CN111786824A - Data center energy efficiency ratio optimization method, system, equipment and readable storage medium - Google Patents
Data center energy efficiency ratio optimization method, system, equipment and readable storage medium Download PDFInfo
- Publication number
- CN111786824A CN111786824A CN202010581410.5A CN202010581410A CN111786824A CN 111786824 A CN111786824 A CN 111786824A CN 202010581410 A CN202010581410 A CN 202010581410A CN 111786824 A CN111786824 A CN 111786824A
- Authority
- CN
- China
- Prior art keywords
- data center
- prediction model
- data
- efficiency ratio
- energy efficiency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
- H04L47/2408—Traffic characterised by specific attributes, e.g. priority or QoS for supporting different services, e.g. a differentiated services [DiffServ] type of service
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the field of data centers, and discloses a method, a system, equipment and a readable storage medium for optimizing energy efficiency ratio of a data center, wherein the optimization method comprises the following steps: when the service type of the data center changes, the type of the service type of the data center is obtained, and a preset AI prediction model is selected according to the type of the service type; performing energy consumption evaluation and server load prediction of the data center through the selected AI prediction model to obtain an energy efficiency ratio optimization basis of the data center; and optimizing the energy efficiency ratio of the data center according to the energy efficiency ratio of the data center. When the service type changes, the preset AI prediction model is selected, the training time of the AI prediction model is not required to be waited, the instant response of energy consumption evaluation and server load prediction is realized, and the energy efficiency ratio of the data center is further improved.
Description
Technical Field
The invention belongs to the field of data centers, and relates to a method, a system and equipment for optimizing energy efficiency ratio of a data center and a readable storage medium.
Background
The rapid development of new infrastructure provides new opportunities and challenges for the construction of novel infrastructures such as data centers, and with the great increase of data and calculated amount, the network flow of the data centers is greatly increased, which brings about the problems of partial calculation resource loss and the like. The energy efficiency ratio is a key parameter of the data center, the air-conditioning refrigeration system, the UPS, the machine room illumination and the like are factors influencing the energy consumption of the data center, and how to optimize the parameters of the data center becomes the key of the development of the data center. The machine learning algorithms are numerous, data can be processed, systematic analysis and decision control can be performed on various devices, and the method has important significance for improving the energy efficiency ratio of the data center.
The energy efficiency ratio of the current data center is optimized according to an energy consumption evaluation and server load prediction technology mainly based on an AI model, the training time of the AI model is often dozens of hours or even days, and with the diversification of the training data volume of the AI model and the service type of the data center, when the service type of the data center is changed, the energy efficiency ratio can not be supported immediately.
Disclosure of Invention
The invention aims to overcome the defects that in the prior art, when the service type of a data center changes, the AI model learning time is long and instant support cannot be provided for the optimization of the energy efficiency ratio, and provides a method, a system, equipment and a readable storage medium for optimizing the energy efficiency ratio of the data center.
In order to achieve the purpose, the invention adopts the following technical scheme to realize the purpose:
on one hand, the invention provides a method for optimizing the energy efficiency ratio of a data center, which comprises the following steps:
when the service type of the data center changes, the type of the service type of the data center is obtained, and a preset AI prediction model is selected according to the type of the service type;
performing energy consumption evaluation and server load prediction of the data center through the selected AI prediction model to obtain an energy efficiency ratio optimization basis of the data center;
and optimizing the energy efficiency ratio of the data center according to the energy efficiency ratio of the data center.
The energy efficiency ratio optimization method of the data center is further improved as follows:
the specific method for selecting the corresponding AI prediction model according to the type of the service type comprises the following steps:
selecting a corresponding AI prediction model from a preset AI prediction model set according to the type of the service type;
the AI prediction model set comprises a plurality of AI prediction models, and the AI prediction models are in one-to-one correspondence to be suitable for data centers processing different types of service.
