CN111935952B - Large machine room energy consumption regulation and control method and device - Google Patents
Large machine room energy consumption regulation and control method and device Download PDFInfo
- Publication number
- CN111935952B CN111935952B CN202010794074.2A CN202010794074A CN111935952B CN 111935952 B CN111935952 B CN 111935952B CN 202010794074 A CN202010794074 A CN 202010794074A CN 111935952 B CN111935952 B CN 111935952B
- Authority
- CN
- China
- Prior art keywords
- cabinet
- energy consumption
- neural network
- artificial neural
- network model
- 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
Images
Classifications
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
- H05K7/00—Constructional details common to different types of electric apparatus
- H05K7/20—Modifications to facilitate cooling, ventilating, or heating
- H05K7/20709—Modifications to facilitate cooling, ventilating, or heating for server racks or cabinets; for data centers, e.g. 19-inch computer racks
- H05K7/20718—Forced ventilation of a gaseous coolant
- H05K7/20745—Forced ventilation of a gaseous coolant within rooms for removing heat from cabinets, e.g. by air conditioning device
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention belongs to the technical field of artificial intelligence, and provides a method and a device for regulating and controlling energy consumption of a large machine room, wherein the method for regulating and controlling the energy consumption of the large machine room comprises the following steps: acquiring the total power of all servers in each cabinet in a large-scale machine room, the number of virtualization schedulable units deployed in each cabinet and the air inlet temperature of each cabinet, wherein the virtualization schedulable units comprise: POD, container and/or virtual machine; and regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualized schedulable units, the air inlet temperature and a preset artificial neural network model. The method and the device for regulating and controlling the energy consumption of the large machine room can reduce the temperature of the air inlet of the cabinet and eliminate local hot spots; and further, the cold quantity supply of the air conditioner in the machine room can be adjusted, and the total energy consumption of the large machine room is reduced.
Description
Technical Field
The invention relates to the technical field of block chains, in particular to application of a block chain technology in the financial field, and specifically relates to a method and a device for regulating and controlling energy consumption of a large machine room.
Background
The energy consumption of a data center consists of the following two parts: energy consumption of IT equipment and energy consumption of other auxiliary equipment. The parameter characterizing the energy efficiency level of a data center is PUE, which is defined as the ratio of the total energy consumption of a data center to the energy consumption of IT equipment. The energy consumption of the refrigeration equipment accounts for most of the energy consumption of other auxiliary equipment in the data center. With the rapid development of cloud computing technology, as a physical platform of cloud computing, data centers around the world have also been developed unprecedentedly. The rapidly increasing number of data centers also causes significant energy consumption overhead for operators. The energy consumption of large data centers has continued to increase year by year.
Disclosure of Invention
The invention belongs to the technical field of artificial intelligence, and aims at solving the problems in the prior art, the energy consumption regulation and control method and the energy consumption regulation and control device for the large machine room provided by the invention can reduce the energy consumption of the refrigeration equipment in the large machine room and the energy consumption of the IT equipment in the machine room, thereby realizing energy conservation in two aspects and being beneficial to prolonging the service life of the IT equipment in the large machine room.
In order to solve the technical problems, the invention provides the following technical scheme:
in a first aspect, the invention provides a method for regulating and controlling energy consumption of a large machine room, which comprises the following steps:
acquiring the total power of all servers in each cabinet in a large-scale machine room, the number of virtualization schedulable units deployed in each cabinet and the air inlet temperature of each cabinet, wherein the virtualization schedulable units comprise: POD, container and/or virtual machine;
and regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualized schedulable units, the air inlet temperature and a preset artificial neural network model.
In one embodiment, the artificial neural network model is generated by:
determining the number of nodes of an input layer of the artificial neural network model according to the number of the virtualization schedulable units;
calculating a vector element value of the input layer according to the total power of all the servers in each cabinet and the air inlet temperature of each cabinet;
determining the number of nodes of a hidden layer and the number of nodes of an output layer of the artificial neural network model according to a preset training constraint condition;
generating an initial model of the artificial neural network model according to the number of the nodes of the input layer, the vector element value of the input layer, the number of the nodes of the hidden layer and the number of the nodes of the output layer by using an artificial neural network algorithm;
training an initial model of the artificial neural network model according to a preset training constraint condition to generate the artificial neural network model of each cabinet; the preset training constraint conditions comprise: and the temperature of the air inlet reaches a preset temperature range and/or the training times reach a preset value.
In an embodiment, the adjusting and controlling the energy consumption of each cabinet according to the total power, the number of the virtual schedulable units, the air inlet temperature, and a preset artificial neural network model includes:
comparing the temperature of the air inlet of each cabinet with the preset temperature range to generate an input sequence;
traversing the combination of the virtualization schedulable units in each cabinet in the input sequence, and inputting the combination to the artificial neural network model of the corresponding cabinet to generate an energy consumption regulation result.
In one embodiment, the energy consumption regulation result includes: the energy consumption regulation and control result is within a preset temperature range, and the total power corresponding to the energy consumption regulation and control result reaches a preset range.
In an embodiment, the method for regulating and controlling energy consumption of a large-scale machine room further includes: and updating the artificial neural network model at a preset time period.
In a second aspect, the present invention provides an energy consumption control device for a large machine room, including:
a data obtaining unit, configured to obtain a total power of all servers in each cabinet in a large-scale computer room, a number of virtualization schedulable units deployed in each cabinet, and an air inlet temperature of each cabinet, where the virtualization schedulable units include: POD, container and/or virtual machine;
and the energy consumption regulation and control unit is used for regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualization schedulable units, the air inlet temperature and a preset artificial neural network model.
In one embodiment, the energy consumption control device for a large-scale machine room further includes a model generation unit for generating an artificial neural network model, and the model generation unit includes:
the input quantity determining module is used for determining the quantity of nodes of an input layer of the artificial neural network model according to the quantity of the virtualization schedulable units;
the element value calculating module is used for calculating a vector element value of the input layer according to the total power of all the servers in each cabinet and the air inlet temperature of each cabinet;
the output node determining module is used for determining the number of nodes of a hidden layer and the number of nodes of an output layer of the artificial neural network model according to a preset training constraint condition;
the initial model generation module is used for generating an initial model of the artificial neural network model according to the number of the nodes of the input layer, the vector element value of the input layer, the number of the nodes of the hidden layer and the number of the nodes of the output layer by using an artificial neural network algorithm;
the initial model training module is used for training an initial model of the artificial neural network model according to preset training constraint conditions so as to generate the artificial neural network model of each cabinet; the preset training constraint conditions comprise: and the temperature of the air inlet reaches a preset temperature range and/or the training times reach a preset value.
In one embodiment, the energy consumption control device for a large-scale machine room further comprises: the model updating unit is used for updating the artificial neural network model in a preset period; the energy consumption regulation and control unit comprises:
the input sequence generation module is used for comparing the air inlet temperature of each cabinet with the preset temperature range to generate an input sequence;
the result generation module is used for traversing the combination of the virtualization schedulable units in each cabinet in the input sequence and inputting the combination into the artificial neural network model of the corresponding cabinet to generate an energy consumption regulation and control result;
the energy consumption regulation and control result comprises the following steps: the energy consumption regulation and control result is within a preset temperature range, and the total power corresponding to the energy consumption regulation and control result reaches a preset range.
In a third aspect, the present invention provides an electronic device, which includes a memory, a processor, and a computer program that is stored in the memory and is executable on the processor, and when the processor executes the computer program, the method for regulating and controlling energy consumption in a large-scale computer room is implemented.
In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the method for regulating and controlling energy consumption in a large-scale computer room.
As can be seen from the above description, in the method and the apparatus for regulating and controlling energy consumption of a large-scale computer room according to the embodiments of the present invention, first, the total power of all servers in each cabinet in the large-scale computer room, the number of the virtualized schedulable units deployed in each cabinet, and the air inlet temperature of each cabinet are obtained, where the virtualized schedulable units include: POD, container and/or virtual machine; and regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualized schedulable units, the air inlet temperature and a preset artificial neural network model. The invention can reduce the temperature of the air inlet of the cabinet and eliminate local hot spots; and further, the cooling capacity supply of the air conditioner in the machine room can be adjusted, and the total energy consumption of the large machine room is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a large-scale machine room energy consumption regulation and control method in an embodiment of the invention;
FIG. 2 is a flowchart of step 300 in an embodiment of the present invention;
FIG. 3 is a flowchart of step 200 in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a large-scale machine room structure in an embodiment of the present invention;
FIG. 5 is a schematic flow chart of a method for regulating and controlling energy consumption of a large-scale machine room in a specific application example of the present invention;
FIG. 6 is a schematic flow chart of step S1 in an embodiment of the present invention;
FIG. 7 is a schematic structural diagram of a cabinet A according to an embodiment of the present invention;
FIG. 8 is a flowchart illustrating a method for generating an artificial neural network according to an embodiment of the present invention;
FIG. 9 is a flowchart illustrating step S2 according to an embodiment of the present invention;
FIG. 10 is a diagram illustrating an energy consumption regulation result in an embodiment of the present invention;
fig. 11 is a first structural block diagram of an energy consumption control device of a large-scale machine room in an embodiment of the present invention;
fig. 12 is a structural block diagram ii of an energy consumption control device of a large-scale machine room in the embodiment of the present invention;
FIG. 13 is a block diagram of a model generation unit according to an embodiment of the present invention;
fig. 14 is a structural block diagram of a large-scale machine room energy consumption regulating and controlling device in the embodiment of the invention;
fig. 15 is a block diagram of an energy consumption adjusting unit according to an embodiment of the present invention;
fig. 16 is a schematic structural diagram of an electronic device in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, 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 will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of this application and the above-described drawings are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In the large-scale machine room component module, the installed IT equipment consumes power and generates heat due to the calculation and storage functions, and the machine room air conditioner is required to provide cold energy to take away heat, so that the electric energy of the air conditioner is also consumed. The cold supply of the air conditioner enables the temperature of the air inlet of each cabinet to be kept within a desired temperature range, such as 23 +/-1 ℃ required by the old national standard, and 18-27 ℃ after the new national standard GB50174 is released in 2017.
Within a room module, the cabinets are typically deployed in a "face-to-face, back-to-back" manner, forming cold aisles and hot aisles. Cold air enters the cabinet from the cold channel at the front part of the cabinet and takes away heat and then goes out from the hot channel at the back part of the cabinet. And a temperature sensor is arranged at the air inlet of each cabinet, so that the temperature of the air inlet of the cabinet is acquired in real time. The machine room air conditioner ensures that the temperature of the air inlet of the cold channel of each cabinet is in a desired range. A server is deployed in the cabinet. Because the servers installed in each cabinet have different power consumptions (caused by differences in the number, model and load of the servers), different machine room environments (caused by differences in the layout of air conditioners at the tail end of the machine room, the layout of the cabinets and the airflow organization), and different demands of each cabinet on cooling capacity. The cooling capacity supply setting (usually the temperature set value of the air conditioner in the machine room) for the air conditioner at the tail end of the machine room needs to be capable of meeting the requirement that the temperature of the air inlet of the cabinet with the largest cooling capacity requirement is within an expected range. If there are local hot spots in one machine room module, i.e. the temperature in one location is much higher than the temperature in other locations, more cooling energy supply is needed. Under the condition, after the local hot spots are eliminated, the cold quantity supply of the air conditioner at the tail end of the machine room can be reduced, and the purpose of energy conservation is achieved.
