CN116361703A

CN116361703A - Energy-saving control method and device for data center, electronic equipment and readable medium

Info

Publication number: CN116361703A
Application number: CN202211634931.8A
Authority: CN
Inventors: 聂斌
Original assignee: China Telecom Corp Ltd
Current assignee: China Telecom Corp Ltd
Priority date: 2022-12-19
Filing date: 2022-12-19
Publication date: 2023-06-30

Abstract

The embodiment of the invention provides an energy-saving control method and device for a data center, electronic equipment and a readable medium, wherein the method comprises the following steps: the data center monitoring system monitors and collects at least one type of energy consumption data of each device in the data center for a period of time, compares each type of energy consumption data of the device with historical average energy consumption data respectively to obtain a comparison result, determines whether the device is in a health state according to the comparison result, and executes energy-saving control operation on the device under the condition that the device is not in the health state. According to the method, by monitoring and collecting various types of energy consumption data of the equipment, whether the equipment is in a healthy state or not can be judged based on comprehensive and complete data, the actual energy consumption situation of the data center is more closed, when the equipment is in an unhealthy state, various energy consumption nodes of the equipment are dynamically adjusted, energy-saving control of the equipment of the data center is optimized, and the accuracy of energy-saving control of the equipment is improved.

Description

Energy-saving control method and device for data center, electronic equipment and readable medium

Technical Field

The present invention relates to the technical field of data centers, and in particular, to an energy-saving control method for a data center, an energy-saving control device for a data center, an electronic device, and a computer readable medium.

Background

With the rapid development of computer technology and the promotion of human informatization and intelligence times, data centers are increasingly built, and the development of large-scale and high-density data centers is tended to be realized, so that the power consumption of the data centers in China is continuously increased. And the power consumption of the data center is different from the theoretical design power consumption in the dynamic operation process of the data center, so that the energy-saving management of the data center node in the dynamic operation of the data center is very important. The traditional energy-saving control of the data center on the nodes is generally realized by configuring node modes and operation flows by an administrator, so that the nodes are completely operated according to the fixed modes and flows, thereby realizing the management of the energy consumption of the nodes, and the temperature, the energy consumption, the load and the like of the data center can be changed more complicated in the dynamic operation process of the data center, the continuous availability requirement of the data center in a complex environment is hardly met by the management strategy of the fixed modes, the reconfiguration is carried out manually, and the efficiency is low and the error rate is greatly increased along with the improvement of the complexity of the data center and the frequent change of the operation state. In the prior art, the management of the node energy consumption of the data center mainly aims at hardware equipment, and the energy consumption caused by storage, network transmission, CPU and GPU operation calculation is ignored, so that the statistical energy consumption has a larger difference from the actual energy consumption of the data center, and the energy-saving management of the data center is not facilitated.

Disclosure of Invention

In view of the foregoing, embodiments of the present invention have been made to provide a power saving control method of a data center, a power saving control apparatus of a data center, an electronic device, and a computer readable medium that overcome or at least partially solve the foregoing problems.

The embodiment of the invention discloses energy-saving control of a data center, which is applied to a data center monitoring system, wherein the data center monitoring system stores at least one type of historical energy consumption data; the types include operation energy consumption, heat dissipation energy consumption, storage energy consumption, transmission energy consumption and operation energy consumption; comprising the following steps:

monitoring and collecting at least one type of energy consumption data for a period of time for each device in the data center; the device comprises a server and a heat dissipation device;

respectively comparing the energy consumption data of each type of the equipment with historical average energy consumption data; the historical average energy consumption data is obtained by calculation through the historical energy consumption data;

determining whether the device is in a healthy state according to the comparison result;

and if the equipment is not in a healthy state, executing energy-saving control operation on the equipment.

Optionally, the step of determining whether the device is in a health state according to the comparison result includes:

Determining the score of each type of energy consumption data of the equipment according to the comparison result;

calculating a total energy consumption score of the device using the score of each type of energy consumption data of the device; the total energy consumption score indicates a health status of the device;

determining whether the total energy consumption score is lower than a historical average total energy consumption score of the device; the historical average total energy consumption score is calculated by using the score of the historical energy consumption data;

if yes, determining that the equipment is not in a health state;

if not, determining that the equipment is in a health state.

Optionally, the step of determining the score of each type of energy consumption data of the device according to the comparison result includes:

if the energy consumption data of one type is higher than the historical average energy consumption data corresponding to the type, determining that the score of the energy consumption data of the type is a first score;

if the energy consumption data of one type is equal to the historical average energy consumption data corresponding to the type, judging that the score of the energy consumption data of the type is a second score;

if the energy consumption data of one type is lower than the historical average energy consumption data corresponding to the type, judging that the score of the energy consumption data of the type is a third score; the third score is greater than the second score, which is greater than the first score.