The establishing method of the AI prediction model set comprises the following steps:
establishing an initial AI model for energy consumption evaluation and server load prediction of a data center;
acquiring a plurality of classes of service types of a data center, and acquiring actual energy consumption data and actual server load data when the data center processes the service types of each class to obtain a plurality of groups of actual energy consumption data and actual server load data;
and training the initial AI model respectively through a plurality of groups of actual energy consumption data and actual server load data to obtain a plurality of AI prediction models, and combining the plurality of AI prediction models to obtain an AI prediction model set.
The establishing method of the AI prediction model set comprises the following steps:
acquiring a plurality of categories of service types of a data center;
selecting an AI prediction model which is adopted when the existing data center with the same software and hardware configuration processes the same type of service according to the type of the service type;
and sequentially selecting AI prediction models corresponding to the service types of the plurality of categories to obtain a plurality of AI prediction models, and combining the AI prediction models to obtain an AI prediction model set.
Further comprising:
and acquiring actual energy consumption data and actual server load data of the data center, adding the actual energy consumption data and the actual server load data into a training set of the selected AI prediction model to obtain an updated training set, training the selected AI prediction model through the updated training set, and replacing the selected AI prediction model with the trained AI prediction model to be used as an AI prediction model preset by the current class of service type.
In another aspect of the present invention, a system for optimizing energy efficiency ratio in a data center includes:
the AI prediction model selection module is used for acquiring the type of the service type of the data center when the service type of the data center changes and selecting a preset AI prediction model according to the type of the service type;
the optimization basis acquisition module is used for carrying out energy consumption evaluation and server load prediction on the data center through the selected AI prediction model to obtain an energy efficiency ratio optimization basis of the data center; and
and the energy efficiency ratio optimizing module is used for optimizing the energy efficiency ratio of the data center according to the energy efficiency ratio of the data center.
The energy efficiency ratio optimization system of the data center is further improved in that:
the device also comprises an AI prediction model set building module, wherein the AI prediction model set building module comprises:
the initial AI model establishing module is used for establishing an initial AI model for energy consumption evaluation and server load prediction of the data center;
the training set generation module is used for acquiring a plurality of classes of service types of the data center, acquiring actual energy consumption data and actual server load data when the data center processes the service types of each class, and acquiring a plurality of groups of actual energy consumption data and actual server load data; and
the training integration module is used for respectively training the initial AI model through a plurality of groups of actual energy consumption data and actual server load data to obtain a plurality of AI prediction models, and the AI prediction models are combined to obtain an AI prediction model set;
the AI prediction model selection module is specifically configured to:
when the service type of the data center changes, the type of the service type of the data center is obtained, and a corresponding AI prediction model is selected from the AI prediction model set according to the type of the service type.
The device also comprises an AI prediction model updating module;
the AI prediction model updating module is used for acquiring actual energy consumption data of the data center and actual server load data, adding the actual energy consumption data and the actual server load data into a training set of the selected AI prediction model to obtain an updated training set, training the selected AI prediction model through the updated training set, and replacing the selected AI prediction model with the trained AI prediction model to serve as an AI prediction model preset by the current class of service types.
In another aspect of the present invention, a terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the data center energy efficiency ratio optimization method when executing the computer program.
In still another aspect of the present invention, a computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, implements the steps of the data center energy efficiency ratio optimization method.
Compared with the prior art, the invention has the following beneficial effects:
the invention relates to a method for optimizing energy efficiency ratio of a data center, which selects a preset AI prediction model according to the service type category of the data center when the service type of the data center changes, because the AI prediction model corresponding to the service type category of each data center is preset in advance, when the service type of the data center is obtained subsequently, the corresponding AI prediction model can be directly selected when the service type of the data center changes, so that the establishment of the AI prediction model can be completed in a very fast time when facing any service type, compared with the existing mode that the training time often needs tens of hours or even days, the establishment time of the corresponding AI prediction model when the service type changes is greatly reduced, the instant response of energy consumption evaluation and server load prediction is realized, and the energy efficiency ratio optimization basis of the data center is obtained in time, and instant support is provided for optimizing the energy efficiency ratio of the data center, and the aim of improving the energy efficiency ratio of the data center is fulfilled.
Furthermore, actual energy consumption data and actual server load data of the data center are obtained and added into the training set of the selected AI prediction model to obtain an updated training set, and the selected AI prediction model is updated and trained through the updated training set, so that the prediction accuracy of the AI prediction model is improved, and the optimization effect of the energy efficiency ratio of the data center is better realized.
Drawings
FIG. 1 is a logical schematic diagram of a data center energy efficiency ratio optimization method of the present invention;
FIG. 2 is a block diagram of a flow chart of a method for optimizing energy efficiency ratio of a data center according to an embodiment of the invention;
FIG. 3 is a block diagram illustrating a flow chart of a method for optimizing energy efficiency ratio of a data center according to an embodiment of the invention;
FIG. 4 is a schematic diagram of a data center energy efficiency ratio optimization system according to an embodiment of the invention;
FIG. 5 is a schematic diagram of a data center energy efficiency ratio optimization system according to an embodiment of the invention;
FIG. 6 is a schematic structural diagram of an AI prediction model set building module according to an embodiment of the invention;
fig. 7 is a schematic structural diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It is noted that the terms "comprises" and "comprising," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The invention is described in further detail below with reference to the accompanying drawings:
referring to fig. 1, the energy efficiency ratio optimization method for a data center of the present invention relates to a data center energy efficiency optimization technology, and in the invention process, mainly aiming at the problem that the learning time is long when the data center uses an AI model to perform energy consumption assessment and server load prediction, the data center is subjected to relevant model training in advance to obtain AI prediction models corresponding to different service types through an application scenario facing to typical service types of the data center, and the relevant AI prediction models are switched when the data center service application changes, so as to realize the instant response of the energy consumption assessment and the server load prediction.
Referring to fig. 2, a schematic diagram of a data center energy efficiency ratio optimization method in an embodiment of the present invention is shown, and the embodiment provides a data center energy efficiency ratio optimization method, where the method includes the following steps: s1: when the service type of the data center changes, the type of the service type of the data center is obtained, and a preset AI prediction model is selected according to the type of the service type; s2: performing energy consumption evaluation and server load prediction of the data center through the selected AI prediction model to obtain an energy efficiency ratio optimization basis of the data center; s3: and optimizing the energy efficiency ratio of the data center according to the energy efficiency ratio of the data center.
Here, as can be understood by those skilled in the art, the method and the system provided by the invention are based on the preset AI prediction model, and further, when the class of the current data center service type is changed, the preset AI prediction model is selected in time and correspondingly according to the class information of the data center service type detected in real time, so that the energy consumption assessment and the server load prediction of the data center are realized, the training time of the AI prediction model is not required to be waited, the instant response of the energy consumption assessment and the server load prediction can be realized, the optimization basis can be timely provided for the energy efficiency ratio optimization when the data center service type is changed, and the integrated optimization capability of the energy efficiency ratio can be effectively realized for the scene of the data center service type fluctuation.
The specific method for selecting the preset AI prediction model according to the type of the service type comprises the following steps: selecting a corresponding AI prediction model from a preset AI prediction model set according to the type of the service type; the AI prediction model set comprises a plurality of AI prediction models, and the AI prediction models are in one-to-one correspondence to be suitable for data centers processing different types of service. The AI prediction model set includes a plurality of AI prediction models, and the data centers which are suitable for processing different types of service types and correspond to the AI prediction models one to one are the key for realizing the rapid establishment of the AI prediction models under different types of service types of the data center, which requires to acquire or establish the AI prediction model set first.
One of the methods is to obtain the types of a plurality of types of service types of the data center, that is, to investigate a typical service scenario of the data center in advance, so as to obtain respective data information of each type of service type of the data center when the service type is implemented, and then to train an initial AI model by classification on the basis of the data information, so as to obtain AI prediction models corresponding to various working types, that is, to obtain a pre-selected AI prediction model set corresponding to various service types operated by the data center in advance. Specifically, when the corresponding AI prediction models are respectively established for each type of service, the corresponding actual energy consumption data and the actual server load data are generally investigated by a data center in the actual scene of each type of service, the actual energy consumption data and the actual server load data are used as training set data corresponding to each type of service, the initial AI model is respectively trained through the training set corresponding to each type of service, the AI prediction model corresponding to each type of service is obtained, and the AI prediction models corresponding to each type of service are combined to obtain the AI prediction model set.
The other is to implement migration application of the AI prediction model set or the AI prediction model on the basis of the data center with the same software and hardware configuration, that is, when the AI prediction model set is established, the AI prediction models with the same service type in the AI prediction model sets in other existing data centers can be directly migrated according to the type of the service type on the premise of the same software and hardware configuration, or the AI prediction model set of the data center is directly migrated, so that the establishment time of the AI prediction model set is reduced to a certain extent.
The establishment process of the AI prediction model set is completed, and in practical application, the establishment process of the AI prediction model set is not required to be implemented every time, the established AI prediction model set can be used all the time, and the AI prediction models corresponding to the new types of service types can be gradually added in the process.
When the energy efficiency ratio of the data center is optimized, the category of the service type of the data center needs to be acquired, and then the corresponding AI prediction model is matched according to the category of the service type.
After the establishment phase of the AI prediction model and the acquisition of the service type of the data center, the corresponding AI prediction model is selected from the AI prediction model set according to the service type of the data center, and in the process, the training and learning do not need to be restarted when different service types are faced, and the AI prediction model pre-trained in the AI prediction model set is directly adopted, so that the instant response of the energy consumption evaluation of the data center and the server load prediction is ensured, the optimization basis of the energy efficiency ratio of the data center is obtained more quickly, and the aim of improving the energy efficiency ratio of the data center is fulfilled.
After the AI prediction model which is adaptive to the current service type category of the data center is obtained, energy consumption assessment and server load prediction of the data center are directly performed by using the AI prediction model, then a data center energy efficiency ratio optimization basis is obtained according to an assessment and prediction result, then the data center energy efficiency ratio can be optimized according to the data center energy efficiency ratio optimization basis, for example, energy saving and power consumption reduction operations are performed on a server in the data center according to the data center energy efficiency ratio optimization basis, and then the energy efficiency ratio of the data center is improved.
Referring to fig. 3, a schematic diagram of a data center energy efficiency ratio optimization method according to an embodiment of the present invention is shown, where the embodiment provides a data center energy efficiency ratio optimization method, the method includes all the steps in the data center energy efficiency ratio optimization method according to the previous embodiment of the present invention, and compared with the data center energy efficiency ratio optimization method according to the previous embodiment, step S4 is added: and acquiring actual energy consumption data and actual server load data of the data center, adding the actual energy consumption data and the actual server load data into a training set of the selected AI prediction model to obtain an updated training set, training the selected AI prediction model through the updated training set, and replacing the selected AI prediction model with the trained AI prediction model to be used as an AI prediction model preset by the current class of service type.
Compared with the previous embodiment, after the whole data center energy efficiency ratio process is completed, the actual energy consumption data and the actual server load data of the data center are obtained, the data are added into the selected training set of the AI prediction model, and the AI prediction model is trained and updated, so that the prediction result of the AI prediction model can better accord with the actual situation, the prediction accuracy of the AI prediction model is improved, a more accurate data center energy efficiency ratio optimization basis is obtained, the accuracy of final prediction is ensured through continuous training and updating, and the capability of the method on the data center energy efficiency ratio is continuously improved.
Referring to fig. 4, a schematic diagram of a data center energy efficiency ratio optimization system according to an embodiment of the present invention is shown, and a data center energy efficiency ratio optimization system is provided, through which the data center energy efficiency ratio optimization method shown in fig. 2 can be implemented, but is not limited to, the system includes an AI prediction model selection module, an optimization basis acquisition module, and an energy efficiency ratio optimization module.
