Method for predicting refrigeration energy consumption of data center and related equipment

Abstract

The invention provides a method for predicting refrigeration energy consumption of a data center and related equipment. The method comprises the steps that multiple pieces of first monitoring data of the data center in a first historical time period are acquired; preprocessing the plurality of pieces of first monitoring data to obtain a plurality of pieces of target monitoring data; each piece of target monitoring data is sequentially input into a predetermined target prediction model, and first refrigeration energy consumption in a future time period corresponding to the first historical time period is output through the target prediction model; wherein the target prediction model is obtained by screening a plurality of pre-constructed prediction models, the technical problem of low prediction accuracy of the refrigeration energy consumption of the data center in the prior art is solved, and the accuracy and efficiency of the refrigeration energy consumption prediction are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method for predicting cooling energy consumption of a data center and related equipment. Background Art

[0002] With the rapid development of the communications industry, there are more and more large data centers. Data centers are buildings that provide an operating environment for electronic information equipment that is centrally placed. They store, calculate and exchange data in a centralized manner and are the core infrastructure at the bottom of cloud computing. Data centers include IT computing equipment represented by servers, as well as basic supporting facilities to ensure the normal operation of IT equipment, such as power supply and distribution systems, refrigeration systems, etc. In order to ensure stable operation of equipment, data centers must maintain a certain temperature and humidity. Therefore, data centers will generate cooling energy consumption. It is necessary to predict the cooling energy consumption of data centers in the future time period and optimize the corresponding energy consumption based on the prediction results.

[0003] However, in the prior art, there are often problems such as data transmission errors and inaccurate labeling, which result in low data quality for refrigeration energy consumption prediction, and thus inaccurate output results of the refrigeration energy consumption prediction model. In addition, the selected refrigeration energy consumption prediction model is not the most suitable for predicting refrigeration energy consumption, which also results in inaccurate output results of the refrigeration energy consumption prediction model. Summary of the invention

[0004] In view of this, the purpose of the present application is to propose a method for predicting the cooling energy consumption of a data center and related equipment to overcome all or part of the deficiencies in the prior art.

[0005] Based on the above purpose, the present application provides a method for predicting the cooling energy consumption of a data center, comprising: obtaining multiple first monitoring data of the data center within a first historical time period; preprocessing the multiple first monitoring data to obtain multiple target monitoring data; inputting each target monitoring data into a predetermined target prediction model in turn, and outputting the first cooling energy consumption of a future time period that corresponds to the first historical time period through the target prediction model; wherein the target prediction model is screened from multiple pre-constructed prediction models.

[0006] Optionally, the screening method of the target prediction model includes: obtaining multiple second monitoring data of the data center within a second historical time period, and obtaining a second cooling energy consumption of a third historical time period corresponding to the second historical time period; for each pre-trained prediction model, inputting each second monitoring data into the prediction model in turn, and outputting a third cooling energy consumption corresponding to the third historical time period through the prediction model; and determining the target prediction model based on the second cooling energy consumption and the third cooling energy consumption corresponding to each prediction model.

[0007] Optionally, the target prediction model is determined based on the second refrigeration energy consumption and the third refrigeration energy consumption corresponding to each prediction model, including: calculating the absolute value of the difference between the second refrigeration energy consumption and the third refrigeration energy consumption for each prediction model; and determining the prediction model corresponding to the minimum absolute value of the difference among all the absolute values ​​of the difference as the target prediction model.

[0008] Optionally, the preprocessing of the multiple first monitoring data to obtain the multiple target monitoring data includes: performing a cleaning operation on the multiple first monitoring data; and performing a normalization operation on the multiple first monitoring data after the cleaning operation to obtain the multiple target monitoring data.

[0009] Optionally, the cleaning operation on the multiple first monitoring data includes: performing numerical detection on the multiple first monitoring data; in response to determining that there are missing values ​​and / or abnormal values ​​in the multiple first monitoring data, performing numerical replacement on the missing values ​​and / or abnormal values.

[0010] Optionally, the normalizing the plurality of first monitoring data after the cleaning operation to obtain the plurality of target monitoring data comprises: obtaining the target monitoring data by the following formula: Wherein, x' is the target monitoring data, x is the first monitoring data after the cleaning operation, min(x) is the minimum value among the multiple first monitoring data after the cleaning operation, and max(x) is the maximum value among the multiple first monitoring data after the cleaning operation.

[0011] Optionally, after the target prediction model outputs the first refrigeration energy consumption of the future time period corresponding to the first historical time period, the method includes: periodically optimizing the target prediction model.

[0012] Based on the same inventive concept, the present application also provides a device for predicting the cooling energy consumption of a data center, comprising: an acquisition module, configured to acquire multiple first monitoring data of the data center within a first historical time period; a preprocessing module, configured to preprocess the multiple first monitoring data to obtain multiple target monitoring data; an output module, configured to input each target monitoring data into a predetermined target prediction model in turn, and output the first cooling energy consumption of a future time period corresponding to the first historical time period through the target prediction model; wherein the target prediction model is screened from multiple pre-built prediction models.

[0013] Based on the same inventive concept, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method as described above when executing the computer program.

[0014] Based on the same inventive concept, the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the method as described above.

[0015] From the above, it can be seen that the present application provides a method and related equipment for predicting the cooling energy consumption of a data center, and the method includes obtaining multiple first monitoring data of the data center within a first historical time period. The multiple first monitoring data are preprocessed to obtain multiple target monitoring data, thereby improving the data quality of the multiple first monitoring data. Each target monitoring data is sequentially input into a predetermined target prediction model, and the target prediction model outputs the first cooling energy consumption of a future time period that corresponds to the first historical time period; wherein the target prediction model is obtained by screening from multiple pre-built prediction models, ensuring that the first cooling energy consumption output by the target prediction model is accurate and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A schematic diagram of a flow chart of a method for predicting cooling energy consumption of a data center according to an embodiment of the present application;

[0018] Figure 2A schematic diagram of the structure of a device for predicting cooling energy consumption of a data center according to an embodiment of the present application;

[0019] Figure 3 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0021] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0022] As mentioned in the background technology section, with the rapid development of the communications industry, there are more and more large data centers. A data center is a building that provides an operating environment for electronic information equipment that is centrally placed. It stores, calculates and exchanges data in a centralized manner and is the core infrastructure at the bottom of cloud computing. A data center includes IT computing equipment represented by servers, as well as basic supporting facilities to ensure the normal operation of IT equipment, such as power supply and distribution systems, refrigeration systems, etc. In order to ensure stable operation of the equipment, the data center must maintain a certain temperature and humidity. Therefore, the data center will generate cooling energy consumption. It is necessary to predict the cooling energy consumption of the data center in the future time period and optimize the energy consumption accordingly based on the prediction results.

[0023] In addition, smart energy management is a method of using information technology to improve energy efficiency, reduce energy waste and control energy costs. It uses advanced technologies such as modern information technology, big data, cloud computing, the Internet of Things and artificial intelligence to intelligently monitor, optimize scheduling and finely manage energy production, transmission, distribution, use and storage. Based on historical data and real-time information, it analyzes and predicts energy usage trends to provide managers with scientific decision-making support. This helps companies make plans in advance to cope with changes in the energy market. Therefore, in order for smart energy management to make plans in advance, it is very necessary to predict the cooling energy consumption of the data center.

[0024] However, in the prior art, there are often problems such as data transmission errors and inaccurate labeling, which result in low data quality for refrigeration energy consumption prediction. The training and learning of the prediction model requires a large amount of high-quality data to support it. However, in actual applications, there are often problems such as low data quality and inaccurate labeling, which in turn affect the prediction accuracy of the prediction model and also affect the prediction efficiency of the prediction model. In addition, the selected refrigeration energy consumption prediction model is not the most suitable for predicting refrigeration energy consumption, which also leads to inaccurate output results of the refrigeration energy consumption prediction model. For the prediction and optimization of data center refrigeration energy consumption, the poor output results of the prediction model may make it difficult for operation and maintenance personnel to understand and trust the decision results of the algorithm, thereby affecting its acceptance in actual applications.