Optionally, the step of performing the energy-saving control operation on the device if the device is not in a healthy state includes:

when the server is not in a healthy state, judging whether the storage energy consumption of the server is higher than the historical average storage energy consumption of the server or not;

if yes, detecting the use state of the memory card of the server;

when the memory card accesses data, determining that the memory card is in a busy state, and keeping the memory card in an open mode;

and when the memory card has no access to data, determining that the memory card is in an idle state, and adjusting the memory card to be in a dormant mode.

when the server is not in a healthy state, judging whether the transmission energy consumption of the server is higher than the historical average transmission energy consumption of the server or not;

if so, respectively calculating the transmission energy consumption required by each network line for transmitting the data when the data is transmitted;

determining at least one target network line according to the transmission energy consumption;

and transmitting the data by adopting the target network line.

Optionally, a plurality of operation tasks are operated in the server; and if the equipment is not in a health state, executing energy-saving control operation on the equipment, wherein the energy-saving control operation comprises the following steps of:

when the server is not in a healthy state, judging whether the operation energy consumption of the server is higher than the historical average operation energy consumption of the server or not;

if yes, calculating a target computing power resource required by the computing task;

detecting idle computing power resources of a central processor and a graphic processor on the server respectively;

determining a target central processor and/or a target graphic processor for processing the operation task according to the target computing power resource and the idle computing power resource;

and adjusting other central processors and/or graphic processors except the target central processor and/or the target graphic processor on the server to a sleep mode.

when the heat dissipation equipment is not in a healthy state, calculating total heat dissipation energy consumption of all the heat dissipation equipment in the data center;

and if the total heat dissipation energy consumption is higher than the historical average total heat dissipation energy consumption of all the heat dissipation devices in the data center, determining the closable heat dissipation devices and closing time according to the difference value of the total heat dissipation energy consumption and the historical average total heat dissipation energy consumption and the heat dissipation efficiency of each heat dissipation device.

when the server is not in a healthy state, judging whether the running energy consumption of the server is higher than the historical average running energy consumption of the server or not;

if yes, judging whether the task to be processed is stored on the server;

and if the task to be processed is not stored on the server, the server is adjusted to be in a dormant mode.

The embodiment of the invention discloses an energy-saving control device of a data center, which is applied to a data center monitoring system, wherein the data center monitoring system stores at least one type of historical energy consumption data; the types include operation energy consumption, heat dissipation energy consumption, storage energy consumption, transmission energy consumption and operation energy consumption; comprising the following steps:

an acquisition module for monitoring and acquiring at least one type of energy consumption data for a period of time for each device in the data center; the device comprises a server and a heat dissipation device;

the comparison module is used for respectively comparing the energy consumption data of each type of the equipment with the historical average energy consumption data corresponding to each type; the historical average energy consumption data is obtained by calculation through the historical energy consumption data;

The health state determining module is used for determining whether the equipment is in a health state or not according to the comparison result;

and the control module is used for executing energy-saving control operation on the equipment if the equipment is not in a healthy state.

Optionally, the health status determination module includes:

the score determining submodule is used for determining the score of each type of energy consumption data of the equipment according to the comparison result;

a total energy consumption score determination submodule, configured to calculate a total energy consumption score of the device using the score of each type of energy consumption data of the device; the total energy consumption score indicates a health status of the device;

a first judging sub-module, configured to judge whether the total energy consumption score is lower than a historical average total energy consumption score of the device; the historical average total energy consumption score is calculated by using the score of the historical energy consumption data;

a first health status determination submodule configured to determine, if yes, that the device is not in a health status;

and the second health state determining submodule determines that the equipment is in a health state if the equipment is not in the health state.

Optionally, the score determination submodule includes:

the first score determining unit is used for determining that the score of the energy consumption data of one type is a first score if the energy consumption data of the type is higher than the historical average energy consumption data corresponding to the type;

A second score determining unit, configured to determine that the score of the type of energy consumption data is a second score if the type of energy consumption data is equal to the historical average energy consumption data corresponding to the type;

a third score determining unit, configured to determine that the score of the type of energy consumption data is a third score if the type of energy consumption data is lower than the historical average energy consumption data corresponding to the type; the third score is greater than the second score, which is greater than the first score.

Optionally, the control module includes:

the second judging submodule is used for judging whether the storage energy consumption of the server is higher than the historical average storage energy consumption of the server or not when the server is not in a healthy state;

the using state determining submodule is used for detecting the using state of the memory card of the server if yes;

the starting sub-module is used for determining that the memory card is in a busy state when the memory card accesses data, and keeping the memory card in a starting mode;

and the dormancy sub-module is used for determining that the memory card is in an idle state when the memory card has no access to data, and adjusting the memory card into a dormancy mode.