The AI prediction model selection module is used for acquiring the type of the service type of the data center when the service type of the data center changes, and selecting a preset AI prediction model according to the type of the service type; the optimization basis acquisition module is used for carrying out energy consumption evaluation and server load prediction on the data center through the selected AI prediction model to obtain an energy efficiency ratio optimization basis of the data center; the energy efficiency ratio optimization module is used for optimizing the energy efficiency ratio of the data center according to the energy efficiency ratio optimization criterion of the data center.
Referring to fig. 5, a schematic diagram of the data center energy efficiency ratio optimization system according to an embodiment of the present invention is shown, and a data center energy efficiency ratio optimization system is provided, through which the data center energy efficiency ratio optimization method shown in fig. 3 can be implemented, and compared with the data center energy efficiency ratio optimization system according to the previous embodiment of the present invention, all components included in the data center energy efficiency ratio optimization system according to the previous embodiment of the present invention, that is, the AI prediction model selection module, the optimization criterion acquisition module, and the energy efficiency ratio optimization module, at least include an AI prediction model update module.
The AI prediction model updating module is used for acquiring actual energy consumption data of the data center and actual server load data, adding the actual energy consumption data and the actual server load data into a training set of the selected AI prediction model to obtain an updated training set, training the selected AI prediction model through the updated training set, and replacing the selected AI prediction model with the trained AI prediction model to serve as an AI prediction model preset by the current class of service types.
In a fifth embodiment of the present invention, a data center energy efficiency ratio optimization system is provided, where the data center energy efficiency ratio optimization system includes an AI prediction model set building module in addition to an AI prediction model selecting module, an optimization criterion obtaining module, and an energy efficiency ratio optimization module, and referring to fig. 6, the AI prediction model set building module includes: the initial AI model establishing module is used for establishing an initial AI model for energy consumption evaluation and server load prediction of the data center; the training set generation module is used for acquiring a plurality of classes of service types of the data center, acquiring actual energy consumption data and actual server load data when the data center processes the service types of each class, and acquiring a plurality of groups of actual energy consumption data and actual server load data; and the training integration module is used for respectively training the initial AI model through a plurality of groups of actual energy consumption data and actual server load data to obtain a plurality of AI prediction models, and the AI prediction models are combined to obtain an AI prediction model set.
In this embodiment, the AI prediction model selection module is specifically configured to: when the service type of the data center changes, the type of the service type of the data center is obtained, and a corresponding AI prediction model is selected from the AI prediction model set according to the type of the service type.
Based on the above description of the method embodiments and the device embodiments, those skilled in the art will understand that the energy efficiency ratio optimization method of the data center of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
Referring to fig. 7, an embodiment of the present invention further provides a terminal device, where the terminal device includes at least a processor, an input device, an output device, and a computer storage medium. The processor, input device, output device, and computer storage medium within the terminal may be connected by a bus or other means.
A computer storage medium may be stored in the memory of the terminal, the computer storage medium for storing a computer program comprising program instructions, the processor for executing the program instructions stored by the computer storage medium. The Processor may be a Central Processing Unit (CPU), or may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable gate array (FPGA) or other Programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc., which is a computing core and a control core of the terminal, and is adapted to implement one or more instructions, and is specifically adapted to load and execute one or more instructions to implement a corresponding method flow or a corresponding function; in one embodiment, the processor according to the embodiment of the present invention may be used for the operation of the data center energy efficiency ratio optimization method, including: when the service type of the data center changes, the type of the service type of the data center is obtained, and a preset AI prediction model is selected according to the type of the service type; performing energy consumption evaluation and server load prediction of the data center through the selected AI prediction model to obtain an energy efficiency ratio optimization basis of the data center; optimizing the energy efficiency ratio of the data center according to the energy efficiency ratio of the data center, and the like.
The embodiment of the invention also provides a computer storage medium (Memory), which is a Memory device in the terminal device and is used for storing programs and data. It is understood that the computer storage medium herein may include a built-in storage medium in the terminal device, and may also include an extended storage medium supported by the terminal device. The computer storage medium provides a storage space that stores an operating system of the terminal. Also, one or more instructions, which may be one or more computer programs (including program code), are stored in the memory space and are adapted to be loaded and executed by the processor. The computer storage medium may be a high-speed RAM memory, or may be a non-volatile memory (non-volatile memory), such as at least one disk memory; and optionally at least one computer storage medium located remotely from the processor.
