CN111174375B - Data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method - Google Patents

Data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method Download PDF

Info

Publication number
CN111174375B
CN111174375B CN201911267853.0A CN201911267853A CN111174375B CN 111174375 B CN111174375 B CN 111174375B CN 201911267853 A CN201911267853 A CN 201911267853A CN 111174375 B CN111174375 B CN 111174375B
Authority
CN
China
Prior art keywords
data center
crac
energy consumption
server
temperature
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
Application number
CN201911267853.0A
Other languages
Chinese (zh)
Other versions
CN111174375A (en
Inventor
伍卫国
徐一轩
赵东方
李祯华
康益菲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian Jiaotong University
Original Assignee
Xian Jiaotong University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xian Jiaotong University filed Critical Xian Jiaotong University
Priority to CN201911267853.0A priority Critical patent/CN111174375B/en
Publication of CN111174375A publication Critical patent/CN111174375A/en
Application granted granted Critical
Publication of CN111174375B publication Critical patent/CN111174375B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
    • F24F11/46—Improving electric energy efficiency or saving
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • F24F11/63—Electronic processing
    • F24F11/64—Electronic processing using pre-stored data

Abstract

The invention discloses a data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method, which comprises the steps of firstly, respectively establishing a data center job distribution matrix A, CRAC regulated and controlled dynamic energy consumption model P through historical data of a data center machine roomDCAnd a data center temperature prediction model; establishing thermal coupling relation between set temperature of refrigeration equipment and operating temperature of IT equipment through a data center temperature prediction model, ensuring that the temperature of a data center machine room is within a constraint condition when performing operation scheduling and refrigeration equipment control, and adjusting CRAC state and overall regulation and control of the refrigeration equipment by adopting a simulated annealing algorithm to ensure that P is in a range of PDCAnd the overall energy consumption of the data center is reduced. The invention ensures that the overall energy consumption of the data center is the lowest and ensures the safe operation of equipment.

Description

Data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method
Technical Field
The invention belongs to the technical field of data center operation scheduling, and particularly relates to an operation scheduling and machine room air conditioner regulating and controlling method for minimizing energy consumption of a data center.
Background
At present, the Power Usage Efficiency (PUE) of a large data center is about 1.5, the problem of energy waste generally exists, and most data centers still use air cooling as a main refrigeration means, such as liquid cooling and free cooling, and other technologies are not generally used. The reduction of the energy consumption of the data center and the improvement of the energy use efficiency are of great significance for promoting the healthy development of the data center and relieving the social power supply pressure.
The main energy consumption waste problem faced by the current data center is summarized as the following 3 points:
(1) the IT equipment is single in target consideration due to the operation scheduling strategy, so that the energy consumption of the IT equipment is wasted, and the safe operation of the IT equipment can be influenced.
(2) In order to cope with various sudden situations of the data center, the refrigeration equipment is generally set to be low in temperature, and excessive refrigeration is caused.
(3) The refrigeration equipment is usually based on feedback control, and is adjusted according to the temperature of the IT equipment, and the thermal coupling relationship of the data center is complex due to the air cooling characteristic, so that the problem of cooling delay is easily caused, and the operation of the IT equipment is influenced.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a method for scheduling jobs and regulating and controlling air conditioners in a machine room, which is oriented to minimizing energy consumption of a data center, in order to reduce energy consumption of the data center, aiming at the defects in the prior art.
The invention adopts the following technical scheme:
a data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method includes the steps that firstly, a dynamic energy consumption model P regulated and controlled by a data center job distribution matrix A, CRAC is respectively established through historical data of a data center machine roomDCAnd a data center temperature prediction model; establishing thermal coupling relation between set temperature of refrigeration equipment and operating temperature of IT equipment through a data center temperature prediction model, ensuring that the temperature of a data center machine room is within a constraint condition when performing operation scheduling and refrigeration equipment control, and adjusting CRAC state and overall regulation and control of the refrigeration equipment by adopting a simulated annealing algorithm to ensure that P is in a range of PDCAnd the overall energy consumption of the data center is reduced.
Specifically, the data center overall dynamic energy consumption model PDCThere are m servers, k refrigeration plants, denoted as:
PDC＝Pcrac(C)+Pserver(S+AT)
wherein, PcracFor CRAC power consumption, PserverFor Server power consumption, C is a CRAC state matrix, S is a Server current state matrix, T is a Task queue application resource matrix, and A is a job distribution matrix.
Further, the job allocation matrix a specifically includes:
Figure BDA0002313365690000021
where n is the number of jobs, Aij ∈ {0,1}, and Aij ═ 1, indicates that the jth task is assigned to the ith server.
Further, the current state matrix S of the server is specifically:
Figure BDA0002313365690000022
wherein each server is represented by p parameters.
Further, the refrigeration equipment state matrix C is specifically:
Figure BDA0002313365690000031
where tk denotes the set temperature of the kth CRAC and fk denotes the kth CRAC blower rate.
Specifically, the data center temperature prediction model is a data center temperature prediction model based on a recurrent neural network, a server air inlet temperature prediction model is respectively established for each server, and [ cpu, mem, t ] is usedin，tout，tCRAC，f]Training model with data samples, wherein cpu, mem, tin，toutRespectively showing the current server cpu, the memory service condition, the air inlet temperature and the air outlet temperature, tCRACAnd f denotes the set temperature and blower rate for the room CRAC group.
Specifically, the constraint conditions include:
Figure BDA0002313365690000032
and is
Figure BDA0002313365690000033
S+A′T＜＝S#
Forecast(C′，S+A′T)＜T#
Wherein, Aij belongs to {0,1}, m represents the number of servers in the cluster, n represents the number of jobs, S # represents the maximum limit of all server resources, T # represents the maximum threshold of all server inlet temperatures, and C 'and A' represent adjusted matrixes C and A.
Compared with the prior art, the invention has at least the following beneficial effects:
the invention relates to a data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulating and controlling method, which can simultaneously carry out job scheduling and CRAC control under the constraint of predicted temperature, reduce the overall energy consumption of a data center and improve the energy use efficiency.
Furthermore, an energy consumption model of the data center is established according to the operation state of the data center server and the CRAC operation state, compared with other energy-saving methods only aiming at IT equipment or CRAC, the established energy consumption model is the whole energy consumption model of the data center, single regulation and control are avoided being considered, and the job scheduling and CRAC regulation and control can be based on the basis.
Furthermore, thermal coupling relation between the set temperature of the refrigeration equipment and the operating temperature of the IT equipment is established through a temperature prediction model, the temperature of a machine room is guaranteed to be within a safety threshold value when operation scheduling and refrigeration equipment control are carried out, and due to the fact that the temperature is based on prediction, the problems of hot spots and cooling lag can be avoided by setting a certain prediction view.
Further, the set constraint conditions ensure the reasonability of operation allocation and CRAC regulation, and the specific constraint conditions are as follows: ensuring that jobs can be distributed to one or more servers, ensuring that each server does not exceed available resource limits, and ensuring that temperature predictions are within safe thresholds after job distribution and CRAC regulation.
In summary, the objective of the present invention in integrally controlling the operation scheduling and the refrigeration equipment is to minimize the overall energy consumption of the data center, and avoid the situation of energy consumption trade-off caused by single control; and establishing a thermal coupling relation between the temperature prediction model and the equipment by using the temperature prediction model, then uniformly regulating and controlling, and considering the constraint condition whether the predicted temperature is below a temperature threshold value, so that the reduction of energy consumption and the safe operation of the equipment are ensured.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a block diagram of the system of the present invention;
FIG. 2 is a flow chart of a simulated annealing algorithm of the present invention.
Detailed Description
The invention provides a data center energy consumption minimization-oriented job scheduling and machine room air conditioner (CRAC computer room air conditioner) regulation and control method, which is characterized in that a temperature prediction model is established through historical data of a machine room of a data center to realize temperature prediction, a thermal coupling relation between the set temperature of refrigeration equipment and the operating temperature of IT equipment is established through the temperature prediction model, the temperature of the machine room is ensured to be within a safety threshold value during job scheduling and refrigeration equipment control, and the problems of hot spots and cooling lag are avoided through reasonable setting of a prediction view field due to the fact that the temperature is based on the predicted temperature. The overall regulation and control of the operation scheduling and the refrigeration equipment aim to minimize the overall energy consumption of the data center and avoid the condition of energy consumption trade off caused by single regulation and control; and establishing a thermal coupling relation between the temperature prediction model and the equipment by using the temperature prediction model, then uniformly regulating and controlling, and considering the constraint condition whether the predicted temperature is below a temperature threshold value, so that the reduction of energy consumption and the safe operation of the equipment are ensured.
Referring to fig. 1, the present invention provides a method for scheduling jobs and controlling a Computer Room Air Conditioner (CRAC) oriented to minimization of energy consumption of a data center, including a data center and a data center overall energy consumption model, the data center comprises refrigeration equipment and IT equipment, the data center respectively sends the acquired data to the data center overall energy consumption model and the data center temperature prediction model, the data center overall energy consumption model determines an objective function with minimum energy consumption estimation and sends the objective function to the data center scheduling strategy and the refrigeration system configuration strategy, the data center temperature prediction model determines the constraint of temperature prediction below a threshold value and sends the constraint to the data center scheduling strategy and the refrigeration system configuration strategy, and the data center is regulated and controlled by the data center and sends the regulated and controlled state to the data center overall energy consumption model and the data center temperature prediction model respectively.
The data center energy consumption minimization oriented job scheduling and machine room air conditioner (CRAC) regulation and control method comprises the following specific steps:
s1, establishing a dynamic energy consumption model P regulated by a data center job distribution matrix A and a CRACDC；
The application resource matrix T of the job in queue (Task) is specifically:
Figure BDA0002313365690000061