In view of the above, an embodiment of the present invention provides a specific implementation manner of a method for regulating and controlling energy consumption of a large-scale machine room, and referring to fig. 1, the method specifically includes the following steps:
step 100: acquiring the total power of all servers in each cabinet in a large-scale machine room, the number of virtualized schedulable units deployed in each cabinet and the air inlet temperature of each cabinet, wherein the virtualized schedulable units comprise: POD, container, and/or virtual machine.
Specifically, the temperature of each cabinet air inlet is collected through a temperature sensor installed in each cabinet. The method comprises the steps that the total power of all servers in each cabinet is collected according to a power distribution unit in each cabinet, and further, the instantaneous power of all installed servers of the cabinet can be collected through an intelligent PDU (power distribution unit) in the cabinet; and then the total power of all the servers in the cabinet is obtained.
It is understood that virtualizing the schedulable units in step 100 includes: POD, container, or virtual machine; POD refers to kubernets (K8 s, open source container cluster management system), POD represents a container or a combination of multiple containers, which is the most basic scheduling and operating unit in kubernets, and K8s is a cluster with a central node architecture, and consists of Master nodes and nodes. The request such as container starting of the client is firstly sent to the master node, and the master node is provided with a scheduler which can analyze the available state of node resources (CPU and memory) and find the best-adapted node to start the container requested by the user. The Master Node is responsible for management and control, the Node is a workload Node, and a specific container is arranged in the Node.
Step 200: and regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualized schedulable units, the air inlet temperature and a preset artificial neural network model.
Specifically, the total power of a specific cabinet, the number of the virtualized schedulable units, and the air inlet temperature are input into the artificial neural network model of the cabinet to meet preset conditions (e.g., the temperature after regulation is within a preset temperature range, and the total power of the cabinet after regulation is the lowest in all schemes).
As can be seen from the above description, in the energy consumption control method for a large-scale computer room according to the embodiment of the present invention, first, the total power of all servers in each cabinet in the large-scale computer room, the number of the virtualized schedulable units deployed in each cabinet, and the air inlet temperature of each cabinet are obtained, where the virtualized schedulable units include: POD, container and/or virtual machine; and regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualized schedulable units, the air inlet temperature and a preset artificial neural network model. The invention can reduce the temperature of the air inlet of the cabinet and eliminate local hot spots; and further, the cold quantity supply of the air conditioner in the machine room can be adjusted, and the total energy consumption of the large machine room is reduced.
In an embodiment, the method for regulating and controlling energy consumption of the large-scale machine room further includes:
step 300: and generating an artificial neural network model. Referring to fig. 2, step 300 further includes:
step 301: determining the number of nodes of an input layer of the artificial neural network model according to the number of the virtualization schedulable units;
step 302: calculating a vector element value of the input layer according to the total power of all the servers in each cabinet and the air inlet temperature of each cabinet;
step 303: determining the number of nodes of a hidden layer and the number of nodes of an output layer of the artificial neural network model according to preset training constraint conditions;
in steps 301 to 303, the types of processing units in the artificial neural network are classified into three types: an input layer, an output layer, and a hidden layer. Each layer has respective nodes (neurons), and the input layer receives signals and data of the outside world; the output unit realizes the output of the system processing result; an implied layer is a unit that is located between the input layer and the output layer and cannot be viewed from outside the system. The connection weight between the neurons reflects the connection strength between the units, and the representation and the processing of the information are reflected in the connection relation of the network processing unit. The essence of the method is that a parallel distributed information processing function is obtained through the transformation and dynamic behavior of a network, and the information processing function of a human cranial nerve system is simulated in different degrees and layers.
Step 304: generating an initial model of the artificial neural network model according to the number of the nodes of the input layer, the vector element value of the input layer, the number of the nodes of the hidden layer and the number of the nodes of the output layer by using an artificial neural network algorithm;
it will be appreciated that the initial model in step 304 is an untrained artificial neural network model, and the parameters are initial parameters, typically default values for the system. Through the processes of model training, model self-learning and the like, the initial model is gradually changed into an artificial neural network model (final model). Step 304 is essentially the initialization of the artificial neural network model.
Step 305: training an initial model of the artificial neural network model according to a preset training constraint condition to generate the artificial neural network model of each cabinet;
it is understood that the preset training constraints include: and the temperature of the air inlet reaches a preset temperature range and/or the training times reach a preset value. In addition, hundreds or even thousands of cabinets exist in the large machine room, and a plurality of servers exist in each cabinet, so that if an artificial neural network model is adopted to optimize the energy consumption of all the servers of the large machine room, the regulation and control speed can be greatly reduced.
In one embodiment, referring to fig. 3, step 200 further comprises:
step 201: comparing the temperature of the air inlet of each cabinet with the preset temperature range to generate an input sequence;
preferably, an input sequence is generated according to the number of the cabinet with the temperature greater than the preset temperature range; the cabinet temperature in the input sequence is changed from high to low.
Step 202: traversing the combination of the virtualization schedulable units in each cabinet in the input sequence, and inputting the combination to the artificial neural network model of the corresponding cabinet to generate an energy consumption regulation result.
Specifically, in step 201 and step 202, when a trigger condition of an energy consumption scheduling algorithm (artificial neural network model) is met, energy consumption scheduling is started, and first, cabinets in the machine room module are divided into three types, wherein one type is that the temperature of an air inlet is within an average temperature range, and the cabinet type is not adjusted; the second type is that the temperature of the air inlet is larger than the average temperature range, the third type is that the temperature of the air inlet is smaller than the average temperature range, and a part of the virtualized schedulable unit on the server in the second type cabinet needs to be migrated to the server of the third type cabinet; and calculating each second and third type of cabinets according to the artificial neural network model to obtain the quantity of the virtual schedulable units which can be deployed by each server in the cabinet when the temperatures of the air inlets of the two types of cabinets reach the average temperature. Traversing the combination of the number of the virtualization schedulable units deployed on each server in the cabinet as the input of the artificial neural network, and obtaining the output of the temperature of the air inlet of the cabinet and the power consumption of the cabinet. The input with the output as the average temperature range is the desired deployment number combination. And if a plurality of groups of expected inputs are obtained, the scheme with the lowest power consumption of the cabinet is selected and output.
In one embodiment, the energy consumption regulation result includes: the energy consumption regulation and control result comprises the following steps: the energy consumption regulation and control result is within a preset temperature range, and the total power corresponding to the energy consumption regulation and control result reaches a preset range.
Preferably, the total power of the finally selected energy consumption regulation and control result in the multiple energy consumption regulation and control result schemes is the minimum value, so that the energy consumption of the large machine room is better saved.
In an embodiment, the method for regulating and controlling energy consumption of the large-scale machine room further includes: and updating the artificial neural network model at a preset period.
Specifically, in the operation process, sample data is continuously collected according to a certain period to train and update the model.
As can be seen from the above description, in the energy consumption control method for the large-scale machine room according to the embodiment of the present invention, the number of the virtualized schedulable units (POD, container, or virtual machine) running on the server installed in each cabinet in the large-scale machine room, the total power consumption actual power of the servers installed in the cabinets, and the temperature of the air inlets of the cabinets are collected, and then, an artificial neural network model is established; during optimized scheduling, generating a list of the cabinet to be migrated and the target cabinet, a list of the number of the virtualized schedulable units to be migrated and a list of the number of the receiving virtualized schedulable units of the migration target server according to the acquired temperature of the air inlet of the cabinet; after the migration is completed, the schedulable virtual units in the cabinet in the local hot spot area are redeployed, the power load of the cabinet is redeployed, and the power of the cabinet in the local hot spot area and the temperature of the air inlet are both reduced. Because the local hot spot is eliminated, the maximum refrigerating demand is reduced, the cold quantity supply of the air conditioner at the tail end of the machine room can be reduced, the energy consumption of the air conditioner of the machine room is reduced, and the energy conservation is realized. Meanwhile, the invention reduces the power consumption of IT equipment to a certain extent and realizes energy conservation based on the principle of lowest cabinet power during dispatching. The invention simultaneously reduces the energy consumption of IT equipment and refrigeration equipment in the machine room, and realizes energy conservation from two aspects.
To further explain the scheme, the invention provides a specific application example of the energy consumption regulation and control method for the large-scale machine room, which specifically comprises the following contents.
In the prior art, fig. 4 is a schematic diagram of a machine room module having four rows of cabinets (two groups of cold channels) and four terminal machine room air conditioners, and when loads of the cabinets in the machine room are different, the situations of local overheating and local supercooling will occur, which causes waste of cooling capacity of the air conditioner. At this time, two energy-saving methods are used for optimization adjustment, one is to differentially and dynamically adjust the cooling capacity supply (air conditioner temperature set value) of each air conditioner in the machine room, control the air inlet temperature of each cabinet to reach a desired value, and perform accurate refrigeration, but the method needs to establish a complex model of the machine room air conditioner temperature set value and the cabinet air inlet temperature, the model is multi-working-condition, and the model can be acquired only by greatly adjusting the machine room air conditioner temperature set value, and often cannot be satisfied. Another approach is to rearrange the IT load carried within each cabinet. The simplest method is to physically move one or more servers to a cabinet with low temperature for the cabinet with local hot spots and high temperature. However, the method relates to physical relocation of the server, has large workload, and cannot accurately estimate the number of the servers to be relocated and the effect after relocation.
With the development of cloud computing in recent years, a plurality of virtual machines, containers, and PODs (K8S environment) are deployed on one physical server. The virtual machine, the container, the POD are all schedulable units. After a part or all of the virtualized schedulable unit (virtual machine, container, POD) on one physical machine is migrated to another physical machine in the same machine room on line, the power consumption of the physical machine is reduced, so that the power consumption of the cabinet where the physical machine is located is reduced, the requirement on cooling capacity is reduced, and the temperature of the air inlet of the cabinet is reduced. The key of the method is how to perform the migration and the rearrangement of the schedulable unit when a local hot spot of the computer room occurs, namely, two problems exist, namely, where to migrate and how much to migrate. The invention provides a large-scale machine room energy consumption regulation and control method formally based on the thought.
