CN114936810B - Day-ahead scheduling method based on data center space-time transfer characteristics - Google Patents
Day-ahead scheduling method based on data center space-time transfer characteristics Download PDFInfo
- Publication number
- CN114936810B CN114936810B CN202210874019.3A CN202210874019A CN114936810B CN 114936810 B CN114936810 B CN 114936810B CN 202210874019 A CN202210874019 A CN 202210874019A CN 114936810 B CN114936810 B CN 114936810B
- Authority
- CN
- China
- Prior art keywords
- data center
- task
- time
- constraint
- area
- 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
- 238000012546 transfer Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000003287 optical effect Effects 0.000 claims abstract description 47
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims abstract description 24
- 229910052799 carbon Inorganic materials 0.000 claims abstract description 24
- 230000005540 biological transmission Effects 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 3
- 238000010248 power generation Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 239000013307 optical fiber Substances 0.000 claims 1
- 238000005265 energy consumption Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000764238 Isis Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
Images
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
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Power Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention discloses a day-ahead scheduling method based on time-space transfer characteristics of a data center, and belongs to the field of power systems. Acquiring regional power grid photovoltaic output and load prediction data, optical network parameters, data center parameters and distributed work task amount prediction data; constructing a regional multi-data-center space-time transfer day-ahead scheduling model based on the space-time transfer characteristics of data center loads, and taking the lowest carbon emission of all regional data centers and an optical network in one day as a target function; constructing an area power balance constraint, a working state constraint, a user satisfaction constraint and an optical network transmission constraint based on a time-space transfer constraint of a data center load; and optimizing the regional multi-data center and optical network carbon emission schemes according to the minimum carbon emission objective function, the regional power balance constraint, the working state constraint, the user satisfaction constraint and the optical network transmission constraint, thereby reducing the carbon emission of the regional data center network and improving the average utilization rate of the CPU of the data center server.
Description
Technical Field
The invention belongs to the field of power systems and automation thereof and the field of computer science and technology, and particularly relates to a day-ahead scheduling method based on time-space transfer characteristics of a data center.
Background
The global network traffic has seen explosive growth driven by the digital economic era, and by the end of 2019, the global network traffic has reached 2.1ZB, growing more than 12 times in the past decade. Meanwhile, the explosion of data processing requirements is also prompting cloud service operators to build more geographically dispersed data centers to cope with the trend of continuous development. The 2016 world data center consumed approximately 416TWh of electricity, accounting for approximately 3% of the total world power consumption, and still increased at a rapid rate. In some economically developed cities such as Beijing in China, the existing data center cabinets in Beijing in 2021 account for about 10% to 12% of the total amount of China, and the total power of the data center accounts for about 8% of the average power supply load of the whole Beijing city. Therefore, as a large-size and rapidly-growing space-time flexibility load, the method has great significance for fully mining the regulation potential of the data center load in the power system.
At present, related researches on energy consumption management mechanisms of data centers are performed at home and abroad, and the research on applying the time-space transfer characteristic of the data centers to the energy consumption management mechanisms of regional multiple data centers involves less. The operation cost and the carbon emission of the data center can be reduced only by deeply exploring the space-time transfer characteristics and the energy consumption management mechanism of the data center. Therefore, a day-ahead scheduling method based on the space-time transfer characteristic of the data center is provided.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the day-ahead scheduling method based on the space-time transfer characteristic of the data center is provided and used for relieving the problem of high carbon emission of the regional data center.
In order to solve the technical problems, the invention adopts the technical scheme that: a day-ahead scheduling method based on space-time transfer characteristics of a data center comprises the following steps:
acquiring photovoltaic output and load prediction data of a regional power grid, optical network parameters, data center parameters and distributed work task amount prediction data;
constructing a regional multi-data-center space-time transfer day-ahead scheduling model based on the space-time transfer characteristics of data center loads, and taking the lowest carbon emission of all regional data centers and an optical network in one day as a target function;
constructing an area power balance constraint, a working state constraint, a user satisfaction constraint and an optical network transmission constraint based on the space-time transfer constraint of the data center load;
and optimizing the regional multi-data center and optical network carbon emission schemes according to the minimum carbon emission objective function, the regional power balance constraint, the working state constraint, the user satisfaction constraint and the optical network transmission constraint.
The objective function can be specifically expressed as:
wherein,Tthe number of time periods divided for a day,Nis the total number of the data centers,eis the carbon emission rate of thermal power generation,P i,t DC as a data centeriIn thattThe power at the moment of time is,PUEfor the efficiency of the power utilization of the data center,M i,t ON as a data centeriIn thattThe number of servers that have been turned on at the moment,is the static power at which the server is running,Kis a collection of different operating states of the server,TASKfor the set of all the task types, the task type is,for data centersiIn thattThe time is from the working statekThe type of server processing istaskThe number of tasks of (a) is,γ task is a singletaskThe server capacity that the type task needs to occupy,μ i,k as a data centeriThe middle operating state iskThe service rate of the server is set by the server,the coefficient is a constant coefficient,f i,k for data centersiMiddle working stateIs composed ofkThe frequency of operation of the server is such that,is an optical network link (i,j) In thattThe power that is consumed at a time of day,for a fixed power consumed by the optical network links,Lfor the purpose of the set of links,is a link (i,j) In thattThe flow rate at the time of day,the dynamic power consumed for the optical network links,as a network elementiIn thattThe power that is consumed at a time of day,for all and nodesiThe link of the connection.
The power balance constraint may be specifically expressed as:
wherein,P i,t PV is a regioniIn thattThe photovoltaic output at the moment is generated,P i,t grid is a regioniIn thattThe power output of the power grid at the moment,P i,t Load is a regioniIn thattThe load consumption at the moment of time is,P i,t DC as a data centeriIn thattThe load consumption at the moment of time is,is a regioniAnd the maximum power output limit of the power grid.
According to the working state constraint, the working frequency of the CPU of the server is adjusted based on the dynamic frequency adjustment technology to change the working state, which is specifically expressed as:
wherein,as a data centeriIn thattThe number of servers that are in the working state k at the moment,as a data centeriThe minimum number of servers that are turned on,M i as a data centeriThe total number of servers that are owned,as a data centeriIn thattThe average utilization of servers at time in working state k,as a data centeriIn the working statekMaximum utilization of the server.
Establishing a cosine distribution time satisfaction function according to the user satisfaction degree constraintS(t) Specifically, it is represented as:
wherein,is composed oftaskThe maximum response time of the type task is,L task is a reasonable value set.
According to fullThe method comprises the steps that an intention function establishes a completion number matrix A of each time period of batch tasks so as to determine the completion condition of each batch task in each time period; the matrix A is oneTThe sparse matrix of the order is composed of zero elements in the lower left corner and the upper right corner, and the zero elements in the lower left corner are represented int=iThe task load coming at a moment cannot beiProcessing before the moment, wherein the zero element at the upper right corner represents that the processing time is longer thanThe number of loads of (a) is zero to satisfy the maximum response time constraint required by the user satisfaction, which is specifically expressed as:
wherein,indicating that the data center ist=iIs received at and atHandling completion within a period of timetaskThe number of type tasks to be performed,is composed oftaskThe average satisfaction of the users of the type task,is composed oftaskType task when completion time isIs determined by the user's satisfaction with,indicating that the data center isHandling completion within a period of timetaskThe total number of type tasks,is the minimum satisfaction required.
The constraint of the maximum response time may be specifically expressed as:
wherein,as a data centeriIn thattTime of day processing from a data centerjIs/are as followstaskThe number of type tasks to be performed,as a data centeriIn thattTime of day processing transfer remainstaskThe number of type tasks to be performed,as a data centeriIn thatkTime of day receptiontaskThe number of type tasks that can be performed,for data centersiIn thatkTime of day transfer to data centerjInner parttaskThe number of tasks of a type.
The optical network transmission constraint may be specifically expressed as:
wherein,for nodes of an optical networkiNode towards optical networkjTransmitted bytaskThe number of type tasks to be performed,for nodes of optical networksjNode towards optical networkiTransmitted bytaskThe number of type tasks to be performed,as a data centeriClean receptiontaskThe number of type tasks to be performed,as a data centerjIn thatkTime of day transfer to data centeriInner parttaskThe number of tasks of a type is,sin order to be the starting point of the transfer,din order to reach the end of the transfer,is a link (i,j) In thattThe capacity is used at all times of the day,is a transfer unittaskThe capacity required for the type of task,is a link (i,j) Maximum bandwidth capacity.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a day-ahead scheduling method based on the time-space transfer characteristic of a data center, which comprises the following steps: acquiring photovoltaic output and load prediction data of a regional power grid, optical network parameters, data center parameters and distributed work task amount prediction data; constructing a regional multi-data-center space-time transfer day-ahead scheduling model based on the load space-time transfer characteristics of the data centers, and taking the lowest carbon emission of all the regional data centers and an optical network in one day as a target function; constructing an area power balance constraint, a working state constraint, a user satisfaction constraint and an optical network transmission constraint based on the space-time transfer constraint of the data center load; and optimizing the regional multi-data center and optical network carbon emission schemes according to the minimum carbon emission objective function, the regional power balance constraint, the working state constraint, the user satisfaction constraint and the optical network transmission constraint, thereby reducing the carbon emission of the regional data center network and improving the average utilization rate of a CPU (central processing unit) of the data center server.
Drawings
FIG. 1 is a flow chart of a method for day-ahead scheduling based on spatiotemporal transfer characteristics of a data center according to the present invention;
FIG. 2 is a schematic diagram of a regional data center network according to the present invention;
FIG. 3 is a graph comparing carbon emissions before and after the method of the present invention is used;
fig. 4 is a comparison graph of average utilization of servers before and after the method of the present invention is used.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. 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.
As shown in fig. 1, the day-ahead scheduling method based on the time-space transfer characteristic of the data center is applied to the fields of power systems and automation thereof and computer science and technology, and comprises the following steps:
acquiring photovoltaic output and load prediction data of a regional power grid, optical network parameters, data center parameters and distributed work task amount prediction data;
constructing a regional multi-data-center space-time transfer day-ahead scheduling model based on the space-time transfer characteristics of data center loads, and taking the lowest carbon emission of all regional data centers and an optical network in one day as a target function;
constructing an area power balance constraint, a working state constraint, a user satisfaction constraint and an optical network transmission constraint based on the space-time transfer constraint of the data center load;
and optimizing the regional multi-data center and optical network carbon emission schemes according to the minimum carbon emission objective function, the regional power balance constraint, the working state constraint, the user satisfaction constraint and the optical network transmission constraint.
The objective function can be specifically expressed as:
wherein,Tthe number of time periods divided for a day,Nis the total number of the data centers,eis the carbon emission rate of thermal power generation,P i,t DC as a data centeriIn thattThe power at the moment of time is,PUEfor the efficiency of the power utilization of the data center,M i,t ON as a data centeriIn thattThe number of servers that have been turned on at the moment,is the static power at which the server is running,Kis a collection of different operating states of the server,TASKfor the set of all the task types, the task type is,as a data centeriIn thattThe time is from the working statekThe type of server processing istaskThe number of tasks of (a) is,γ task is a singletaskThe server capacity that the type task needs to occupy,μ i,k as a data centeriThe middle working state iskThe service rate of the server is set,the coefficient is a constant coefficient,f i,k as a data centeriThe middle operating state iskThe frequency of operation of the server is such that,is an optical network link (i,j) In thattThe power that is consumed at a time of day,for a fixed power consumption of the optical network link,Lis a set of links to be transmitted to the mobile station,is a link (i,j) In thattThe flow rate at the time of day,the dynamic power consumed for the optical network links,as a network elementiIn thattThe power that is consumed at a time of day,for all and nodesiThe link of the connection.
The power balance constraint may be specifically expressed as:
wherein,P i,t PV is a regioniIn thattThe photovoltaic output at a moment of time,P i,t grid is a regioniIn thattThe power output of the power grid at the moment,P i,t Load is a regioniIn thattThe load consumption at the moment of time is,P i,t DC as a data centeriIn thattThe load consumption at the moment of time is,is a regioniAnd the maximum power output limit of the power grid.
According to the working state constraint, the working frequency of the CPU of the server is adjusted based on the dynamic frequency adjustment technology to change the working state, which is specifically expressed as:
wherein,as a data centeriIn thattThe number of servers that are in the working state k at the moment,as a data centeriThe minimum number of servers that are turned on,M i as a data centeriThe number of all servers that are owned,as a data centeriIn thattThe average utilization of the servers in working state k at the moment,for data centersiIn the middle working statekMaximum utilization of the server.
Establishing a cosine distribution time satisfaction function according to the user satisfaction constraintS(t) Specifically, it is represented as:
wherein,is composed oftaskThe maximum response time of the type task,L task is a reasonable value set.
Establishing a completion number matrix A of each time interval of the batch tasks according to the satisfaction function so as to determine the completion condition of each batch task in each time interval; the matrix A is oneTThe sparse matrix of the order has zero elements in the lower left corner and the upper right corner, and the zero elements in the lower left corner are represented int=iThe task load of the coming moment can not beiProcessing before the moment, wherein the zero element at the upper right corner represents that the processing time is longer thanThe load quantity of (2) is zero to satisfy the maximum response time constraint required by the user satisfaction, which is specifically expressed as:
wherein,indicating that the data center ist=iIs received at and atHandling completion within a period of timetaskThe number of type tasks to be performed,is composed oftaskThe average satisfaction of the users of the type task,is composed oftaskType task when completion time isThe degree of satisfaction of the user of (c),indicating that the data center isHandling completion within a period of timetaskThe total number of type tasks,is the minimum satisfaction required.
The maximum response time constraint may be specifically expressed as:
wherein,as a data centeriIn thattTime of day processing from a data centerjIs/are as followstaskThe number of type tasks to be performed,as a data centeriIn thattTime of day processing transfer remainstaskThe number of type tasks to be performed,as a data centeriIn thatkTime of day receptiontaskThe number of type tasks that can be performed,as a data centeriIn thatjTime of day transfer to data centerjInner parttaskThe number of tasks of a type.
The optical network transmission constraint may be specifically expressed as:
wherein,for nodes of optical networksiNode towards optical networkjTransmitted bytaskThe number of type tasks to be performed,for nodes of optical networksjNode towards optical networkiTransmitted bytaskThe number of type tasks to be performed,as a data centeriClean receptiontaskThe number of type tasks to be performed,as a data centerjIn thatkTime of day transfer to data centeriInner parttaskThe number of tasks of a type is,sin order to be the starting point of the transfer,din order to reach the end point of the transfer,is a link (i,j) In thattThe capacity is used at a moment in time,is a transfer unittaskThe capacity required for the type task is,is a link (i,j) Maximum bandwidth capacity.
As shown in fig. 2, in an embodiment of the present invention, taking a data center network in a certain area as an example, the area is composed of 6 data center sites and 8 optical cable links of the same type, and the bandwidth capacities are all 400Gbit/s.
As shown in fig. 3, in an embodiment of the present invention, the total carbon emission of the regional data center and the optical network is reduced by 17.51% compared with the time domain transfer alone by using the data center day-ahead scheduling method of the present invention.
As shown in fig. 4, in an embodiment of the present invention, by using the data center day-ahead scheduling method provided by the present invention, the average utilization rate of the CPU of the server is improved by 78.69% compared with the method of only time domain transfer.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting the protection scope thereof, and although the present invention has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that after reading the present invention, they can make various changes, modifications or equivalents to the specific embodiments of the present invention, but these changes, modifications or equivalents are within the protection scope of the appended claims.
Claims (4)
1. A day-ahead scheduling method based on space-time transfer characteristics of a data center is characterized by comprising the following steps:
s1, acquiring photovoltaic output and load prediction data of a regional power grid, optical network parameters, data center parameters and distributed work task amount prediction data;
s2, constructing a regional multi-data-center space-time transfer day-ahead scheduling model based on the space-time transfer characteristics of data center loads, and taking the lowest carbon emission of all regional data centers and an optical network in one day as a target function;
s3, constructing an area power balance constraint, a working state constraint, a user satisfaction constraint and an optical network transmission constraint based on the space-time transfer constraint of the data center load;
s4, optimizing a regional multi-data center and optical network carbon emission scheme according to a minimum carbon emission objective function, regional power balance constraint, working state constraint, user satisfaction constraint and optical network transmission constraint;
the objective function is specifically expressed as:
wherein,Tthe number of time periods divided for a day,Nis the total number of the data centers,eis the carbon emission rate of thermal power generation,P i,t DC to be located in an areaiIn a data centertThe power of the moment in time of day,PUEfor the efficiency of the power utilization of the data center,M i,t ON to be located in the areaiIn a data centertThe number of servers that have been turned on at the moment,is the static power at which the server is running,Kis a collection of different operating states of the server,TASKfor the set of all the task types, the task type is,to be located in the areaiIn a data center oftThe time is from the working statekThe type of server processing istaskThe number of tasks of (a) is,γ task is a singletaskThe server capacity that the type task needs to occupy,μ i,k to be located in an areaiThe working state in the data center iskThe service rate of the server is set by the server,is a constant coefficient of the number of the optical fibers,f i,k to be located in the areaiIn a data center of which the operating state iskThe frequency of operation of the server is such that,for optical network links (i,j) In thattThe power that is consumed at a time of day,for a fixed power consumed by the optical network links,Lfor the purpose of the set of links,is a link (i,j) In thattThe flow rate at the time of day,the dynamic power consumed for the optical network links,to be located in an areaiIntThe power that is consumed at a time of day,is all and areaiA link to which a network element node is connected;
the power balance constraint is specifically expressed as:
wherein,P i,t PV is a regioniIn thattThe photovoltaic output at the moment is generated,P i,t grid is a regioniIn thattThe power output of the power grid at the moment,P i,t Load is a regioniIn thattThe load consumption at the moment of time is,P i,t DC to be located in an areaiIn a data center oftThe load consumption at the moment of time is,is a regioniThe maximum power output by the power grid is limited;
the working state constraint adjusts the working frequency of the server CPU based on the dynamic frequency adjustment technology to change the working state of the server CPU, which is specifically expressed as:
wherein,to be located in an areaiIn a data center oftThe number of servers that are in the working state k at the moment,to be located in the areaiThe data center of (a) is the least open server,M i to be located in the areaiThe total number of servers owned by the data center,to be located in the areaiIn a data center oftThe average utilization of servers at time in working state k,to be located in the areaiIs in an operating state in the data centerkMaximum utilization of the server;
the optical network transmission constraints are specifically expressed as:
wherein,to be located in the areaiTo a location areaDomainjTransmitted by network element nodetaskThe number of type tasks to be performed,to be located in the areajTowards a network element node located in an areaiTransmitted by network element nodetaskThe number of type tasks to be performed,to be located in the areaiData center net reception oftaskThe number of type tasks to be performed,to be located in the areajIn a data center ofkTime shift to localized areaiIn a data centertaskThe number of tasks of a type is,sin order to be the starting point of the transfer,din order to reach the end point of the transfer,is a link (i,j) In thattThe capacity is used at all times of the day,is a transfer unittaskThe capacity required for the type task is,is a link (i,j) Maximum bandwidth capacity.
3. The day-ahead scheduling method based on the data center space-time transfer characteristics as claimed in claim 2, wherein the satisfaction function establishes a matrix A of the number of completed batches of tasks in each time period to clarify the completion of each batch of tasks in each time period; the matrix A is oneTThe sparse matrix of the order is composed of zero elements in the lower left corner and the upper right corner, and the zero elements in the lower left corner are represented int=iThe task load coming at a moment cannot beiProcessing before the moment, wherein the zero element at the upper right corner represents that the processing time is longer thanThe load quantity of (2) is zero to satisfy the maximum response time constraint required by the user satisfaction, which is specifically expressed as:
wherein,indicating that the data center ist=iIs received at and atHandling completion within a period of timetaskNumber of type tasks,Is composed oftaskThe average satisfaction of the users of the type task,is composed oftaskType task when completion time isThe degree of satisfaction of the user of (c),indicating that the data center isHandling completion within a period of timetaskThe total number of type tasks,is the minimum satisfaction required.
4. The method for scheduling data center space-time transfer characteristics in the future according to claim 3, wherein the maximum response time constraint is specifically expressed as:
wherein,to be located in the areaiIn a data center oftTime of day processing from a data centerjIs/are as followstaskThe number of type tasks to be performed,to be located in an areaiIn a data centertTime of day processing transfer remainstaskThe number of type tasks to be performed,to be located in the areaiIn a data center ofkTime of day receptiontaskThe number of type tasks that can be performed,to be located in an areaiIn a data center ofkTime shift to localized areajIn the data centertaskThe number of tasks of a type.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210874019.3A CN114936810B (en) | 2022-07-25 | 2022-07-25 | Day-ahead scheduling method based on data center space-time transfer characteristics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210874019.3A CN114936810B (en) | 2022-07-25 | 2022-07-25 | Day-ahead scheduling method based on data center space-time transfer characteristics |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114936810A CN114936810A (en) | 2022-08-23 |
CN114936810B true CN114936810B (en) | 2022-10-18 |
Family
ID=82868778
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210874019.3A Active CN114936810B (en) | 2022-07-25 | 2022-07-25 | Day-ahead scheduling method based on data center space-time transfer characteristics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114936810B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108898282A (en) * | 2018-06-06 | 2018-11-27 | 华北电力大学 | Data center resource Optimization Scheduling and computer storage medium |
CN113553718A (en) * | 2021-07-28 | 2021-10-26 | 国网上海市电力公司 | Method for configuring equipment capacity of comprehensive energy supply system of green data center |
CN113904372A (en) * | 2021-10-15 | 2022-01-07 | 华北电力大学 | Active power distribution network multi-objective optimization operation method considering 5G base station access |
CN114597894A (en) * | 2022-03-15 | 2022-06-07 | 天津大学合肥创新发展研究院 | Day-ahead scheduling method and device for power distribution network considering carbon cost and multiple uncertainties |
CN114662319A (en) * | 2022-03-25 | 2022-06-24 | 华北电力大学 | Construction method of active power distribution network planning model considering data center |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014205585A1 (en) * | 2013-06-28 | 2014-12-31 | Polyvalor, Société En Commandite | Method and system for optimizing the location of data centers or points of presence and software components in cloud computing networks using a tabu search algorithm |
-
2022
- 2022-07-25 CN CN202210874019.3A patent/CN114936810B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108898282A (en) * | 2018-06-06 | 2018-11-27 | 华北电力大学 | Data center resource Optimization Scheduling and computer storage medium |
CN113553718A (en) * | 2021-07-28 | 2021-10-26 | 国网上海市电力公司 | Method for configuring equipment capacity of comprehensive energy supply system of green data center |
CN113904372A (en) * | 2021-10-15 | 2022-01-07 | 华北电力大学 | Active power distribution network multi-objective optimization operation method considering 5G base station access |
CN114597894A (en) * | 2022-03-15 | 2022-06-07 | 天津大学合肥创新发展研究院 | Day-ahead scheduling method and device for power distribution network considering carbon cost and multiple uncertainties |
CN114662319A (en) * | 2022-03-25 | 2022-06-24 | 华北电力大学 | Construction method of active power distribution network planning model considering data center |
Non-Patent Citations (1)
Title |
---|
基于计算负荷时–空双维迁移的互联多数据中心碳中和调控方法研究;杨挺 等;《中国电机工程学报》;20220131;第42卷(第1期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN114936810A (en) | 2022-08-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021244000A1 (en) | Virtual aggregation system and method for regional energy source complex | |
CN109240223A (en) | A kind of energy management system for industrial park | |
WO2020207067A1 (en) | Blockchain-based new energy settlement system | |
CN107423133B (en) | Data network load distribution method among data centers for reducing power grid loss | |
CN110784779A (en) | Data acquisition method of electricity consumption information acquisition system | |
CN109190818B (en) | Power resource management method and system, server and computer readable storage medium | |
CN115102953A (en) | Power distribution network cloud edge terminal cooperative control system and method | |
Kumar et al. | An optimized framework of the integrated renewable energy and power quality model for the smart grid | |
CN109284336B (en) | Geographically distributed data center system and scheduling method thereof | |
Yi et al. | Energy‐aware disaster backup among cloud datacenters using multiobjective reinforcement learning in software defined network | |
CN114936810B (en) | Day-ahead scheduling method based on data center space-time transfer characteristics | |
CN110689175A (en) | Energy consumption optimization method for distributed green cloud data center with chaotic multiple universes | |
CN112350435A (en) | Virtual power plant management and control device based on micro-grid group and electric power controllable load | |
CN116307110A (en) | Distributed roof photovoltaic power generation aggregation management method and system | |
CN114936240B (en) | Data center space-time transfer potential mining and evaluating method | |
Xiang et al. | Optimal expansion planning of 5G and distribution systems considering source-network-load-storage coordination | |
CN112103997B (en) | Active power distribution network operation flexibility improving method considering data center adjustment potential | |
CN108173969A (en) | High-frequency acquisition system and method for energy consumption data of demand side | |
CN114648248A (en) | Park energy internet energy equipment power utilization regulation and control optimal configuration system and method | |
CN113162038A (en) | Load demand response resource aggregation method based on multiple small data networks | |
CN118350613B (en) | Optimized scheduling method and system based on partitioned virtual power plant | |
CN117331670A (en) | Multi-data center carbon neutralization regulation and control method based on calculation load space-time characteristic migration | |
He et al. | Beetle Swarm Optimization Algorithm‐Based Load Control with Electricity Storage | |
Yuan et al. | A Cluster Based Data Transmission Scheme for Distributed Photovoltaic Systems | |
CN117595517B (en) | Intelligent cluster control method and system based on distributed photovoltaic |
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 |