where n is the number of jobs, each Task applies for p resources, and the execution time of all jobs is assumed to be the same and is represented by a constant L.
The Server (Server) current state matrix S specifically includes:
Figure BDA0002313365690000062
wherein, each server of m servers is represented by p parameters, each Task is represented by the same number of parameters, and only the Task application resources are considered to be cpu and memory mem.
A refrigeration equipment (CRAC) state matrix C, specifically:
Figure BDA0002313365690000063
where k CRACs, tk represents set temperatures, and fk represents CRAC blower rates.
The job allocation matrix a specifically includes:
Figure BDA0002313365690000064
the j belongs to {0,1}, n is the number of the jobs, m servers in the cluster are assumed to be independent of each other, no dependency exists, the performances of the servers in the cluster are consistent, and the j is 1, which means that the j-th task is distributed to the ith server.
Dynamic energy consumption model in L period:
CRAC Power consumption Pcrac(tcracAnd f) is expressed as a set temperature tcracTemperature t of return air0As a function of blower speed f, as follows:
Pcrac(tcrac,f)＝w0|t0-tCRAC|x+w1|t0-tCRAC+w2f+w3
wherein, w0，w1，w2，w3For the experimental calculation of the coefficient, L is the job execution duration.
Server power consumption Pserver(ucpu,umem) Representing CPU utilization ucpuAnd memory utilization umemThe functional relationship of (1) is as follows:
Figure BDA0002313365690000071
wherein u is0，u1，u2，u3X is an experimentally calculated coefficient, ucpuAnd umemRespectively representing the occupancy rates of the CPU and the Mem, and the value range is 0-100.
Data center overall dynamic energy consumption model PDCThere are m servers, n tasks to be distributed, k refrigeration plants, expressed as:
Figure BDA0002313365690000072
wherein, PcFor CRAC energy consumption, PsFor server energy consumption, C is a CRAC state matrix, S is a Servers current state matrix, T is a Task queue application resource matrix, and A is a job distribution matrix.
S2, establishing a data center temperature prediction model;
due to the complex thermal coupling relationships of data centers, common methods for temperature prediction of data centers are divided into thermodynamic solutions based on fluid mechanics and prediction models based on neural networks. Because the thermodynamics-based method for simulating temperature evolution has strong dependence on the machine room environment, the method uses a neural network-based temperature prediction model which has good adaptability and is convenient for real-time prediction.
The invention uses a model based on a Recurrent Neural Network (RNN) to predict the temperature, because the change of the temperature is gradual, for the time point to be measured, the recurrent neural network not only considers the data of the current time, but also considers the influence of the previous time on the predicted point, and accords with the rule that the temperature is gradual.
Respectively establishing a server air inlet temperature prediction model for each server by using [ cpu, mem, t ]in，tout，tCRAC，f]Training model with data samples, wherein cpu, mem, tin，toutRespectively showing the current server cpu, the memory service condition, the air inlet temperature and the air outlet temperature, tCRACAnd f represents the set temperature and blower speed of the CRAC group in the computer room, the prediction horizon is taken to be 5 minutes, and the output of the model is the server inlet temperature after 5 minutes.
S3, adjusting CRAC status and job assignmentDCMinimizing, i.e. adjusting the matrices C and a to C 'and a', satisfying the following constraints:
Figure BDA0002313365690000081
and is
Figure BDA0002313365690000082
S+A′T＜＝S#
Where S # represents the maximum limit for all server resources.
Forecast(C′，S+A′T)＜T#
Where T # represents the maximum threshold for all server inlet temperatures.
Each IT device has a temperature prediction model, and the temperature prediction model uses C' used and the resource condition of the local device after job deployment.
To P isDCMinimization, an optimal solution is sought using a simulated annealing algorithm (SA), as shown in fig. 2.
And after the operation comes, taking N tasks from the operation queue, then acquiring real-time monitoring data, distributing the operation and regulating the CRAC by the SA to enable the energy consumption of the server to be minimum, ending the operation if the setting is successful, executing N-1 if the setting is unsuccessful, and returning to take the N tasks from the operation queue again.
The algorithm is as follows: job scheduling and CRAC configuration method
Inputting: n job (Task) application resource matrix T, M Server Current State matrix S
And (3) outputting: job assignment matrix a (mxn); CRAC configuration matrix C
Figure BDA0002313365690000091
In summary, the invention is directed to research on a data center-oriented job scheduling and CRAC control method for optimizing energy consumption, so that the energy consumption of IT equipment and refrigeration equipment is the lowest on the premise of ensuring the temperature safety requirement of the data center.
The above-mentioned contents are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modification made on the basis of the technical idea of the present invention falls within the protection scope of the claims of the present invention.

Claims (4)

1. The method for scheduling the operation and regulating and controlling the air conditioner in the machine room facing the minimization of the energy consumption of the data center is characterized in that a dynamic energy consumption model P regulated and controlled by a data center operation distribution matrix A, CRAC is firstly respectively established through historical data of the machine room of the data centerDCAnd a data center temperature prediction model; establishing thermal coupling relation between set temperature of refrigeration equipment and operating temperature of IT equipment through a data center temperature prediction model, ensuring that the temperature of a data center machine room is within a constraint condition when performing operation scheduling and refrigeration equipment control, and adopting simulated annealingThe algorithm enables P to be adjusted by adjusting CRAC state and overall regulation and control of refrigeration equipmentDCMinimization and reduction of the overall energy consumption of the data center;
data center overall dynamic energy consumption model PDCThere are m servers, k refrigeration plants, denoted as:
PDC＝Pcrac(C)+Pserver(S+AT)
wherein, PcracFor CRAC power consumption, PserverFor Server power consumption, C is a CRAC state matrix, S is a Servers current state matrix, T is a Task queue application resource matrix, and a is an operation allocation matrix, which specifically includes:
Figure FDA0002715379910000011
wherein, n is the number of jobs, Aij belongs to {0,1}, Aij equals 1, which indicates that the jth task is allocated to the ith server;
the constraint conditions include:
Figure FDA0002715379910000012
and is
Figure FDA0002715379910000013
S+A′T＜＝S#
Forecast(C′，S+A′T)＜T#
Wherein, Aij belongs to {0,1}, m represents the number of servers in the cluster, n represents the number of jobs, S # represents the maximum limit of all server resources, T # represents the maximum threshold of all server inlet temperatures, and C 'and A' represent adjusted matrixes C and A.
2. The data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method according to claim 1, wherein the current state matrix S of the server is specifically as follows:
Figure FDA0002715379910000021
wherein each server is represented by p parameters.
3. The data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method as claimed in claim 1, wherein the refrigeration equipment state matrix C is specifically:
Figure FDA0002715379910000022
where tk denotes the set temperature of the kth CRAC and fk denotes the kth CRAC blower rate.
4. The data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method as claimed in claim 1, wherein the data center temperature prediction model is a data center temperature prediction model based on a recurrent neural network, a server air inlet temperature prediction model is respectively established for each server, and [ cpu, mem, t ] is usedin，tout，tCRAC，f]Training model with data samples, wherein cpu, mem, tin，toutRespectively showing the current server cpu, the memory service condition, the air inlet temperature and the air outlet temperature, tCRACAnd f denotes the set temperature and blower rate for the room CRAC group.
CN201911267853.0A 2019-12-11 2019-12-11 Data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method Active CN111174375B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911267853.0A CN111174375B (en) 2019-12-11 2019-12-11 Data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911267853.0A CN111174375B (en) 2019-12-11 2019-12-11 Data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method

Publications (2)

Publication Number Publication Date
CN111174375A CN111174375A (en) 2020-05-19
CN111174375B true CN111174375B (en) 2021-02-02

Family

ID=70657146

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911267853.0A Active CN111174375B (en) 2019-12-11 2019-12-11 Data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method

Country Status (1)

Country Link
CN (1) CN111174375B (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112888268B (en) * 2021-02-04 2022-08-09 中国工商银行股份有限公司 Energy-saving control method, device and equipment for data center machine room and storage medium
CN115875809A (en) * 2021-09-26 2023-03-31 中国移动通信集团浙江有限公司 Energy-saving method and device for heat exchange equipment of machine room and computer readable storage medium
CN114996093B (en) * 2022-06-08 2023-02-03 三峡智控科技有限公司 Intelligent inspection optimization method for energy-saving system of data center
CN117289765A (en) * 2022-06-23 2023-12-26 华为技术有限公司 Control method, device, equipment and system of liquid cooling system
CN115220900B (en) * 2022-09-19 2022-12-13 山东省计算中心（国家超级计算济南中心） Energy-saving scheduling method and system based on operation power consumption prediction
CN116193819B (en) * 2023-01-19 2024-02-02 中国长江三峡集团有限公司 Energy-saving control method, system and device for data center machine room and electronic equipment
CN117150580B (en) * 2023-08-15 2024-04-02 速度科技股份有限公司 Data storage hardware safety protection system of intelligent database

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104698843A (en) * 2015-02-06 2015-06-10 同济大学 Model prediction control based energy saving control method of data center
WO2017025696A1 (en) * 2015-08-07 2017-02-16 Khalifa University of Science, Technology, and Research Methods and systems for workload distribution
CN106528941A (en) * 2016-10-13 2017-03-22 内蒙古工业大学 Data center energy consumption optimization resource control algorithm under server average temperature constraint
CN109189190A (en) * 2018-10-16 2019-01-11 西安交通大学 A kind of data center's thermal management method based on temperature prediction
CN109375994A (en) * 2018-09-10 2019-02-22 西安交通大学 Data center's task temperature prediction and dispatching method based on RBF neural
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
CN109871268A (en) * 2019-01-10 2019-06-11 暨南大学 A kind of energy-saving scheduling method based on air current composition at data-oriented center
EP3525563A1 (en) * 2018-02-07 2019-08-14 ABB Schweiz AG Method and system for controlling power consumption of a data center based on load allocation and temperature measurements

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104698843A (en) * 2015-02-06 2015-06-10 同济大学 Model prediction control based energy saving control method of data center
WO2017025696A1 (en) * 2015-08-07 2017-02-16 Khalifa University of Science, Technology, and Research Methods and systems for workload distribution
CN106528941A (en) * 2016-10-13 2017-03-22 内蒙古工业大学 Data center energy consumption optimization resource control algorithm under server average temperature constraint
EP3525563A1 (en) * 2018-02-07 2019-08-14 ABB Schweiz AG Method and system for controlling power consumption of a data center based on load allocation and temperature measurements
CN109375994A (en) * 2018-09-10 2019-02-22 西安交通大学 Data center's task temperature prediction and dispatching method based on RBF neural
CN109189190A (en) * 2018-10-16 2019-01-11 西安交通大学 A kind of data center's thermal management method based on temperature prediction
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
CN109871268A (en) * 2019-01-10 2019-06-11 暨南大学 A kind of energy-saving scheduling method based on air current composition at data-oriented center

Also Published As

Publication number Publication date
CN111174375A (en) 2020-05-19

Similar Documents

Publication Publication Date Title
CN111174375B (en) Data center energy consumption minimization-oriented job scheduling and machine room air conditioner regulation and control method
CN109800066B (en) Energy-saving scheduling method and system for data center
CN109189190B (en) Data center heat management method based on temperature prediction
CN109375994B (en) Data center task temperature prediction and scheduling method based on RBF neural network
CN104698843B (en) A kind of data center's energy-saving control method based on Model Predictive Control
Fang et al. Thermal-aware energy management of an HPC data center via two-time-scale control
Fang et al. Qos-driven power management of data centers via model predictive control
CN107404409B (en) Method and system for predicting quantity of container cloud flexible supply containers for sudden load
CN104991830A (en) YARN resource allocation and energy-saving scheduling method and system based on service level agreement
CN104158754B (en) Based on heat load data center's adaptivity Power Management method in a balanced way
CN101655272A (en) Energy-saving control management system of network central air conditioner and method thereof
Yao et al. Adaptive power management through thermal aware workload balancing in internet data centers
CN114063545B (en) Data center energy consumption control system and method fusing edge calculation and controller
CN114816699A (en) Data center job scheduling method and system based on temperature prediction
CN115081220A (en) Adjusting method and system for high-energy-efficiency central air-conditioning system
CN113028599B (en) Heating ventilation air conditioner monitoring system and method based on cloud platform
CN113064480B (en) Multi-data center collaborative energy saving method based on multi-agent reinforcement learning
CN111083201B (en) Energy-saving resource allocation method for data-driven manufacturing service in industrial Internet of things
CN116028193B (en) Big data task dynamic high-energy-efficiency scheduling method and system for mixed part cluster
CN113225994A (en) Intelligent air conditioner control method facing data center
CN111935952A (en) Large machine room energy consumption regulation and control method and device
CN103873576A (en) Monitoring and management method and system based on virtual system
CN113632132A (en) Computer-aided energy management method and energy management system
Fang et al. Using model predictive control in data centers for dynamic server provisioning
CN106507640A (en) A kind of server admin strategy of green data center temperature sensing

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