CN112308734B - IT equipment non-IT energy consumption metering and cost sharing method and electronic device - Google Patents
IT equipment non-IT energy consumption metering and cost sharing method and electronic device Download PDFInfo
- Publication number
- CN112308734B CN112308734B CN202011162740.7A CN202011162740A CN112308734B CN 112308734 B CN112308734 B CN 112308734B CN 202011162740 A CN202011162740 A CN 202011162740A CN 112308734 B CN112308734 B CN 112308734B
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- metering
- network
- result
- sum
- 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.)
- Active
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 127
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000000605 extraction Methods 0.000 claims abstract description 17
- 230000003993 interaction Effects 0.000 claims abstract description 9
- 238000005259 measurement Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 4
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000005057 refrigeration Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 8
- 238000013135 deep learning Methods 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Water Supply & Treatment (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for metering and distributing non-IT energy consumption of IT equipment and an electronic device, which are suitable for a system consisting of at least two similar IT equipment and non-IT equipment, and comprise the following steps: inputting the acquired information of each IT device into a feature extraction network, and extracting interaction features between adjacent servers; and inputting the interaction characteristics into an automatic encoder network to obtain non-IT energy consumption metering results of all IT devices. The method solves the problems that the prior art has an empirical formula, the corresponding non-IT energy consumption is only calculated roughly based on the energy consumption of the server/virtual machine, and other influencing factors are not fully considered, so that the accuracy and the reliability of a metering result are improved.
Description
Technical Field
The invention relates to the field of data centers, in particular to a metering and cost sharing method for non-IT energy consumption of IT equipment and an electronic device.
Background
Energy consumption metering has been an important issue for data center energy management. The energy of the data center is mainly consumed in IT equipment and non-IT equipment, the IT equipment mainly comprises a server and a switch, and the non-IT equipment mainly comprises a refrigerating and power supplying system. In general, the total energy consumption of non-IT devices occupies about half of the total energy consumption of the data center, and thus, the energy consumption measurement of non-IT devices is gradually the focus of research. However, accurate, fine-grained metering of non-IT energy consumption by servers and virtual machines within a data center is challenging, mainly because non-IT devices are typically shared by multiple servers, and existing measurement means can only measure total non-IT energy consumption as a whole. The existing non-IT energy consumption measuring method is based on the energy consumption of a server/virtual machine to roughly calculate the corresponding non-IT energy consumption, other influencing factors are not considered, and the method is empirical and lacks theoretical basis, so that the accuracy of a measuring result is greatly reduced.
In addition, in recent years, the scale of the multi-tenant data center is continuously increased, and the tenant rents the server of the data center, bears the electric charge of the operation of the server, and shares the corresponding refrigeration charge. Because the refrigeration system in the multi-tenant data center is shared by all tenants, a reasonable refrigeration electric charge sharing policy needs to be formulated for all tenants. The existing research commonly distributes the refrigeration electricity fee according to the IT energy consumption of the tenant server in proportion, and the situation that the position of the tenant server and the temperature of the adjacent server also influence the consumption of the refrigeration capacity is not considered, so the existing distribution method is not fair.
Disclosure of Invention
The invention provides a metering and cost sharing method for non-IT energy consumption of IT equipment and an electronic device, wherein the non-IT energy consumption is metered by a deep learning method, so that the problem of low metering accuracy caused by that various influencing factors are not comprehensively considered and metering decisions are made only by experience in the related technology is solved.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a method for measuring non-IT energy consumption of IT equipment is suitable for a system consisting of at least two similar IT equipment and non-IT equipment, and comprises the following steps:
1) Inputting the acquired information of each IT device into a feature extraction network, and extracting interaction features between adjacent servers;
2) And inputting the interaction characteristics into an automatic encoder network to obtain non-IT energy consumption metering results of all IT devices.
Further, the IT device includes: a server or virtual machine.
Further, the non-IT device that generates non-IT energy consumption includes: refrigeration system and power supply system.
Further, IT equipment information includes IT energy consumption, temperature, and location information.
Further, the location information includes: spatial three-dimensional position information.
Further, the feature extraction network includes: a CNN network; the network structure of the CNN network comprises: an input layer, two convolution layers and two fully connected layers, wherein the convolution layers use ReLU as an activation function.
Further, the network structure of the automatic encoder network includes: a fully connected layer and a neuron, wherein the fully connected layer uses Sigmoid as an activation function.
Further, the feature extraction network performs end-to-end training with the auto-encoder network.
Further, training the objective functions of the feature extraction network and the automatic encoder network includes: minimizing a linear weighted sum of the feature extraction network objective and the auto encoder network objective; the feature extraction network objective includes: minimizing a square error between the data sum output by the feature extraction network and the historical non-IT energy consumption sum or the experimental non-IT energy consumption sum; the automatic encoder network targets include: and minimizing the square error between the sum of the data output by the automatic encoder network and the historical non-IT energy consumption sum or the experimental non-IT energy consumption sum.
Further, when the non-IT energy consumption metering result is out of the set range, the non-IT energy consumption metering result is corrected through the following strategy:
1) When the non-IT energy consumption measurement result q is greater than the upper limit value L of the set range max In this case, the non-IT energy consumption measurement correction result q' =q×a, where a is a set parameter, 0<a<1；
2) When the non-IT energy consumption measurement result q is smaller than the small limit value L of the set range min At this time, the non-IT energy consumption measurement correction result q' =p×b, where P is the reference measurement result, b is the set parameter, 0<b<1；
Wherein, according to the reference measurement result P, a set range is obtained.
Further, a reference metering result is obtained by:
1) Acquiring energy consumption of each IT device;
2) Acquiring non-IT total energy consumption;
3) And (5) proportionally distributing non-IT total energy consumption according to the energy consumption of each IT device to obtain a reference metering result of each IT device.
Further, a setting parameter a and a setting parameter b are selected through the following steps;
1) Respectively selecting candidate sets of the setting parameter a and the setting parameter b;
2) And traversing the candidate combination of the set parameter a and the set parameter b, selecting the combination with the maximum sum of the similarity degrees of the non-IT energy consumption measurement result curve and the IT energy consumption, temperature and position three curves, and obtaining the set parameter a and the set parameter b, wherein the similarity degrees of the non-IT energy consumption measurement result curve and the IT energy consumption, temperature and position three curves are calculated through cosine similarity degrees.
A method for allocating the cost of non-IT energy consumption of IT equipment comprises the following steps:
1) According to the non-IT energy consumption metering result obtained by the method, calculating the non-IT energy consumption of each IT device;
2) And obtaining the non-IT energy consumption cost of each IT device according to the total non-IT energy consumption cost and the non-IT energy consumption of each IT device.
A storage medium having a computer program stored therein, wherein the computer program is arranged to perform the method described above when run.
An electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer to perform the method described above.
Compared with the prior art, the invention has the positive effects that:
according to the method and the device, IT energy consumption, temperature and position information of all servers/virtual machines are acquired and input into a preset CNN to extract interaction characteristics between adjacent servers/virtual machines; inputting the output of the CNN into a preset AE to obtain non-IT energy consumption metering results of all servers/virtual machines; the non-IT energy consumption metering results of the servers/virtual machines are input into a preset Fine-tuner to obtain final non-IT energy consumption metering results of all the servers/virtual machines, and the problems that the corresponding non-IT energy consumption is calculated only roughly based on the energy consumption of the servers/virtual machines and other influencing factors are not fully considered in the prior art are solved, so that the accuracy and reliability of the metering results are improved.
Drawings
FIG. 1 is a block diagram of a non-IT energy metering method in accordance with an embodiment of the present invention;
fig. 2 is a block diagram of a CNN network according to an embodiment of the present invention;
fig. 3 is a block diagram of the AE network according to an embodiment of the present invention;
FIG. 4 is a block diagram of a Fine-tuner according to an embodiment of the present invention;
FIG. 5 is a block diagram of a refrigeration expense allocation method based on non-IT energy consumption in accordance with an embodiment of the present invention;
Detailed Description
The present invention will be described in detail with reference to examples.
Fig. 1 is a flow chart of a method for metering and cost sharing of non-IT energy consumption of IT equipment, where the IT equipment includes a server or a virtual machine.
The non-IT energy consumption metering method of the server comprises the following steps:
and step 101, acquiring IT energy consumption, temperature and position information of all servers. The server position information can be simply represented by the space three-dimensional coordinates of the server in the machine room. As known to those skilled in the art, IT energy consumption data of the server can be obtained through a power meter, and temperature data of the server can also be obtained through a software and hardware mode;
and 102, extracting the characteristics by using the acquired server information. As known to those skilled in the art, CNN networks are a method of feature extraction that can efficiently extract feature information from high-dimensional data. Therefore, the acquired information is input into a preset CNN to extract interaction characteristics between adjacent servers;
and 103, coding and decoding by utilizing the features extracted by the CNN to obtain a reasonable non-IT energy consumption metering result. As known to those skilled in the art, AE networks can perform data dimension reduction to better visualize existing data to present a more interpretative model. Therefore, the features extracted by the CNN are input into a preset AE, and non-IT energy consumption metering results of all servers are obtained through two processes of encoding and decoding, so that the problem of interpretation of a model is solved;
104, the deep learning model generally has a robustness problem, in order to ensure the robustness of the output result, the non-IT energy consumption metering result of the server is input into a preset Fine-tuner, and the output result is limited by a preset threshold value, so that a more reliable non-IT energy consumption metering result of the server is obtained.
By the non-IT energy consumption metering method based on deep learning, the problem that the corresponding non-IT energy consumption is calculated only roughly based on the energy consumption of the server/virtual machine in the related technology and other influencing factors are not fully considered is solved, and therefore the accuracy and reliability of metering results are improved.
During the training phase, CNN and AE may be trained simultaneously. The objective function for simultaneous training of CNN and AE is to minimize CNN training objectives (Cost CNN ) And AE training objective (Cost) AE ) Is a linear weighted sum of (c), i.e., cost=αcost CNN +(1-α)Cost AE 。
As known to those skilled in the art, CNNs typically include several convolution modules and several fully-connected modules. Fig. 2 is a block diagram of a CNN network according to an embodiment of the present invention. For example, assuming 174 servers in a data center, one server having 5 dimensions of information (IT energy consumption, temperature, three-dimensional coordinates x, y, z), the preset CNN model structure and parameters may be set as follows: an input layer (201), two convolution layers (202 and 203), two fully connected layers (204 and 205), the convolution layers using ReLU as an activation function. The training set size is denoted by M, training object (Cost CNN ) Is to minimize the last full connection layer output (CNN) out ) Square error between the sum of data and the sum of non-IT energy consumption (NE), namely:
as known to those skilled in the art, AEs typically contain one encoder and one decoder to approximate the true allocation of non-IT energy consumption. Fig. 3 is a block diagram of the AE network according to an embodiment of the present invention. If the output (206) of the CNN model is taken as an input for AE, the preset AE model structure and parameters may be set as follows: a full connection layer (301) as encoder and a neuron (302) as decoder, the encoder uses Sigmoid as activation function to limit the output to (0, max) Φ ) Within the range where Φ is the output of the encoder. Training object (Cost) AE ) Is to minimize the square error between the AE output data and the corresponding historical or experimental data of the non-IT energy consumption sum, namely:
in order to improve accuracy and robustness of metering results based on a deep learning model, fine-tuning of non-IT energy consumption metering results of a server is performed by using a Fine-tuner. Fig. 4 is a block diagram of a Fine-tuner according to an embodiment of the present invention. A preset threshold L is adjusted according to three conditions:
case 401: if the metering result q of a certain server is L larger than the reference metering result p of the server, the Fine-tuner reduces the metering result of the certain server by a (0 < a < 1) times and then outputs the reduced metering result;
case 403: if the measurement result q of a certain server is smaller than the reference measurement result p of the server by L, the Fine-tuner reduces the reference measurement result of the server by b (0 < b < 1) times and outputs the reduced reference measurement result;
case 402: if the two conditions are not met, no fine tuning is performed.
The values of parameters a and b may be selected as follows: the candidate value sets of a and b are set as {0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9}, so that 18 candidate combinations of a and b are provided, the 18 combinations are traversed, and the combination which can maximize the similarity degree sum of the metering result curve and the IT energy consumption, temperature and position three curves is selected. The similarity of the two curves can be calculated by cosine similarity.
The reference metering result p of the server can be calculated as follows: and the total non-IT energy consumption NE is obtained by proportionally distributing the IT energy consumption of the server, and if the IT energy consumption of the server is S and the sum of the IT energy consumption of all the servers is S, the non-IT energy consumption of the service is NE S/S.
In this embodiment, a method for measuring non-IT energy consumption of a virtual machine in a data center is provided, the data center includes a server system including at least two servers, two virtual machines and a machine room air conditioning system, and fig. 1 is a flowchart of a method for measuring non-IT energy consumption of a virtual machine in a data center according to an embodiment of the present invention, where the flowchart includes the following steps:
and step 101, acquiring IT energy consumption of all virtual machines and temperature and position information of a server where the virtual machines are located. The server position information can be simply represented by the space three-dimensional coordinates of the server in the machine room. As known to those skilled in the art, IT energy consumption data of the virtual machine can be obtained by a software mode, and temperature data of the server can also be obtained by a software and hardware mode;
and 102, extracting the characteristics by using the obtained information of the virtual machine and the server where the virtual machine is located. As known to those skilled in the art, CNN networks are a method of feature extraction that can efficiently extract feature information from high-dimensional data. Therefore, the acquired information is input into a preset CNN to extract interaction characteristics between adjacent virtual machines;
and 103, coding and decoding by utilizing the features extracted by the CNN to obtain a reasonable non-IT energy consumption metering result. As known to those skilled in the art, AE networks can perform data dimension reduction to better visualize existing data to present a more interpretative model. Therefore, the features extracted by the CNN are input into a preset AE, and non-IT energy consumption metering results of all virtual machines are obtained through two processes of encoding and decoding, so that the problem of interpretation of the model is solved;
104, the deep learning model generally has a robustness problem, in order to ensure the robustness of the output result, the non-IT energy consumption metering result of the virtual machine is input into a preset Fine-tuner, and the output result is limited by a preset threshold value, so that a more reliable non-IT energy consumption metering result of the virtual machine is obtained.
The CNN and AE model structures, training targets and training methods in the non-IT energy consumption metering method of the virtual machine are similar to those in the non-IT energy consumption metering method of the server, and are not repeated here.
In view of the above problems, please refer to fig. 5, in this embodiment, a refrigeration cost allocation method based on non-IT energy consumption is provided, which not only considers the server IT energy consumption, but also fully considers two influencing factors of the server location and the adjacent server temperature, so that the method is more fair. The method comprises the following steps:
step 501: the refrigeration energy consumption of each server is calculated by using the non-IT energy consumption metering method of the server based on deep learning;
step 502: and the total refrigeration electricity charge NC is obtained by proportionally distributing the refrigeration energy consumption of the server, and if the refrigeration energy consumption of the server is H and the sum of the refrigeration energy consumption of all the servers is H, the refrigeration electricity charge which the server should distribute is NC H/H.
The present example verifies the proposed technique in the form of a system simulation as shown in table 1: the three technical schemes are respectively expressed as: (1) Policy II represents the existing non-IT energy consumption distributed proportionally to IT power; (2) Policy IV represents the existing distributed non-IT energy consumption based on Shapley values; (3) NEAPD represents the non-IT energy consumption metering result taking into account IT power consumption, temperature and location as proposed by the present invention. IT power, temperature and Location respectively represent the similarity between the metering curve obtained by the three methods and the three curves of IT energy consumption, temperature and position. As shown in Table 1, the invention not only reflects the influence of IT energy consumption on the metering result, but also reflects the influence of temperature and position on the metering result, thereby being closer to the actual situation.
| Policy | IT Power | Temperature | Location |
| Policy II | 1.0 | 0.8503 | 0.6211 |
| Policy IV | 0.9883 | 0.8827 | 0.6443 |
| NEAPD | 0.9051 | 0.9178 | 0.7454 |
TABLE 1
The above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and those skilled in the art may modify or substitute the technical solution of the present invention without departing from the spirit and scope of the present invention, and the protection scope of the present invention shall be defined by the claims.
Claims (4)
1. A method for metering non-IT energy consumption of IT devices, suitable for a system composed of at least two similar IT devices and non-IT devices generating non-IT energy consumption, said IT devices comprising: a server or virtual machine, the non-IT device that generates non-IT energy consumption comprising: the refrigerating system and the power supply system comprise the following steps:
1) Inputting the acquired information of each IT device into a feature extraction network, and extracting interaction features between adjacent servers; the IT equipment information comprises IT energy consumption, temperature and position information, wherein the position information comprises: spatial three-dimensional location information, the feature extraction network comprising: a CNN network, the network structure of the CNN network comprising: an input layer, two convolution layers and two fully-connected layers, wherein the convolution layers use a ReLU as an activation function;
2) Inputting the interaction characteristics into an automatic encoder network to obtain non-IT energy consumption metering results of all IT devices; wherein the network structure of the automatic encoder network comprises: a fully connected layer and a neuron, wherein the fully connected layer uses Sigmoid as an activation function;
3) When the non-IT energy consumption metering result is outside the set range, correcting the non-IT energy consumption metering result through the following strategy:
when the non-IT energy consumption measurement result q is greater than the upper limit value L of the set range max In this case, the non-IT energy consumption measurement correction result q' =q×a, where a is a set parameter, 0<a<1, calculating the setting range according to a reference metering result P;
the reference metering result P is obtained by:
acquiring energy consumption of each IT device;
acquiring non-IT total energy consumption;
according to the energy consumption of each IT device, non-IT total energy consumption is distributed proportionally, and a reference metering result P of each IT device is obtained;
the method comprises the following steps of selecting a setting parameter a and a setting parameter b:
respectively selecting candidate sets of the setting parameter a and the setting parameter b;
traversing the candidate combination of the set parameter a and the set parameter b, selecting the combination with the maximum sum of the similarity degrees of the non-IT energy consumption measurement result curve and the IT energy consumption, temperature and position three curves, and obtaining the set parameter a and the set parameter b, wherein the similarity degrees of the non-IT energy consumption measurement result curve and the IT energy consumption, temperature and position three curves are calculated through cosine similarity degrees;
when the non-IT energy consumption measurement result q is smaller than the small limit value L of the set range min At this time, the non-IT energy consumption measurement correction result q' =p×b, where P is the reference measurement result, b is the set parameter, 0<b<1；
The feature extraction network and the automatic encoder network perform end-to-end training; training the objective functions of the feature extraction network and the automatic encoder network includes: minimizing a linear weighted sum of the feature extraction network objective and the auto encoder network objective; the feature extraction network objective includes: minimizing a square error between the data sum output by the feature extraction network and the historical non-IT energy consumption sum or the experimental non-IT energy consumption sum; the automatic encoder network targets include: and minimizing the square error between the sum of the data output by the automatic encoder network and the historical non-IT energy consumption sum or the experimental non-IT energy consumption sum.
2. A method for allocating the cost of non-IT energy consumption of IT equipment comprises the following steps:
1) Calculating the non-IT energy consumption of each IT device according to the non-IT energy consumption metering result obtained by the method of claim 1;
2) And obtaining the non-IT energy consumption cost of each IT device according to the total non-IT energy consumption cost and the non-IT energy consumption of each IT device.
3. A storage medium having a computer program stored therein, wherein the computer program performs the method of any of claims 1-2.
4. An electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the method of any of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011162740.7A CN112308734B (en) | 2020-10-27 | 2020-10-27 | IT equipment non-IT energy consumption metering and cost sharing method and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011162740.7A CN112308734B (en) | 2020-10-27 | 2020-10-27 | IT equipment non-IT energy consumption metering and cost sharing method and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112308734A CN112308734A (en) | 2021-02-02 |
| CN112308734B true CN112308734B (en) | 2024-01-05 |
Family
ID=74330797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011162740.7A Active CN112308734B (en) | 2020-10-27 | 2020-10-27 | IT equipment non-IT energy consumption metering and cost sharing method and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112308734B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103778020A (en) * | 2014-02-08 | 2014-05-07 | 中国联合网络通信集团有限公司 | Virtual machine placing method and device |
| CN105975385A (en) * | 2016-04-28 | 2016-09-28 | 浪潮(北京)电子信息产业有限公司 | Fuzzy neural network-based virtual machine energy consumption prediction method and system |
| CN109445903A (en) * | 2018-09-12 | 2019-03-08 | 华南理工大学 | Cloud computing energy-saving distribution implementation method based on the discovery of QoS feature |
| CN109800066A (en) * | 2018-12-13 | 2019-05-24 | 中国科学院信息工程研究所 | A kind of data center's energy-saving scheduling method and system |
| CN110069392A (en) * | 2019-04-30 | 2019-07-30 | 南京邮电大学 | A kind of acquisition methods reflecting data center's information technoloy equipment efficiency feature |
| CN110781068A (en) * | 2019-11-07 | 2020-02-11 | 南京邮电大学 | Isomorphic decomposition method-based data center cross-layer energy consumption prediction method |
| CN112070353A (en) * | 2020-08-04 | 2020-12-11 | 中国科学院信息工程研究所 | Method and system for accurately detecting energy efficiency of data center |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116384240A (en) * | 2023-03-29 | 2023-07-04 | 济南浪潮数据技术有限公司 | Server energy consumption prediction method, device and storage medium |
| CN116301275B (en) * | 2023-05-23 | 2023-08-15 | 苏州浪潮智能科技有限公司 | Energy consumption adjusting method and device, electronic equipment and medium |
-
2020
- 2020-10-27 CN CN202011162740.7A patent/CN112308734B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103778020A (en) * | 2014-02-08 | 2014-05-07 | 中国联合网络通信集团有限公司 | Virtual machine placing method and device |
| CN105975385A (en) * | 2016-04-28 | 2016-09-28 | 浪潮(北京)电子信息产业有限公司 | Fuzzy neural network-based virtual machine energy consumption prediction method and system |
| CN109445903A (en) * | 2018-09-12 | 2019-03-08 | 华南理工大学 | Cloud computing energy-saving distribution implementation method based on the discovery of QoS feature |
| CN109800066A (en) * | 2018-12-13 | 2019-05-24 | 中国科学院信息工程研究所 | A kind of data center's energy-saving scheduling method and system |
| CN110069392A (en) * | 2019-04-30 | 2019-07-30 | 南京邮电大学 | A kind of acquisition methods reflecting data center's information technoloy equipment efficiency feature |
| CN110781068A (en) * | 2019-11-07 | 2020-02-11 | 南京邮电大学 | Isomorphic decomposition method-based data center cross-layer energy consumption prediction method |
| CN112070353A (en) * | 2020-08-04 | 2020-12-11 | 中国科学院信息工程研究所 | Method and system for accurately detecting energy efficiency of data center |
Non-Patent Citations (1)
| Title |
|---|
| "Temperature and Power Aware Server Placement Optimization for Enterprise Data Center";Longchuan Yan 等;《2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)》;第434-440页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112308734A (en) | 2021-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111525601B (en) | Charging and discharging control method and device for user side energy storage equipment and storage medium | |
| CN110287942A (en) | Training method, age estimation method and the corresponding device of age estimation model | |
| Han et al. | Scaling up cooperative game theory-based energy management using prosumer clustering | |
| CN110504716B (en) | Photovoltaic inverter reactive mode optimization selection method, terminal equipment and storage medium | |
| CN110503656A (en) | A kind of superpixel segmentation method and relevant device | |
| CN116167581A (en) | Battery demand estimation method and device, scheduling method and computer equipment | |
| CN112308734B (en) | IT equipment non-IT energy consumption metering and cost sharing method and electronic device | |
| CN117406844B (en) | Display card fan control method and related device based on neural network | |
| CN112039058A (en) | Unit combination method, system, medium and device based on wind power prediction interval | |
| CN110533218A (en) | A kind of resident's multiple-objection optimization electricity consumption strategy and system based on data mining | |
| CN110598894A (en) | Data processing method and device for energy Internet and electronic equipment | |
| CN115860388A (en) | Multi-load regulation and control method, device, terminal and storage medium | |
| CN112884316B (en) | Power regulation method, device, computer equipment and storage medium | |
| CN111951123B (en) | Method and device for controlling electrical load, computer equipment and storage medium | |
| CN112925793A (en) | Distributed mixed storage method and system for multiple structural data | |
| CN110033116A (en) | A kind of distribution line optimization method and system based on multidimensional index superposition | |
| CN112968438B (en) | Charging power regulation and control method and device, computer equipment and storage medium | |
| CN113807630B (en) | Method, device, equipment and storage medium for acquiring requirements of robot service platform | |
| CN117353302B (en) | New energy power generation power prediction method, device, equipment and medium | |
| CN115528712B (en) | Method and system for balancing energy storage capacities of different areas of source network charge storage | |
| CN114742285B (en) | Construction method and application of resident power consumption mode prediction model | |
| Xiang et al. | Hierarchical multi-objective unit commitment optimization considering negative peak load regulation ability | |
| CN116014743A (en) | Method and device for voltage partitioning of direct-current power distribution network | |
| CN118227267A (en) | Heterogeneous cluster virtual machine replay method and device based on scale variable reinforcement learning | |
| CN117575190A (en) | Energy demand density prediction method and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |