Data center humidifying device control method, device and equipment

Abstract

The invention provides a data center humidifying device control method, device and equipment. The method comprises the steps that real-time relative humidity data of preset point positions of all areas of a data center machine room are obtained; preprocessing the real-time relative humidity data to obtain preprocessed humidity data; inputting the preprocessed humidity data into a processing layer of a humidity prediction model for processing to obtain a processing result of the processing layer; inputting the processing result of the processing layer into a prediction layer of the humidity prediction model to carry out humidity prediction processing so as to obtain a humidity prediction result; according to the humidity prediction result, control parameters of a data center humidifying device are determined; the data center humidifying device is an ultrasonic humidifying device; and according to the control parameters, the data center humidification device is controlled to operate for humidification. According to the scheme, the ultrasonic humidifying device can be accurately controlled, the humidifying energy consumption is reduced while the humidity requirement is met, the ultrasonic humidifying device is used for humidifying, and the humidifying energy consumption is further reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of humidity control and regulation, and particularly to a control method, device and equipment for a humidifying device in a data center. Background Art

[0002] The main reasons for the need to humidify and dehumidify the data center computer room include the following points: preventing the accumulation of static electricity and endangering equipment: too low humidity (below 40%) will cause the accumulation of static electricity in the air, and dust on the surface of the equipment and in the air is likely to generate high static electricity voltage due to friction. When discharging, it may damage sensitive electronic components (such as chips, integrated circuit boards), resulting in hardware failures or data loss, and damaging sensitive electronic components or server equipment; ensuring equipment stability: in a high-humidity environment, metal components (such as slots, connectors) may have poor contact due to thermal expansion and contraction or oxidation, resulting in abnormal signal transmission or equipment downtime; at the same time, some insulating materials or storage media (such as magnetic tapes) may shrink or deform in a dry environment, affecting performance or lifespan; in addition, too high humidity may cause condensation and corrosion of equipment, while too low humidity may cause electrostatic discharge;

[0003] Humidifying the data center computer room helps to maintain balance, keeping the relative humidity of the data center computer room within a suitable range, which is an important measure to maintain compliance and ensure the effectiveness of equipment quality assurance;

[0004] At present, there are two most commonly used humidifying devices in air-cooled precision air conditioners in data centers, electrode humidifiers and heating lamp humidifiers. The existing two humidifying devices have high operating power consumption and do not conform to the concept of energy conservation and environmental protection. Summary of the Invention

[0005] The present invention provides a control method, device and equipment for a humidifying device in a data center, which can accurately control an ultrasonic humidifying device, reduce the humidifying energy consumption while meeting the humidity requirements, and further reduce the humidifying energy consumption by using the ultrasonic humidifying device for humidification.

[0006] To solve the above technical problems, the technical solution of the present invention is as follows:

[0007] A control method for a humidifying device in a data center includes:

[0008] Obtaining the real-time relative humidity data of preset points in each area of the data center computer room;

[0009] Preprocessing the real-time relative humidity data to obtain preprocessed humidity data;

[0010] Inputting the preprocessed humidity data into the processing layer of a humidity prediction model for processing to obtain the processing result of the processing layer;

[0011] Input the processing result of the processing layer into the prediction layer of the humidity prediction model for humidity prediction processing to obtain a humidity prediction result; wherein, the processing layer of the humidity prediction model is trained according to a first preset network model and a second preset network model, and the prediction layer of the humidity prediction model is trained according to a third preset network model;

[0012] Determine the control parameters of the humidification device in the data center according to the humidity prediction result and the real-time relative humidity data; wherein the humidification device in the data center is an ultrasonic humidification device;

[0013] Control the operation of the humidification device in the data center for humidification according to the control parameters.

[0014] Optionally, preprocess the real-time relative humidity data to obtain preprocessed humidity data, including:

[0015] Perform data cleaning processing on the real-time relative humidity data to obtain a first processing result;

[0016] Perform normalization processing on the first processing result to obtain preprocessed humidity data.

[0017] Optionally, input the preprocessed humidity data into the processing layer of the humidity prediction model for processing to obtain a processing result of the processing layer, including:

[0018] Input the preprocessed humidity data into the first processing module of the processing layer of the humidity prediction model to effectively analyze and predict the periodic and trend time series in the preprocessed humidity data to obtain a first processing result of the processing layer;

[0019] Input the preprocessed humidity data into the second processing module of the processing layer of the humidity prediction model to effectively analyze and predict the non-linear and non-stationary time series in the preprocessed humidity data to obtain a second processing result of the processing layer.

[0020] Optionally, input the processing result of the processing layer into the prediction layer of the humidity prediction model for humidity prediction processing to obtain a humidity prediction result, including:

[0021] Obtain the first weight of the first processing result of the processing layer and the second weight of the second processing result of the processing layer;

[0022] Input the first processing result of the processing layer, the first weight, the second processing result of the processing layer, and the second weight into the prediction layer of the humidity prediction model for weighted averaging to obtain a humidity prediction result.

[0023] Optionally, determine the control parameters of the humidification device in the data center according to the humidity prediction result and the real-time relative humidity data, including:

[0024] Determine the start time of the humidifying device in the data center according to the humidity prediction result, the real-time relative humidity data, and a preset standard humidity range;

[0025] Determine the start duration and humidifying power of the humidifying device in the data center according to the humidity prediction result, the real-time relative humidity data, and a preset humidity stop value.