Optionally, the control module includes:

a third judging sub-module, configured to judge whether the transmission energy consumption of the server is higher than the historical average transmission energy consumption of the server when it is determined that the server is not in a healthy state;

the transmission energy consumption transmission sub-module is used for respectively calculating the transmission energy consumption required by each network line for transmitting the data when the data are transmitted if the data are transmitted;

the target network line determining submodule is used for determining at least one target network line according to the transmission energy consumption;

and the transmission sub-module is used for transmitting the data by adopting the target network line.

Optionally, a plurality of operation tasks are operated in the server; the control module includes:

a fourth judging sub-module, configured to judge whether the operation energy consumption of the server is higher than the historical average operation energy consumption of the server when it is determined that the server is not in a healthy state;

the target computing power resource determining submodule is used for calculating and processing the target computing power resource required by the computing task if the target computing power resource is positive;

the detection submodule is used for respectively detecting idle computing power resources of the central processor and the graphic processor on the server;

The target processor determining submodule is used for determining a target central processor and/or a target graphic processor for processing the operation task according to the target computing power resource and the idle computing power resource;

and the first adjusting sub-module is used for adjusting other central processing units and/or graphic processing units except the target central processing unit and/or the target graphic processing unit on the server into a dormant mode.

Optionally, the control module includes:

a total heat dissipation energy consumption determination submodule for calculating total heat dissipation energy consumption of all heat dissipation devices in the data center when it is determined that the heat dissipation devices are not in a healthy state;

and the heat radiation equipment determining submodule is used for determining closable heat radiation equipment and closing time according to the difference value of the total heat radiation energy consumption and the historical average total heat radiation energy consumption and the heat radiation efficiency of each heat radiation equipment if the total heat radiation energy consumption is higher than the historical average total heat radiation energy consumption of all the heat radiation equipment in the data center.

Optionally, the control module includes:

a fifth judging sub-module, configured to judge whether the operation energy consumption of the server is higher than the historical average operation energy consumption of the server when it is determined that the server is not in a healthy state;

A sixth judging sub-module, configured to judge whether a task to be processed is stored on the server if yes;

and the second adjusting sub-module is used for adjusting the server to be in a dormant mode if the task to be processed is not stored in the server.

The embodiment of the invention also discloses electronic equipment, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

the memory is used for storing a computer program;

the processor is used for realizing the data center energy-saving control method according to the embodiment of the invention when executing the program stored in the memory.

Embodiments of the present invention also disclose one or more computer readable media having instructions stored thereon that, when executed by one or more processors, cause the processors to perform a method of energy saving control of a data center according to embodiments of the present invention.

The embodiment of the invention has the following advantages:

in the embodiment of the invention, the data center monitoring system monitors and collects at least one type of energy consumption data of each device in the data center for a period of time, and respectively compares each type of energy consumption data of the device with historical average energy consumption data to obtain a comparison result, and according to the comparison result, whether the device is in a health state or not is determined, and under the condition that the device is not in the health state, energy-saving control operation is executed on the device. According to the method, by monitoring and collecting various types of energy consumption data of the equipment, whether the equipment is in a healthy state or not can be judged based on comprehensive and complete data, the actual energy consumption situation of the data center is more closely related, when the equipment is in an unhealthy state, various energy consumption nodes of the equipment are dynamically adjusted, the fixed adjusting process is not restricted, the energy-saving control of the equipment of the data center is optimized, and the accuracy of the energy-saving control of the equipment is improved.

Drawings

FIG. 1 is a system block diagram of a data center energy saving control system provided in an embodiment of the present invention;

FIG. 2 is a flow chart of steps of a method for energy saving control of a data center according to an embodiment of the present invention;

FIG. 3 is a flow chart of steps of another method for energy saving control of a data center provided in an embodiment of the present invention;

FIG. 4 is a block diagram of an energy-saving control device of a data center according to an embodiment of the present invention;

FIG. 5 is a block diagram of an electronic device provided in an embodiment of the invention;

fig. 6 is a schematic diagram of a computer readable medium provided in an embodiment of the invention.

Detailed Description

In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.

Referring to fig. 1, a system architecture block diagram of a data center energy saving control system in accordance with the present invention is shown.

The data center energy saving control system 101 may include a data center monitoring system 102, a data center 103, and the data center 103 may include at least one server 104, at least one heat dissipating device 105.

The data center monitoring system 102 is configured to monitor and collect energy consumption data of the server 104 and the heat dissipation device 105, determine whether the server 104 and the heat dissipation device 105 are in a healthy state according to the collected energy consumption data, and perform an energy-saving control operation on the server 104 and the heat dissipation device 105 when the server 104 and the heat dissipation device 105 are not in the healthy state.

