Let be the target fluctuation characterization value for the suspected fluctuating temperature data b, exp() be an exponential function with a base of e, W1 be the first index value of the suspected fluctuating temperature data b, W2 be the second index value of the suspected fluctuating temperature data b, W3 be the third index value of the suspected fluctuating temperature data b, and C1 be a preset first constant, where C1 is used to... The result is normalized, therefore, this embodiment requires the value of C1 to be greater than 3, that is, in this embodiment, C1 can be set to 3.

[0050] Furthermore, the larger W1, W2, and W3 are, the more abrupt or random the suspected temperature fluctuation data b is within its neighborhood, and the less it exhibits process-like change characteristics within that neighborhood. These process-like change characteristics refer to the data within the neighborhood of the suspected temperature fluctuation data b generally showing an increasing or decreasing trend. The more abrupt or random the suspected temperature fluctuation data b is within its neighborhood, and the less it exhibits process-like change characteristics, the higher the probability that the suspected temperature fluctuation data b is noise data. Conversely, the smaller W1, W2, and W3 are, the lower the probability that the suspected temperature fluctuation data b is noise data. Also, because the larger W1, W2, and W3 are... The smaller the value, the more likely it is that when The smaller the value, the greater the likelihood that the suspected fluctuating temperature data b is noise temperature data; conversely, the larger the value, the greater the likelihood that the data is noise. The larger the value, the less likely the suspected fluctuating temperature data b is noise temperature data.

[0051] Therefore, based on the above process of obtaining the target fluctuation characterization value of suspected fluctuating temperature data b, this embodiment can obtain the target fluctuation characterization value of each suspected fluctuating temperature data. Based on the above analysis, it is known that the target fluctuation characterization value is primarily used to filter out noise temperature data in the suspected fluctuating temperature data. It cannot distinguish whether the noise temperature data is caused by a sudden temperature rise in the heat source itself or by uneven local flow in the coolant pipeline. However, the presence of noise temperature data will also affect the prediction results. Therefore, it is necessary to first filter out the noise temperature data in the suspected fluctuating temperature data based on the target fluctuation characterization value, then smooth out the noise temperature data, and finally determine the fluctuating data to be analyzed after smoothing. Therefore, this embodiment will next obtain the data sequence to be analyzed and the fluctuating data to be analyzed in the temperature data sequence corresponding to each set of water-cooled equipment based on the target fluctuation characterization value of the suspected fluctuating temperature data. That is, the specific process of obtaining the data sequence to be analyzed and the fluctuating data to be analyzed in the temperature data sequence is as follows:

[0052] For any suspected fluctuating temperature data b, if the target fluctuation characterization value of the suspected fluctuating temperature data b is not less than the preset second fluctuation threshold, then the suspected fluctuating temperature data b is determined to be fluctuating temperature data; otherwise, the suspected fluctuating temperature data b is determined to be noise temperature data. In specific applications, the implementer needs to set the preset second fluctuation threshold according to the actual situation and mathematical experimental statistics. For example, in this embodiment, the preset second fluctuation threshold can be set to 0.6.

[0053] Therefore, the noise temperature data in the suspected fluctuating temperature data b can be identified through the above method. After identifying the noise temperature data, the replacement value of each noise temperature data is obtained. The replacement value of the noise temperature data is the average of the adjacent temperature data pairs of the noise temperature data. The adjacent temperature data pairs of any noise temperature data consist of the temperature data adjacent to and to the left of the noise temperature data and the temperature data adjacent to and to the right of the noise temperature data. That is, the data in the noise temperature data and the data in the adjacent temperature data pairs of the noise temperature data belong to the same sequence. Then, each noise temperature data in the temperature data sequence is replaced with the replacement value of the corresponding noise temperature data, and the new sequence obtained after the replacement is recorded as the data sequence to be analyzed of the corresponding temperature data sequence. If the f-th temperature data in any temperature data sequence is fluctuating temperature data, then the f-th data to be analyzed in the data sequence to be analyzed of the temperature data sequence is recorded as fluctuating data to be analyzed.