[0026] Optionally, determining the start time of the humidifying device in the data center according to the humidity prediction result, the real-time relative humidity data, and a preset standard humidity range includes:

[0027] Determine humidity adjustment information according to the humidity prediction result, the real-time relative humidity data, and a preset standard humidity range;

[0028] Determine the start time of the humidifying device in the data center according to the humidity adjustment information and a preset standard humidity range.

[0029] Optionally, determining the start duration and humidifying power of the humidifying device in the data center according to the humidity prediction result, the real-time relative humidity data, and a preset humidity stop value includes:

[0030] Determine the total humidification amount according to the humidity prediction result, the real-time relative humidity data, and a preset humidity stop value;

[0031] Determine the start duration and humidifying power of the humidifying device in the data center according to the total humidification amount.

[0032] The present invention also provides a control device for a humidifying device in a data center, including:

[0033] An acquisition module for acquiring real-time relative humidity data of preset points in each area of the data center computer room;

[0034] A processing module for preprocessing the real-time relative humidity data to obtain preprocessed humidity data; inputting the preprocessed humidity data into a processing layer of a humidity prediction model for processing to obtain a processing result of the processing layer; inputting the processing result of the processing layer into a prediction layer of the humidity prediction model for humidity prediction processing to obtain a humidity prediction result; wherein, the processing layer of the humidity prediction model is trained according to a first preset network model and a second preset network model, and the prediction layer of the humidity prediction model is trained according to a third preset network model; determine control parameters of the humidifying device in the data center according to the humidity prediction result and the real-time relative humidity data; wherein the humidifying device in the data center is an ultrasonic humidifying device; control the humidifying device in the data center to operate for humidification according to the control parameters.

[0035] The present invention also provides a computing device, including: a processor and a memory storing a computer program, and when the computer program is run by the processor, the above-described method is executed.

[0036] The present invention also provides a computer-readable storage medium storing instructions, and when the instructions are run on a computer, the computer is caused to execute the above-described method.

[0037] The above solution of the present invention has at least the following beneficial effects:

[0038] In the above solution of the present invention, by obtaining the real-time relative humidity data of preset points in each area of the data center computer room; preprocessing the real-time relative humidity data to obtain preprocessed humidity data; inputting the preprocessed humidity data into the processing layer of the humidity prediction model for processing to obtain a processing result of the processing layer; inputting the processing result of the processing layer into the prediction layer of the humidity prediction model for humidity prediction processing to obtain a humidity prediction result; determining the control parameters of the data center humidifying device according to the humidity prediction result, where the data center humidifying device is an ultrasonic humidifying device; controlling the operation of the data center humidifying device for humidification according to the control parameters; it is possible to accurately control the ultrasonic humidifying device, meet the humidity requirements while reducing the humidification energy consumption, and at the same time use the ultrasonic humidifying device for humidification to further reduce the humidification energy consumption. Description of the Drawings

[0039] Figure 1 is a flowchart of the data center humidifying device control method provided by the embodiment of the present invention;

[0040] Figure 2 A module diagram of the data center humidifying device control device provided by the embodiment of the present invention. Detailed Embodiments

[0041] The exemplary embodiments of the present invention will be described in more detail below with reference to the drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present invention can be more thoroughly understood and the scope of the present invention can be fully conveyed to those skilled in the art.

[0042] As Figure 1 shown, an embodiment of the present invention provides a data center humidifying device control method, including:

[0043] Step 11, obtaining the real-time relative humidity data of preset points in each area of the data center computer room;

[0044] Step 12: Preprocess the real-time relative humidity data to obtain preprocessed humidity data;

[0045] Step 13: Input the preprocessed humidity data into the processing layer of the humidity prediction model for processing to obtain the processing result of the processing layer;

[0046] Step 14: Input the processing result of the processing layer into the prediction layer of the humidity prediction model for humidity prediction processing to obtain a humidity prediction result; wherein, the processing layer of the humidity prediction model is trained according to a first preset network model and a second preset network model, and the prediction layer of the humidity prediction model is trained according to a third preset network model;

[0047] Step 15: Determine the control parameters of the humidification device in the data center according to the humidity prediction result and the real-time relative humidity data; wherein the humidification device in the data center is an ultrasonic humidification device;

[0048] Step 16: Control the operation of the humidification device in the data center for humidification according to the control parameters.

[0049] In this embodiment, by obtaining the real-time relative humidity data of each preset point in the computer room of the data center; preprocessing the real-time relative humidity data to obtain preprocessed humidity data; inputting the preprocessed humidity data into the processing layer of the humidity prediction model for processing to obtain the processing result of the processing layer; inputting the processing result of the processing layer into the prediction layer of the humidity prediction model for humidity prediction processing to obtain a humidity prediction result; determining the control parameters of the humidification device in the data center according to the humidity prediction result; wherein the humidification device in the data center is an ultrasonic humidification device; controlling the operation of the humidification device in the data center for humidification according to the control parameters; it is possible to accurately control the ultrasonic humidification device, meet the humidity requirements while reducing the humidification energy consumption, and at the same time use the ultrasonic humidification device for humidification to further reduce the humidification energy consumption.

[0050] In an alternative embodiment of the present invention, Step 12 includes:

[0051] Step 121: Perform data cleaning processing on the real-time relative humidity data to obtain a first processing result;

[0052] Step 122: Perform normalization processing on the first processing result to obtain preprocessed humidity data.