Referring to fig. 2, a step flowchart of a method for controlling energy saving of a data center according to an embodiment of the present invention may specifically include the following steps:

step 201, monitoring and collecting at least one type of energy consumption data for a period of time for each device in a data center; the device comprises a server and a heat dissipation device;

for energy-saving control of data center equipment, in the prior art, only the energy consumption of hardware equipment is usually concerned, but the energy consumption caused by storage, network transmission, CPU and GPU operation calculation is ignored, so that the statistical energy consumption has a larger difference from the actual energy consumption of the data center, and the energy-saving management of the data center is not facilitated. And the equipment is regulated by adopting a fixed process, and the regulation is not carried out according to the actual running condition of the data center, so that the energy consumption of the data center cannot be effectively reduced.

Therefore, the invention provides an energy-saving control method of a data center, by arranging a data center system, at least one type of energy consumption data of each device in the data center in a time period can be monitored and collected in a data center monitoring system, and the data center can store at least one type of historical energy consumption data before the time period. The types may include operation energy consumption, heat dissipation energy consumption, storage energy consumption, transmission energy consumption, operation energy consumption, and other energy consumption types, and the devices may include servers, heat dissipation devices, and other devices.

Specifically, the eddy current sensor may be set at different nodes of the device to collect different types of energy consumption data, for example, for a server, the eddy current sensor may be set at a memory card to collect energy consumption, the eddy current sensor may be set at a CPU and GPU to collect operation energy consumption, and so on. The data center can acquire the current and the voltage of different nodes of each device in real time by adopting an eddy current sensor, calculate the power consumption in the time period and acquire the energy consumption data of each type of the device.

Step 202, respectively comparing each type of energy consumption data of the equipment with historical average energy consumption data; the historical average energy consumption data is obtained by calculation through the historical energy consumption data;

after collecting each type of energy consumption data of the equipment, the data center monitoring system can respectively compare each type of energy consumption data with the historical average energy consumption data corresponding to the type, obtain each type of comparison result, and then synthesize all types of comparison results to determine whether energy saving control is needed for the equipment. For example, comparing the stored energy consumption data for the period of time with historical average stored energy consumption data; comparing the transmission energy consumption data of the time period with historical average transmission energy consumption data; comparing the operational energy consumption data for the time period with historical average operational energy consumption data, and so on.

The historical average energy consumption data is obtained by calculating the historical energy consumption data, the historical energy consumption data before the time period is stored in the data center monitoring system, and the historical average energy consumption data of each type is obtained by calculating the average value of all the energy consumption data of each type before the time period.

Step 203, determining whether the equipment is in a health state according to the comparison result;

and when the energy consumption data comparison result of each type of equipment is obtained, the energy consumption data comparison results of all types can be integrated to judge whether the equipment is in a health state. If the comparison result is that the energy consumption data of each type is higher than the historical average energy consumption data, the equipment can be determined to be in an unhealthy state; if the comparison result is that the energy consumption data of each type is lower than the historical average energy consumption data, the equipment can be determined to be in a health state; if the comparison result is that the energy consumption data of one part of types is lower than the historical average energy consumption data and the energy consumption data of the other part of types is higher than the historical average energy consumption data, whether the equipment is in a health state or not can be further determined according to the proportion of the types of the energy consumption data higher than the historical average energy consumption data and the types of the energy consumption data lower than the historical average energy consumption data.

And 204, if the equipment is not in a healthy state, executing energy-saving control operation on the equipment.

When the data center monitoring system determines that the equipment is in a health state, the equipment can be subjected to energy-saving control operation so as to reduce the energy consumption of the data center. Specifically, the data center monitoring system can adjust the energy conservation of the equipment, and can adjust the whole equipment or the components of the equipment, so that the actual condition of a specific component of the equipment can be adjusted, the energy conservation control of the data center equipment is optimized, and the accuracy of the energy conservation control of the equipment is improved.

According to the energy-saving control method for the data center, the data center monitoring system monitors and collects at least one type of energy consumption data of each device in the data center for a period of time, compares each type of energy consumption data with historical average energy consumption data respectively to obtain a comparison result, determines whether the device is in a healthy state according to the comparison result, and executes energy-saving control operation on the device under the condition that the device is not in the healthy state. According to the method, by monitoring and collecting various types of energy consumption data of the equipment, whether the equipment is in a healthy state or not can be judged based on comprehensive and complete data, the actual energy consumption situation of the data center is more closely related, when the equipment is in an unhealthy state, various energy consumption nodes of the equipment are dynamically adjusted, the fixed adjusting process is not restricted, the energy-saving control of the equipment of the data center is optimized, and the accuracy of the energy-saving control of the equipment is improved.