In yet another embodiment, one or more instructions stored in a computer storage medium may be loaded and executed by a processor to perform the corresponding steps of the method described above with respect to the data center energy efficiency ratio optimization method embodiment; in a specific implementation, one or more instructions in a computer storage medium are loaded by a processor and perform the following steps: when the service type of the data center changes, the type of the service type of the data center is obtained, and a preset AI prediction model is selected according to the type of the service type; performing energy consumption evaluation and server load prediction of the data center through the selected AI prediction model to obtain an energy efficiency ratio optimization basis of the data center; and optimizing the energy efficiency ratio of the data center according to the energy efficiency ratio of the data center.
In yet another embodiment, one or more instructions in a computer storage medium are loaded by a processor and perform the following steps: when the service type of the data center changes, the type of the service type of the data center is obtained, and a preset AI prediction model is selected according to the type of the service type; performing energy consumption evaluation and server load prediction of the data center through the selected AI prediction model to obtain an energy efficiency ratio optimization basis of the data center; optimizing the energy efficiency ratio of the data center according to the optimization criterion of the energy efficiency ratio of the data center; and acquiring actual energy consumption data and actual server load data of the data center, adding the actual energy consumption data and the actual server load data into a training set of the selected AI prediction model to obtain an updated training set, training the selected AI prediction model through the updated training set, and replacing the selected AI prediction model with the trained AI prediction model to be used as an AI prediction model preset by the current class of service type.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (10)
1. A method for optimizing the energy efficiency ratio of a data center is characterized by comprising the following steps:
when the service type of the data center changes, the type of the service type of the data center is obtained, and a preset AI prediction model is selected according to the type of the service type;
performing energy consumption evaluation and server load prediction of the data center through the selected AI prediction model to obtain an energy efficiency ratio optimization basis of the data center;
and optimizing the energy efficiency ratio of the data center according to the energy efficiency ratio of the data center.
2. The method for optimizing the energy efficiency ratio of the data center according to claim 1, wherein the specific method for selecting the preset AI prediction model according to the type of the service is as follows:
selecting a corresponding AI prediction model from a preset AI prediction model set according to the type of the service type;
the AI prediction model set comprises a plurality of AI prediction models, and the AI prediction models are in one-to-one correspondence to be suitable for data centers processing different types of service.
3. The method for optimizing the energy efficiency ratio of the data center according to claim 2, wherein the method for establishing the AI prediction model set comprises the following steps:
establishing an initial AI model for energy consumption evaluation and server load prediction of a data center;
acquiring a plurality of classes of service types of a data center, and acquiring actual energy consumption data and actual server load data when the data center processes the service types of each class to obtain a plurality of groups of actual energy consumption data and actual server load data;
and training the initial AI model respectively through a plurality of groups of actual energy consumption data and actual server load data to obtain a plurality of AI prediction models, and combining the plurality of AI prediction models to obtain an AI prediction model set.
4. The method for optimizing the energy efficiency ratio of the data center according to claim 2, wherein the method for establishing the AI prediction model set comprises the following steps:
acquiring a plurality of categories of service types of a data center;
selecting an AI prediction model which is adopted when the existing data center with the same software and hardware configuration processes the same type of service according to the type of the service type;
and sequentially selecting AI prediction models corresponding to the service types of the plurality of categories to obtain a plurality of AI prediction models, and combining the AI prediction models to obtain an AI prediction model set.
5. The data center energy efficiency ratio optimization method according to claim 1, further comprising:
and acquiring actual energy consumption data and actual server load data of the data center, adding the actual energy consumption data and the actual server load data into a training set of the selected AI prediction model to obtain an updated training set, training the selected AI prediction model through the updated training set, and replacing the selected AI prediction model with the trained AI prediction model to be used as an AI prediction model preset by the current class of service type.