[0053] In this embodiment, perform data cleaning processing on the real-time relative humidity data to obtain a first processing result;

[0054] Specifically, by judging the outliers in the real-time relative humidity data;

[0055] Among them, the real-time relative humidity data sequence is representing the standard deviation of the real-time relative humidity data sequence; representing the mean value of the real-time relative humidity data sequence; n represents the number of samples;

[0056] When the data of the data point satisfies then the data of this data point is an outlier;

[0057] By replacing the outlier;

[0058] Among them, representing the estimated humidity value; representing the time point that needs interpolation, the time point is located between the time point and the time point ; representing the humidity value corresponding to the time point ; representing the humidity value corresponding to the time point ;

[0059] By performing data cleaning processing on the real-time relative humidity data to ensure the accuracy and smoothness of the real-time relative humidity data;

[0060] Performing normalization processing on the first processing result to obtain preprocessed humidity data;

[0061] Specifically, by performing normalization processing on the first processing result;

[0062] Among them, the humidity value after normalization processing; representing the minimum value in the real-time relative humidity data sequence; representing the maximum value in the real-time relative humidity data sequence; representing the humidity value corresponding to the time point ;

[0063] By performing normalization processing on the first processing result to ensure the standardization and consistency of the data, which is convenient for subsequent processing.

[0064] In an optional embodiment of the present invention, step 13 includes:

[0065] Step 131, inputting the preprocessed humidity data into the first processing module of the processing layer of the humidity prediction model to effectively analyze and predict the periodic and trend time series in the preprocessed humidity data, and obtaining the processing result of the first processing layer;

[0066] Step 132: Input the preprocessed humidity data into the second processing module of the processing layer of the humidity prediction model to effectively analyze and predict the non-linear and non-stationary time series in the preprocessed humidity data, and obtain the processing result of the second processing layer.

[0067] In this embodiment, step 131 may include:

[0068] Step 1311: Input the preprocessed humidity data into the stationarity test sub-module of the first processing module of the processing layer of the humidity prediction model for stationarity test and differencing processing, and obtain the first test result;

[0069] Step 1312: Input the first test result into the prediction sub-module of the first processing module of the processing layer of the humidity prediction model for prediction, and obtain the processing result of the first processing layer;

[0070] Through the first processing module of the processing layer of the humidity prediction model, the linear relationship and short-term dependence structure in the preprocessed humidity data can be captured, and the periodic and trend time series in the preprocessed humidity data can be effectively analyzed and predicted;

[0071] Among them, the first processing module of the processing layer of the humidity prediction model is trained according to the first preset network model, and the training process of the first preset network model is as follows:

[0072] Obtain the training relative humidity data;

[0073] Preprocess the training relative humidity data to obtain the training preprocessed humidity data;

[0074] Stationarity test, through Obtain ;

[0075] Through Obtain the test statistic s;

[0076] Compare the test statistic s with the preset critical value to determine whether to reject the null hypothesis;

[0077] Specifically, if is greater than the preset critical value, then reject the null hypothesis and consider that the training preprocessed humidity data is stationary; otherwise, do not reject the null hypothesis, that is, consider that the training preprocessed humidity data is non-stationary; where is the value of the training preprocessed humidity data at time t; , represents the first-order difference; represents the parameter to be estimated for testing the unit root; P represents the lag order; represents the coefficient of the lag term; represents the error term, which is usually assumed to be white noise; denotes the estimated value of; denotes the standard error of; s represents the test statistic; if the training preprocessed humidity data is non-stationary, perform differencing calculation on the training preprocessed humidity data and conduct a stationarity test on the training preprocessed humidity data after the differencing calculation is completed until the training preprocessed humidity data is stationary;

[0078] Parameter determination, the training preprocessed humidity data is a sequence of ; through ; ; ; ; obtain the autocorrelation function graph, observe the variation law of the autocorrelation coefficient with the time interval k. After a certain order in the autocorrelation function graph, the autocorrelation coefficient rapidly approaches 0, then this order is the moving average order q of the first processing module in the processing layer of the humidity prediction model; where, represents the value of the training preprocessed humidity data at time t; represents the mean value of the training preprocessed humidity data; represents the autocovariance at time interval 0; represents the autocovariance function at time interval k; represents the autocorrelation function of the training preprocessed humidity data at time interval k; k represents a constant; n represents the number of samples;

[0079] Through obtain the partial autocorrelation coefficient value, draw the partial autocorrelation function graph through the partial autocorrelation coefficient value. After a certain order in the partial autocorrelation function graph, the partial autocorrelation coefficient rapidly approaches 0, then this order is the autoregressive order p of the first processing module in the processing layer of the humidity prediction model; where, represents the partial autocorrelation coefficient; represents the autocorrelation function of the training preprocessed humidity data at time interval k; k represents a constant;

[0080] Determine the model order d of the first processing module in the processing layer of the humidity prediction model through AIC = 2m - 2ln(L); BIC = mln(n) - 2ln(L); specifically, by calculating the AIC and BIC values of the model under different p, q combinations, select the combination with the smallest AIC and BIC values as the final model order d; where, m represents the number of parameters; L represents the likelihood function value; AIC represents the Akaike information criterion; BIC represents the Bayesian information criterion;

[0081] Construct a likelihood function, and use a numerical optimization algorithm to solve for the parameter estimates that maximize the likelihood function, obtaining the autoregressive coefficient p, the moving average coefficient q, and the model order d;

[0082] Input the preprocessed humidity data for training into the first preset network model to obtain the first processing module of the processing layer of the humidity prediction model; perform residual analysis on the first processing module of the processing layer of the trained humidity prediction model to check whether the residual sequence is white noise. If the residual sequence is white noise, it indicates that the model has fully extracted the information in the data and the model fitting effect is good; if the residual sequence is not white noise, it means that there may be information in the model that has not been captured and the model needs to be adjusted again;

[0083] Input the test relative humidity data into the first processing module of the processing layer of the trained humidity prediction model for prediction, and evaluate the prediction performance of the model by calculating prediction error metrics (such as mean square error MSE, mean absolute error MAE, root mean square error RMSE, etc.); if the prediction error is within an acceptable range, it indicates that the model has good prediction ability; if the prediction error is large, the model needs to be adjusted and optimized; until the first processing module of the processing layer of the final humidity prediction model is obtained;

[0084] In this embodiment, step 132 may include:

[0085] Step 1321, input the preprocessed humidity data into the input layer of the second processing module of the processing layer of the humidity prediction model to obtain the input layer result;

[0086] Step 1322, input the input layer result into the hidden layer of the second processing module of the processing layer of the humidity prediction model to obtain the hidden layer result;

[0087] Step 1323, input the hidden layer result into the output layer of the second processing module of the processing layer of the humidity prediction model to obtain the second processing layer processing result;

[0088] Through the second processing module of the processing layer of the humidity prediction model, the long-term dependence relationship in the preprocessed humidity data can be captured, and the non-linear and non-stationary time series in the preprocessed humidity data can be effectively analyzed and predicted;

[0089] Among them, the second processing module of the processing layer of the humidity prediction model is trained according to the second preset network model, and the specific training process of the second preset network model is as follows:

[0090] Obtain the training relative humidity data;

[0091] Preprocess the training relative humidity data to obtain the preprocessed training humidity data;

[0092] Input the preprocessed humidity data for training into the second preset network model for training;

[0093] Among them, the loss function is ; Among them, represents the actual humidity value corresponding to the training relative humidity data; represents the predicted humidity value; MSE represents the mean square error; n represents the number of samples;

[0094] During training, the second preset network model updates parameters such as weights and biases in the model units according to the gradient information calculated by the loss function to minimize the loss function; among them, the optimizer can be the Adam optimizer;

[0095] During the model verification process, closely monitor its performance on the independent validation set and adjust the hyperparameters accordingly, such as: learning rate, number of network layers, and number of units in each layer, etc.; after completing the training, comprehensively evaluate the model and record multiple performance indicators such as MAE (Mean Absolute Error), MSE (Mean Square Error), and coefficient of determination (R², Coefficient of Determination) as the basis for comprehensive evaluation; among them, the formula for the coefficient of determination is as follows:

[0096]

[0097] Among them, represents the number of samples; represents the actual humidity value corresponding to the training relative humidity data; represents the predicted humidity value; represents the average value of the preprocessed humidity data for training; represents the coefficient of determination;

[0098] After multiple rounds of iterative optimization, select the model with the best performance as the second processing module of the processing layer of the humidity prediction model;

[0099] During training, set the output of each neuron to 0 with a certain probability. L2 regularization limits the size of the model parameters by adding a penalty term to the loss function, thereby reducing the model complexity and avoiding overfitting; for the second preset network model, the penalty term is usually the product of the sum of the squares of all weights and a small constant:

[0100]

[0101] Among them, represents the original loss function; represents the regularization strength hyperparameter; represents the weight parameter in the model; represents the penalty term;

[0102] The first processing module of the processing layer of the humidity prediction model can capture the linear relationship and short-term dependence structure in the preprocessed humidity data, and effectively analyze and predict the periodic and trending time series in the preprocessed humidity data; through the second processing module of the processing layer of the humidity prediction model, the long-term dependence relationship in the preprocessed humidity data can be captured, and the non-linear and non-stationary time series in the preprocessed humidity data can be effectively analyzed and predicted;

[0103] By separately processing the preprocessed humidity data through the first processing module and the second processing module of the processing layer of the humidity prediction model and obtaining corresponding results, the processing accuracy of the processing layer of the humidity prediction model can be improved.

[0104] In an optional embodiment of the present invention, step 14 may include:

[0105] Step 141, obtaining the first weight of the processing result of the first processing layer and the second weight of the processing result of the second processing layer;

[0106] Step 142, inputting the processing result of the first processing layer, the first weight, the processing result of the second processing layer, and the second weight into the prediction layer of the humidity prediction model for weighted averaging to obtain a humidity prediction result.

[0107] In this embodiment, through ; the humidity prediction result is obtained;

[0108] wherein, represents the humidity prediction result; represents the processing result of the first processing layer; represents the first weight of the processing result of the first processing layer; represents the processing result of the second processing layer; represents the second weight of the processing result of the second processing layer;

[0109] and The determination process of:

[0110] Input the test relative humidity data into the first processing module of the processing layer of the humidity prediction model for processing to obtain a first test predicted humidity value;

[0111] Input the test relative humidity data into the second processing module of the processing layer of the humidity prediction model for processing to obtain a second test predicted humidity value;

[0112] Adopt a grid search optimization algorithm to perform weighted averaging on the first test predicted humidity value and the second test predicted humidity value, and traverse different weight combinations;

[0113] By calculating the RMSE (root mean square error) value for each combination and selecting the weight combination with the minimum RMSE value as the final model weight to determine and ; where n represents the number of samples; m represents the number of models. In this embodiment, m = 2; represents the true value of the i-th sample; represents the predicted value of the i-th sample by the j-th model; represents the weight of the j-th model.

[0114] In an alternative embodiment of the present invention, step 15 includes:

[0115] Step 151, determining the start time of the humidification device in the data center according to the humidity prediction result, the real-time relative humidity data, and a preset standard humidity range;

[0116] Step 152, determining the start duration and humidification power of the humidification device in the data center according to the humidity prediction result, the real-time relative humidity data, and a preset humidity stop value.

[0117] Further, step 151 may include:

[0118] Step 1511, determining humidity adjustment information according to the humidity prediction result, the real-time relative humidity data, and a preset standard humidity range;

[0119] Step 1512, determining the start time of the humidification device in the data center according to the humidity adjustment information and a preset standard humidity range.

[0120] Further, step 152 may include:

[0121] Step 1521, determining the total humidification amount according to the humidity prediction result, the real-time relative humidity data, and a preset humidity stop value;

[0122] Step 1522, determining the start duration and humidification power of the humidification device in the data center according to the total humidification amount.

[0123] In this embodiment, humidity adjustment information is determined according to the humidity prediction result, the real-time relative humidity data, and a preset standard humidity range. Specifically, when both the real-time relative humidity data and the humidity prediction result are within the preset standard humidity range, the humidity adjustment information is that no adjustment is needed; when either the real-time relative humidity data or the humidity prediction result is less than the preset standard humidity range, the humidity adjustment information is that humidification is needed; when either the real-time relative humidity data or the humidity prediction result is greater than the preset standard humidity range, the humidity adjustment information is that dehumidification is needed.

[0124] According to the humidity adjustment information and the preset standard humidity range, the start time of the humidification device in the data center is determined. Specifically, when the humidity adjustment information is that humidification is needed: when the real-time relative humidity data is less than the preset standard humidity range, the humidification device in the data center is started immediately; when the real-time relative humidity data is within the preset standard humidity range and the humidity prediction result is less than the preset standard humidity range, through ; where represents the start timing time of the humidification device in the data center, that is, after the elapsed time , the humidification device in the data center is started; T represents the humidity prediction duration; represents the real-time relative humidity data; represents the minimum humidity value of the preset standard humidity range; represents the humidity prediction result, that is, the humidity value after the predicted time T;

[0125] According to the humidity prediction result, the real-time relative humidity data, and the preset humidification stop humidity, the total humidification amount is determined; according to the total humidification amount, the start duration and humidification power of the humidification device in the data center are determined.

[0126] Specifically, if the real-time relative humidity data is less than the preset standard humidity range and the humidity prediction result is less than the real-time relative humidity data, it indicates that the humidity is in a decreasing state;

[0127] Through , the total humidification amount is determined ; where Q represents the total humidification amount; represents the air density; V represents the space volume of the data center computer room; represents the preset humidification stop humidity, and in practice can take the intermediate value of the preset standard humidity range; represents the humidity prediction result; d s represents the moisture content of saturated air at the same temperature;

[0128] The humidification power of the humidification device in the data center is the full power of the ultrasonic humidification device;

[0129] By , determine the humidification duration of the humidification device in the data center ; where represents the humidification duration of the humidification device in the data center; Q represents the total humidification amount; represents the proportionality constant, which can be determined through experiments; represents the humidification power of the humidification device in the data center, specifically the full power of the ultrasonic humidification device; A represents the vibration area of the transducer of the ultrasonic humidification device;

[0130] If the real-time relative humidity data is less than the preset standard humidity range and the humidity prediction result is greater than the real-time relative humidity data, it indicates that the humidity is in an increasing state;

[0131] Humidify in two time periods. By determine the total humidification amount in the first stage ; By determine the total humidification amount in the second stage ; where represents the total humidification amount in the first stage; represents the total humidification amount in the second stage; represents the air density; V represents the space volume of the data center computer room; represents the preset humidification stop humidity, and in practice can take the middle value of the preset standard humidity range; represents the humidity prediction result; represents the real-time relative humidity data; represents the minimum humidity value of the preset standard humidity range; d s represents the moisture content of saturated air at the same temperature;

[0132] The first-stage humidification power of the humidification device in the data center is the full power of the ultrasonic humidification device; the second-stage humidification power of the humidification device in the data center is 50% of the full power of the ultrasonic humidification device;

[0133] By , determine the first-stage humidification duration of the humidification device in the data center ; By , determine the second-stage humidification duration of the humidification device in the data center ; where represents the first-stage humidification duration of the humidification device in the data center; represents the second-stage humidification duration of the humidification device in the data center; represents a proportionality constant that can be determined through experiments; represents the first-stage humidification power of the data center humidification device, specifically the full power of the ultrasonic humidification device; represents the second-stage humidification power of the data center humidification device, specifically 50% of the full power of the ultrasonic humidification device; A represents the vibration area of the transducer of the ultrasonic humidification device; represents the total humidification amount in the first stage; represents the total humidification amount in the second stage;

[0134] If the real-time relative humidity data is within the preset standard humidity range and the humidity prediction result is less than the preset standard humidity range, it indicates that the humidity is in a decreasing state;

[0135] Through , determine the humidification duration of the data center humidification device ;

[0136] Through , determine the total humidification amount ;

[0137] Through , determine the processing power of the data center humidification device ; Among them, represents the humidification duration of the data center humidification device; T represents the humidity prediction duration; represents the real-time relative humidity data; represents the minimum humidity value of the preset standard humidity range; represents the humidity prediction result; Q represents the total humidification amount; represents the air density; V represents the space volume of the data center computer room; represents the preset humidification stop humidity, and in practice can take the middle value of the preset standard humidity range; represents the humidification power of the data center humidification device; Q represents the total humidification amount; represents a proportionality constant that can be determined through experiments; A represents the vibration area of the transducer of the ultrasonic humidification device; d s represents the moisture content of saturated air at the same temperature.

[0138] The implementation process of a specific embodiment of the present invention is as follows: The control process of the data center humidification device includes the following steps:

[0139] Step 1, obtain the real-time relative humidity data of the preset points in each area of the data center computer room;

[0140] Step 2: Perform data cleaning on the real-time relative humidity data to obtain a first processing result; perform normalization on the first processing result to obtain preprocessed humidity data;

[0141] Step 3: Input the preprocessed humidity data into the first processing module of the processing layer of the humidity prediction model for processing to obtain a first processing layer result; input the preprocessed humidity data into the second processing module of the processing layer of the humidity prediction model for processing to obtain a second processing layer result;

[0142] Step 4: Input the first processing layer result and the second processing layer result into the prediction layer of the humidity prediction model for weighted averaging to obtain a humidity prediction result;

[0143] Step 5: Determine humidity adjustment information based on the humidity prediction result, the real-time relative humidity data, and a preset standard humidity range. Specifically, when both the real-time relative humidity data and the humidity prediction result are within the preset standard humidity range, the humidity adjustment information is no adjustment; when either the real-time relative humidity data or the humidity prediction result is less than the preset standard humidity range, the humidity adjustment information is humidification required; when either the real-time relative humidity data or the humidity prediction result is greater than the preset standard humidity range, the humidity adjustment information is dehumidification required;

[0144] Step 6: Determine the activation time of the data center humidification device based on the humidity adjustment information and the preset standard humidity range. Specifically, when the humidity adjustment information is humidification required: when the real-time relative humidity data is less than the preset standard humidity range, the data center humidification device is activated immediately; when the real-time relative humidity data is within the preset standard humidity range and the humidity prediction result is less than the preset standard humidity range, by ; where represents the activation timing of the data center humidification device, that is, after a time the data center humidification device is activated; T represents the humidity prediction duration; represents the real-time relative humidity data; represents the minimum humidity value of the preset standard humidity range; represents the humidity prediction result, that is, the humidity value after a predicted time T;

[0145] Step 7: Determine the total humidification amount based on the humidity prediction result, the real-time relative humidity data, and a preset humidification stop humidity;

[0146] Step 8: Determine the activation duration and humidification power of the data center humidification device based on the total humidification amount;

[0147] Specifically, if the real-time relative humidity data is less than the preset standard humidity range and the humidity prediction result is less than the real-time relative humidity data, it indicates that the humidity is in a decreasing state;

[0148] By , the total humidification amount is determined ; where Q represents the total humidification amount; represents the air density; V represents the space volume of the data center computer room; represents the preset humidity stop humidity, and in practice can take the middle value of the preset standard humidity range; represents the humidity prediction result; d s represents the moisture content of saturated air at the same temperature;

[0149] The humidification power of the data center humidification device is the full power of the ultrasonic humidification device;

[0150] By , the humidification duration of the data center humidification device is determined ; where represents the humidification duration of the data center humidification device; Q represents the total humidification amount; represents the proportionality constant, which can be determined through experiments; represents the humidification power of the data center humidification device, specifically the full power of the ultrasonic humidification device; A represents the vibration area of the transducer of the ultrasonic humidification device;

[0151] If the real-time relative humidity data is less than the preset standard humidity range and the humidity prediction result is greater than the real-time relative humidity data, it indicates that the humidity is in an increasing state;

[0152] Humidification is carried out in two time periods. By the total humidification amount in the first stage is determined ; By the total humidification amount in the second stage is determined ; where represents the total humidification amount in the first stage; represents the total humidification amount in the second stage; represents the air density; V represents the space volume of the data center computer room; represents the preset humidity stop humidity, and in practice can take the middle value of the preset standard humidity range; represents the humidity prediction result; represents the real-time relative humidity data; represents the minimum humidity value of the preset standard humidity range; d s represents the moisture content of saturated air at the same temperature;

[0153] The first-stage humidification power of the data center humidification device is the full power of the ultrasonic humidification device; the second-stage humidification power of the data center humidification device is 50% of the full power of the ultrasonic humidification device;

[0154] Through , determine the first-stage humidification duration of the data center humidification device ; Through , determine the second-stage humidification duration of the data center humidification device ; Among them, represents the first-stage humidification duration of the data center humidification device; represents the second-stage humidification duration of the data center humidification device; represents the proportionality constant, which can be determined through experiments; represents the first-stage humidification power of the data center humidification device, specifically the full power of the ultrasonic humidification device; represents the second-stage humidification power of the data center humidification device, specifically 50% of the full power of the ultrasonic humidification device; A represents the vibration area of the transducer of the ultrasonic humidification device; represents the total humidification amount in the first stage; represents the total humidification amount in the second stage;