Referring to fig. 5, the present embodiment generally includes two steps: firstly, establishing an artificial neural network model of the number of the virtualized schedulable units deployed on a server installed in each cabinet, the power consumption of the cabinet and the temperature of an air inlet of the cabinet; the second is the working step of the scheduling algorithm. The method comprises the following specific steps:
s1: and establishing an artificial neural network model of the number of the virtual schedulable units of each cabinet, the power consumption of the cabinet and the temperature of an air inlet of the cabinet.
Further, referring to fig. 6, step S1 again includes:
step S11: the number of virtualized schedulable units (PODs, containers, or virtual machines) deployed on installed servers within each cabinet is collected.
As illustrated in fig. 7, the cabinet a has 7 servers installed therein, and the virtualization management software can acquire the number of PODs, containers, or virtual machines deployed on each server.
Step S12: and the temperature of the air inlet of each cabinet is collected through a temperature sensor arranged in each cabinet.
Step S13: the instantaneous power of all installed servers in the cabinet can be collected through an intelligent PDU (power distribution unit) in the cabinet.
Step S14: and training the collected sample data to obtain an artificial neural network model. As exemplified in fig. 8.
Step S15: and in the operation process, continuously collecting sample data according to a certain period to train and update the model.
S2: and regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualized schedulable units, the air inlet temperature and a preset artificial neural network model.
Further, referring to fig. 9, step S2 again includes:
step S21: conditions are set for triggering the energy consumption scheduling.
If the number of the cabinets with the air inlet temperature not within the average temperature range (such as the average temperature plus or minus 1 ℃) in the machine room module is set to be more than 10% of the total number of the cabinets in the machine room. Or directly set an optimization period, such as a certain time point every day or every week. The trigger condition can be adjusted and set according to the actual condition;
step S22: and acquiring the air inlet temperature of each cabinet in the machine room module, the total power of the servers installed on each cabinet and the number of the virtualized schedulable units deployed on each server in each cabinet in real time, and updating the artificial neural network model.
Step S23: and (5) classifying the cabinets.
Specifically, when a triggering condition of an optimized scheduling algorithm is met, the scheduling algorithm is started, firstly, cabinets in the machine room module are divided into three types, one type is that the temperature of an air inlet is in an average temperature range, and the cabinet type is not adjusted; the second type is that the temperature of the air inlet is larger than the average temperature range, the third type is that the temperature of the air inlet is smaller than the average temperature range, and a part of the virtualized schedulable unit on the server in the second type cabinet needs to be migrated to the server of the third type cabinet; for convenience of explanation, the second type of cabinet is numbered from high to low according to the temperature of the air inlet: m of A1/A2/A3 … Am; the third type of cabinet is numbered as B1/B2/B3 … Bn from low to high according to the temperature of the air inlet, and the number of the third type of cabinet is n.
Step S24: and performing energy consumption regulation and control calculation on each of the second and third cabinets according to the artificial neural network model.
Specifically, the number of the virtual schedulable units that can be deployed by each server in the two types of cabinets when the air inlet temperatures of the cabinets reach the average temperature is obtained. Traversing the combination of the number of the virtualization schedulable units deployed on each server in the cabinet as the input of the artificial neural network, and obtaining the output of the temperature of the air inlet of the cabinet and the power consumption of the cabinet. The input with the output as the average temperature range is the desired deployment number combination. And if a plurality of groups of expected inputs are obtained, the group with the lowest power consumption of the cabinet is taken and output. An example is shown in fig. 10. 4 servers are installed on the cabinet C1, the number of the virtualization units deployed on the four servers is respectively 9, 7, 8 and 7 before migration, the temperature of an air inlet of the cabinet is 27 degrees, the electric power of the cabinet is 6KW, and the average temperature of the collected machine room modules is 23 degrees, so that the cabinet is the second type cabinet needing migration. Traversing the number of the virtualization units deployed on 4 servers by using the artificial neural network model of the cabinet obtained in step 202 to obtain two groups of input, wherein the temperatures of the output air inlets are 23 ℃, the power consumption is 5.8KW and 5.3KW respectively, and the input with the lower output power consumption of 5.3KW is taken as the virtualization units deployed on each server after the dispatching of the cabinet, that is, the number of the virtualization units deployed on the four servers from top to bottom is 7, 8 and 6 respectively. Thus, the 1 st server of the enclosure needs to be migrated out of 2 virtualization units, and the 4 th server of the enclosure needs to be migrated out of 1 virtualization unit.
Step S25: and for the A1/A2/A3 … Am cabinets, each cabinet respectively implements the step S24.
Obtaining the number of virtualization units to be migrated in each cabinet through step S25, and sequentially forming a queue AA; the number of the virtualization units needing to be migrated is X; and (4) respectively carrying out the step S4 on each cabinet in the B1/B2/B3 … Bn cabinets to obtain the number of the virtualization units which can be migrated in each cabinet, and sequentially forming a queue BB. The number of the virtualization units which can be migrated is Y; the virtual units to be migrated are sequentially migrated from the A1 cabinet to a group of cabinets started from the B1 cabinet, that is, the cabinets with the highest cabinet temperature start migration, and the cabinets which start to receive migration are the cabinets with the lowest cabinet temperature. When X is larger than Y, Y cabinets are migrated, and under the condition, the temperature of the air inlets of a small number of cabinets is slightly higher than the average temperature before scheduling migration after migration; when X < Y, X is transferred, and under the condition, the temperature of the air inlet of a small number of cabinets is slightly lower than the average temperature before the transfer after the transfer is finished.
Step S26: the cooling capacity supply of the air conditioner in the machine room is reduced.