[0054] Therefore, this embodiment can obtain the data sequence to be analyzed and the fluctuation data to be analyzed in each temperature data sequence through the above process.

[0055] Step S003: Based on the order of each piece of data to be analyzed in the data sequence to be analyzed and the fluctuating data to be analyzed in the data sequence to be analyzed, obtain the coefficient adjustment factor of the fluctuating data to be analyzed.

[0056] When the coolant flow in the cooling system's piping is uneven, it can cause a temporary lack of coolant circulation, resulting in a brief malfunction of the cooling system. However, this usually resolves itself within the coolant system, so power adjustment is not necessary during this period. However, during data prediction, the fluctuations caused by this phenomenon can affect the prediction results. Specifically, these fluctuations might lead to errors in determining the appropriate power adjustment method based on the prediction results, resulting in lower reliability or effectiveness of the adjustment. Therefore, this embodiment aims to reduce the coefficient of the fluctuations caused by this phenomenon during prediction, i.e., to reduce the impact of this phenomenon. The impact of the fluctuation data caused by the fluctuations on the prediction results; however, since the fluctuation data obtained above includes not only fluctuation data caused by uneven local flow in the coolant pipeline, but also fluctuation data caused by sudden temperature rises in the heat source itself, and when there is a trend of sudden temperature rises in the heat source itself, it is necessary to adjust the power of the water cooling equipment in a timely manner. Therefore, it is necessary to retain the importance of the fluctuation data caused by sudden temperature rises in the heat source itself as much as possible, that is, to avoid adjusting the coefficient of the fluctuation data caused by sudden temperature rises in the heat source itself as much as possible. In this embodiment, the heat source is the main factor affecting the temperature in the scenario in which the water cooling system is applied.

[0057] Furthermore, since a sudden increase in heat source temperature occurs at a certain moment, the coolant temperature in multiple water-cooling devices in the water-cooling system will fluctuate significantly. However, when the coolant flow is uneven in a localized area of ​​a water-cooling device, it is highly likely that only the coolant temperature in that device will fluctuate significantly. Therefore, this embodiment obtains the coefficient adjustment factor for the fluctuating data based on the characteristics described above. Specifically, this embodiment will obtain the coefficient adjustment factor for each fluctuating data in the data sequence based on the order of the data to be analyzed and the fluctuating data in the data sequence. The specific method for obtaining the coefficient adjustment factor for the fluctuating data is as follows:

[0058] First, based on the order of the data to be analyzed in each temperature data sequence, the feature label value of each data point in the analysis sequence is obtained, and the feature label value of the g-th data point in each analysis sequence is g. Then, in all the analysis sequences, all data points with the same feature label value are grouped into the same set, and each set is denoted as a feature subset. The feature label value of the data points in each feature subset is used as the identification value of the corresponding feature subset, that is, the feature label values ​​of the data points in the same feature subset are consistent. Then, the K-means clustering algorithm is used to cluster the data points in each feature subset, resulting in each cluster corresponding to each feature subset. In specific applications, the K value during clustering, that is, the number of cluster centroids, is determined by the elbow method. Since the process of clustering using the k-means clustering algorithm and the process of determining the number of cluster centroids using the elbow method are well-known techniques, this embodiment will not describe them in detail.

[0059] After clustering each feature subset, the coefficient adjustment factor for each fluctuation data to be analyzed is obtained based on the clustering results. Furthermore, for ease of understanding, this embodiment will subsequently use the coefficient adjustment factor of any fluctuation data h in any data sequence to be analyzed, i.e., the specific method for obtaining the coefficient adjustment factor of fluctuation data h is as follows:

