An environmental parameter control method, device, equipment and readable storage medium

Abstract

The specification discloses an environment parameter control method, device, equipment and readable storage medium, based on a current environment parameter and a load of a server in a current period, a predicted environment parameter corresponding to a data center in a next period is obtained through a prediction model, so that a control instruction is generated based on the predicted environment parameter in the next period, and the control instruction is sent to an environment parameter control device, so as to adjust the environment parameter of the data center based on the predicted environment parameter in the next period. It can be seen that by automatically and reasonably adjusting the environment parameter of the data center according to the predicted environment parameter in the next period output by the prediction model, the energy utilization efficiency can be improved, the purpose of saving energy can be achieved, and the security of private data can be improved.

Description

Technical Field

[0001] This specification relates to the field of computer technology, and in particular to an environmental parameter control method, apparatus, device, and readable storage medium. Background Technology

[0002] With increasing public concern about data privacy, data centers have received widespread attention. Data centers house a large number of servers for centralized data storage, processing, and distribution. In practice, frequent use of data center servers can lead to overheating. To prevent data center malfunctions due to overheating, server cooling is necessary. Since server cooling consumes a significant amount of energy, effectively managing server temperatures and conserving energy for cooling has become a pressing issue.

[0003] Based on this, this specification provides a method for controlling environmental parameters. Summary of the Invention

[0004] This specification provides an environmental parameter control method, apparatus, device, and readable storage medium to partially solve the aforementioned problems existing in the prior art.

[0005] The following technical solution is adopted in this specification:

[0006] This specification provides a method for controlling environmental parameters, the method comprising:

[0007] Obtain the current environmental parameters corresponding to the data center for the current time period, as well as the load of each server in the data center during the current time period;

[0008] The current environmental parameters and the load within the current time period are used as inputs to a pre-trained prediction model to obtain the predicted environmental parameters of the data center for the next time period of the current time period output by the prediction model.

[0009] Based on the predicted environmental parameters for the next time period, a control command is generated and sent to the environmental parameter control device, so that the environmental parameter control device adjusts the environmental parameters of the data center according to the predicted environmental parameters for the next time period.

[0010] This specification provides an environmental parameter control device, the device comprising:

[0011] The acquisition module is used to acquire the current environmental parameters of the data center for the current time period, as well as the load of each server in the data center during the current time period.

[0012] The prediction module is used to take the current environmental parameters and the load in the current time period as inputs, input them into a pre-trained prediction model, and obtain the predicted environmental parameters of the data center in the next time period of the current time period output by the prediction model.

[0013] The control module is used to generate control commands based on the predicted environmental parameters for the next time period, and send the control commands to the environmental parameter control device so that the environmental parameter control device adjusts the environmental parameters of the data center according to the predicted environmental parameters for the next time period.

[0014] This specification provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described environmental parameter control method.

[0015] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described environmental parameter control method.

[0016] The above-mentioned technical solutions adopted in this specification can achieve the following beneficial effects:

[0017] The environmental parameter control method provided in this specification uses a predictive model to obtain the predicted environmental parameters for the data center in the next time period based on the current environmental parameters and the server load during the current time period. Control commands are then generated based on these predicted environmental parameters and sent to the environmental parameter control device to adjust the data center's environmental parameters accordingly. Therefore, by automatically and reasonably adjusting the data center's environmental parameters based on the predicted environmental parameters for the next time period output by the predictive model, energy efficiency can be improved, achieving the goal of energy conservation. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this specification and form part of this specification, illustrate exemplary embodiments and their descriptions, serving to explain this specification and do not constitute an undue limitation thereof.

[0019] In the picture:

[0020] Figure 1 This is a flowchart illustrating an environmental parameter control method described in this specification.

[0021] Figure 2 This is a flowchart illustrating an environmental parameter control method described in this specification.

[0022] Figure 3 This is a schematic diagram of an environmental parameter control device provided in this specification;

[0023] Figure 4 The corresponding information provided in this specification Figure 1 A schematic diagram of an electronic device. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0025] Additionally, it should be noted that all actions involving the acquisition of signals, information, or data in this manual are performed in accordance with the relevant data protection regulations and policies of the locality and with authorization from the owner of the relevant device.

[0026] Data centers are facilities that centrally store, process, and distribute data, used to transmit, accelerate, display, compute, and store data information on the Internet infrastructure. Data centers integrate a large number of servers, resulting in high heat density. To prevent server failures due to overheating, it is necessary to control the environmental parameters of the data center to ensure servers operate normally in a suitable environment. Therefore, rationally controlling the environmental parameters of data centers and conserving the resources consumed by environmental parameter control equipment is of great significance. Data center environmental parameter control systems typically consist of multiple environmental parameter control devices. Due to the large scale and complex composition of these devices, manual control is not only complex to maintain but also results in significant energy waste. To save labor and achieve automated environmental parameter control, rule-based solutions exist. These solutions control data center environmental parameters and the energy consumption of environmental parameter control devices based on pre-set rules. For example, when server load is light, the power supply of environmental parameter control devices can be turned off or reduced to decrease cooling power and reduce energy consumption. The disadvantage of this solution is that setting the rules requires experience and expertise, and it is difficult to achieve optimal results in complex scenarios.

[0027] Based on this, this specification provides an environmental parameter control method that automatically and reasonably adjusts the environmental parameters of the data center according to the predicted environmental parameters for the next time period output by the prediction model, thereby achieving the goal of improving energy utilization efficiency and saving energy.

[0028] The technical solutions provided in the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0029] Figure 1This is a flowchart illustrating an environmental parameter control method provided in this specification.

[0030] S100: Obtain the current environmental parameters corresponding to the current time period of the data center, and the load of each server included in the data center during the current time period.

[0031] The environmental parameter control method provided in the embodiments of this specification can be executed by an electronic device such as a server used to determine environmental parameters. Furthermore, during the execution of this environmental parameter control method, the electronic device executing the training process of the prediction model and the electronic device executing the environmental parameter control method can be the same or different; this specification does not impose any limitations on this.

[0032] In the embodiments described in this specification, the environmental parameters of the data center include at least one of the outdoor temperature, outdoor humidity, indoor temperature, and indoor humidity of the data center. Optionally, the environmental parameters of the data center may also include other existing environmental parameters that affect the operating status of servers in the data center, such as solar radiation intensity, electromagnetic field intensity, noise decibels, vibration intensity, and electrostatic parameters.

[0033] Environmental parameters for a data center are acquired through sensors deployed both inside and outside the data center. Specifically, temperature and humidity sensors can be deployed outside the data center to collect outdoor temperature and humidity data. Inside the data center, temperature and humidity sensors can be deployed to collect indoor temperature and humidity data. Additionally, the data center's geographical location and local weather conditions can also be obtained and used as environmental parameters.

[0034] In this embodiment, environmental parameters are collected in real time at high frequency and stored in an environmental parameter database. To avoid fluctuations in environmental parameters and increased energy consumption caused by frequent adjustments, this embodiment adjusts parameters in preset time periods. Therefore, in this step, the current environmental parameters of the data center in the current time period are obtained, and in the subsequent step S102, the predicted environmental parameters of the data center in the next time period are predicted. The specific duration of the time period can be set according to actual needs, such as 15 minutes, 30 minutes, and 1 hour. Generally, the duration of the current time period is the same as the duration of the next time period. Of course, the duration of the time period can also be dynamically adjusted according to the specific application scenario, which is not limited in this specification.

[0035] In practical applications, humidity is used to characterize the dryness of an environment. At a given temperature, the less water vapor in a given volume of air, the drier the air; the more water vapor, the more humid the air. Creating a suitable humidity environment is essential for the operation of data centers. Tiny water droplets floating in the air can penetrate even the smallest areas and spaces of any component. If this situation persists, materials may deform, causing permanent damage and incurring high maintenance costs for data center operators. Even after removing the moisture, corrosive deposits can continue to cause damage.

[0036] When the relative humidity of the air is high, a water film may adhere to the server surface. This water film can easily create "conductive circuits" or arcing, severely reducing the reliability of the server's circuitry. With a constant relative humidity, the higher the temperature, the greater the impact on the equipment. This is because water vapor pressure increases with temperature, making it easier for water molecules to penetrate the material's interior.

[0037] Data center load refers to the workload borne by various hardware devices and software services within a data center. Data center load is typically dynamic, changing with variations in user volume, business volume, and data volume. The greater the workload undertaken by data center servers, the higher the heat generated, and the greater the need to adjust environmental parameters. Load is usually determined by measuring the utilization of system resources, such as CPU utilization, memory utilization, disk I / O, and network bandwidth.

[0038] In practical applications, to ensure high availability, high performance, and high efficiency of data centers, it is necessary to dynamically monitor and optimize the data center load, such as through measures like load balancing, resource scheduling, and capacity planning. These measures can help data centers maximize resource utilization and improve business reliability and performance. This manual does not specify the methods for monitoring server load in data centers.

[0039] S102: The current environmental parameters and the load in the current time period are used as inputs to a pre-trained prediction model to obtain the predicted environmental parameters of the data center in the next time period of the current time period output by the prediction model.

[0040] After obtaining the current environmental parameters and load within the current time period in step S100, data preprocessing operations can be performed on the current environmental parameters and load to clean and process the collected current environmental parameters and load, including data cleaning, data denoising, outlier handling, filling missing data, data normalization, etc., in order to improve the accuracy and objectivity of the input to the prediction model.

[0041] Furthermore, this specification employs a pre-trained prediction model, using current environmental parameters and load as inputs. The prediction model can extract features of the current environmental parameters and load from the current environmental parameters and server load, respectively, and then determine the predicted environmental parameters of the data center for the next time period based on these features. Since environmental parameters have a certain time lag, this embodiment can predict the environmental parameters for the next time period based on the current environmental parameters, enabling proactive regulation based on the changing trends of environmental parameters and reducing the energy consumption of the environmental parameter control equipment.

[0042] In this specification, predicted environmental parameters represent the predicted values ​​of the data center's environmental parameters for the next time period. The difference between the predicted environmental parameters and the current environmental parameters is used to characterize the trend and magnitude of change in the data center's environmental parameters for the next time period. For example, if the current environmental parameter is an indoor temperature of 22 degrees Celsius for the current time period, and the predicted environmental parameter is an indoor temperature of 22.5 degrees Celsius for the next time period, the difference between the predicted and current environmental parameters indicates that the indoor temperature of the data center will increase by 0.5 degrees Celsius in the next time period.

[0043] This manual does not limit the model structure of the prediction model. It can be one or more of the following: regression analysis, time series analysis, long short-term memory (LSTM) neural network, support vector machine, etc.

[0044] S104: Generate control instructions based on the predicted environmental parameters for the next time period, and send the control instructions to the environmental parameter control device so that the environmental parameter control device adjusts the environmental parameters of the data center according to the predicted environmental parameters for the next time period.

[0045] In this step, taking as an example that the executing entity of the environmental parameter control method provided in this specification is a control device different from the environmental parameter control device, this control device can determine the changing trend and amount of the data center environmental parameters based on the predicted environmental parameters of the data center in the next time period output by the prediction model, and the current environmental parameters in the current time period. Based on the changing trend and amount, it determines the adjustment trend and amount of the environmental parameter control room equipment to adjust the environmental parameters, and generates control commands accordingly. These control commands can carry the adjustment trend and amount of the environmental parameter control device's adjustment of the environmental parameters. The environmental parameter control device responds to the control commands, parses the adjustment trend and amount from the commands, and determines its own strategy for adjusting the environmental parameters based on these trends and amounts. For example, if the adjustment trend is cooling and the adjustment amount is 0.5 degrees Celsius, then the strategy of the environmental parameter control device could be to increase cooling power. Of course, in this specification, the executing entity of the environmental parameter control method can also be the environmental parameter control device itself. In this case, the control commands generated by the environmental parameter control device do not need to be sent again (or sent to a specific environmental parameter control device, such as a temperature control device), but the data center environmental parameters are adjusted directly based on the generated control commands.

[0046] Optionally, in practical applications, there may be situations where the difference between the predicted environmental parameters and the current environmental parameters is too small. In this case, to avoid frequent adjustments to environmental parameters that would waste resources, the following scheme can be implemented: Before generating control instructions based on the predicted environmental parameters for the next time period in step S104, the method further includes: determining that the difference between the predicted environmental parameters and the current environmental parameters is a first difference; determining whether the first difference is greater than a preset difference threshold; if so, then step S104 is executed; otherwise, no control instructions are generated. The purpose of this scheme is to avoid frequent adjustments to the data center's environmental parameters due to excessively small differences in environmental parameters, thereby preventing resource waste.

[0047] Optionally, the adjustment trend of the environmental parameters carried in the control command is generally determined directly based on the difference between the predicted environmental parameters and the current environmental parameters, but the adjustment amount of the environmental parameters is not necessarily directly based on the difference between the predicted environmental parameters and the current environmental parameters. Alternatively, the adjustment can be determined based on a control function. This control function outputs control parameters based on current and predicted environmental parameters. These control parameters characterize the adjustment amount of the data center's environmental parameters in the next time period. The adjustment amount characterized by this control parameter is usually less than the absolute value of the difference between the predicted and current environmental parameters. Due to the time lag of environmental parameters such as temperature and humidity, if the temperature is adjusted according to the difference between the predicted and current environmental parameters, the environmental parameters will change further after the data center's environmental parameters are adjusted to the current environmental parameters in the next time period. For example, if the indoor temperature is 22 degrees Celsius in the current time period and the predicted environmental parameter is 22.5 degrees Celsius in the next time period, and the adjustment amount of the environmental parameter control device is 0.5 degrees Celsius, the indoor temperature will drop by 0.5 degrees Celsius in the next time period and reach 22 degrees Celsius. However, since the adjustment of the cooling power of the environmental control device will not cause a drastic change in temperature in a short period of time, even if the cooling power is adjusted immediately after reaching 22 degrees Celsius, the indoor temperature will be further reduced, resulting in wasted resources.

[0048] Alternatively, the external natural environment can be fully utilized to control data center environmental parameters. Environmental parameter control equipment can control the ventilation level inside the data center, thereby controlling changes in the data center's environmental parameters by utilizing the outdoor natural environment. For example, when the outdoor temperature is much lower than the indoor temperature, the compressor of the cooling system can be turned off to reduce energy consumption, and the ventilation level of the data center can be increased by automatically opening windows, thereby cooling the indoor environment of the data center.

[0049] The environmental parameter control method provided in this specification uses a prediction model to obtain the predicted environmental parameters of the data center for the next time period based on the current environmental parameters and the server load during the current time period. Then, control commands are generated based on the predicted environmental parameters of the next time period and sent to the environmental parameter control device so as to adjust the environmental parameters of the data center based on the predicted environmental parameters of the next time period.

[0050] It is evident that by automatically and reasonably adjusting the environmental parameters of the data center based on the predicted environmental parameters for the next time period output by the prediction model, energy utilization efficiency can be improved, thereby achieving the goal of energy conservation.

[0051] In one optional embodiment of this specification, Figure 1In step S104, since the current environmental parameters of the data center may not be the optimal parameters for the normal operation of the servers within the data center, adjusting the data center's environmental parameters solely based on the predicted environmental parameters for the next time period may not meet the server's needs. The parameters used to generate control commands, in addition to the predicted environmental parameters for the next time period output by the prediction model, can also incorporate target environmental parameters. This makes the adjustment of the data center's environmental parameters by the environmental parameter control equipment more reasonable and in line with the data center's needs. Figure 2 As shown, the specific solution is as follows:

[0052] S200: Obtain target environment parameters.

[0053] In practical applications, the current environmental parameters may not be the optimal environmental parameters for the server to work properly. That is, the environmental parameter control equipment needs to adjust the environmental parameters based on the original current environmental parameters. Even if the difference between the predicted environmental parameters for the next period and the current environmental parameters is small, the data center environmental parameters still need to be adjusted because there is still a gap between the current or predicted environmental parameters and the optimal environmental parameters for the server to work properly. This is to make the data center environmental parameters reach the optimal environmental parameters for the server to work properly.

[0054] Therefore, this step involves obtaining the target environment parameters, which are the optimal environmental parameters for the normal operation of the server in the data center. These target environment parameters can be fixed values ​​set manually, or they can be dynamically changed values ​​based on the actual situation of the server. This manual does not limit this.

[0055] S202: Generate control instructions based on the target environmental parameters, the current environmental parameters, and the predicted environmental parameters for the next time period.

[0056] Specifically, the target environmental parameters are the optimal environmental parameters for the server to operate normally, the current environmental parameters are the environmental parameters of the data center in the current time period, and the predicted environmental parameters are the environmental parameters of the data center in the next time period output by the prediction model. To generate control instructions based on these three environmental parameters, the following approach can be taken: determine the difference between the target environmental parameters and the current environmental parameters as the first difference, and determine the difference between the current environmental parameters and the predicted environmental parameters as the second difference; determine the adjustment trend and adjustment amount of the environmental parameters based on the first and second differences; and generate control instructions based on the adjustment trend and adjustment amount of the environmental parameters.

[0057] For example, if the current environmental parameter is an indoor temperature of 22 degrees Celsius, the predicted environmental parameter is an indoor temperature of 22.5 degrees Celsius, and the target environmental parameter is an indoor temperature of 21 degrees Celsius, then the first difference can be determined as a decrease in indoor temperature of 0.5 degrees Celsius, and the second difference as a decrease in indoor temperature of 1 degree Celsius. Therefore, the adjustment trend of the environmental parameter can be determined as a decrease in temperature, with an adjustment amount of 1.5 degrees Celsius. Based on this adjustment trend and adjustment amount, a control command is generated. The environmental parameter control equipment responds to the control command by increasing the cooling power to achieve a decrease in indoor temperature.

[0058] In S202 above, control parameters can be determined through a pre-optimized control function, thereby generating control commands based on the control parameters. The specific scheme is as follows:

[0059] First, the difference between the target environmental parameters and the current environmental parameters is determined as the first difference.

[0060] Similar to step S202 above, it will not be repeated here.

[0061] Secondly, the difference between the current environmental parameters and the predicted environmental parameters for the next time period is determined as a second difference.

[0062] Similar to step S202 above, it will not be repeated here.

[0063] Then, the first difference and the second difference are used as inputs to the pre-optimized control function to obtain the control parameters output by the control function.

[0064] Specifically, environmental parameters have a certain time lag. If the temperature is adjusted according to the difference between the predicted environmental parameters and the current environmental parameters, the environmental parameters will change further after the data center's environmental parameters are adjusted to the current environmental parameters in the next time period. In order to further save the resources consumed by the environmental parameter control equipment, the control parameters can be determined by a pre-optimized control function. The control parameters represent the adjustment trend and adjustment amount of the data center's environmental parameters. The adjustment amount represented by the control parameters can be less than the adjustment amount of the environmental parameters determined based on the sum of the first difference and the second difference.

[0065] Starting with the current environmental parameters, the data center's environmental parameters are adjusted according to the adjustment amount represented by the control parameter. Although it's impossible to adjust the data center's environmental parameters to the target environmental parameters in the next time period, the trend of change in the data center's environmental parameters is towards the target environmental parameters, while saving resource consumption of the environmental parameter control equipment. Furthermore, in subsequent time periods, after multiple rounds of environmental parameter adjustments, the data center's environmental parameters can maintain a dynamic balance before and after the target environmental parameters, effectively reducing the resource consumption of the environmental parameter control equipment.

[0066] Finally, control commands are generated based on the control parameters.

[0067] Alternatively, the control function used in the above scheme can be obtained through iterative optimization using the following scheme:

[0068] Step 1: Obtain historical environmental parameters of the data center in advance for multiple historical periods.

[0069] In this step, the historical environmental parameters for each historical period can be arranged sequentially from beginning to end according to the start time of that historical period, resulting in a sequence of historical environmental parameters. This allows for iterative optimization of the control function using each historical environmental parameter in subsequent steps.

[0070] The durations corresponding to different historical periods can be the same or different; this manual does not impose any restrictions on this. The specific types of parameters included in the historical environment parameters are similar to those in step S100, and will not be described again here.

[0071] Step 2: Initialize the first control weight, the second control weight, and the third control weight of the control function.

[0072] Step 3: For each historical period, determine the difference between the historical environmental parameters of the historical period and the historical environmental parameters of the previous historical period as the candidate difference for the historical period, and use the first control weight to weight the candidate differences for the historical period to obtain the first weighted result.

[0073] The candidate differences corresponding to this historical period are used to characterize the adjustment trend and magnitude of the data center's historical environmental parameters from the previous historical period to this historical period. The larger the adjustment magnitude, the more drastic the change in historical environmental parameters. Conversely, the smaller the adjustment magnitude, the more gradual the change in historical environmental parameters.

[0074] The first control weight characterizes the linear relationship between the output of the control function and the candidate differences. A larger first control weight indicates a more sensitive response of the control function to candidate differences, reflected in a larger absolute value of the adjustment amount. Conversely, a smaller first control weight indicates a less sensitive response of the control function to candidate differences. The first weight is used to weight the candidate differences corresponding to the historical period, resulting in a first weighted result, which is then used to determine the environmental parameters to be optimized for the next historical period corresponding to the control function's output for that historical period.

[0075] Step 4: Use the second control weight to weight each candidate difference from the first historical period to the current historical period to obtain the second weighted result.

[0076] Because the adjustment of environmental parameters has a time lag, if the environmental parameters to be optimized output by the control function are determined solely based on the first weighted result, these parameters will change after reaching the environmental parameters of the next historical period due to objective natural factors such as heat dissipation and ventilation. Essentially, the environmental parameters to be optimized, determined solely based on the first weighted result, will fluctuate around the historical environmental parameters of the next historical period, meaning they cannot be stably maintained at the historical environmental parameters of the next historical period. Therefore, a second control weight is introduced to characterize the linear relationship between the output of the control function and the integral of the candidate differences. Considering that the candidate differences corresponding to each historical period are discrete data, the sum of all candidate differences from the first historical period to this historical period is used as the integral of the candidate differences. The second control weight is then used to weight the sum of all candidate differences from the first historical period to this historical period, resulting in a second weighted result. The second weighted result considers the control effect of the candidate differences of each historical period on the environmental parameters to be optimized output by the control function. The second weighted result is not only related to the candidate differences corresponding to this historical period but also to the duration of the candidate differences. As long as the candidate differences exist... The second weighted result will be continuously accumulated until the candidate difference is zero, thereby reducing the possibility that the environmental parameters to be optimized will fluctuate around the historical environmental parameters in the next historical period.

[0077] Step 5: Determine the changing trend of the environmental parameters corresponding to the historical period based on the candidate differences and the duration of the historical period, and use the third control weight to weight the changing trend of the environmental parameters corresponding to the historical period to obtain the third weighted result.

[0078] Furthermore, since the control of environmental parameters is time-varying, that is, the changes in candidate differences have a trend, the trend of environmental parameter changes in the corresponding historical period is determined based on the candidate differences and the duration of the corresponding historical period. The third control weight is then used to weight this trend, thereby making the environmental parameters to be optimized in the next historical period output by the control function more accurate.

[0079] Step 6: Based on the first weighted result, the second weighted result, and the third weighted result, determine the environmental parameters to be optimized for the next historical period corresponding to this historical period.

[0080] Generally, the environmental parameters to be optimized for the next historical period are obtained by summing the first weighted result, the second weighted result, and the third weighted result.

[0081] Step 7: Taking the minimization of the difference between the historical environmental parameters of the next historical period and the environmental parameters to be optimized corresponding to the next historical period as the optimization objective, adjust the first control weight, the second control weight, and the third control weight of the control function until the preset conditions are met.

[0082] The environmental parameters of the next historical period are used as the desired environmental parameters, i.e., the adjustment target. When adjusting the first, second, and third control weights of the control function, any existing weight adjustment method can be used, such as trial and error or a self-tuning algorithm; this specification does not limit this approach.

[0083] The preset conditions can be that the difference between the historical environmental parameters of the next historical period and the environmental parameters to be optimized corresponding to the next historical period is less than a preset difference threshold, or the number of iterations is greater than a preset number threshold. This specification does not limit this.

[0084] Step 8: Determine the optimized control function based on the first, second, and third control weights after optimization.

[0085] In one optional embodiment of this specification, Figure 1 The prediction model used to predict the environmental parameters for the next time period in step S202 can be pre-trained iteratively based on the following scheme, the specific steps of which are as follows:

[0086] First, the historical environmental parameters of the data center in multiple historical periods are obtained in advance, as well as the historical load of each server in the data center in each historical period.

[0087] The durations corresponding to different historical periods can be the same or different; this manual does not impose any restrictions on this. The specific types of parameters included in the historical environment parameters are similar to those in step S100, and will not be described again here.

[0088] Secondly, for each historical period, the historical environment parameters and historical load of that historical period are used as training samples, and the historical environment parameters of the next historical period are used as the annotations of the training samples.

[0089] In this specification, the purpose of the prediction model is to predict the environmental parameters for the next time period based on the environmental parameters and server load of the previous time period. Therefore, the input to the prediction model during training is the historical environmental parameters and historical load of the current historical time period, and the output is the predicted environmental parameters for the next historical time period. Thus, the training samples are the historical environmental parameters and historical load of the current historical time period, labeled as the historical environmental parameters for the next historical time period. During training, the prediction model is trained with the objective of minimizing the difference between the labeled training samples and the predicted environmental parameters for the next historical time period output by the prediction model.

[0090] Then, based on the training samples and their annotations, a prediction model to be trained is trained.

[0091] Optionally, after the prediction model is trained and put into use, iterative optimization can be performed based on the environmental parameters and load of the data center during each time period stored during the model's use, to further improve the accuracy of the prediction model. The specific solution is as follows:

[0092] First, monitor the real-time environmental parameters of the data center over multiple time periods, as well as the real-time load over those multiple time periods.

[0093] Secondly, the real-time environmental parameters and the real-time load in each time period are used as new training samples, and the real-time environmental parameters of the next time period corresponding to each time period are used as labels for the new training samples.

[0094] Then, based on the newly added training samples and their representations, the model parameters of the trained prediction model are optimized.

[0095] In one optional embodiment of this specification, adjusting the environmental parameters of the data center to maintain suitable environmental parameters for normal server operation requires the use of resources. These resources can be any resources that can be used to adjust environmental parameters, such as electrical energy, natural gas resources, water resources, and wind power resources. Figure 1 The predicted environmental parameters for the next time period obtained in step S104 can be used to determine the amount of resources required for the environmental parameter control equipment to adjust the environmental parameters in the next time period. Therefore, the resource provider can provide resources to the environmental parameter control equipment based on the required resource amount, achieving the goal of rational resource allocation. The specific scheme is as follows:

[0096] Step 1: Determine the first amount of resources required by the environmental parameter control equipment based on the predicted environmental parameters for the next time period.

[0097] In practical applications, environmental parameter control equipment requires resources to adjust data center environmental parameters. Rational allocation of these resources can improve data center resource utilization efficiency, reduce resource waste, lower carbon emissions, and save operating costs. Therefore, in this step, a first resource quantity is determined based on the predicted environmental parameters. Specifically, the difference between the predicted and current environmental parameters can be determined, and the unit resource quantity consumed by the environmental parameter control equipment to adjust a unit of environmental parameter in the data center can be obtained. Based on the difference between the predicted and current environmental parameters and the unit resource quantity, the first resource quantity required for the environmental parameter control equipment to adjust the environmental parameters is determined.

[0098] Step 2: Determine the size of the data center based on the number of servers it contains.

[0099] Furthermore, since a data center contains multiple servers, each deployed in different locations, the more servers there are, the more heat they generate. In order to effectively control environmental parameters, the environmental parameter control equipment requires more resources. Therefore, when determining the actual resources required for the environmental parameter control equipment, we must consider not only the predicted environmental parameters but also the scale of the data center, in order to fully utilize resources and accurately control environmental parameters.

[0100] Optionally, for large data centers, multiple environmental parameter control devices can be deployed within the data center. For each environmental control device, the number of servers contained in the data center covered by the environmental control device is determined based on the device's location within the data center. The size of the data center corresponding to the environmental control device is then determined based on the number of servers covered by the environmental control device. In subsequent steps, the second resource quantity required by the environmental parameter control device is determined based on the first resource quantity and the size of the data center corresponding to the environmental control device.

[0101] Step 3: Based on the first resource quantity and the scale of the data center, determine the second resource quantity required by the environmental parameter control device.

[0102] Step 4: Generate a resource acquisition request based on the second resource quantity, and send the resource acquisition request to the resource provider so that the resource provider can provide resources to the environmental parameter control device based on the second resource quantity.

[0103] Figure 3 This specification provides a schematic diagram of an environmental parameter control device, which specifically includes:

[0104] The acquisition module 300 is used to acquire the current environmental parameters of the data center for the current time period, as well as the load of each server in the data center during the current time period.

[0105] Prediction module 302 is used to input the current environmental parameters of the current time period and the load within the current time period into a pre-trained prediction model to obtain the predicted environmental parameters of the data center for the next time period of the current time period output by the prediction model.

[0106] The control module 304 is used to generate control instructions based on the predicted environmental parameters for the next time period, and send the control instructions to the environmental parameter control device so that the environmental parameter control device adjusts the environmental parameters of the data center according to the predicted environmental parameters for the next time period.

[0107] Optionally, the control module 304 is specifically used to: acquire target environmental parameters; and generate control commands based on the target environmental parameters, the current environmental parameters, and the predicted environmental parameters for the next time period.

[0108] Optionally, the control module 304 is specifically configured to: determine the difference between the target environmental parameter and the current environmental parameter as a first difference; determine the difference between the current environmental parameter and the predicted environmental parameter for the next time period as a second difference; input the first difference and the second difference as inputs into a pre-optimized control function to obtain control parameters output by the control function; and generate control commands based on the control parameters.

[0109] Optionally, the device further includes:

[0110] Optimization module 306 is specifically used to: pre-acquire historical environmental parameters of the data center within multiple historical time periods; initialize the first control weight, second control weight, and third control weight of the control function; sequentially, for each historical time period, determine the difference between the historical environmental parameters of that historical time period and the historical environmental parameters of the previous historical time period as candidate differences corresponding to that historical time period; use the first control weight to weight the candidate differences corresponding to that historical time period to obtain a first weighted result; use the second control weight to weight each candidate difference from the first historical time period to that historical time period to obtain a second weighted result; and determine the corresponding historical time period based on the candidate differences and the duration of that historical time period. The changing trend of environmental parameters is analyzed, and the changing trend of environmental parameters corresponding to the historical period is weighted using the third control weight to obtain a third weighted result. Based on the first weighted result, the second weighted result, and the third weighted result, the environmental parameters to be optimized for the next historical period are determined. With minimizing the difference between the historical environmental parameters of the next historical period and the environmental parameters to be optimized for the next historical period as the optimization objective, the first control weight, the second control weight, and the third control weight of the control function are adjusted until a preset condition is met. Based on the optimized first control weight, the second control weight, and the third control weight, the optimized control function is determined.

[0111] Optionally, the device further includes:

[0112] The training module 308 is specifically used to pre-acquire historical environmental parameters of the data center in multiple historical time periods, as well as the historical load of each server in the data center in each historical time period; for each historical time period, the historical environmental parameters and historical load of that historical time period are used as training samples, and the historical environmental parameters of the next historical time period are used as the annotations of the training samples; and the prediction model to be trained is trained based on the training samples and the annotations of the training samples.

[0113] Optionally, the device further includes:

[0114] The resource determination module 310 is specifically used to determine the first amount of resources required by the environmental parameter control device based on the predicted environmental parameters for the next time period; determine the size of the data center based on the number of servers contained in the data center; determine the second amount of resources required by the environmental parameter control device based on the first amount of resources and the size of the data center; generate a resource acquisition request based on the second amount of resources, and send the resource acquisition request to the resource provider, so that the resource provider provides resources to the environmental parameter control device based on the second amount of resources.

[0115] Optionally, the environmental parameters of the data center include at least one of the outdoor temperature, outdoor humidity, indoor temperature, and indoor humidity.

[0116] This specification also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 The environmental parameter control method is shown.

[0117] This instruction manual also provides Figure 4 The diagram shows a schematic structural representation of the electronic device. Figure 4 At the hardware level, the electronic device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for the business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it to achieve the above-mentioned functions. Figure 1 The environmental parameter control method is shown. Of course, in addition to the software implementation method, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0118] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0119] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0120] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0121] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0122] Those skilled in the art will understand that embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0123] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0124] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0125] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0126] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0127] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0128] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0129] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0130] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0131] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0132] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0133] The above description is merely an embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for controlling environmental parameters, the method comprising: Obtain the current environmental parameters corresponding to the data center for the current time period, as well as the load of each server in the data center during the current time period; The current environmental parameters and the load within the current time period are used as inputs to a pre-trained prediction model to obtain the predicted environmental parameters of the data center for the next time period of the current time period output by the prediction model. Based on the predicted environmental parameters for the next time period, a control command is generated and sent to the environmental parameter control device, so that the environmental parameter control device adjusts the environmental parameters of the data center according to the predicted environmental parameters for the next time period. Specifically, the generation of control commands based on the predicted environmental parameters for the next time period includes: Obtain the target environment parameters; the target environment parameters are the optimal environment parameters for the normal operation of the servers in the data center; Control commands are generated based on the target environmental parameters, the current environmental parameters, and the predicted environmental parameters for the next time period; Specifically, generating control instructions based on the target environmental parameters, the current environmental parameters, and the predicted environmental parameters for the next time period includes: The difference between the target environmental parameter and the current environmental parameter is defined as the first difference; The difference between the current environmental parameters and the predicted environmental parameters for the next time period is defined as the second difference; The first difference and the second difference are used as inputs to a pre-optimized control function to obtain the control parameters output by the control function. Control commands are generated based on the control parameters.

2. The method as described in claim 1, wherein pre-optimization of the control function specifically includes: Pre-acquire historical environmental parameters of the data center over multiple historical periods; Initialize the first control weight, the second control weight, and the third control weight of the control function; For each historical period, the difference between the historical environmental parameters of that historical period and the historical environmental parameters of the previous historical period is determined as the candidate difference for that historical period. The first control weight is used to weight the candidate differences for that historical period to obtain the first weighted result. The second control weight is used to weight each candidate difference from the first historical period to that historical period to obtain the second weighted result; The changing trend of the environmental parameters corresponding to the historical period is determined based on the candidate differences and the duration of the historical period, and the changing trend of the environmental parameters corresponding to the historical period is weighted by the third control weight to obtain the third weighted result. Based on the first weighted result, the second weighted result, and the third weighted result, determine the environmental parameters to be optimized for the next historical period corresponding to the current historical period. The optimization objective is to minimize the difference between the historical environmental parameters of the next historical period and the environmental parameters to be optimized corresponding to the next historical period. The first control weight, the second control weight, and the third control weight of the control function are adjusted until the preset conditions are met. Based on the optimized first control weight, second control weight, and third control weight, the optimized control function is determined.

3. The method as described in claim 1, wherein pre-training the prediction model specifically includes: Historical environmental parameters of the data center in multiple historical periods are obtained in advance, as well as the historical load of each server in the data center in each historical period; For each historical period, the historical environment parameters and historical load of that historical period are used as training samples, and the historical environment parameters of the next historical period are used as the annotations of the training samples. The prediction model to be trained is trained based on the training samples and their annotations.

4. The method of claim 1, further comprising: Based on the predicted environmental parameters for the next time period, determine the first amount of resources required by the environmental parameter control equipment; The size of the data center is determined based on the number of servers it contains; Based on the first resource quantity and the scale of the data center, determine the second resource quantity required by the environmental parameter control device; A resource acquisition request is generated based on the second resource quantity, and the resource acquisition request is sent to the resource provider so that the resource provider provides resources to the environmental parameter control device according to the second resource quantity.

5. The method as described in claim 1, wherein the environmental parameters of the data center include at least one of the outdoor temperature, outdoor humidity, indoor temperature, and indoor humidity of the data center.

6. An environmental parameter control device, the device comprising: The acquisition module is used to acquire the current environmental parameters of the data center for the current time period, as well as the load of each server in the data center during the current time period. The prediction module is used to take the current environmental parameters and the load in the current time period as inputs, input them into a pre-trained prediction model, and obtain the predicted environmental parameters of the data center in the next time period of the current time period output by the prediction model. The control module is used to generate control commands based on the predicted environmental parameters for the next time period, and send the control commands to the environmental parameter control device so that the environmental parameter control device adjusts the environmental parameters of the data center according to the predicted environmental parameters for the next time period. Specifically, the control module is used to: acquire target environmental parameters; generate control instructions based on the target environmental parameters, the current environmental parameters, and the predicted environmental parameters for the next time period; the target environmental parameters are the optimal environmental parameters for the normal operation of the servers in the data center; The control module is further configured to: determine the difference between the target environmental parameter and the current environmental parameter as a first difference; determine the difference between the current environmental parameter and the predicted environmental parameter for the next time period as a second difference; input the first difference and the second difference as inputs into a pre-optimized control function to obtain control parameters output by the control function; and generate control commands based on the control parameters.

7. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any one of claims 1 to 5.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in any one of claims 1 to 5.

Images