Specifically, after the dispatching and the migration, local hot spots of the machine room modules are eliminated, the maximum requirement on cooling capacity is reduced, and at the moment, the cooling capacity supply of the machine room air conditioner can be properly reduced, so that the purpose of energy conservation is achieved.
As can be seen from the above description, in the energy consumption control method for a large-scale computer room according to the embodiment of the present invention, first, the total power of all servers in each cabinet in the large-scale computer room, the number of the virtualized schedulable units deployed in each cabinet, and the air inlet temperature of each cabinet are obtained, where the virtualized schedulable units include: POD, container and/or virtual machine; and regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualized schedulable units, the air inlet temperature and a preset artificial neural network model. The invention can reduce the temperature of the air inlet of the cabinet and eliminate local hot spots; and further, the cold quantity supply of the air conditioner in the machine room can be adjusted, and the total energy consumption of the large machine room is reduced. Specifically, the invention has the following beneficial effects:
1. an artificial neural network model of the temperature of the air inlet of the cabinet and the total power of all the servers of the cabinet and the virtualized schedulable unit arranged on each server installed in each cabinet in the large-scale data computer room is established.
2. Based on the artificial neural network model, the virtual schedulable units deployed on the cabinet servers in the local hot spot area are scheduled, virtual resources are redeployed, and then the total power consumption of the cabinet is adjusted, the temperature of the air inlet of the cabinet is reduced, and local hot spots are eliminated; and further, the cooling capacity supply of the air conditioner in the machine room can be adjusted, and the energy consumption of the air conditioner is reduced.
3. When the virtual resources are redeployed, the energy consumption of the IT equipment can be reduced to a certain extent based on the principle that the power consumption of the cabinet is the lowest, so that the aim of saving energy is fulfilled.
Based on the same inventive concept, the embodiment of the present application further provides an energy consumption regulation and control device for a large-scale machine room, which can be used for implementing the method described in the above embodiment, such as the following embodiments. Because the principle of solving the problems of the large-scale machine room energy consumption regulating and controlling device is similar to that of the large-scale machine room energy consumption regulating and controlling method, the implementation of the large-scale machine room energy consumption regulating and controlling device can refer to the implementation of the large-scale machine room energy consumption regulating and controlling method, and repeated parts are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. While the system described in the embodiments below is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.
An embodiment of the present invention provides a specific implementation manner of a large-scale machine room energy consumption regulation and control device capable of implementing a large-scale machine room energy consumption regulation and control method, and referring to fig. 11, the large-scale machine room energy consumption regulation and control device specifically includes the following contents:
a data obtaining unit 10, configured to obtain a total power of all servers in each cabinet in a large-scale computer room, a number of virtualized schedulable units deployed in each cabinet, and an air inlet temperature of each cabinet, where the virtualized schedulable units include: POD, container, and/or virtual machine;
and the energy consumption regulation and control unit 20 is used for regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualization schedulable units, the air inlet temperature and a preset artificial neural network model.
In an embodiment, referring to fig. 12, the energy consumption control apparatus for a large-scale machine room further includes a model generating unit 30, configured to generate an artificial neural network model, referring to fig. 13, where the model generating unit 30 includes:
an input number determining module 301, configured to determine the number of nodes in an input layer of the artificial neural network model according to the number of the virtualized schedulable units;
an element value calculating module 302, configured to calculate a vector element value of the input layer according to the total power of all servers in each cabinet and the air inlet temperature of each cabinet;
an output node determining module 303, configured to determine, according to a preset training constraint condition, the number of nodes in a hidden layer and the number of nodes in an output layer of the artificial neural network model;
an initial model generating module 304, configured to generate an initial model of the artificial neural network model according to the number of nodes of the input layer, the vector element value of the input layer, the number of nodes of the hidden layer, and the number of nodes of the output layer by using an artificial neural network algorithm;
an initial model training module 305, configured to train an initial model of the artificial neural network model according to a preset training constraint condition, so as to generate the artificial neural network model for each cabinet; the preset training constraint conditions comprise: and the temperature of the air inlet reaches a preset temperature range and/or the training times reach a preset value.
In an embodiment, referring to fig. 14, the energy consumption control device for a large-scale machine room further includes: a model updating unit 40, configured to update the artificial neural network model at a preset period; referring to fig. 15, the energy consumption adjusting and controlling unit 20 includes:
an input sequence generating module 201, configured to compare the air inlet temperature of each cabinet with the preset temperature range, so as to generate an input sequence;
a result generating module 202, configured to traverse a combination of the virtualized schedulable units in each cabinet in the input sequence, and input the combination to an artificial neural network model of a corresponding cabinet to generate an energy consumption regulation result;
the energy consumption regulation and control result comprises the following steps: the energy consumption regulation and control result is within a preset temperature range, and the total power corresponding to the energy consumption regulation and control result reaches a preset range.
As can be seen from the above description, in the energy consumption control apparatus for a large-scale computer room provided in the embodiment of the present invention, first, the total power of all servers in each cabinet in the large-scale computer room, the number of the virtualized schedulable units deployed in each cabinet, and the air inlet temperature of each cabinet are obtained, where the virtualized schedulable units include: POD, container and/or virtual machine; and regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualized schedulable units, the air inlet temperature and a preset artificial neural network model. The invention can reduce the temperature of the air inlet of the cabinet and eliminate local hot spots; and further, the cold quantity supply of the air conditioner in the machine room can be adjusted, and the total energy consumption of the large machine room is reduced. Specifically, the invention has the following beneficial effects:
1. an artificial neural network model of the temperature of the air inlet of the cabinet and the total power of all the servers of the cabinet and the virtualized schedulable unit arranged on each server installed in each cabinet in the large-scale data computer room is established.