Referring to fig. 3, a flowchart illustrating steps of another method for controlling energy saving of a data center according to an embodiment of the present invention may specifically include the following steps:

step 301, monitoring and collecting at least one type of energy consumption data for a period of time for each device in a data center; the device comprises a server and a heat dissipation device;

at least one type of energy consumption data for a period of time for each device in the data center may be monitored and collected in the data center monitoring system, and the data center may store at least one type of historical energy consumption data prior to the period of time.

Step 302, comparing each type of energy consumption data of the device with historical average energy consumption data respectively; the historical average energy consumption data is obtained by calculation through the historical energy consumption data;

after collecting each type of energy consumption data of the equipment, the data center monitoring system can respectively compare each type of energy consumption data with the historical average energy consumption data corresponding to the type, obtain each type of comparison result, and then synthesize all types of comparison results to determine whether energy saving control is needed for the equipment.

Step 303, determining the score of each type of energy consumption data of the equipment according to the comparison result;

Comparison of each type of energy consumption data with historical average energy consumption data may occur in three situations: each type of energy consumption data is higher than the historical average energy consumption data; each type of energy consumption data is equal to historical average energy consumption data; each type of energy consumption data is lower than the historical average energy consumption data; setting a score corresponding to each comparison result, and determining the score of each type of energy consumption data of the equipment by the data center monitoring system according to the specific comparison result.

In one embodiment of the present invention, the step of determining the score of each type of energy consumption data of the device according to the comparison result includes:

s11, if the energy consumption data of one type is higher than the historical average energy consumption data corresponding to the type, judging that the score of the energy consumption data of the type is a first score;

s12, if the energy consumption data of one type is equal to the historical average energy consumption data corresponding to the type, judging that the score of the energy consumption data of the type is a second score;

s13, if the energy consumption data of one type is lower than the historical average energy consumption data corresponding to the type, judging that the score of the energy consumption data of the type is a third score; the third score is greater than the second score, which is greater than the first score.

In the embodiment of the invention, the energy consumption data of a certain type is higher than the historical average energy consumption data corresponding to the type, so that the energy consumption of the type of the equipment is higher, and the higher energy consumption can obtain lower scores, thereby indicating that the equipment or the components corresponding to the type can be adjusted to reduce the energy consumption of the data center.

Specifically, if the energy consumption data of a type is higher than the historical average energy consumption data corresponding to the type, determining that the score of the energy consumption data of the type is a first score, if the energy consumption data of the type is equal to the historical average energy consumption data corresponding to the type, determining that the score of the energy consumption data of the type is a second score, and if the energy consumption data of the type is lower than the historical average energy consumption data corresponding to the type, determining that the score of the energy consumption data of the type is a third score; the third fraction is greater than the second fraction, and the second fraction is greater than the first fraction, so that the type with a lower fraction has higher energy consumption, the device and/or the device component can be adjusted, and the type with a higher fraction has lower energy consumption and can not be adjusted.

Step 304, calculating the total energy consumption score of the equipment by adopting the score of each type of energy consumption data of the equipment;

After determining the score of each type of energy consumption data of the device, the data center monitoring system may add the scores of each type of energy consumption data of the device, and calculate a total energy consumption score of the device, where the total energy consumption score may be used to indicate a health state of the device.

Step 305, determining whether the total energy consumption score is lower than a historical average total energy consumption score of the device; the historical average total energy consumption score is calculated by using the score of the historical energy consumption data;

step 306, if yes, determining that the device is not in a healthy state;

step 307, if not, determining that the device is in a healthy state.

After obtaining the total energy consumption score of the device, the data center monitoring system may compare the total energy consumption score of the device with the historical average total energy consumption score of the device, and determine whether the total energy consumption score of the device is lower than the historical average total energy consumption score of the device. If the total energy consumption score of the device is lower than the historical average total energy consumption score of the device, determining that the device is not in a healthy state; if the total energy consumption score of the device is equal to or greater than the historical average total energy consumption score of the device, it may be determined that the device is in a healthy state.

The historical average total energy consumption score is calculated by using the scores of the historical energy consumption data, and specifically, because at least one type of historical energy consumption data is stored in the data center monitoring system, the data center monitoring system can calculate the score of each type of historical energy consumption data first, and then sum calculation and average calculation are performed by using the scores of all types of historical energy consumption data to obtain the historical average total energy consumption score.

And step 308, if the equipment is not in a healthy state, executing energy-saving control operation on the equipment.