6. A data center energy efficiency ratio optimization system, comprising:
the AI prediction model selection module is used for acquiring the type of the service type of the data center when the service type of the data center changes and selecting a preset AI prediction model according to the type of the service type;
the optimization basis acquisition module is used for carrying out energy consumption evaluation and server load prediction on the data center through the selected AI prediction model to obtain an energy efficiency ratio optimization basis of the data center; and
and the energy efficiency ratio optimizing module is used for optimizing the energy efficiency ratio of the data center according to the energy efficiency ratio of the data center.
7. The data center energy efficiency ratio optimization system of claim 6, further comprising an AI predictive model set creation module, the AI predictive model set creation module comprising:
the initial AI model establishing module is used for establishing an initial AI model for energy consumption evaluation and server load prediction of the data center;
the training set generation module is used for acquiring a plurality of classes of service types of the data center, acquiring actual energy consumption data and actual server load data when the data center processes the service types of each class, and acquiring a plurality of groups of actual energy consumption data and actual server load data; and
the training integration module is used for respectively training the initial AI model through a plurality of groups of actual energy consumption data and actual server load data to obtain a plurality of AI prediction models, and the AI prediction models are combined to obtain an AI prediction model set;
the AI prediction model selection module is specifically configured to:
when the service type of the data center changes, the type of the service type of the data center is obtained, and a corresponding AI prediction model is selected from the AI prediction model set according to the type of the service type.
8. The data center energy efficiency ratio optimization system of claim 6, further comprising an AI prediction model update module;
the AI prediction model updating module is used for acquiring actual energy consumption data of the data center and actual server load data, adding the actual energy consumption data and the actual server load data into a training set of the selected AI prediction model to obtain an updated training set, training the selected AI prediction model through the updated training set, and replacing the selected AI prediction model with the trained AI prediction model to serve as an AI prediction model preset by the current class of service types.
9. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the data center energy efficiency ratio optimization method according to any one of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium storing a computer program, wherein the computer program is configured to implement the steps of the method for optimizing energy efficiency ratio in a data center according to any one of claims 1 to 5 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010581410.5A CN111786824A (en) | 2020-06-23 | 2020-06-23 | Data center energy efficiency ratio optimization method, system, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010581410.5A CN111786824A (en) | 2020-06-23 | 2020-06-23 | Data center energy efficiency ratio optimization method, system, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111786824A true CN111786824A (en) | 2020-10-16 |
Family
ID=72757107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010581410.5A Pending CN111786824A (en) | 2020-06-23 | 2020-06-23 | Data center energy efficiency ratio optimization method, system, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111786824A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114265695A (en) * | 2021-12-26 | 2022-04-01 | 特斯联科技集团有限公司 | Energy control device and system based on decision technology |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103428282A (en) * | 2013-08-06 | 2013-12-04 | 浪潮(北京)电子信息产业有限公司 | On-line energy-saving control method and device for cloud computing data center |
| CN105117810A (en) * | 2015-09-24 | 2015-12-02 | 国网福建省电力有限公司泉州供电公司 | Residential electricity consumption mid-term load prediction method under multistep electricity price mechanism |
| CN105279692A (en) * | 2015-11-17 | 2016-01-27 | 中国建设银行股份有限公司 | Financial information technology system performance prediction method and apparatus |
| CN107634866A (en) * | 2017-10-27 | 2018-01-26 | 朱秋华 | A kind of distribution network communication system performance estimating method and device |
| CN109034660A (en) * | 2018-08-22 | 2018-12-18 | 平安科技（深圳）有限公司 | Based on the determination method and relevant apparatus of the risk control strategy of prediction model |
| CN109324875A (en) * | 2018-09-27 | 2019-02-12 | 杭州电子科技大学 | A kind of data center server power managed and optimization method based on intensified learning |
| CN110365503A (en) * | 2018-03-26 | 2019-10-22 | 华为技术有限公司 | A kind of Index and its relevant device |
| CN110390387A (en) * | 2018-04-20 | 2019-10-29 | 伊姆西Ip控股有限责任公司 | Deep learning application used resource is assessed |
-
2020
- 2020-06-23 CN CN202010581410.5A patent/CN111786824A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103428282A (en) * | 2013-08-06 | 2013-12-04 | 浪潮(北京)电子信息产业有限公司 | On-line energy-saving control method and device for cloud computing data center |
| CN105117810A (en) * | 2015-09-24 | 2015-12-02 | 国网福建省电力有限公司泉州供电公司 | Residential electricity consumption mid-term load prediction method under multistep electricity price mechanism |
| CN105279692A (en) * | 2015-11-17 | 2016-01-27 | 中国建设银行股份有限公司 | Financial information technology system performance prediction method and apparatus |
| CN107634866A (en) * | 2017-10-27 | 2018-01-26 | 朱秋华 | A kind of distribution network communication system performance estimating method and device |
| CN110365503A (en) * | 2018-03-26 | 2019-10-22 | 华为技术有限公司 | A kind of Index and its relevant device |
| CN110390387A (en) * | 2018-04-20 | 2019-10-29 | 伊姆西Ip控股有限责任公司 | Deep learning application used resource is assessed |
| CN109034660A (en) * | 2018-08-22 | 2018-12-18 | 平安科技（深圳）有限公司 | Based on the determination method and relevant apparatus of the risk control strategy of prediction model |
| CN109324875A (en) * | 2018-09-27 | 2019-02-12 | 杭州电子科技大学 | A kind of data center server power managed and optimization method based on intensified learning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114265695A (en) * | 2021-12-26 | 2022-04-01 | 特斯联科技集团有限公司 | Energy control device and system based on decision technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2019003271A (en) | Machine learning device, control device, and machine learning program | |
| CN112433819A (en) | Heterogeneous cluster scheduling simulation method and device, computer equipment and storage medium | |
| CN113157422A (en) | Cloud data center cluster resource scheduling method and device based on deep reinforcement learning | |
| TW201717066A (en) | Method, system and apparatus of planning resources for cluster computing architecture | |
| CN116127899B (en) | Chip design system, method, electronic device, and storage medium | |
| CN115238599B (en) | Energy-saving method and model reinforcement learning training method and device for refrigerating system | |
| CN115373861B (en) | GPU resource scheduling method and device, electronic equipment and storage medium | |
| CN111369011A (en) | Method and device for applying machine learning model, computer equipment and storage medium | |
| CN114169536A (en) | Data management and control method and related device | |
| CN111786824A (en) | Data center energy efficiency ratio optimization method, system, equipment and readable storage medium | |
| CN114338416B (en) | Space-time multi-index prediction method and device and storage medium | |
| CN116739388B (en) | Emission reduction measure evaluation method, device and storage medium | |
| CN113592064A (en) | Ring polishing machine process parameter prediction method, system, application, terminal and medium | |
| CN114217944A (en) | Dynamic load balancing method for neural network aiming at model parallelism | |
| CN117687356A (en) | Production scheduling method, terminal device and computer readable storage medium | |
| US20220138574A1 (en) | Method of training models in ai and electronic device | |
| CN104965745A (en) | Air conditioner system program updating device and method | |
| CN114449550A (en) | Parameter optimization method and device of base station energy-saving system | |
| CN111368408A (en) | Seq2 seq-based data center energy efficiency optimization continuous decision method | |
| CN113569366B (en) | Heating network optimization design method based on big data and terminal equipment | |
| CN114679899B (en) | Self-adaptive energy-saving control method and device, medium and equipment for machine room air conditioner | |
| CN114650190B (en) | Energy-saving method, system, terminal equipment and storage medium for data center network | |
| CN114615144B (en) | Network optimization method and system | |
| CN116454890B (en) | Combined control method, device and equipment for unit based on SCUC model | |
| WO2023119623A1 (en) | Management device, communication system, control method, and non-transitory computer-readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |