Method and equipment for predicting and adjusting temperature of machine room and storage medium

Abstract

The invention provides a method and equipment for predicting and adjusting the temperature of a machine room and a storage medium, and relates to the field of temperature control. The method comprises the following steps: acquiring a time node of which the temperature of a machine room needs to be predicted and adjusted and historical influence data corresponding to the time node; inputting the historical influence data into the target temperature prediction model to obtain a predicted temperature corresponding to the time node in the current period; the target temperature prediction model is a time sequence-based prediction model obtained according to target training data in multiple groups of training data, and different groups of training data correspond to different time period numbers; the predicted temperature is compared with a machine room temperature threshold value to obtain a temperature difference value, and the set temperature of an air conditioner in the machine room is adjusted at the time node according to the temperature difference value, so that the indoor temperature of the machine room is smaller than the machine room temperature threshold value. According to the method, the indoor temperature of the machine room is predicted through the temperature prediction model, the air conditioner is adjusted, and the purpose of improving the energy utilization efficiency is achieved.

Description

Technical Field

[0001] This application relates to the field of temperature control, and particularly to a method, device, and storage medium for predicting and adjusting the temperature of a computer room. Background Art

[0002] With the development of network technology and the continuous increase in the number of users, the power consumption of communication equipment operation has become the main operating cost that is constantly rising. Among them, the cost of air conditioning power consumption occupies a relatively large proportion. Therefore, how to reduce the expenditure of air conditioning power consumption has become an important issue that communication enterprises urgently need to study. With the network speed increase and fee reduction and the large-scale construction of communication networks, the power consumption of communication computer room base stations continues to increase. With the continuous sharp increase in data traffic demand, the network load has increased significantly, and problems in aspects such as power consumption of computer room base stations, equipment heat dissipation, and energy-saving management need to be solved urgently.

[0003] At present, the management state of computer room air conditioners is still open management, with fixed settings of temperature, air volume, etc., resulting in excessive cooling and energy consumption waste. The maintenance of air conditioners depends on the operation status alarms of air conditioners, and effective operation and maintenance of air conditioners cannot be carried out. Summary of the Invention

[0004] This application provides a method, device, and storage medium for predicting and adjusting the temperature of a computer room to solve the technical problem of backward means of controlling the temperature of a computer room in the prior art, resulting in unnecessary energy waste.

[0005] In a first aspect, this application provides a method for predicting and adjusting the temperature of a computer room, including:

[0006] Obtaining a time node that needs to predict and adjust the temperature of the computer room and historical influence data corresponding to the time node; the historical influence data includes multiple indoor temperature influence factors at the same time node in N historical periods;

[0007] Inputting the historical influence data into a target temperature prediction model to obtain a predicted temperature corresponding to the time node in the current period; the target temperature prediction model is a time series-based prediction model obtained according to target training data in multiple groups of training data. The number of time periods corresponding to different groups of training data is different, and the number of target time periods of the target training data is N, where N is a natural number;

[0008] Comparing the predicted temperature with a computer room temperature threshold to obtain a temperature difference, and adjusting the set temperature of the air conditioner in the computer room according to the temperature difference at the time node, so that the indoor temperature of the computer room is less than the computer room temperature threshold.

[0009] In a possible design, the target temperature prediction model is trained in the following manner:

[0010] Obtain multiple training data sets, each training data set includes multiple groups of training data, and each group of training data includes multiple indoor temperature influencing factors at the same time node in multiple historical periods and the actual historical temperature of the target node. Among them, the number of time periods corresponding to adjacent groups of training data differs by 1, the time periods corresponding to the target nodes in the same training data set are the same, and the target nodes in different training data sets correspond to different time periods;

[0011] Based on each group of training data, train and obtain a candidate temperature prediction model based on time series, and based on the actual historical temperature and the predicted temperature of the target node output by the candidate temperature prediction model, obtain an error data set for each candidate temperature prediction model. The error data set includes multiple difference data, and the difference data is the difference between the actual historical temperature and the prediction result;

[0012] Obtain the target temperature prediction model according to the error data set of each candidate temperature prediction model.

[0013] In one possible design, the obtaining the target temperature prediction model according to the error data set of each candidate temperature prediction model includes:

[0014] For each training data set, perform mean processing on the difference data in each error data set to obtain an error mean value, compare the multiple error mean values corresponding to multiple groups of training data with a preset error threshold, and screen out the maximum number of time periods to the minimum number of time periods less than the preset error threshold; among them, different training data sets correspond to their own preset error thresholds;

[0015] For the maximum number of time periods to the minimum number of time periods corresponding to each training data set, determine the target temperature prediction model among the candidate temperature prediction models.

[0016] In one possible design, the determining the target temperature prediction model among the candidate temperature prediction models for the maximum number of time periods to the minimum number of time periods corresponding to each training data set includes:

[0017] Based on the maximum number of time periods to the minimum number of time periods, obtain multiple error mean values corresponding to each time period number among the different time period numbers;

[0018] According to the error mean value corresponding to each time period number, take the time period number with the error mean value less than the preset error mean value as the target time period number, and the corresponding candidate temperature prediction model is the target temperature prediction model.

[0019] In a possible design, adjusting the set temperature of the air conditioner in the computer room according to the temperature difference at the time node includes:

[0020] Determine whether the predicted temperature is greater than the computer room temperature threshold;

[0021] If the predicted temperature is greater than the computer room temperature threshold, reduce the value of the set temperature of the air conditioner by the temperature difference at the time node;

[0022] If the predicted temperature is less than or equal to the computer room temperature threshold, turn off the air conditioner at the time node.

[0023] In a possible design, the method further includes:

[0024] Obtain the location information of the computer room;

[0025] Match the location information with a preset warning threshold database to obtain the temperature warning threshold corresponding to the location information; the warning threshold database stores temperature warning thresholds corresponding to multiple regions;

[0026] Calculate the computer room temperature threshold according to the temperature warning threshold and a preset energy-saving difference.

[0027] In a possible design, before adjusting the set temperature of the air conditioner in the computer room according to the temperature difference at the time node, the method further includes:

[0028] Obtain the real-time temperature data of the computer room at the time node;

[0029] Determine whether the real-time temperature data is greater than the temperature warning threshold;

[0030] If the real-time temperature data is greater than the temperature warning threshold, perform an alarm feedback according to the real-time temperature data and adjust the set temperature of the air conditioner to the minimum;

[0031] If the real-time temperature data is less than or equal to the temperature warning threshold, perform an error analysis on the temperature prediction model according to the real-time temperature data, and adjust the set temperature of the air conditioner in the computer room according to the error analysis result.

[0032] In a possible design, the performing an error analysis on the temperature prediction model according to the real-time temperature data, and adjusting the set temperature of the air conditioner in the computer room according to the error analysis result includes:

[0033] Compare the real-time temperature data with the predicted temperature to obtain difference data;

[0034] Determine whether the difference data is greater than a preset difference;

[0035] If the difference data is greater than the preset difference value, perform model anomaly feedback according to the difference data, and obtain a temperature difference by comparing the real-time temperature data with the computer room temperature threshold, and adjust the set temperature of the air conditioner in the computer room according to the temperature difference;

[0036] If the difference data is less than or equal to the preset difference value, adjust the set temperature of the air conditioner in the computer room according to the temperature difference.

[0037] In a second aspect, the present application provides a device for predicting and adjusting the temperature of a computer room, including:

[0038] An acquisition module, configured to acquire a time node for predicting and adjusting the temperature of the computer room and historical influence data corresponding to the time node; the historical influence data includes multiple indoor temperature influence factors at the same time node in N historical periods;

[0039] A prediction module, configured to input the historical influence data into a target temperature prediction model to obtain a predicted temperature corresponding to the time node in the current period; the target temperature prediction model is a time series-based prediction model obtained according to target training data in multiple groups of training data, the number of time periods corresponding to different groups of training data is different, the number of target time periods of the target training data is the N, and the N is a natural number;

[0040] An adjustment module, configured to compare the predicted temperature with the computer room temperature threshold to obtain a temperature difference, and adjust the set temperature of the air conditioner in the computer room according to the temperature difference at the time node, so that the indoor temperature of the computer room is less than the computer room temperature threshold.

[0041] In a possible design, the prediction module is specifically configured to:

[0042] Acquire multiple training data sets, each training data set includes multiple groups of training data, each group of training data includes multiple indoor temperature influence factors at the same time node in multiple historical periods and the actual historical temperature of the target node, wherein the number of time periods corresponding to adjacent groups of training data differs by 1, the number of time periods corresponding to the target node in the same training data set is the same, and the target nodes corresponding to different training data sets correspond to different time periods;

[0043] Based on each group of training data, train and obtain a candidate temperature prediction model based on time series, and based on the actual historical temperature and the predicted temperature of the target node output by the candidate temperature prediction model, obtain an error data set of each candidate temperature prediction model, and the error data set includes multiple difference data, and the difference data is the difference between the actual historical temperature and the prediction result;

[0044] Obtain the target temperature prediction model according to the error data set of each candidate temperature prediction model.

[0045] In a possible design, the prediction module is specifically configured to:

[0046] For each training data set, perform mean processing on the difference data in each error data set to obtain an error mean value, compare the multiple error mean values corresponding to multiple groups of training data with a preset error threshold, and screen out the maximum number of time periods to the minimum number of time periods less than the preset error threshold; wherein, different training data sets correspond to their respective preset error thresholds;

[0047] For the maximum number of time periods to the minimum number of time periods corresponding to each training data set, determine the target temperature prediction model among the candidate temperature prediction models.

[0048] In a possible design, the prediction module is specifically configured to:

[0049] Based on the maximum number of time periods to the minimum number of time periods, obtain multiple error mean values corresponding to each time period number among the different time period numbers;

[0050] According to the error mean value corresponding to each time period number, use the time period number with an error mean value less than the preset error mean value as the target time period number, and the corresponding candidate temperature prediction model as the target temperature prediction model.

[0051] In a possible design, the adjustment module is specifically configured to:

[0052] Judge whether the predicted temperature is greater than the machine room temperature threshold;

[0053] If the predicted temperature is greater than the machine room temperature threshold, reduce the numerical value of the set temperature of the air conditioner by the temperature difference at the time node;

[0054] If the predicted temperature is less than or equal to the machine room temperature threshold, turn off the air conditioner at the time node.

[0055] In a possible design, the adjustment module is further configured to:

[0056] Obtain the location information of the machine room;

[0057] Match the location information with a preset alarm threshold database to obtain the temperature alarm threshold corresponding to the location information; the alarm threshold database stores temperature alarm thresholds corresponding to multiple regions;

[0058] Calculate the computer room temperature threshold based on the temperature warning threshold and the preset energy-saving difference value.

[0059] In a possible design, the adjustment module is further configured to:

[0060] Obtain the real-time temperature data of the computer room at the time node;

[0061] Determine whether the real-time temperature data is greater than the temperature warning threshold;

[0062] If the real-time temperature data is greater than the temperature warning threshold, perform an alarm feedback based on the real-time temperature data, and adjust the set temperature of the air conditioner to the minimum;

[0063] If the real-time temperature data is less than or equal to the temperature warning threshold, perform an error analysis on the temperature prediction model based on the real-time temperature data, and adjust the set temperature of the air conditioner in the computer room according to the error analysis result.

[0064] In a possible design, the adjustment module is specifically configured to:

[0065] Compare the real-time temperature data with the predicted temperature to obtain difference data;

[0066] Determine whether the difference data is greater than the preset difference value;

[0067] If the difference data is greater than the preset difference value, perform a model anomaly feedback based on the difference data, and obtain a temperature difference by comparing the real-time temperature data with the computer room temperature threshold, and adjust the set temperature of the air conditioner in the computer room according to the temperature difference;

[0068] If the difference data is less than or equal to the preset difference value, adjust the set temperature of the air conditioner in the computer room according to the temperature difference.

[0069] In a third aspect, the present application provides a device for predicting and adjusting the temperature of a computer room, including: a processor, and a memory communicatively connected to the processor;

[0070] The memory stores computer execution instructions;

[0071] The processor executes the computer execution instructions stored in the memory, so that the path query device accessing the network resources executes the method for predicting and adjusting the temperature of the computer room in any one of the first aspects.

[0072] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer execution instructions are stored, and when the computer execution instructions are executed by a processor, they are used to implement the method for predicting and adjusting the temperature of a computer room in any one of the first aspects.

[0073] The method, device and storage medium for predicting and adjusting the temperature of a computer room provided by this application obtain the time nodes for predicting and adjusting the temperature of the computer room and the historical influencing data corresponding to the time nodes; the historical influencing data includes multiple indoor temperature influencing factors at the same time nodes in N historical periods; input the historical influencing data into the target temperature prediction model to obtain the predicted temperature corresponding to the time nodes in the current period; the target temperature prediction model is a time-series-based prediction model obtained according to the target training data in multiple groups of training data, the number of time periods corresponding to different groups of training data is different, and the number of target time periods of the target training data is N, where N is a natural number; compare the predicted temperature with the computer room temperature threshold to obtain the temperature difference, and adjust the set temperature of the air conditioner in the computer room according to the temperature difference at the time nodes, so that the indoor temperature of the computer room is less than the computer room temperature threshold. By intelligently adjusting the air conditioner according to the prediction result, while ensuring the normal operation of the computer room equipment, the energy utilization efficiency is improved, and accurate energy consumption reduction and intelligent energy saving are realized. Brief Description of the Drawings

[0074] The drawings here are incorporated into the description and form a part of this description, showing the embodiments consistent with this application, and are used together with the description to explain the principles of this application.

[0075] Figure 1 is a schematic flowchart of the method for predicting and adjusting the temperature of a computer room provided by an embodiment of this application Figure 1 ;

[0076] Figure 2 is a schematic flowchart of the method for predicting and adjusting the temperature of a computer room provided by an embodiment of this application Figure 2 ;

[0077] Figure 3 is a schematic diagram of the error change corresponding to different training data sets provided by an embodiment of this application;

[0078] Figure 4 is a schematic diagram of the prediction error corresponding to different numbers of time periods provided by an embodiment of this application;

[0079] Figure 5 is a schematic flowchart of the method for predicting and adjusting the temperature of a computer room provided by an embodiment of this application Figure 3 ;

[0080] Figure 6 is a schematic flowchart of the method for predicting and adjusting the temperature of a computer room provided by an embodiment of this application Figure 4 ;

[0081] Figure 7 is a schematic structural diagram of the device for predicting and adjusting the temperature of a computer room provided by an embodiment of this application;

[0082] Figure 8 It is a schematic diagram of the hardware structure of the device for predicting and adjusting the temperature of the computer room provided by the embodiment of the present application.

[0083] Through the above-mentioned drawings, the clear embodiments of the present application have been shown, and more detailed descriptions will be given later. These drawings and text descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0084] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0085] In the prior art, the management state of the computer room air conditioner is still open management, with fixed settings for temperature, air volume, etc., resulting in waste of cooling energy due to excessive cooling. The maintenance of the air conditioner depends on the operation status alarm of the air conditioner, and the air conditioner cannot be effectively maintained. Through the temperature prediction model, the present application predicts the indoor temperature of the computer room, can predict the temperature at a future moment in advance, and thus can more effectively select corresponding methods to manage the air conditioner, achieving the purpose of reducing the energy consumption of the air conditioner and equipment and improving the energy utilization efficiency.

[0086] The method for predicting and adjusting the temperature of the computer room provided by the present application aims to solve the above technical problems in the prior art.

[0087] The following uses specific embodiments to elaborate in detail on the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems. These several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0088] Figure 1 It is a schematic flowchart of the method for predicting and adjusting the temperature of the computer room according to the embodiment of the present invention Figure 1 , as Figure 1 shown, this embodiment provides a method for predicting and adjusting the temperature of the computer room, and the process includes the following steps:

[0089] Step S101: Obtain the time node that needs to predict and adjust the temperature of the computer room and the historical impact data corresponding to the time node; the historical impact data includes multiple indoor temperature impact factors at the same time node in N historical periods.

[0090] Specifically, the influencing data affecting the computer room temperature include the maintenance structure, area, cooling capacity and quantity of air conditioners, heat generation of equipment, etc. Among them, the cooling load is mainly determined by the cooling capacity and quantity of air conditioners, and the heating load includes the heating loads of equipment, lighting and building maintenance structures, as well as indoor-outdoor heat conduction. Since the working conditions of equipment vary at different times, the power of the equipment can be analyzed by obtaining the DC voltage and DC current of the equipment's switching power supply. The air conditioner data can obtain the supply air temperature and return air temperature. When predicting the computer room temperature at a certain moment of a certain day, the historical influencing data to be obtained are the historical influencing data at the same moment in N historical periods. The historical period can be set according to the actual situation or requirements. For example, if a historical period is 1 day and it is necessary to predict the indoor temperature at 12 o'clock on a certain day, then the historical influencing data corresponding to 12 o'clock every day in the N days before that certain day need to be obtained.

[0091] Step S102: Input the historical influencing data into the target temperature prediction model to obtain the predicted temperature corresponding to the time node in the current period; the target temperature prediction model is a time series-based prediction model obtained according to the target training data in multiple groups of training data. The number of time periods corresponding to different groups of training data is different, and the number of target time periods of the target training data is N, where N is a natural number.

[0092] Specifically, the target temperature prediction model is a time series-based prediction model that can capture the relationships between multiple quantities that change over time, and predict the indoor temperature at a future moment based on the historical influencing data at corresponding moments in multiple time periods. The target temperature prediction model can select the vector autoregressive model. During the model training process, multiple models are trained according to multiple groups of training data, and then the most accurate target temperature prediction model is obtained through screening. The number of target time periods of this target temperature prediction model is N. The prediction method is more accurate and simpler to implement compared with the traditional simultaneous equation model.

[0093] Step S103: Compare the predicted temperature with the computer room temperature threshold to obtain the temperature difference, and adjust the set temperature of the air conditioner in the computer room according to the temperature difference at the time node, so that the indoor temperature of the computer room is less than the computer room temperature threshold.

[0094] Specifically, since the equipment in the computer room is usually concentrated and has a large power consumption, too high a temperature will not only cause the energy consumption cost of the computer room to become high, but also cause the equipment to overheat and even malfunction or be damaged. Moreover, a higher temperature will accelerate the aging of electronic components and have an adverse impact on the life of the equipment. The computer room temperature threshold is the temperature to ensure the normal and stable operation of the equipment in the computer room. By adjusting the set temperature of the air conditioner in the computer room according to the temperature difference at the time node, so that the indoor temperature of the computer room is less than the computer room temperature threshold, it is possible to improve the energy utilization efficiency while ensuring the normal and stable operation of the equipment, and achieve precise energy consumption reduction and intelligent energy conservation.

[0095] The method for predicting and adjusting the temperature in the computer room provided by the embodiment of the present invention can predict the indoor temperature of the computer room through a temperature prediction model, and can predict the temperature at a future moment in advance, so that a corresponding method can be selected more effectively to manage the air conditioner, achieving the purpose of reducing the energy consumption of the air conditioner and equipment and improving the energy utilization efficiency.

[0096] Figure 2 Schematic flowchart of the method for predicting and adjusting the temperature in the computer room provided by the embodiment of the present application Figure 2 As Figure 2 shown, the training process of the target temperature prediction model in the above embodiment is described in detail in this embodiment. The specific implementation manner of this process includes the following steps:

[0097] Step S201: Obtain a plurality of training data sets. Each training data set includes multiple groups of training data. Each group of training data includes multiple indoor temperature influencing factors at the same time node in multiple historical periods and the actual historical temperature at the target node. Among them, the number of time periods corresponding to adjacent groups of training data differs by 1. The time periods corresponding to the target nodes in the same training data set are the same, and the target nodes in different training data sets correspond to different time periods.

[0098] Specifically, for example, each time period is 1 day, there are 8 training data sets, and the target node is 12 o'clock on one or more prediction dates; the first training data set includes multiple indoor temperature influencing factors at 12 o'clock in the 8 historical days closest to the prediction date and the actual historical temperature at 12 o'clock on the prediction date, the second training data set includes multiple indoor temperature influencing factors at 12 o'clock in the 9 historical days closest to the prediction date and the actual historical temperature at 12 o'clock on the prediction date,..., the seventh training data set includes multiple indoor temperature influencing factors at 12 o'clock in the 15 historical days closest to the prediction date and the actual historical temperature at 12 o'clock on the prediction date.

[0099] Step S202: Based on each group of training data, train and obtain a candidate temperature prediction model based on time series, and based on the actual historical temperature and the predicted temperature of the target node output by the candidate temperature prediction model, obtain an error data set for each candidate temperature prediction model. The error data set includes multiple difference data, and the difference data is the difference between the actual historical temperature and the prediction result.

[0100] Specifically, by comparing the actual historical temperature at the moment corresponding to the target prediction date with the predicted temperatures generated by different historical cycle corresponding prediction models, the error differences between the actual temperature and the prediction results of each prediction model can be obtained, and the error differences are summarized to obtain an error data set. Through the data in the error data set, the temperature errors of the same candidate temperature prediction model for multiple different target nodes can be intuitively seen.

[0101] Taking Figure 3 the schematic diagram of error changes corresponding to different training data sets shown as an example, in the figure, taking May 1 - May 5 as an example, the temperatures at the same moment on these five days (five target nodes) are predicted using different candidate temperature prediction models. Each candidate temperature prediction model corresponds to a different time period, and the MSE change trend graph for each day is generated based on the error data generated by the predictions of different candidate temperature prediction models.

[0102] Step S203: For each training data set, perform mean processing on the difference data in each error data set to obtain an error mean. Compare the multiple error means corresponding to multiple groups of training data with a preset error threshold, and screen out the maximum number of time periods to the minimum number of time periods that are less than the preset error threshold; among them, different training data sets correspond to their respective preset error thresholds.

[0103] Specifically, performing mean processing on the difference data in each error data set is to narrow the selection range of time periods. Taking Figure 3 as an example, when the time period is 8 days, the error mean is relatively large. When the selected training set size is from 9th to 15th, the algorithm may produce the optimal prediction result; by comparing the multiple error means corresponding to multiple groups of training data with a preset error threshold, the number of time periods with larger errors can be eliminated, narrowing the selection range of the number of time periods, reducing the amount of later data processing, and improving the model accuracy and model establishment efficiency.

[0104] Step S204: Based on the maximum number of time periods to the minimum number of time periods, obtain the multiple error means corresponding to each number of time periods among different numbers of time periods.

[0105] Specifically, the maximum number of time periods to the minimum number of time periods is the scale range of the optimal training set after narrowing. By obtaining the error mean corresponding to each number of time periods, the temperature prediction model with the highest accuracy can be screened.

[0106] Step S205: According to the error mean corresponding to each number of time periods, take the number of time periods whose error means are all less than the preset error mean as the target number of time periods, and the corresponding candidate temperature prediction model as the target temperature prediction model.

[0107] Specifically, by comparing and screening the mean error corresponding to each number of time periods, the number of periods with a mean error meeting the error requirement is selected to ensure the prediction accuracy and reliability of the temperature prediction model. As Figure 4 shown in the schematic diagram of prediction errors corresponding to different numbers of time periods, different numbers of time periods correspond to curves of different colors. Among them, when the number of days is 12, the error of the temperature prediction for each day is the smallest. By comparing the fitting degree change curves under different numbers of time periods, the candidate temperature prediction model with the smallest error is selected as the target temperature prediction model.

[0108] Figure 5 Schematic flowchart of the method for predicting and adjusting the computer room temperature provided by the embodiment of the present application Figure 4 As Figure 5 shown, this embodiment details the process of adjusting the set temperature of the air conditioner in the computer room in the above embodiment. The specific implementation manner of this process includes the following steps:

[0109] Step S501: Determine whether the predicted temperature is greater than the computer room temperature threshold.

[0110] Specifically, by determining whether the predicted temperature is greater than the computer room temperature threshold, different methods are selected to control the air conditioner, so as to achieve the effect of air conditioner energy saving while controlling the computer room temperature.

[0111] Step S502: If the predicted temperature is greater than the computer room temperature threshold, reduce the value of the set temperature of the air conditioner by a temperature difference at the time node.

[0112] Specifically, when the predicted temperature is greater than the computer room temperature threshold, it indicates that at the time node, the indoor temperature in the computer room is too high due to factors such as equipment heat dissipation, which may have an adverse impact on the equipment. The current set temperature of the air conditioner cannot maintain the temperature in the computer room to ensure the safe and stable operation of the equipment, and the high temperature will increase the equipment energy consumption. Therefore, it is necessary to cool down the computer room.

[0113] Step S503: If the predicted temperature is less than or equal to the computer room temperature threshold, turn off the air conditioner at the time node.

[0114] Specifically, by judging, the air conditioner is turned off when the temperature is low to achieve energy saving. If there is an energy-saving option in the air conditioner settings, the energy-saving mode can also be selected when the temperature is low to reduce energy consumption.

[0115] In some alternative embodiments, the process of obtaining the temperature threshold of the computer room includes: obtaining the location information of the computer room; matching the location information with a preset warning threshold database to obtain the temperature warning threshold corresponding to the location information; the warning threshold database stores the temperature warning thresholds corresponding to multiple regions; calculating the temperature threshold of the computer room according to the temperature warning threshold and a preset energy-saving difference.

[0116] Specifically, since there are significant differences in temperature between the north and south regions in different seasons and the warning thresholds in different regions are different, the method of positioning the computer room and then matching the warning threshold according to the positioning is more flexible, unified and accurate. The preset energy-saving difference is a fixed difference lower than the temperature warning threshold. When the temperature in the computer room is lower than the temperature warning threshold and the difference from the temperature warning threshold is greater than the preset energy-saving difference, the air conditioner can be adjusted, turned off or put into the energy-saving mode to maximize the energy-saving benefit on the premise of ensuring the normal operation of the computer room equipment.

[0117] Figure 6 Schematic flow chart of the method for predicting and adjusting the temperature of the computer room provided by the embodiment of the present application Figure 4 As Figure 6 shown, before adjusting the set temperature of the air conditioner in the computer room in this embodiment for the above embodiment, the process of error analysis and feedback with reference to the real-time temperature is described in detail. The specific implementation manner of this process includes the following steps:

[0118] Step S601: Obtain the real-time temperature data of the computer room at a time node.

[0119] Specifically, the real-time temperature in the computer room is obtained through temperature monitoring devices such as temperature sensors. Obtaining the real-time temperature data is for feedback adjustment and to prevent the indoor environmental temperature from deviating too much from the predicted temperature output by the model due to uncontrollable factors such as a sudden change in outdoor conditions or a sudden increase in the business volume of the computer room on a certain day.

[0120] Step S602: Determine whether the real-time temperature data is greater than the temperature warning threshold.

[0121] Specifically, the temperature warning threshold is the upper limit of the temperature for the normal operation of the equipment in the computer room. When the real-time temperature exceeds the temperature warning threshold, it will cause the equipment to overheat and malfunction or be damaged, affecting the service life of the equipment.

[0122] Step S603: If the real-time temperature data is greater than the temperature warning threshold, perform an alarm feedback according to the real-time temperature data and adjust the set temperature of the air conditioner to the minimum.

[0123] Specifically, when the real-time temperature exceeds the temperature alarm threshold, it is necessary to quickly cool down the temperature in the computer room. Therefore, the set temperature of the air conditioner is adjusted to the minimum to quickly reduce the temperature in the computer room, and an alarm feedback is given to remind the relevant management personnel to detect the reason for the high temperature and eliminate the potential safety hazards of the equipment in a timely manner.

[0124] Step S604, if the real-time temperature data is less than or equal to the temperature alarm threshold, compare the real-time temperature data with the predicted temperature to obtain the difference data.

[0125] Specifically, by analyzing the difference data, check whether the accuracy of the predicted temperature meets the requirements. If there is an abnormal data accuracy situation, the model needs to be adjusted in a timely manner to ensure the model accuracy.

[0126] Step S605, determine whether the difference data is greater than the preset difference.

[0127] Specifically, the preset difference is the model accuracy requirement value, and check whether the accuracy meets the standard by judgment.

[0128] Step S606, if the difference data is greater than the preset difference, perform model anomaly feedback according to the difference data, and compare the real-time temperature data with the computer room temperature threshold to obtain the temperature difference, and adjust the set temperature of the air conditioner in the computer room according to the temperature difference.

[0129] Specifically, if the difference data is greater than the preset difference, it means that the model accuracy does not meet the requirements. The model is adjusted by means of manual intervention after model anomaly feedback to ensure the accuracy and reliability of the model.

[0130] Step S607, if the difference data is less than or equal to the preset difference, adjust the set temperature of the air conditioner in the computer room according to the temperature difference.

[0131] Specifically, if the difference data is less than or equal to the preset difference, it means that the model accurately predicts the indoor temperature and meets the accuracy requirements. The set temperature of the air conditioner in the computer room is directly adjusted according to the temperature difference between the prediction result and the computer room temperature threshold.

[0132] Figure 7 It is a schematic structural diagram of the device for predicting and adjusting the computer room temperature provided by the embodiment of the present invention. As Figure 7 shown, the device 70 for predicting and adjusting the computer room temperature includes: an acquisition module 701, a prediction module 702, and an adjustment module 703. Among them

[0133] The acquisition module 701 is used to acquire the time node for predicting and adjusting the computer room temperature and the historical influence data corresponding to the time node; the historical influence data includes multiple indoor temperature influence factors at the same time node in N historical periods.

[0134] A prediction module 702, configured to input historical impact data into a target temperature prediction model to obtain a predicted temperature corresponding to a time node in the current cycle; the target temperature prediction model is a time-series-based prediction model obtained according to target training data in multiple groups of training data, the number of time cycles corresponding to different groups of training data is different, and the number of target time cycles of the target training data is N, where N is a natural number.

[0135] An adjustment module 703, configured to compare the predicted temperature with a computer room temperature threshold to obtain a temperature difference, and adjust the set temperature of the air conditioner in the computer room according to the temperature difference at the time node, so that the indoor temperature of the computer room is less than the computer room temperature threshold.

[0136] In a possible design, the prediction module 702 is specifically configured to:

[0137] Obtain multiple training data sets, each training data set includes multiple groups of training data, each group of training data includes multiple indoor temperature influencing factors at the same time node in multiple historical cycles and the actual historical temperature of the target node, where the number of time cycles corresponding to adjacent groups of training data differs by 1, the time cycles corresponding to the target nodes in the same training data set are the same, and the target nodes in different training data sets correspond to different time cycles;

[0138] Based on each group of training data, train and obtain a candidate temperature prediction model based on time series, and based on the actual historical temperature and the predicted temperature of the target node output by the candidate temperature prediction model, obtain an error data set for each candidate temperature prediction model, and the error data set includes multiple difference data, and the difference data is the difference between the actual historical temperature and the prediction result;

[0139] According to the error data set of each candidate temperature prediction model, obtain the target temperature prediction model.

[0140] In a possible design, the prediction module 702 is specifically configured to:

[0141] For each training data set, perform mean processing on the difference data in each error data set to obtain an error mean, compare the multiple error means corresponding to multiple groups of training data with a preset error threshold, and screen out the maximum number of time cycles to the minimum number of time cycles less than the preset error threshold; among them, different training data sets correspond to their respective preset error thresholds;

[0142] For the maximum number of time cycles to the minimum number of time cycles corresponding to each training data set, determine the target temperature prediction model among the candidate temperature prediction models.

[0143] In a possible design, the prediction module 702 is specifically configured to:

[0144] Obtain multiple error means corresponding to each number of time periods among different numbers of time periods, based on the maximum number of time periods to the minimum number of time periods;

[0145] According to the error means respectively corresponding to each number of time periods, use the number of time periods with error means all less than a preset error mean as the target number of time periods, and the corresponding candidate temperature prediction model as the target temperature prediction model.

[0146] In a possible design, the adjustment module 703 is specifically configured to:

[0147] Determine whether the predicted temperature is greater than the machine room temperature threshold;

[0148] If the predicted temperature is greater than the machine room temperature threshold, reduce the value of the set temperature of the air conditioner by a temperature difference at the time node;

[0149] If the predicted temperature is less than or equal to the machine room temperature threshold, turn off the air conditioner at the time node.

[0150] In a possible design, the adjustment module 703 is further configured to:

[0151] Obtain the location information of the machine room;

[0152] Match the location information with a preset warning threshold database to obtain the temperature warning threshold corresponding to the location information; multiple temperature warning thresholds corresponding to multiple regions are stored in the warning threshold database;

[0153] Calculate the machine room temperature threshold according to the temperature warning threshold and a preset energy-saving difference.

[0154] In a possible design, the adjustment module 703 is further configured to:

[0155] Obtain the real-time temperature data of the machine room at the time node;

[0156] Determine whether the real-time temperature data is greater than the temperature warning threshold;

[0157] If the real-time temperature data is greater than the temperature warning threshold, perform an alarm feedback according to the real-time temperature data and adjust the set temperature of the air conditioner to the minimum;

[0158] If the real-time temperature data is less than or equal to the temperature warning threshold, perform an error analysis on the temperature prediction model according to the real-time temperature data, and adjust the set temperature of the air conditioner in the machine room according to the error analysis result.

[0159] In a possible design, the adjustment module 703 is specifically configured to:

[0160] Compare the real-time temperature data with the predicted temperature to obtain difference data;

[0161] Determine whether the difference data is greater than a preset difference value;

[0162] If the difference data is greater than the preset difference value, perform model anomaly feedback based on the difference data, obtain a temperature difference by comparing the real-time temperature data with the computer room temperature threshold, and adjust the set temperature of the air conditioner in the computer room according to the temperature difference;

[0163] If the difference data is less than or equal to the preset difference value, adjust the set temperature of the air conditioner in the computer room according to the temperature difference.

[0164] The device for predicting and adjusting the computer room temperature provided in this embodiment can be used to execute the above method for predicting and adjusting the computer room temperature. The implementation principle and technical effect are similar, and will not be elaborated here in this embodiment.

[0165] Figure 8 It is a schematic hardware structure diagram of the device for predicting and adjusting the computer room temperature provided in the embodiment of the present invention. As Figure 8 shown, the device 80 for predicting and adjusting the computer room temperature includes: at least one processor 801 and a memory 802. Optionally, the device 80 for predicting and adjusting the computer room temperature further includes a communication component 803. Among them, the processor 801, the memory 802, and the communication component 803 are connected through a bus 804.

[0166] In the specific implementation process, at least one processor 801 executes the computer execution instructions stored in the memory 802, so that at least one processor 801 executes the above method for predicting and adjusting the computer room temperature.

[0167] The communication component 803 can perform data interaction with the server.

[0168] The specific implementation process of the processor 801 can be referred to the above method embodiment. The implementation principle and technical effect are similar, and will not be elaborated here in this embodiment.

[0169] In the above Figure 8In the illustrated embodiments, it should be understood that the processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly embodied as being executed and completed by a hardware processor, or by a combination of hardware and software modules in the processor.

[0170] The memory may include high-speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.

[0171] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, the buses in the drawings of this application are not limited to only one bus or one type of bus.

[0172] This application also provides a computer-readable storage medium storing computer-executable instructions, and when the processor executes the computer-executable instructions, the method for predicting and adjusting the temperature of the computer room as described above is implemented.

[0173] For the above-mentioned computer-readable storage medium, the above-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a disk or an optical disc. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0174] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0175] The division of 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 couplings or direct couplings or communication connections shown or discussed between each other can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0176] The units described as separate components may or may not be physically separated. The components shown 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.

[0177] In addition, in each embodiment of the present invention, the functional units 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.

[0178] 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 part of this technical solution can be embodied in the form of a software product. The 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 in each embodiment of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical discs that can store program codes.

[0179] Those of ordinary skill in the art will understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of including the above method embodiments; and the foregoing storage medium includes: various media such as ROM, RAM, magnetic disk, or optical disc that can store program codes.

[0180] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting and adjusting the temperature of a computer room, characterized in that Including: Obtain the time nodes that need to predict and adjust the computer room temperature and the historical influence data corresponding to the time nodes; the historical influence data includes multiple indoor temperature influence factors at the same time node in N historical periods; Input the historical influence data into the target temperature prediction model to obtain the predicted temperature corresponding to the time node in the current period; the target temperature prediction model is a time-series-based prediction model obtained according to the target training data in multiple groups of training data. The number of time periods corresponding to different groups of training data is different, and the number of target time periods of the target training data is N, and N is a natural number; Compare the predicted temperature with the computer room temperature threshold to obtain a temperature difference, and adjust the set temperature of the air conditioner in the computer room according to the temperature difference at the time node, so that the indoor temperature of the computer room is less than the computer room temperature threshold.

2. The method according to claim 1, wherein The target temperature prediction model is trained in the following manner: Obtain multiple training data sets. Each training data set includes multiple groups of training data. Each group of training data includes multiple indoor temperature influence factors at the same time node in multiple historical periods and the actual historical temperature of the target node. Among them, the number of time periods corresponding to adjacent groups of training data differs by 1. The number of time periods corresponding to the target nodes in the same training data set is the same, and the target nodes in different training data sets correspond to different time periods; Based on each group of training data, train and obtain a candidate temperature prediction model based on time series, and based on the actual historical temperature and the predicted temperature of the target node output by the candidate temperature prediction model, obtain an error data set for each candidate temperature prediction model. The error data set includes multiple difference data, and the difference data is the difference between the actual historical temperature and the prediction result; According to the error data set of each candidate temperature prediction model, obtain the target temperature prediction model.

3. The method according to claim 2, wherein The obtaining of the target temperature prediction model according to the error data set of each candidate temperature prediction model includes: For each training data set, perform mean processing on the difference data in each error data set to obtain an error mean value. Compare the multiple error mean values corresponding to multiple groups of training data with a preset error threshold, and screen out the maximum number of time periods to the minimum number of time periods less than the preset error threshold; among them, different training data sets correspond to their own preset error thresholds; For the maximum number of time periods to the minimum number of time periods corresponding to each training data set, determine the target temperature prediction model among the candidate temperature prediction models.

4. The method according to claim 3, wherein The determining of the target temperature prediction model among the candidate temperature prediction models for the maximum number of time periods to the minimum number of time periods corresponding to each training data set includes: Based on the maximum number of time periods to the minimum number of time periods, obtain multiple error mean values corresponding to each number of time periods among the different numbers of time periods; Based on the average error corresponding to each quantity of time periods, the quantity of time periods with an average error less than the preset average error is used as the target quantity of time periods, and the corresponding candidate temperature prediction model is the target temperature prediction model.

5. The method according to claim 1, wherein Adjusting the set temperature of the air conditioner in the computer room according to the temperature difference at the time node includes: Judging whether the predicted temperature is greater than the computer room temperature threshold; If the predicted temperature is greater than the computer room temperature threshold, reducing the value of the set temperature of the air conditioner by the temperature difference at the time node; If the predicted temperature is less than or equal to the computer room temperature threshold, turning off the air conditioner at the time node.

6. The method according to claim 1, wherein The method further includes: Obtaining the location information of the computer room; Matching the location information with a preset alarm threshold database to obtain the temperature alarm threshold corresponding to the location information; multiple temperature alarm thresholds corresponding to multiple regions are stored in the alarm threshold database; Calculating the computer room temperature threshold according to the temperature alarm threshold and the preset energy-saving difference.

7. The method according to claim 6, wherein Before adjusting the set temperature of the air conditioner in the computer room according to the temperature difference at the time node, the method further includes: Obtaining the real-time temperature data of the computer room at the time node; Judging whether the real-time temperature data is greater than the temperature alarm threshold; If the real-time temperature data is greater than the temperature alarm threshold, performing alarm feedback according to the real-time temperature data and adjusting the set temperature of the air conditioner to the minimum; If the real-time temperature data is less than or equal to the temperature alarm threshold, performing error analysis on the temperature prediction model according to the real-time temperature data, and adjusting the set temperature of the air conditioner in the computer room according to the error analysis result.

8. The method according to claim 7, characterized in that, The performing error analysis on the temperature prediction model according to the real-time temperature data and adjusting the set temperature of the air conditioner in the computer room according to the error analysis result includes: Comparing the real-time temperature data with the predicted temperature to obtain difference data; Judging whether the difference data is greater than a preset difference; If the difference data is greater than the preset difference, performing model anomaly feedback according to the difference data, comparing the real-time temperature data with the computer room temperature threshold to obtain a temperature difference, and adjusting the set temperature of the air conditioner in the computer room according to the temperature difference; If the difference data is less than or equal to the preset difference, adjusting the set temperature of the air conditioner in the computer room according to the temperature difference.

9. An equipment for predicting and adjusting the temperature of a computer room, characterized in that, Including: An obtaining module, configured to obtain a time node for predicting and adjusting the computer room temperature and historical influence data corresponding to the time node; the historical influence data includes multiple indoor temperature influence factors at the same time node in N historical periods; A predicting module, configured to input the historical influence data into a target temperature prediction model to obtain a predicted temperature corresponding to the time node in the current period; the target temperature prediction model is a time series-based prediction model obtained according to target training data in multiple groups of training data, the quantity of time periods corresponding to different groups of training data is different, the target quantity of time periods of the target training data is N, and N is a natural number; An adjustment module is configured to compare the predicted temperature with the computer room temperature threshold to obtain a temperature difference, and adjust the set temperature of the air conditioner in the computer room according to the temperature difference at the time node, so that the indoor temperature of the computer room is less than the computer room temperature threshold.

10. A device for predicting and adjusting the temperature in a computer room, characterized in that, It includes: a processor and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, Computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by the processor, they are used to implement the method according to any one of claims 1 to 8.

Images