In one embodiment of the present invention, the step of performing the energy saving control operation on the device if the device is not in a healthy state includes:

s21, when the server is not in a healthy state, judging whether the storage energy consumption of the server is higher than the historical average storage energy consumption of the server or not;

upon determining that the server is not in a healthy state, the data center monitoring system may perform energy-saving control operations on the server. Specifically, different types of energy consumption of the server can be checked to determine which types of energy consumption cause the server to be in a healthy state, so that components corresponding to the types of energy consumption which cause the unhealthy server can be adjusted in a targeted manner, and reasonable adjustment can be realized under the condition that the whole server is not affected.

When the data center monitoring system determines that the server is not in a healthy state, the data center monitoring system can judge whether the storage energy consumption of the server is higher than the historical average storage energy consumption of the server so as to determine whether the server is not in the healthy state and is caused by a component corresponding to the storage energy consumption, namely whether the server is not in the healthy state and is due to the fact that the energy consumption of a memory card is too high.

S22, if yes, detecting the use state of the memory card in the server;

if it is determined that the storage energy consumption of the server is higher than the historical average storage energy consumption of the server, it can be stated that the server is not in a healthy state and is caused by the excessively high storage energy consumption, that is, the server is not in a healthy state and is caused by the excessively high energy consumption of the memory card, at this time, the data center monitoring system can detect the use state of the memory card in the server, so as to determine whether to adjust the memory card according to the actual use situation of the memory card. When the memory card is in use, the memory card can be closed to reduce energy consumption without adjusting the memory card.

S23, when the memory card accesses data, determining that the memory card is in a busy state, and keeping the memory card in an open mode;

The data center monitoring system detects the memory card, and if the data is detected to be accessed currently, that is, the data is stored in the memory card, or other components are extracting data from the memory card, the memory card can be determined to be in a busy state, and at the moment, in order not to influence the service operation of the server, the memory card can be not closed, and the memory card is kept in an open mode.

S24, when the memory card has no access to data, determining that the memory card is in an idle state, and adjusting the memory card to a sleep mode.

The data center monitoring system detects the memory card, and if the memory card is detected to be not accessed with data at present, namely, no data is stored in the memory card, and other components are not extracting data from the memory card, the memory card can be determined to be in an idle state, and at the moment, in order to reduce energy consumption, the memory card can be closed, so that the mode of the memory card can be adjusted to be a dormant mode.

s31, when the server is not in a healthy state, judging whether the transmission energy consumption of the server is higher than the historical average transmission energy consumption of the server or not;

When the data center monitoring system determines that the server is not in a healthy state, the data center monitoring system can judge whether the transmission energy consumption of the server is higher than the historical average transmission energy consumption of the server so as to determine whether the server is not in the healthy state and is caused by a component corresponding to the transmission energy consumption, namely whether the server is not in the healthy state and is due to the fact that the energy consumption of network transmission data is too high.

S32, if so, respectively calculating the transmission energy consumption required by each network line for transmitting the data when the data is transmitted;

if it is determined that the transmission energy consumption of the server is higher than the historical average transmission energy consumption of the server, it can be stated that the server is not in a healthy state and is caused by the excessively high transmission energy consumption, that is, the server is not in a healthy state and is caused by excessively high energy consumption of network transmission data, at this time, the data center monitoring system can monitor data transmission operation, and when the data transmission is required, the data center monitoring system can respectively calculate the transmission energy consumption required by each network line to transmit the data, so that the network lines with lower transmission energy consumption are adopted to transmit the data, and the energy consumption of the data center is reduced.

S33, determining at least one target network line according to the transmission energy consumption;

After determining the transmission energy consumption required by each network line to transmit data, in order to transmit data by using a network line with lower transmission energy consumption, the data center monitoring system may select at least one network line with relatively lower transmission energy consumption from all network lines according to the transmission energy consumption. In particular, the transmission energy consumption required for transmitting the data by all network lines can be compared, and at least one target network line with relatively reduced transmission energy consumption can be selected.

And S34, transmitting the data by adopting the target network line.

The data center monitoring system can adopt a target network line to transmit data, so that the electric quantity consumed by transmitting the data is reduced, and the energy-saving optimization of the data center is realized.

s41, judging whether the operation energy consumption of the server is higher than the historical average operation energy consumption of the server or not when the server is not in a healthy state;

when the data center monitoring system determines that the server is not in a healthy state, the data center monitoring system can judge whether the operation energy consumption of the server is higher than the historical average operation energy consumption of the server so as to determine whether the server is not in the healthy state and is caused by a component corresponding to the operation energy consumption, namely whether the server is not in the healthy state and is caused by overhigh operation energy consumption of the CPU and/or the GPU.

S42, if yes, calculating and processing target computing power resources required by the computing task;

if the operation energy consumption of the server is higher than the historical average operation energy consumption of the server, it can be stated that the server is not in a healthy state and is caused by the excessively high operation energy consumption, namely, the server is not in a healthy state and is caused by the excessively high operation energy consumption of the CPU and/or the GPU, at the moment, the data center monitoring system can detect whether the operation task is stored in the server, and if the operation task to be processed is not stored, the data center monitoring system can close the CPU and the GPU of the server so as to reduce the operation energy consumption of the server; if the server stores the operation task, the data center monitoring system can calculate the target calculation power resource required by the operation task, so as to determine how many CPUs and/or GPUs are required to process the operation task according to the target calculation power resource required by the operation task.

S43, respectively detecting idle computing power resources of a central processor and a graphic processor on the server;

the computing task on the processing server is the computing power resource of the central processing unit and the graphic processing unit, so that the data center monitoring system can respectively detect the idle computing power resources of the central processing unit and the graphic processing unit on the server after determining the target computing power resource required for processing the computing task. Specifically, the data center monitoring system can obtain the idle computing power resource information returned by the central processing unit and the graphic processing unit by sending the idle computing power resource query information to the central processing unit and the graphic processing unit, so as to determine the idle computing power resources possessed by the central processing unit and the graphic processing unit.

S44, determining a target central processor and/or a target graphic processor for processing the operation task according to the target computing power resource and the idle computing power resource;

after determining the idle computing power resources of the central processing unit and the graphics processing unit, the data center monitoring system can match the idle computing power resources of the central processing unit and the graphics processing unit with the target computing power resources required by the processing operation task, and determine the target central processing unit and/or the target graphics processing unit for the processing operation task, wherein the determined target central processing unit and/or the target graphics processing unit can be one or at least two.

S45, adjusting other central processing units and/or graphic processing units except the target central processing unit and/or the target graphic processing unit on the server to be in a dormant mode.

In order to reduce the operation energy consumption, after determining the target central processor and/or the target graphic processor, the data center monitoring system can adjust other central processors and/or graphic processors except the target central processor and/or the target graphic processor on the server to be in a dormant mode, so that the operation energy consumption of the server is greatly reduced, and the energy consumption of the data center is reduced.

s51, when the heat dissipation equipment is not in a healthy state, calculating total heat dissipation energy consumption of all the heat dissipation equipment in the data center;

when the data center monitoring system determines that the server is not in a healthy state, the total heat dissipation energy consumption of the server can be compared with the historical average total heat dissipation energy consumption of the server so as to determine whether the server is not in the healthy state or not because the heat dissipation energy consumption of the heat dissipation equipment is too high. Specifically, the data center monitoring system may perform a summation operation by using heat dissipation energy consumption of all heat dissipation devices in the data center, so as to obtain total heat dissipation energy consumption of all heat dissipation devices in the data center.

S52, if the total heat dissipation energy consumption is higher than the historical average total heat dissipation energy consumption of all the heat dissipation devices in the data center, determining the closable heat dissipation devices and closing time according to the difference value of the total heat dissipation energy consumption and the historical average total heat dissipation energy consumption and the heat dissipation efficiency of each heat dissipation device.

After obtaining the total heat dissipation energy consumption of all the heat dissipation devices in the data center, the data center monitoring system can compare the total heat dissipation energy consumption of the server with the historical average total heat dissipation energy consumption of the server, and judge whether the total heat dissipation energy consumption is higher than the historical average total heat dissipation energy consumption of all the heat dissipation devices in the data center.

In order to reduce heat dissipation energy consumption of the data center, under the condition that the total heat dissipation energy consumption is higher than the historical average total heat dissipation energy consumption of all heat dissipation devices in the data center, the data center monitoring system can calculate the difference value between the total heat dissipation energy consumption and the historical average total heat dissipation energy consumption, and determine the closing time of the closable heat dissipation devices and each closable device according to the difference value between the total heat dissipation energy consumption and the historical average total heat dissipation energy consumption and the heat dissipation efficiency of each heat dissipation device, so that the data center monitoring system can close the heat dissipation devices within the closing time of each closable heat dissipation device, thereby reducing the heat dissipation energy consumption of the data center and further reducing the total energy consumption of the data center.

s61, judging whether the running energy consumption of the server is higher than the historical average running energy consumption of the server or not when the server is not in a healthy state;

when the data center monitoring system determines that the server is not in a healthy state, the data center monitoring system can judge whether the running energy consumption of the server is higher than the historical average running energy consumption of the server so as to determine whether the server is not in the healthy state and is caused by a component corresponding to the running energy consumption, namely whether the server is not in the healthy state and the energy consumption is too high due to long-time running of the server.

S62, if so, judging whether a task to be processed is stored on the server;

if it is determined that the operation energy consumption of the server is higher than the historical average operation energy consumption of the server, it may be stated that the server is not in a healthy state and is caused by the excessive operation energy consumption, that is, the server is not in a healthy state and is caused by the excessive energy consumption due to long-time operation of the server, at this time, the data center monitoring system may determine whether a task to be processed is stored on the server, so as to determine whether the server may be turned off. If the task to be processed is stored in the server, the server cannot be closed so as not to influence the normal operation of the service; if the task to be processed is not stored in the server, the server can be closed, so that the running energy consumption of the server is reduced.

And S63, if the task to be processed is not stored in the server, the server is adjusted to be in a dormant mode.

When it is determined that the task to be processed is not stored on the server, the data center monitoring system can adjust the mode of the server to a sleep mode so as to reduce the running energy consumption of the server.

It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.

Referring to fig. 4, a block diagram of an energy-saving control device of a data center provided in an embodiment of the present invention is shown, which may specifically include the following modules:

an acquisition module 401 for monitoring and acquiring at least one type of energy consumption data for a period of time for each device in the data center; the device comprises a server and a heat dissipation device;

a comparison module 402, configured to compare each type of energy consumption data of the device with the historical average energy consumption data corresponding to each type; the historical average energy consumption data is obtained by calculation through the historical energy consumption data;

a health status determining module 403, configured to determine whether the device is in a health status according to the comparison result;

And the control module 404 is configured to perform an energy-saving control operation on the device if the device is not in a healthy state.

Optionally, the health status determination module includes:

Optionally, the score determination submodule includes:

Optionally, the control module includes:

For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

In addition, the embodiment of the invention also provides an electronic device, as shown in fig. 5, which comprises a processor 501, a communication interface 502, a memory 503 and a communication bus 504, wherein the processor 501, the communication interface 502 and the memory 503 complete communication with each other through the communication bus 504,

a memory 503 for storing a computer program;

the processor 501 is configured to execute the program stored in the memory 503, and implement the following steps:

if yes, determining that the equipment is not in a health state;

if not, determining that the equipment is in a health state.

if yes, detecting the use state of the memory card of the server;

and transmitting the data by adopting the target network line.

if yes, judging whether the task to be processed is stored on the server;

The communication bus mentioned by the above terminal may be a peripheral component interconnect standard (Peripheral Component Interconnect, abbreviated as PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated as EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.

The communication interface is used for communication between the terminal and other devices.

The memory may include random access memory (Random Access Memory, RAM) or non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.

The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field-programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

In yet another embodiment of the present invention, as shown in fig. 6, there is also provided a computer-readable storage medium 601 having instructions stored therein, which when run on a computer, cause the computer to perform the energy saving control method of the data center described in the above embodiment.

In yet another embodiment of the present invention, a computer program product containing instructions that, when run on a computer, cause the computer to perform the energy saving control method of a data center described in the above embodiment is also provided.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, 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 one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. The energy-saving control method of the data center is characterized by being applied to a data center monitoring system, wherein the data center monitoring system stores at least one type of historical energy consumption data; the types include operation energy consumption, heat dissipation energy consumption, storage energy consumption, transmission energy consumption and operation energy consumption; comprising the following steps:

2. The method of claim 1, wherein the step of determining whether the device is in a healthy state based on the comparison result comprises:

if yes, determining that the equipment is not in a health state;

if not, determining that the equipment is in a health state.

3. The method of claim 2, wherein the step of determining a score for each type of energy consumption data of the device based on the comparison result comprises:

4. The method of claim 1, wherein the step of performing an energy saving control operation on the device if the device is not in a healthy state comprises:

if yes, detecting the use state of the memory card in the server;

5. The method of claim 1, wherein the step of performing an energy saving control operation on the device if the device is not in a healthy state comprises:

And transmitting the data by adopting the target network line.

6. The method of claim 1, wherein the server has a plurality of computing tasks running therein; and if the equipment is not in a health state, executing energy-saving control operation on the equipment, wherein the energy-saving control operation comprises the following steps of:

7. The method of claim 1, wherein the step of performing an energy saving control operation on the device if the device is not in a healthy state comprises:

8. The method of claim 1, wherein the step of performing an energy saving control operation on the device if the device is not in a healthy state comprises:

if yes, judging whether the task to be processed is stored on the server;

9. An energy-saving control device of a data center is characterized by being applied to a data center monitoring system, wherein the data center monitoring system stores at least one type of historical energy consumption data; the types include operation energy consumption, heat dissipation energy consumption, storage energy consumption, transmission energy consumption and operation energy consumption; comprising the following steps:

10. An electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

the memory is used for storing a computer program;

the processor is configured to implement the method according to any one of claims 1-8 when executing a program stored on a memory.

11. One or more computer-readable media having instructions stored thereon that, when executed by one or more processors, cause the processors to perform the method of any of claims 1-8.