[0060] First, obtain the feature subset whose identification value is the same as the feature label value of the fluctuation data h to be analyzed, and denote it as the target subset corresponding to the fluctuation data h to be analyzed. Then, in each cluster corresponding to the target subset, obtain the cluster containing the fluctuation data h to be analyzed, and denote it as the cluster to be analyzed. Next, obtain the ratio of the total number of data in the cluster to be analyzed to the total number of data in the target subset corresponding to the fluctuation data h to be analyzed, and denote it as the first ratio. Then, obtain the reciprocal of the number of clusters corresponding to the first target subset, and denote it as the second ratio. Then, in the cluster to be analyzed, obtain the nearest neighbor data to be analyzed for each data to be analyzed in the cluster to be analyzed, and denote it as the intra-cluster nearest neighbor data corresponding to the data to be analyzed, that is, the data to be analyzed at this time. The nearest neighbor data within the cluster corresponding to the data to be analyzed is the data closest to the data to be analyzed in the cluster to be analyzed. Then, the absolute value of the difference between each data to be analyzed and its corresponding nearest neighbor data in the cluster to be analyzed is obtained and recorded as the feature difference of the corresponding data to be analyzed. Then, the mean of the feature differences of all data to be analyzed in the cluster to be analyzed is obtained and recorded as the first mean. The negative correlation mapping value of the first mean is recorded as the first mapping value, which is exp(-R), where R is the first mean. Finally, the normalized value of the result obtained by adding the first ratio, the second ratio, and the first mapping value is obtained and recorded as the coefficient adjustment factor of the fluctuating data h to be analyzed. The normalized value can be obtained here using the normalization function norm().

[0061] Furthermore, the larger the first ratio, the second ratio, and the first mapping value, the greater the likelihood that the fluctuation in the data to be analyzed, h, is caused by a sudden increase in the heat source. Since the product of the first coefficient and the coefficient adjustment factor is used as the second coefficient, the larger the coefficient adjustment factor, the less adjustment is made. And since the second coefficient is the coefficient used in subsequent predictions, the larger the first ratio, the second ratio, and the first mapping value, the larger the coefficient adjustment factor of the fluctuation in the data to be analyzed, h. Conversely, the smaller the first ratio, the second ratio, and the first mapping value, the smaller the coefficient adjustment factor of the fluctuation in the data to be analyzed, h.

[0062] Therefore, this embodiment can obtain the coefficient adjustment factor of each fluctuation data to be analyzed through the above process.

[0063] Step S004: Obtain the first coefficient of each data point to be analyzed in the data sequence to be analyzed, and obtain the second coefficient of each data point to be analyzed in the data sequence to be analyzed based on the first coefficient of each data point to be analyzed and the coefficient adjustment factor of the fluctuating data to be analyzed; obtain the predicted coolant temperature data of the water cooling equipment at the future monitoring time based on the second coefficient of the data point to be analyzed and the prediction model.

[0064] This embodiment first obtains the first coefficients of each data point in the data sequence to be analyzed. Since this embodiment uses the ARIMA prediction model for prediction, the first coefficients of the data to be analyzed include the first autoregressive coefficient and the first moving average coefficient. The method for obtaining the first coefficients is as follows: First, an ARIMA prediction model is constructed, and the data sequence to be analyzed is imported into the constructed ARIMA prediction model to obtain the coefficients of each data point in the data sequence to be analyzed. The coefficients of the data to be analyzed obtained at this time are recorded as the first coefficients of the corresponding data to be analyzed. The first coefficients of the data to be analyzed are determined by the traditional coefficient acquisition method in the ARIMA prediction model, such as using the maximum likelihood (MLE) method to determine the first coefficients of the data to be analyzed. Furthermore, since the coefficients of the data to be analyzed include the autoregressive coefficients in the AR model and the moving average coefficients in the MA model, the first coefficient of each data point to be analyzed includes the first autoregressive coefficient and the first moving average coefficient. In addition, it should be noted that the method for obtaining the first coefficients of the data to be analyzed is a well-known technique, so this embodiment will not describe it in detail.

[0065] Next, based on the first coefficient of each data to be analyzed and the coefficient adjustment factor of the fluctuating data to be analyzed, the second coefficient of each data to be analyzed in the data sequence is obtained. That is, the specific method for obtaining the second coefficient of the data to be analyzed is as follows: for any data to be analyzed in any data sequence, if it is determined that the data to be analyzed does not belong to the fluctuating data to be analyzed, then the first coefficient of the data to be analyzed is used as the second coefficient of the data to be analyzed; if it is determined that the data to be analyzed belongs to the fluctuating data to be analyzed, then the product of the first coefficient of the data to be analyzed and the coefficient adjustment factor of the data to be analyzed is used as the second coefficient of the data to be analyzed.

[0066] Then, based on the temperature data sequence to be analyzed for each set of water-cooled equipment, the second coefficient of each data to be analyzed in the temperature data sequence to be analyzed for each set of water-cooled equipment, and the ARIMA prediction model, the predicted coolant temperature data for each set of water-cooled equipment at the next monitoring time is obtained. The predicted coolant temperature data for each set of water-cooled equipment at the next monitoring time refers to the predicted coolant temperature data for each set of water-cooled equipment at the next monitoring time. When using the ARIMA prediction model to obtain the predicted coolant temperature data at the next monitoring time, only the first coefficient of the data to be analyzed is replaced with the second coefficient of the data to be analyzed, and other steps or processes remain unchanged.

[0067] Step S005: Adjust the operating power of the water-cooling equipment in the water-cooling system based on the predicted coolant temperature data.

[0068] This embodiment will then adjust the operating power of each water-cooling device based on the predicted coolant temperature data at future monitoring times. Specifically:

[0069] The system acquires the coolant temperature of each water-cooling unit at the current monitoring time and records it as the actual coolant temperature data at that time. For any water-cooling unit, if the actual coolant temperature at the current monitoring time is greater than the predicted coolant temperature at a future monitoring time, it indicates that the coolant temperature is decreasing. In this case, the operating power of the water-cooling unit should be reduced to save energy consumption. Conversely, if the actual coolant temperature at the current monitoring time is less than the predicted coolant temperature at a future monitoring time, it indicates that the coolant temperature is increasing. In this case, the operating power of the water-cooling unit should be increased to allow the coolant temperature to cool down more quickly and ensure the operation of the water-cooling system. To improve efficiency, if the actual coolant temperature of the water-cooling device at the current monitoring time is equal to the predicted coolant temperature at a future monitoring time, then the operating power of the water-cooling device will not be adjusted. In specific applications, the implementer needs to determine the specific adjustment power value based on the actual situation, but the degree of adjustment must be proportional to the difference between the actual and the predicted values. The difference between the actual and the predicted values ​​refers to the absolute value of the difference between the actual coolant temperature of a water-cooling device at the current monitoring time and the predicted coolant temperature at a future monitoring time. For example, if the difference between the actual and the predicted values ​​is large, and the actual coolant temperature of the water-cooling device at the current monitoring time is less than the predicted coolant temperature at a future monitoring time, then the operating power of the water-cooling device should be increased, and the degree of adjustment should also be large.

[0070] Based on the adjustment principles described above, this embodiment will now take the adjustment process of the working power of any water-cooled device V as an example for specific description. That is, the specific adjustment process of the working power of the water-cooled device V is as follows:

[0071] First, determine whether the actual coolant temperature of the water-cooling device V at the current monitoring time is greater than the predicted coolant temperature at a future monitoring time. If so, adjust the operating power of the water-cooling device V to the first adjustment power S1, that is, adjust the operating power of the water-cooling device V from S0 to S1 starting from the current monitoring time. Otherwise, continue to determine whether the actual coolant temperature of the water-cooling device V at the current monitoring time is less than the predicted coolant temperature at a future monitoring time. If so, adjust the operating power of the water-cooling device V to the second adjustment power S2, that is, adjust the operating power of the water-cooling device V from S0 to S2 starting from the current monitoring time. , Where S1 is the first regulating power, S2 is the second regulating power, and S0 is the operating power of the water-cooled device V at the current monitoring moment. C1 is the preset adjustment control coefficient, C2 is the preset second constant, norm() is the normalization function, T1 is the predicted coolant temperature data of the water-cooled device V at a future monitoring time, and T0 is the actual coolant temperature data of the water-cooled device V at the current monitoring time. Furthermore, if the actual coolant temperature data of the water-cooled device V at the current monitoring time is equal to the predicted coolant temperature data of the water-cooled device V at a future monitoring time, then there is no need to adjust the operating power of the water-cooled device V; that is, the operating power of the water-cooled device V can be maintained at S0. In addition, in specific applications, the implementer needs to set the values ​​of the preset adjustment control coefficient and the preset second constant according to the actual situation and mathematical experimental statistics. For example, in this embodiment, the preset adjustment control coefficient can be set to 0.2, and the value of the preset second constant can be set to 1. The preset adjustment control coefficient is used to control the adjustment ratio.

[0072] Therefore, this embodiment can adjust the working power of other water-cooling devices by using the specific adjustment method for the working power of the water-cooling device V described above. That is, the adjustment method for the working power of other water-cooling devices is the same as the adjustment method for the working power of the water-cooling device V described above.

[0073] In summary, this embodiment first obtains the temperature data sequence corresponding to each set of water-cooling equipment in the water-cooling system; then, based on the time-series decomposition results of the temperature data sequence, it obtains the suspected fluctuating temperature data in the temperature data sequence, and based on the suspected fluctuating temperature data adjacent to the suspected fluctuating temperature data and the temperature data within the neighborhood of the suspected fluctuating temperature data, it obtains the target fluctuation characterization value of the suspected fluctuating temperature data; based on the target fluctuation characterization value, it obtains the data sequence to be analyzed and the fluctuating data to be analyzed in the data sequence to be analyzed; then, based on the order of each data to be analyzed in the data sequence to be analyzed and the fluctuating data to be analyzed in the data sequence to be analyzed, it obtains the coefficient adjustment factor of the fluctuating data to be analyzed; next, it obtains the first coefficient of each data to be analyzed in the data sequence to be analyzed, and based on the first coefficient of each data to be analyzed and the coefficient adjustment factor of the fluctuating data to be analyzed, it obtains the second coefficient of each data to be analyzed in the data sequence to be analyzed; based on the second coefficient of the data to be analyzed and the prediction model, it obtains the predicted coolant temperature data of the water-cooling equipment at the future monitoring time; finally, based on the predicted coolant temperature data, it adjusts the working power of the water-cooling equipment in the water-cooling system. Furthermore, in this embodiment, the first coefficient is adjusted based on the coefficient adjustment factor, and the second coefficient obtained by the adjustment can improve the reliability of the prediction result, thereby ensuring the reliability or effectiveness of subsequent adjustment of the working power of the water-cooling equipment. In other words, it can reliably and effectively carry out intelligent operation and maintenance management of the water-cooling system.

[0074] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A cloud platform-based water cooling system intelligent operation and maintenance management system, comprising a processor and a memory, characterized in that, The processor executes the computer program stored in the memory to implement the following steps: In the current monitoring time period, obtain a temperature data sequence corresponding to each set of water cooling equipment in the water cooling system, and the temperature data in the temperature data sequence is water cooling liquid temperature data; According to the time series decomposition result of the temperature data sequence, obtain suspected fluctuation temperature data in the temperature data sequence, and according to the suspected fluctuation temperature data adjacent to the suspected fluctuation temperature data and the temperature data located in the neighborhood range of the suspected fluctuation temperature data, obtain a target fluctuation characteristic value of the suspected fluctuation temperature data, and according to the target fluctuation characteristic value, obtain a to-be-analyzed data sequence of the temperature data sequence and fluctuation to-be-analyzed data in the to-be-analyzed data sequence; According to the order of each to-be-analyzed data in the to-be-analyzed data sequence and the fluctuation to-be-analyzed data in the to-be-analyzed data sequence, obtain a coefficient adjustment factor of the fluctuation to-be-analyzed data; Obtain a first coefficient of each to-be-analyzed data in the to-be-analyzed data sequence, and the first coefficient of each to-be-analyzed data is a coefficient obtained by importing the to-be-analyzed data sequence into the constructed ARIMA prediction model, and a second coefficient of each to-be-analyzed data in the to-be-analyzed data sequence is obtained according to the first coefficient of each to-be-analyzed data and the coefficient adjustment factor of the fluctuation to-be-analyzed data; and according to the second coefficient of the to-be-analyzed data and a prediction model, obtain predicted cooling liquid temperature data of the water cooling equipment at a future monitoring time; According to the predicted cooling liquid temperature data, adjust the working power of the water cooling equipment in the water cooling system. 2.The cloud platform-based water cooling system intelligent operation and maintenance management system of claim 1, wherein, The method for obtaining suspected fluctuation temperature data in the temperature data sequence comprises: Performing STL time series decomposition on the temperature data sequence to obtain the residual error of each temperature data in the temperature data sequence; A first mapping coordinate system is constructed, the horizontal coordinate axis of the first mapping coordinate system is represented as time, and the vertical coordinate axis is represented as the residual error of temperature data; the collection time of each temperature data in the temperature data sequence and the residual error of the temperature data are mapped into the first mapping coordinate system to obtain a residual error point corresponding to each temperature data in the temperature data sequence; in the first mapping coordinate system, a straight line with a vertical coordinate value of 0 is obtained, and is recorded as a first straight line; According to the residual error point corresponding to the temperature data and the first straight line, an initial fluctuation index value of each temperature data in the temperature data sequence is obtained; For any temperature data a in any temperature data sequence A, if the initial fluctuation characteristic value of the temperature data a is not less than a preset first fluctuation threshold, the temperature data a is recorded as suspected fluctuation temperature data. 3.The cloud platform-based water cooling system intelligent operation and maintenance management system of claim 2, characterized in that, The method for obtaining the initial fluctuation index value of the temperature data comprises: According to the temperature data a in the temperature data sequence A, a set composed of residual points corresponding to all temperature data in the temperature data sequence A except the temperature data a is recorded as a first set, in the first set, a residual point closest to the residual point corresponding to the temperature data a is recorded as a nearest neighbor point corresponding to the temperature data a, a Euclidean distance between the residual point corresponding to the temperature data a and the nearest neighbor point corresponding to the temperature data a is recorded as a first distance, a distance between the residual point corresponding to the temperature data a and the first straight line is recorded as a second distance, and a normalized value of a result obtained by adding the first distance and the second distance is recorded as an initial fluctuation index value of the temperature data a. 4.The cloud platform-based water cooling system intelligent operation and maintenance management system of claim 1, wherein, The method for obtaining the target fluctuation characteristic value of the suspected fluctuation temperature data comprises: According to any suspected fluctuation temperature data b in any temperature data sequence B: In the temperature data sequence B, a sequence composed of continuous preset number of temperature data located on the left side of the suspected fluctuation temperature data b is recorded as a left adjacent sequence of the suspected fluctuation temperature data b, and a sequence composed of continuous preset number of temperature data located on the right side of the suspected fluctuation temperature data b is recorded as a right adjacent sequence of the suspected fluctuation temperature data b; a variance of a difference sequence of the left adjacent sequence is recorded as a first variance, and a variance of a difference sequence of the right adjacent sequence is recorded as a second variance; A second mapping coordinate system is constructed, a horizontal coordinate axis of the second mapping coordinate system is represented as time, and a vertical coordinate axis is represented as temperature data; each temperature data in the temperature data sequence B and a collection time of the temperature data are mapped into the second mapping coordinate system, so that a temperature data point corresponding to each temperature data in the temperature data sequence B is obtained; According to the temperature data point corresponding to each temperature data in the temperature data sequence B, a nearest neighbor suspected data point and a feature set of the suspected fluctuation temperature data b are obtained. According to the first variance, the second variance, the nearest neighbor suspected data point and the feature set, a target fluctuation characteristic value of the suspected fluctuation temperature data b is obtained. 5.The cloud platform-based water cooling system intelligent operation and maintenance management system of claim 4, wherein, The method for obtaining the nearest neighbor suspected data point and the feature set of the suspected fluctuation temperature data b comprises: In the temperature data sequence B, all temperature data points corresponding to suspected fluctuation temperature data except the suspected fluctuation temperature data b are recorded as suspected data points; a temperature data point corresponding to the suspected fluctuation temperature data b is recorded as a first data point; in the second mapping coordinate system, a suspected data point located on the left side of the first data point and closest to the first data point is recorded as a left nearest neighbor suspected data point of the suspected fluctuation temperature data b, and a suspected data point located on the right side of the first data point and closest to the first data point is recorded as a right nearest neighbor suspected data point of the suspected fluctuation temperature data b, the nearest neighbor suspected data point comprises the left nearest neighbor suspected data point and the right nearest neighbor suspected data point; An interval formed by the abscissa value of the left-side neighboring suspected data point and the abscissa value of the first data point is denoted as a left-side interval, and an interval formed by the abscissa value of the right-side neighboring suspected data point and the abscissa value of the first data point is denoted as a right-side interval; in the second mapping coordinate system, a set formed by all temperature data points with an abscissa value belonging to the left-side interval is denoted as a first feature set, and a set formed by all temperature data points with an abscissa value belonging to the right-side interval is denoted as a second feature set, wherein the feature set includes the first feature set and the second feature set. 6.The cloud platform-based water cooling system intelligent operation and maintenance management system of claim 5, wherein, The method for obtaining the target fluctuation characteristic value of the suspected fluctuation temperature data b includes: performing negative correlation mapping on a result obtained by adding the first variance and the second variance, and denoting a mapping result as a first index value; denoting a Euclidean distance between the left-side neighboring suspected data point and the first data point as a left-side neighboring distance, denoting a Euclidean distance between the right-side neighboring suspected data point and the first data point as a right-side neighboring distance, and denoting a negative correlation mapping value of a result obtained by adding the left-side neighboring distance and the right-side neighboring distance as a second index value; denoting an absolute value of a difference between a mean value of ordinate values of all data points in the first feature set and the ordinate value of the first data point as a first difference value, denoting an absolute value of a difference between a mean value of ordinate values of all data points in the second feature set and the ordinate value of the first data point as a second difference value, and denoting a negative correlation mapping value of a result obtained by adding the first difference value and the second difference value as a third index value; denoting a normalized value of a result obtained by adding the first index value, the second index value, and the third index value as the target fluctuation characteristic value of the suspected fluctuation temperature data b. 7.The cloud platform-based water cooling system intelligent operation and maintenance management system of claim 1, wherein, The method for obtaining the to-be-analyzed data sequence of the temperature data sequence and the fluctuation to-be-analyzed data in the to-be-analyzed data sequence includes: For any suspected fluctuation temperature data, if a target fluctuation characteristic value of the suspected fluctuation temperature data is not less than a preset second fluctuation threshold, the suspected fluctuation temperature data is determined as fluctuation temperature data, otherwise, the suspected fluctuation temperature data is determined as noise temperature data; obtaining a replacement value of the noise temperature data, wherein the replacement value of the noise temperature data is a mean value of a pair of adjacent temperature data of the noise temperature data, the pair of adjacent temperature data of the noise temperature data is composed of a temperature data adjacent to the noise temperature data and located on a left side of the noise temperature data and a temperature data adjacent to the noise temperature data and located on a right side of the noise temperature data; replacing each noise temperature data in the temperature data sequence with a replacement value of the corresponding noise temperature data, and denoting a new sequence obtained after the replacement as the to-be-analyzed data sequence of the temperature data sequence; if an fth temperature data in the temperature data sequence is fluctuation temperature data, an fth to-be-analyzed data in the to-be-analyzed data sequence of the temperature data sequence is denoted as fluctuation to-be-analyzed data. 8.The cloud platform-based water cooling system intelligent operation and maintenance management system of claim 1, wherein, The method for obtaining the coefficient adjustment factor of the fluctuation to-be-analyzed data includes: According to the order of each to-be-analyzed data in the to-be-analyzed data sequence, a feature marker value of each to-be-analyzed data in the to-be-analyzed data sequence is obtained, and the feature marker value of the gth to-be-analyzed data in the to-be-analyzed data sequence is g; In all the to-be-analyzed data sequences, all to-be-analyzed data with the same feature marker value are divided into the same set, and are recorded as a feature sub-set. The feature marker value of the to-be-analyzed data in the feature sub-set is taken as an identification value of the corresponding feature sub-set. The to-be-analyzed data in each feature sub-set is clustered by using a clustering algorithm, and each clustering cluster corresponding to each feature sub-set is obtained. For any fluctuant to-be-analyzed data h in any to-be-analyzed data sequence, a feature sub-set with the same identification value and the feature marker value of the fluctuant to-be-analyzed data h is recorded as a target sub-set corresponding to the fluctuant to-be-analyzed data h. In each clustering cluster corresponding to the target sub-set, a clustering cluster containing the fluctuant to-be-analyzed data h is recorded as an analyzed clustering cluster. A ratio of a total number of data in the analyzed clustering cluster to a total number of data in the target sub-set is recorded as a first ratio. A reciprocal of a number of clustering clusters corresponding to the target sub-set is recorded as a second ratio. In the analyzed clustering cluster, a nearest neighbor to-be-analyzed data of each to-be-analyzed data in the analyzed clustering cluster is obtained, and is recorded as a cluster-internal nearest neighbor data corresponding to the corresponding to-be-analyzed data. An absolute value of a difference between each to-be-analyzed data in the analyzed clustering cluster and the cluster-internal nearest neighbor data corresponding to the to-be-analyzed data is recorded as a feature difference value of the to-be-analyzed data. A mean value of the feature difference values of all to-be-analyzed data in the analyzed clustering cluster is recorded as a first mean value, and a negative correlation mapping value of the first mean value is recorded as a first mapping value. A normalized value of a result obtained by adding the first ratio, the second ratio, and the first mapping value is recorded as a coefficient adjustment factor of the fluctuant to-be-analyzed data h. 9.The cloud platform-based water cooling system intelligent operation and maintenance management system of claim 1, wherein, The method for obtaining the second coefficient of each to-be-analyzed data in the to-be-analyzed data sequence comprises: For any to-be-analyzed data in any to-be-analyzed data sequence, if the to-be-analyzed data is not a fluctuant to-be-analyzed data, a first coefficient of the to-be-analyzed data is taken as a second coefficient of the to-be-analyzed data. If the to-be-analyzed data is a fluctuant to-be-analyzed data, a product of the first coefficient of the to-be-analyzed data and a coefficient adjustment factor of the to-be-analyzed data is taken as the second coefficient of the to-be-analyzed data. The first coefficient of the to-be-analyzed data is a coefficient calculated by importing the to-be-analyzed data sequence into an ARIMA prediction model. 10.The cloud platform-based water cooling system intelligent operation and maintenance management system of claim 1, wherein, The method for obtaining the predicted cooling liquid temperature data of the water cooling equipment at a future monitoring time comprises: For any water cooling equipment, according to a to-be-analyzed data sequence of a temperature data sequence corresponding to the water cooling equipment, a second coefficient of each to-be-analyzed data in the to-be-analyzed data sequence corresponding to the temperature data sequence of the water cooling equipment, and an ARIMA prediction model, the predicted cooling liquid temperature data of the water cooling equipment at the future monitoring time is obtained.

Images