[0155] If the real-time relative humidity data is within the preset standard humidity range and the humidity prediction result is less than the preset standard humidity range, it indicates that the humidity is in a decreasing state;

[0156] Through , determine the humidification duration of the data center humidification device ;

[0157] Through , determine the total humidification amount ;

[0158] Through , determine the processing power of the data center humidification device ; Among them, represents the humidification duration of the data center humidification device; T represents the humidity prediction duration; represents the real-time relative humidity data; represents the minimum humidity value of the preset standard humidity range; represents the humidity prediction result; Q represents the total humidification amount; represents the air density; V represents the space volume of the data center computer room; represents the preset humidification stop humidity, in practice It can take the median value of the preset standard humidity range; represents the humidification power of the humidification device in the data center; Q represents the total humidification amount; represents a proportionality constant, which can be determined through experiments; A represents the vibration area of the transducer of the ultrasonic humidification device; d s represents the moisture content of saturated air at the same temperature;

[0159] Step 9, control the operation of the humidification of the data center humidification device according to the control parameter;

[0160] Through the above process, accurate control of the ultrasonic humidification device can be achieved, reducing the humidification energy consumption while meeting the humidity requirements. Humidification is carried out with the ultrasonic humidification device to further reduce the humidification energy consumption; at the same time, the humidity in each area of the data center computer room can be controlled within the middle area of the preset standard humidity range, reducing the usage times of the dehumidification device in the data center computer room and reducing the overall energy consumption of humidity control in the data center computer room.

[0161] Such as Figure 2 shown, an embodiment of the present invention further provides a control device 20 for a data center humidification device, including:

[0162] An acquisition module 21, configured to acquire real-time relative humidity data of preset points in each area of the data center computer room;

[0163] A processing module 22, configured to preprocess the real-time relative humidity data to obtain preprocessed humidity data; input the preprocessed humidity data into the processing layer of the humidity prediction model for processing to obtain a processing result of the processing layer; input the processing result of the processing layer into the prediction layer of the humidity prediction model for humidity prediction processing to obtain a humidity prediction result; wherein, the processing layer of the humidity prediction model is trained according to a first preset network model and a second preset network model, and the prediction layer of the humidity prediction model is trained according to a third preset network model; determine the control parameter of the data center humidification device according to the humidity prediction result and the real-time relative humidity data; wherein the data center humidification device is an ultrasonic humidification device; control the operation of the data center humidification device to humidify according to the control parameter.

[0164] Optionally, preprocessing the real-time relative humidity data to obtain preprocessed humidity data includes:

[0165] Perform data cleaning processing on the real-time relative humidity data to obtain a first processing result;

[0166] Perform normalization processing on the first processing result to obtain preprocessed humidity data.

[0167] Optionally, input the preprocessed humidity data into the processing layer of the humidity prediction model for processing to obtain the processing layer processing result, including:

[0168] Input the preprocessed humidity data into the first processing module of the processing layer of the humidity prediction model to effectively analyze and predict the periodic and trend time series in the preprocessed humidity data, and obtain the first processing layer processing result;

[0169] Input the preprocessed humidity data into the second processing module of the processing layer of the humidity prediction model to effectively analyze and predict the non-linear and non-stationary time series in the preprocessed humidity data, and obtain the second processing layer processing result.

[0170] Optionally, input the processing layer processing result into the prediction layer of the humidity prediction model for humidity prediction processing to obtain the humidity prediction result, including:

[0171] Obtain the first weight of the first processing layer processing result and the second weight of the second processing layer processing result;

[0172] Input the first processing layer processing result, the first weight, the second processing layer processing result, and the second weight into the prediction layer of the humidity prediction model for weighted average to obtain the humidity prediction result.

[0173] Optionally, determine the control parameters of the data center humidification device according to the humidity prediction result and the real-time relative humidity data, including:

[0174] Determine the starting time of the data center humidification device according to the humidity prediction result, the real-time relative humidity data, and the preset standard humidity range;

[0175] Determine the starting duration and humidification power of the data center humidification device according to the humidity prediction result, the real-time relative humidity data, and the preset humidification stop humidity.

[0176] Optionally, determine the starting time of the data center humidification device according to the humidity prediction result, the real-time relative humidity data, and the preset standard humidity range, including:

[0177] Determine the humidity adjustment information according to the humidity prediction result, the real-time relative humidity data, and the preset standard humidity range;

[0178] Determine the starting time of the data center humidification device according to the humidity adjustment information and the preset standard humidity range.

[0179] Optionally, determining the opening duration and humidifying power of the humidifying device in the data center according to the humidity prediction result, the real-time relative humidity data, and a preset humidity for stopping humidification includes:

[0180] Determining the total humidification amount according to the humidity prediction result, the real-time relative humidity data, and the preset humidity for stopping humidification;

[0181] Determining the opening duration and humidifying power of the humidifying device in the data center according to the total humidification amount.

[0182] It should be noted that this device corresponds to the above method. All implementation manners in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effects.

[0183] An embodiment of the present invention further provides a computing device, including: a processor and a memory storing a computer program. When the computer program is run by the processor, it executes the method described in the above embodiments. All implementation manners in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0184] An embodiment of the present invention further provides a computer-readable storage medium storing an instruction. When the instruction runs on a computer, it causes the computer to execute the method described in the above embodiments. All implementation manners in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0185] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0186] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0187] In the embodiments provided by the present invention, it should be understood that the disclosed apparatus and method can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the apparatus or unit can be in electrical, mechanical or other forms.

[0188] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0189] In addition, each functional unit in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0190] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0191] In addition, it should be noted that in the device and method of the present invention, obviously, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present invention. Moreover, the steps of performing the above series of processes can naturally be executed in chronological order according to the described order, but it is not necessary to execute them in chronological order. Some steps can be executed in parallel or independently of each other. For those of ordinary skill in the art, it is possible to understand that all or any steps or components of the method and device of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in the form of hardware, firmware, software, or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0192] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a well-known general-purpose device. Therefore, the object of the present invention can also be achieved only by providing a program product containing program code for implementing the method or device. That is to say, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be noted that in the device and method of the present invention, obviously, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present invention. Moreover, the steps of performing the above series of processes can naturally be executed in chronological order according to the described order, but it is not necessary to execute them in chronological order. Some steps can be executed in parallel or independently of each other.

[0193] The above is the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A data center humidification device control method, characterized in that: include: Obtain real-time relative humidity data at preset points in each area of ​​the data center room; Preprocessing the real-time relative humidity data to obtain preprocessed humidity data; Inputting the pre-processed humidity data into the processing layer of the humidity prediction model for processing to obtain a processing result of the processing layer; Inputting the processing result of the processing layer into the prediction layer of the humidity prediction model for humidity prediction processing to obtain a humidity prediction result; wherein the processing layer of the humidity prediction model is trained according to the first preset network model and the second preset network model, and the prediction layer of the humidity prediction model is trained according to the third preset network model; Determining control parameters of a data center humidification device according to the humidity prediction result and the real-time relative humidity data; wherein the data center humidification device is an ultrasonic humidification device; According to the control parameters, the data center humidification device is controlled to perform humidification.

2. The data center humidification device control method according to claim 1, characterized in that: Preprocessing the real-time relative humidity data to obtain preprocessed humidity data includes: Performing data cleaning processing on the real-time relative humidity data to obtain a first processing result; The first processing result is normalized to obtain pre-processed humidity data.

3. The data center humidification device control method according to claim 1, characterized in that: The pre-processed humidity data is input into the processing layer of the humidity prediction model for processing to obtain the processing result of the processing layer, including: Input the pre-processed humidity data to the first processing module of the processing layer of the humidity prediction model to effectively analyze and predict the periodicity and trend time series in the pre-processed humidity data to obtain the processing result of the first processing layer; The pre-processed humidity data is input to the second processing module of the processing layer of the humidity prediction model to effectively analyze and predict the nonlinear and non-stationary time series in the pre-processed humidity data to obtain the processing results of the second processing layer.

4. The data center humidification device control method according to claim 3, characterized in that: Inputting the processing result of the processing layer into the prediction layer of the humidity prediction model for humidity prediction processing to obtain a humidity prediction result, including: Obtaining a first weight of a processing result of the first processing layer and a second weight of a processing result of the second processing layer; The processing result of the first processing layer, the first weight, the processing result of the second processing layer and the second weight are input into the prediction layer of the humidity prediction model for weighted averaging to obtain a humidity prediction result.

5. The data center humidification device control method according to claim 1, characterized in that: Determining control parameters of a data center humidification device according to the humidity prediction result and the real-time relative humidity data includes: Determining a start time of the data center humidification device according to the humidity prediction result, the real-time relative humidity data and a preset standard humidity range; The start time and humidification power of the data center humidification device are determined according to the humidity prediction result, the real-time relative humidity data and the preset humidification stop humidity.

6. The data center humidification device control method according to claim 5, characterized in that: Determining the start time of the data center humidification device according to the humidity prediction result, the real-time relative humidity data and a preset standard humidity range, including: Determining humidity adjustment information according to the humidity prediction result, the real-time relative humidity data and a preset standard humidity range; The start time of the data center humidification device is determined according to the humidity adjustment information and a preset standard humidity range.

7. The data center humidification device control method according to claim 5, characterized in that: Determining the start time and humidification power of the data center humidification device according to the humidity prediction result, the real-time relative humidity data and the preset humidification stop humidity, including: Determining a total humidification amount according to the humidity prediction result, the real-time relative humidity data and a preset humidification stop humidity; The start time and humidification power of the data center humidification device are determined according to the total humidification amount.

8. A data center humidification device control device, characterized in that: include: An acquisition module is used to obtain real-time relative humidity data of preset points in each area of ​​the data center computer room; A processing module is used to preprocess the real-time relative humidity data to obtain preprocessed humidity data; input the preprocessed humidity data into the processing layer of the humidity prediction model for processing to obtain a processing result of the processing layer; input the processing result of the processing layer into the prediction layer of the humidity prediction model for humidity prediction processing to obtain a humidity prediction result; wherein the processing layer of the humidity prediction model is trained according to a first preset network model and a second preset network model, and the prediction layer of the humidity prediction model is trained according to a third preset network model; according to the humidity prediction result and the real-time relative humidity data, determine the control parameters of a data center humidification device; wherein the data center humidification device is an ultrasonic humidification device; according to the control parameters, control the data center humidification device to operate humidification.

9. A computing device, characterized in that include: A processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to any one of claims 1 to 7 is performed.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images