[0025] In view of this, the present application embodiment proposes a method for predicting the cooling energy consumption of a data center, referring to Figure 1 , including the following steps:

[0026] Step 101: Acquire a plurality of first monitoring data of the data center within a first historical time period.

[0027] In this step, before predicting the cooling energy consumption of the data center, it is necessary to obtain monitoring data, and the purpose of predicting the cooling energy consumption is achieved by processing the monitoring data. Since it is necessary to predict the cooling energy consumption in the future time period, it is necessary to obtain multiple first monitoring data in the first historical time period that has a corresponding relationship with the future time period, wherein the corresponding relationship can be a relationship between adjacent months of the same year. For example, if it is necessary to predict the cooling energy consumption in December of this year, the first historical time period is November of this year. The corresponding relationship can also be a relationship between the same months of adjacent years. For example, if the cooling energy consumption in December of this year is predicted, the first historical time period is December of last year. The monitoring data is data that is highly correlated with the cooling energy consumption. The monitoring data is collected from the environmental monitoring system, energy management system, and IT equipment monitoring system of the data center. The monitoring data includes but is not limited to outdoor temperature and humidity, indoor temperature and humidity, IT equipment load, air conditioning system operating status, cooling tower operating status, and other data.

[0028] Step 102: pre-process the plurality of first monitoring data to obtain a plurality of target monitoring data.

[0029] In this step, due to sensor failure, data transmission error and other reasons, missing data or abnormal data may appear in the multiple first monitoring data, resulting in poor data quality of the multiple first monitoring data. In addition, the first monitoring data may also have the problem of inconsistent dimensions, which also leads to poor data quality of the multiple first monitoring data. The poor data quality of the first monitoring data will lead to low accuracy and low efficiency of the prediction results output by the subsequent target prediction model. Therefore, it is necessary to preprocess the multiple first monitoring data to obtain multiple target monitoring data, thereby improving the data quality of the multiple first monitoring data.

[0030] Step 103, input each target monitoring data into a predetermined target prediction model in turn, and output the first refrigeration energy consumption of a future time period corresponding to the first historical time period through the target prediction model; wherein the target prediction model is screened from multiple pre-built prediction models.

[0031] In this step, each target monitoring data is sequentially input into a predetermined target prediction model, and the target prediction model outputs the first cooling energy consumption of the future time period corresponding to the first historical time period. Among them, the corresponding relationship is the relationship between adjacent months of the same year or the relationship between the same month of adjacent years. The target monitoring data is high-quality monitoring data, so that the first cooling energy consumption output by the target prediction model is ensured to be accurate and efficient. Among them, the target prediction model is screened from multiple pre-built prediction models. Since there are many types of machine learning models, for example, supervised machine learning models, unsupervised machine learning models, and semi-supervised machine learning models. Machine learning models can be trained by applying different methods. Predicting cooling energy consumption through different machine learning models will have different results. In order to make the cooling energy consumption predicted by the model more accurate, the present application pre-constructs multiple prediction models, selects the target prediction model from multiple prediction models, and ensures that the cooling energy consumption predicted by the target prediction model is more accurate. Through accurate cooling energy consumption prediction, the data center can accurately match the actual demand with the operating status of the refrigeration system, effectively avoiding energy waste caused by over-cooling or insufficient cooling. Continuously optimize the operation strategy and control parameters of the cooling system based on the forecast results and data center operation needs.