2. Based on the artificial neural network model, the virtual schedulable units deployed on the cabinet servers in the local hot spot area are scheduled, virtual resources are redeployed, and then the total power consumption of the cabinet is adjusted, the temperature of the air inlet of the cabinet is reduced, and local hot spots are eliminated; and further, the cold quantity supply of the air conditioner in the machine room can be adjusted, and the energy consumption of the air conditioner is reduced.
3. When the virtual resources are redeployed, the energy consumption of the IT equipment can be reduced to a certain extent based on the principle that the power consumption of the cabinet is the lowest, so that the aim of saving energy is fulfilled.
The apparatuses, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or implemented by a product with certain functions. A typical implementation device is an electronic device, which may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
In a typical example, the electronic device specifically includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the method for regulating and controlling energy consumption of a large-scale computer room is implemented, where the method includes:
step 100: acquiring the total power of all servers in each cabinet in a large-scale machine room, the number of virtualization schedulable units deployed in each cabinet and the air inlet temperature of each cabinet, wherein the virtualization schedulable units comprise: POD, container and/or virtual machine;
step 200: and regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualized schedulable units, the air inlet temperature and a preset artificial neural network model.
Referring now to FIG. 16, shown is a schematic diagram of an electronic device 600 suitable for use in implementing embodiments of the present application.
As shown in fig. 16, the electronic apparatus 600 includes a Central Processing Unit (CPU) 601 that can perform various appropriate jobs and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM)) 603. In the RAM603, various programs and data necessary for the operation of the system 600 are also stored. The CPU601, ROM602, and RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted as necessary on the storage section 608.
In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, an embodiment of the present invention includes a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for regulating and controlling energy consumption of a large-scale computer room, where the steps include:
step 100: acquiring the total power of all servers in each cabinet in a large-scale machine room, the number of virtualized schedulable units deployed in each cabinet and the air inlet temperature of each cabinet, wherein the virtualized schedulable units comprise: POD, container and/or virtual machine;
step 200: and regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualized schedulable units, the air inlet temperature and a preset artificial neural network model.
In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
For convenience of description, the above devices are described as being divided into various units by function, respectively. Of course, the functionality of the various elements may be implemented in the same one or more pieces of software and/or hardware in the practice of the present application.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (7)
1. A method for regulating and controlling energy consumption of a large machine room is characterized by comprising the following steps:
acquiring the total power of all servers in each cabinet in a large-scale machine room, the number of virtualization schedulable units deployed in each cabinet and the air inlet temperature of each cabinet, wherein the virtualization schedulable units comprise: POD, container and/or virtual machine;
regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualized schedulable units, the temperature of the air inlet and a preset artificial neural network model;
the artificial neural network model is generated by the following steps:
determining the number of nodes of an input layer of the artificial neural network model according to the number of the virtualization schedulable units;
calculating a vector element value of the input layer according to the total power of all the servers in each cabinet and the air inlet temperature of each cabinet;
determining the number of nodes of a hidden layer and the number of nodes of an output layer of the artificial neural network model according to a preset training constraint condition;
generating an initial model of the artificial neural network model according to the number of the nodes of the input layer, the vector element value of the input layer, the number of the nodes of the hidden layer and the number of the nodes of the output layer by using an artificial neural network algorithm;
training an initial model of the artificial neural network model according to preset training constraint conditions to generate the artificial neural network model of each cabinet; the preset training constraint conditions comprise: and the temperature of the air inlet reaches a preset temperature range and/or the training times reach a preset value.
2. The method for regulating and controlling the energy consumption of the large machine room according to claim 1, wherein the regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualized schedulable units, the air inlet temperature and a preset artificial neural network model comprises:
comparing the temperature of the air inlet of each cabinet with the preset temperature range to generate an input sequence;
traversing the combination of the virtualization schedulable units in each cabinet in the input sequence, and inputting the combination to the artificial neural network model of the corresponding cabinet to generate an energy consumption regulation result.
3. The energy consumption regulation and control method for the large machine room according to claim 2, wherein the energy consumption regulation and control result comprises: the energy consumption regulation and control result is within a preset temperature range, and the total power corresponding to the energy consumption regulation and control result reaches a preset range.
4. The energy consumption regulation and control method for the large machine room according to claim 1, further comprising: and updating the artificial neural network model at a preset time period.
5. The utility model provides a large-scale computer lab energy consumption regulation and control device which characterized in that includes:
a data obtaining unit, configured to obtain a total power of all servers in each cabinet in a large-scale computer room, a number of virtualized schedulable units deployed in each cabinet, and an air inlet temperature of each cabinet, where the virtualized schedulable units include: POD, container and/or virtual machine;
the energy consumption regulation and control unit is used for regulating and controlling the energy consumption of each cabinet according to the total power, the number of the virtualization schedulable units, the temperature of the air inlet and a preset artificial neural network model;
a model generation unit for generating an artificial neural network model, the model generation unit comprising:
the input quantity determining module is used for determining the quantity of nodes of an input layer of the artificial neural network model according to the quantity of the virtualization schedulable units;
the element value calculating module is used for calculating a vector element value of the input layer according to the total power of all the servers in each cabinet and the air inlet temperature of each cabinet;
the output node determining module is used for determining the number of nodes of a hidden layer and the number of nodes of an output layer of the artificial neural network model according to preset training constraint conditions;
an initial model generation module, configured to generate, by using an artificial neural network algorithm, an initial model of the artificial neural network model according to the number of nodes of the input layer, the vector element value of the input layer, the number of nodes of the hidden layer, and the number of nodes of the output layer;
the initial model training module is used for training an initial model of the artificial neural network model according to preset training constraint conditions so as to generate the artificial neural network model of each cabinet; the preset training constraint conditions comprise: and the temperature of the air inlet reaches a preset temperature range and/or the training times reach a preset value.
6. The energy consumption regulating and controlling device for the large machine room according to claim 5, further comprising: the model updating unit is used for updating the artificial neural network model in a preset period; the energy consumption regulation and control unit comprises:
the input sequence generation module is used for comparing the air inlet temperature of each cabinet with the preset temperature range to generate an input sequence;
the result generation module is used for traversing the combination of the virtualization schedulable units in each cabinet in the input sequence and inputting the combination into the artificial neural network model of the corresponding cabinet to generate an energy consumption regulation and control result;
the energy consumption regulation and control result comprises the following steps: the energy consumption regulation and control result is within a preset temperature range, and the total power corresponding to the energy consumption regulation and control result reaches a preset range.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method for regulating energy consumption of a large-scale computer room according to any one of claims 1 to 4 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010794074.2A CN111935952B (en) | 2020-08-10 | 2020-08-10 | Large machine room energy consumption regulation and control method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010794074.2A CN111935952B (en) | 2020-08-10 | 2020-08-10 | Large machine room energy consumption regulation and control method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111935952A CN111935952A (en) | 2020-11-13 |
| CN111935952B true CN111935952B (en) | 2022-12-23 |
Family
ID=73308126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010794074.2A Active CN111935952B (en) | 2020-08-10 | 2020-08-10 | Large machine room energy consumption regulation and control method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111935952B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113094325B (en) * | 2021-04-14 | 2024-02-20 | 中国工商银行股份有限公司 | Device deployment method, device, computer system and computer readable storage medium |
| CN114216227B (en) * | 2021-11-09 | 2023-03-07 | 珠海格力电器股份有限公司 | Control method of air conditioner in machine room, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102620378A (en) * | 2011-01-27 | 2012-08-01 | 国际商业机器公司 | Method and system for data center energy saving controlling |
| CN109600956A (en) * | 2018-12-10 | 2019-04-09 | 国家电网有限公司信息通信分公司 | A kind of data center server placement location optimization algorithm and system |
| CN110285532A (en) * | 2019-07-04 | 2019-09-27 | 中国工商银行股份有限公司 | Method for controlling machine room air conditioner, apparatus and system based on artificial intelligence |
-
2020
- 2020-08-10 CN CN202010794074.2A patent/CN111935952B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102620378A (en) * | 2011-01-27 | 2012-08-01 | 国际商业机器公司 | Method and system for data center energy saving controlling |
| CN109600956A (en) * | 2018-12-10 | 2019-04-09 | 国家电网有限公司信息通信分公司 | A kind of data center server placement location optimization algorithm and system |
| CN110285532A (en) * | 2019-07-04 | 2019-09-27 | 中国工商银行股份有限公司 | Method for controlling machine room air conditioner, apparatus and system based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111935952A (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kaur et al. | Container-as-a-service at the edge: Trade-off between energy efficiency and service availability at fog nano data centers | |
| Liu et al. | Job scheduling model for cloud computing based on multi-objective genetic algorithm | |
| CN105302630B (en) | A kind of dynamic adjusting method and its system of virtual machine | |
| CN106534318B (en) | A kind of OpenStack cloud platform resource dynamic scheduling system and method based on flow compatibility | |
| Fang et al. | QoS-driven power management of data centers via model predictive control | |
| CN104657220A (en) | Model and method for scheduling for mixed cloud based on deadline and cost constraints | |
| CN103488539B (en) | Data center energy saving method based on central processing unit (CPU) dynamic frequency modulation technology | |
| Aujla et al. | SDN-based energy management scheme for sustainability of data centers: An analysis on renewable energy sources and electric vehicles participation | |
| CN111935952B (en) | Large machine room energy consumption regulation and control method and device | |
| CN107346264A (en) | A kind of method, apparatus and server apparatus of virtual machine load balance scheduling | |
| CN106933669A (en) | For the apparatus and method of data processing | |
| CN103150003A (en) | Information processing system, and its power-saving control method and device | |
| CN105808341B (en) | A kind of methods, devices and systems of scheduling of resource | |
| Ran et al. | SLAs-aware online task scheduling based on deep reinforcement learning method in cloud environment | |
| CN107046505B (en) | Service control method and service control device | |
| CN107861796A (en) | A kind of dispatching method of virtual machine for supporting cloud data center energy optimization | |
| Vasic et al. | Thermal-aware workload scheduling for energy efficient data centers | |
| Li et al. | Load prediction-based automatic scaling cloud computing | |
| Li et al. | Dynamic virtual machine consolidation algorithm based on balancing energy consumption and quality of service | |
| Deiab et al. | Energy efficiency in cloud computing | |
| CN111242801A (en) | Power system regulation and control cloud power grid operation analysis platform | |
| Zhao et al. | Workload and energy management of geo-distributed datacenters considering demand response programs | |
| Nadalizadeh et al. | GreenPacker: renewable-and fragmentation-aware VM placement for geographically distributed green data centers | |
| CN114243681B (en) | Power utilization regulation and control method, device, equipment and storage medium of power system | |
| Davydov et al. | Development of the methods for resource reallocation in cloud computing systems |
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 |