[0032] It should be noted that the prediction of cooling energy consumption is crucial. Through accurate cooling energy consumption prediction, data centers can accurately match actual demand with the operating status of the cooling system, effectively avoiding energy waste caused by over-cooling or under-cooling. At the same time, this method deeply identifies and optimizes inefficient links, such as unreasonable air conditioning set temperature and air flow path layout, thereby greatly improving energy utilization efficiency. Moreover, the optimization of the cooling system also reduces equipment failures and maintenance frequency. In addition, the optimization of the cooling system also greatly improves the operating stability of the data center. Reasonable air conditioning set temperature and air flow path layout ensure the stability of the internal environmental parameters of the data center, providing a reliable and stable operating environment for IT equipment. This not only reduces the risk of equipment failure and data loss caused by environmental abnormalities, but also further improves the service quality and user satisfaction of the data center. More importantly, the implementation of this method also helps promote the sustainable development of data centers. Reducing cooling energy consumption directly reduces carbon emissions, which is in line with the global trend of energy conservation and emission reduction. Through the implementation of smart energy management, data centers not only ensure operational needs, but also actively fulfill their social responsibilities and demonstrate the concept of green, low-carbon and sustainable development. Finally, it also promotes the improvement of data center management level and intelligence. Relying on advanced data collection, processing and analysis technologies, as well as the application of machine learning algorithms, data center management has become more refined and scientific. Through real-time monitoring and data analysis, data centers can quickly identify potential problems and take preventive measures in advance, thus ensuring the safety and stability of operations.

[0033] Through the above scheme, multiple first monitoring data of the data center in the first historical time period are obtained. The multiple first monitoring data are preprocessed to obtain multiple target monitoring data, thereby improving the data quality of the multiple first monitoring data. Each target monitoring data is sequentially input into a predetermined target prediction model, and the target prediction model outputs the first cooling energy consumption of a future time period that corresponds to the first historical time period; wherein the target prediction model is obtained by screening from multiple pre-built prediction models, ensuring that the first cooling energy consumption output by the target prediction model is accurate and efficient.

[0034] In some embodiments, the screening method of the target prediction model includes: obtaining multiple second monitoring data of the data center within a second historical time period, and obtaining a second cooling energy consumption of a third historical time period corresponding to the second historical time period; for each pre-trained prediction model, inputting each second monitoring data into the prediction model in turn, and outputting a third cooling energy consumption corresponding to the third historical time period through the prediction model; and determining the target prediction model based on the second cooling energy consumption and the third cooling energy consumption corresponding to each prediction model.

[0035] In this embodiment, the accuracy of the prediction model prediction can be reflected by comparing the predicted value of the cooling energy consumption output by the prediction model with the actual value of the cooling energy consumption. Therefore, firstly, a plurality of second monitoring data of the data center in the historical time period is obtained, and the second cooling energy consumption of the third historical time period corresponding to the second historical time period is obtained. Based on the second monitoring data, the third cooling energy consumption of the third historical time period can be predicted by the prediction model. The specific process is: for each pre-trained prediction model, each second monitoring data is sequentially input into the prediction model, and the third cooling energy consumption corresponding to the third historical time period is output by the prediction model. It should be noted that before inputting the plurality of second monitoring data into the prediction model, the plurality of second monitoring data also need to be preprocessed. The third cooling energy consumption is the predicted value of the third historical time period, and the second cooling energy consumption is the actual value of the third historical time period. Based on the comparison of the above-mentioned predicted value with the actual value of each prediction model, the target prediction model can be determined in the plurality of prediction models. The target prediction model is selected from the plurality of prediction models to ensure that the prediction model predicts the cooling energy consumption with accuracy.

[0036] It should be noted that different parameter adjustment methods are applied to the prediction model to adjust the parameters of the prediction model. Exemplarily, the parameter adjustment methods are grid search, random search and Bayesian optimization. Different verification methods are applied to the prediction model to verify the prediction model. Exemplarily, the verification methods are K-fold cross validation and holdout method. Different quantification methods are applied to the prediction model to determine the prediction accuracy of the prediction model. Exemplarily, the quantification methods are mean square error, root mean square error and mean absolute error. Different methods are applied to the prediction model to construct multiple prediction models so that the target prediction model can be screened out from multiple prediction models.

[0037] In some embodiments, the target prediction model is determined based on the second refrigeration energy consumption and the third refrigeration energy consumption corresponding to each prediction model, including: for each prediction model, calculating the absolute value of the difference between the second refrigeration energy consumption and the third refrigeration energy consumption; and determining the prediction model corresponding to the minimum absolute value of all the absolute values ​​of the difference as the target prediction model.

[0038] In this embodiment, the specific comparison process of the second refrigeration energy consumption and the third refrigeration energy consumption corresponding to each prediction model is as follows: for each prediction model, the absolute value of the difference between the second refrigeration energy consumption and the third refrigeration energy consumption is calculated. The minimum absolute value of the difference is determined among multiple absolute values ​​of the difference. The minimum absolute value of the difference indicates that the second refrigeration energy consumption is closest to the third refrigeration energy consumption, which reflects that the prediction result is the most accurate. Therefore, the prediction model corresponding to the minimum absolute value of the difference among all the absolute values ​​of the difference is determined as the target prediction model. By comparing specific values, the purpose of accurately screening the target prediction model is achieved.

[0039] In some embodiments, the preprocessing of the multiple first monitoring data to obtain multiple target monitoring data includes: performing a cleaning operation on the multiple first monitoring data; and performing a normalization operation on the multiple first monitoring data after the cleaning operation to obtain the multiple target monitoring data.

[0040] In this embodiment, since the first monitoring data may have low data quality, the low data quality will affect the accuracy and prediction efficiency of the subsequent target prediction model in predicting the refrigeration energy consumption. In order to eliminate the missing and / or abnormal monitoring data, a cleaning operation is performed on the multiple first monitoring data. In order to improve the prediction efficiency of the model, a normalization operation is performed on the multiple first monitoring data after the cleaning operation to obtain multiple target monitoring data.

[0041] In some embodiments, the cleaning operation on the multiple first monitoring data includes: performing numerical detection on the multiple first monitoring data; in response to determining that there are missing values ​​and / or abnormal values ​​in the multiple first monitoring data, performing numerical replacement on the missing values ​​and / or abnormal values.

[0042] In this embodiment, in order to determine whether there is a problem with the first monitoring data, it is first necessary to perform numerical detection on multiple first monitoring data. When it is determined that there are missing values ​​and / or outliers in the first monitoring data, the missing values ​​and / or outliers are replaced with numerical values. The whole process of data cleaning operation can be completed by using data cleaning tools or data cleaning scripts. The specific technical means for numerically replacing missing values ​​and / or outliers can be interpolation, mean filling, or extrapolation based on adjacent data. By performing numerical replacement on the first monitoring data, the data quality of the first monitoring data is ensured.

[0043] In some embodiments, the normalizing operation is performed on the plurality of first monitoring data after the cleaning operation to obtain the plurality of target monitoring data, including: obtaining the target monitoring data by the following formula: Wherein, x' is the target monitoring data, x is the first monitoring data after the cleaning operation, min(x) is the minimum value among the multiple first monitoring data after the cleaning operation, and max(x) is the maximum value among the multiple first monitoring data after the cleaning operation.

[0044] In this embodiment, the normalization operation can unify data of different dimensions and ranges to the same scale, reduce the adverse effects of uneven data distribution on the prediction model, and reduce the prediction model's dependence on the input feature scale, thereby improving the generalization ability of the model. Data that has not undergone normalization may cause the prediction model to be overly sensitive to certain features and ignore other features, thereby affecting the prediction ability of the prediction model. The target monitoring data is obtained through the formula, and the target monitoring data is unified to a similar dimension, which improves the processing efficiency of the target prediction model for the target monitoring data.

[0045] In some embodiments, after the target prediction model outputs the first refrigeration energy consumption of the future time period corresponding to the first historical time period, the method includes: periodically optimizing the target prediction model.

[0046] In this embodiment, in order to continuously ensure that the prediction results output by the target prediction model are accurate, the target prediction model needs to be optimized according to a predetermined period. The predetermined period is set according to actual needs. For example, the predetermined period is every six months. The target prediction model is optimized using the newly added monitoring data and the newly added actual refrigeration energy consumption within the predetermined period. By periodically optimizing the target prediction model, it is ensured that the target prediction model always has prediction accuracy.

[0047] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0048] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0049] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a device for predicting the cooling energy consumption of a data center.

[0050] refer to Figure 2 , the device for predicting cooling energy consumption of the data center comprises:

[0051] The acquisition module 10 is configured to acquire a plurality of first monitoring data of the data center within a first historical time period.

[0052] The preprocessing module 20 is configured to preprocess the plurality of first monitoring data to obtain a plurality of target monitoring data.

[0053] The output module 30 is configured to input each target monitoring data into a predetermined target prediction model in sequence, and output the first refrigeration energy consumption of a future time period corresponding to the first historical time period through the target prediction model; wherein the target prediction model is screened from multiple pre-built prediction models.

[0054] Through the above-mentioned device, a plurality of first monitoring data of the data center in the first historical time period are obtained. The plurality of first monitoring data are preprocessed to obtain a plurality of target monitoring data, thereby improving the data quality of the plurality of first monitoring data. Each target monitoring data is sequentially input into a predetermined target prediction model, and the target prediction model is used to output the first cooling energy consumption of a future time period corresponding to the first historical time period; wherein the target prediction model is obtained by screening from a plurality of pre-built prediction models, thereby ensuring that the first cooling energy consumption output by the target prediction model is accurate and efficient.

[0055] In some embodiments, a screening module is also included, and the screening module is configured as a screening device for the target prediction model, including: obtaining multiple second monitoring data of the data center within a second historical time period, and obtaining a second cooling energy consumption of a third historical time period corresponding to the second historical time period; for each pre-trained prediction model, each second monitoring data is input into the prediction model in turn, and the third cooling energy consumption corresponding to the third historical time period is output through the prediction model; based on the second cooling energy consumption and the third cooling energy consumption corresponding to each prediction model, the target prediction model is determined.

[0056] In some embodiments, the screening module is further configured to calculate the absolute value of the difference between the second refrigeration energy consumption and the third refrigeration energy consumption for each prediction model; and determine the prediction model corresponding to the minimum absolute value of the difference among all the absolute values ​​of the difference as the target prediction model.

[0057] In some embodiments, the preprocessing module 20 is further configured to perform a cleaning operation on the plurality of first monitoring data; and perform a normalization operation on the plurality of first monitoring data that have undergone the cleaning operation to obtain the plurality of target monitoring data.

[0058] In some embodiments, the preprocessing module 20 is further configured to perform numerical detection on the multiple first monitoring data; in response to determining that there are missing values ​​and / or abnormal values ​​in the multiple first monitoring data, numerically replace the missing values ​​and / or abnormal values.

[0059] In some embodiments, the preprocessing module 20 is further configured to obtain the target monitoring data through the following formula: Wherein, x' is the target monitoring data, x is the first monitoring data after the cleaning operation, min(x) is the minimum value among the multiple first monitoring data after the cleaning operation, and max(x) is the maximum value among the multiple first monitoring data after the cleaning operation.

[0060] In some embodiments, an optimization module is also included, and the optimization module is configured to periodically optimize the target prediction model after the target prediction model outputs the first refrigeration energy consumption of the future time period that corresponds to the first historical time period.

[0061] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0062] The device of the above embodiment is used to implement the corresponding method for predicting the cooling energy consumption of the data center in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0063] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for predicting the cooling energy consumption of a data center as described in any of the above embodiments is implemented.

[0064] Figure 3 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0065] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0066] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0067] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0068] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0069] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0070] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0071] The electronic device of the above embodiment is used to implement the corresponding method for predicting the cooling energy consumption of the data center in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0072] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method for predicting the cooling energy consumption of a data center as described in any of the above embodiments.

[0073] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by 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 technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0074] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the method for predicting the cooling energy consumption of a data center as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0075] Based on the same concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer executes the method for predicting the cooling energy consumption of a data center as described in any of the above embodiments, which has the beneficial effects of the corresponding method embodiments and will not be repeated here.

[0076] It should be noted that the embodiments of the present application can be further described in the following manner:

[0077] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0078] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0079] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0080] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0081] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0082] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0083] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0084] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the protection scope of the present application.

Claims

1. A method for predicting cooling energy consumption of a data center, characterized in that: include: Acquire a plurality of first monitoring data of the data center within a first historical time period; Preprocessing the plurality of first monitoring data to obtain a plurality of target monitoring data; Inputting each target monitoring data into a predetermined target prediction model in sequence, and outputting a first refrigeration energy consumption in a future time period corresponding to the first historical time period through the target prediction model; The target prediction model is obtained by screening out a plurality of pre-built prediction models.

2. The method according to claim 1, characterized in that The screening method of the target prediction model comprises: Acquire a plurality of second monitoring data of the data center in a second historical time period, and acquire a second cooling energy consumption of a third historical time period corresponding to the second historical time period; For each pre-trained prediction model, each second monitoring data is sequentially input into the prediction model, and the third refrigeration energy consumption corresponding to the third historical time period is output through the prediction model; The target prediction model is determined based on the second refrigeration energy consumption and the third refrigeration energy consumption corresponding to each prediction model.

3. The method according to claim 2, characterized in that The determining the target prediction model based on the second refrigeration energy consumption and the third refrigeration energy consumption corresponding to each prediction model includes: For each prediction model, calculating an absolute value of a difference between the second refrigeration energy consumption and the third refrigeration energy consumption; The prediction model corresponding to the minimum absolute value of the difference among all the absolute values ​​of the differences is determined as the target prediction model.

4. The method according to claim 1, characterized in that: The preprocessing of the plurality of first monitoring data to obtain a plurality of target monitoring data includes: Performing a cleaning operation on the plurality of first monitoring data; A normalization operation is performed on the plurality of first monitoring data that have undergone the cleaning operation to obtain the plurality of target monitoring data.

5. The method according to claim 4, characterized in that The cleaning operation on the plurality of first monitoring data includes: Performing numerical detection on the plurality of first monitoring data; In response to determining that there are missing values ​​and / or abnormal values ​​in the plurality of first monitoring data, numerical values ​​of the missing values ​​and / or abnormal values ​​are replaced.

6. The method according to claim 4, characterized in that The normalizing operation is performed on the plurality of first monitoring data after the cleaning operation to obtain the plurality of target monitoring data, including: The target monitoring data is obtained by the following formula: Wherein, x' is the target monitoring data, x is the first monitoring data after the cleaning operation, min(x) is the minimum value among the multiple first monitoring data after the cleaning operation, and max(x) is the maximum value among the multiple first monitoring data after the cleaning operation.

7. The method according to claim 1, characterized in that After outputting the first refrigeration energy consumption of a future time period corresponding to the first historical time period through the target prediction model, the method includes: The target prediction model is optimized periodically.

8. A device for predicting cooling energy consumption of a data center, characterized in that: include: An acquisition module is configured to acquire a plurality of first monitoring data of the data center within a first historical time period; A preprocessing module is configured to preprocess the plurality of first monitoring data to obtain a plurality of target monitoring data; An output module is configured to input each target monitoring data into a predetermined target prediction model in sequence, and output a first refrigeration energy consumption of a future time period corresponding to the first historical time period through the target prediction model; The target prediction model is obtained by screening out a plurality of pre-built prediction models.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images