CN113821339B - Energy consumption monitoring method and device for IDC data center machine room - Google Patents
Energy consumption monitoring method and device for IDC data center machine room Download PDFInfo
- Publication number
- CN113821339B CN113821339B CN202110960636.0A CN202110960636A CN113821339B CN 113821339 B CN113821339 B CN 113821339B CN 202110960636 A CN202110960636 A CN 202110960636A CN 113821339 B CN113821339 B CN 113821339B
- Authority
- CN
- China
- Prior art keywords
- server
- servers
- energy consumption
- mode
- working mode
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/5038—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
- G06F11/3062—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations where the monitored property is the power consumption
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
-
- 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
Abstract
The invention discloses an energy consumption monitoring method for an IDC data center machine room, which comprises the steps of obtaining historical load and energy consumption information of a server, obtaining a task list, carrying out task allocation, setting a server working mode and outputting an energy consumption report. The invention reduces the times of state transition of the server, thereby saving the energy consumption during the state switching, and simultaneously ensures the service availability by setting a certain number of servers which always work.
Description
Technical Field
The invention relates to the technical field of energy consumption monitoring, in particular to an energy consumption monitoring method and device for an IDC data center machine room.
Background
With the gradual expansion of the information-based social range, the energy problem of the computer industry is gradually highlighted, and according to data published by 'national data center application development guide (2018)' in 5 months of the Ministry of industry and communications, the total size of racks in the data center used in China is 166 ten thousand, which is increased by 33.4% on a same scale by the end of 2017, wherein the size of large and ultra-large data centers is increased by 68%.
The scale surge brings about a continuous rise in energy consumption. The data published by the Ministry of industry and communications in 2018 and 2 months show that 28.5 thousands of various in-use data centers are obtained by 2017, the electricity consumption all the year round exceeds 1200 hundred million kilowatts, the data centers account for about 2 percent of the electricity consumption of the whole society of China, and the data centers exceed the electricity generation of 976.05 million kilowatts of each year in a three gorge power station with the highest electricity generation per seat in the world. Meanwhile, only the data center operating internet services is planned to be 107 thousands of data centers from the construction frame to the end of 2017, and the scale and the energy consumption of the data center are still expected to keep high-speed increase of more than 30% in the next years. Different from the traditional high-energy-consumption industry gradually entering a steady development period, the trend that the electricity consumption of the information technology is accelerated and increased along with the expansion of business is very obvious when the information technology is used as a new industry, the overall energy consumption of the data center in China is at least 30% lower than the international advanced level, the difference with the international top is even more than 40%, and the energy consumption problem becomes a main contradiction which hinders the development of the data center industry.
The energy consumption of the information technology industry is mainly generated by the operation of a server of a data center, and the power consumption monitoring can effectively reduce the power consumption of the server, so that the heat dissipation cost caused by the heating of the server is saved.
Disclosure of Invention
The present invention is directed to a method and a system for monitoring energy consumption of an IDC data center, so as to solve one or more technical problems in the prior art, and provide at least one of a beneficial choice and a creation condition.
In order to achieve the technical purpose, the technical scheme of the invention is as follows:
an energy consumption monitoring method for an IDC data center room, the method comprising the steps of:
step 1, acquiring historical load and energy consumption information of a server;
step 2, acquiring a task list;
step 3, distributing tasks and setting a server working mode;
and 4, outputting an energy consumption report.
Further, in step 1, the substep of obtaining the historical load and energy consumption information of the server is:
step 1.1, acquiring device information of a server 30 days before the current time of a system through a server management terminal, wherein the device information comprises an average load and an average energy consumption of the server, carrying out dimensionless processing on the average load and taking a numerical value of the average load, and the average load is recorded as a set L = { L1, L2, \ 8230 \ 8230:, ln }, lx is the average load of an x-th server, the average energy consumption is recorded as E = { E1, E2, \8230;, en Ex is the average energy consumption of the x-th server, and n is the number of servers;
the average energy consumption is the electric energy consumption of the server in the last 30 days;
step 1.2, acquiring a preset service priority of each server, and recording the service priority as a service priority set P = { P1, P2, P3, \8230;, pn }, wherein Px is the service priority of the xth server;
the service priority is sorted from small to large according to the average load of the server in the last 30 days, and the sorted serial number is used as a preset service priority;
step 1.3, acquiring energy consumption information of each server through an energy consumption management terminal, transmitting the energy consumption information to the server management terminal, and establishing a relation LT (L0) between the service volume and the energy consumption information, wherein the L0 is an instant load of the server;
step 1.4, obtaining a load value Le of the lowest point of the energy consumption and the load through the relation LT (L0) of the average load and the energy consumption obtained in the step 1.3, wherein the average load and the load value are expressed in percentage, and the load range is [0%,100% ].
The load value is the CPU 10 minute average load.
Further, in step 2, the sub-step of acquiring the task list is:
a task list J and a desired elapsed time Te for the task list are obtained.
For example, task list J is: the rendering method comprises the steps of processing a rendering task of three-dimensional image data, averagely dividing the imported three-dimensional image data into a plurality of pieces of sub three-dimensional image data with the same size, rendering each piece of three-dimensional image data to be used as a processing task M, and using a sequence formed by each processing task to be used as a task list J.
The expected elapsed time Te for the task list is the average time required to complete each processing task.
Further, in step 3, the substeps of performing task allocation and setting the working mode of the server are as follows:
step 3.1, the number U of servers always in the working mode is set AL Number of servers U in the initial state in the operating mode i The number of servers in the low power consumption mode is n-U i N is the number of servers;
the working modes of the server are as follows: the server starts to process tasks, and the CPU of the server is in a running state.
The low power consumption mode (or called as low power consumption mode) of the server is as follows: the CPU of the server is in a dormant state, and is converted into a working mode after waiting for external interruption.
Step 3.2, refreshing the current task list, calculating the time T0 for the current working mode server to finish the current task list, if T0 is more than Te and the value of T0-Te is more than a set delay tolerance value delta, skipping to step 3.3, if T0 is less than Te and the value of Te-T0 is less than a second threshold value, skipping to step 3.4, otherwise, waiting for a second time interval T2 and re-executing step 3.2;
step 3.3, if the number U of servers in the working mode currently i If the number of the servers in the low power consumption mode is less than n, switching the x servers in the low power consumption mode to the working mode, and if the number of the servers in the working mode is U i If the sum of x is more than or equal to the number n of the servers, x is Ui + x-n, otherwise x is unchanged, and the number U of the servers in the current working mode is set i Is set as U i + x, skipping to step 3.2 after a set first time interval T1;
the substep of switching x servers in the low power consumption mode to the working mode is to obtain the x servers according to the value of the service priority set P of the servers, and specifically comprises the following steps:
sorting the elements in the service priority set P from high to low, sequentially selecting the servers corresponding to the sub-elements in the sorted set P, if the selected server is in the working mode, selecting the server corresponding to the next element in the sorted set P to judge whether the server is in the working mode, and switching the selected x servers to the working mode until x servers in the low power consumption mode are found;
step 3.4, waiting for a second time interval T2, monitoring whether a new task exists in the task list, if the new task exists, calculating the difference between the time T0 for the current server in the working mode to complete the current task list and the expected consumed time Te of the current task list, if the value of T0-Te is greater than a set delay tolerance value delta, skipping to step 3.3, if T0 is greater than Te and the value of Te-T0 is less than a second threshold value, switching y servers in the working mode to a low power consumption mode, and counting the number of the servers in the working mode, namely U i Set the value to U i -y，C h-a Is set to C h-a Y, if U i The value of-y is less than the number of servers U that are always on AL Then y is equal to U i -U AL Waiting for a first time interval T1, and skipping to the step 3.2;
the substep of switching y servers in the working mode to the low power consumption mode is to acquire the y servers according to the value of the service priority set P of the servers, and specifically comprises the following steps:
and sequencing the elements in the service priority set P according to the low to high order, sequentially selecting the servers corresponding to the sub-elements in the sequenced set P, if the selected server is in the working mode, selecting the server corresponding to the next element in the sequenced set P to judge whether the server is in the working mode or not, and switching the selected y servers to a low power consumption mode until y servers in the working mode are found.
In one embodiment, the server type is HTTP server, the number of servers is 1000, and the number of servers U in the working mode all the time AL 64, number of servers in operating mode at initial state U i 132 with a delay tolerance delta of 100ms, x is taken to be [10, 50]And y has a value of [10, 40 ]]The first time interval T1 is 10s, the second time interval T2 is 15s, and the second threshold is 200ms.
In one embodiment, the server type is GPU server, the number of servers is 200, and the number of servers U in the working mode all the time AL 10, number of servers in operation mode at initial state U i 20, the delay tolerance delta is 10s, x is taken as [2,5%]And y has a value of [4, 10 ]]The first time interval T1 is 120s, the second time interval T2 is 150s, and the second threshold is 5s.
In one embodiment, the server type is archive server, the number of servers is 500, and the number of servers in the working mode is U AL 15, number of servers in operation mode at initial state U i 20, the delay tolerance value delta is 5s, x is [6, 20 ]]And y has a value of [8, 15 ]]The first time interval T1 is 10s, the second time interval T2 is 15s, and the second threshold is 5s.
Preferably, the value of x can also be determined by the following sub-steps:
x＝((T0-Te)/Te)×(|Lavg-Le|)×1.2×(n-U i )；
in the formula, T0 is the time T0 of the current working mode server to complete the current task list, te is the expected time consumption Te of the current task list, | Lavg-Le | is the average load of the current working mode server and the lowest energy consumption and loadAbsolute value of difference between load values Le of points, n is number of servers, U i The number of servers currently in the operating mode.
Preferably, the value of y can also be determined by the following sub-steps:
y＝((Te-T0)/Te)×(|Lavg-Le|)×1.4×U i ；
in the formula, T0 is the time T0 of the current working mode server to complete the current task list, te is the expected time consumption Te of the current task list, | Lavg-Le | is the absolute value of the difference between the average load and the energy consumption of the current working mode server and the load value Le at the lowest point of the load, U i The number of servers currently in the operating mode.
Further, in step 4, the sub-step of outputting the energy consumption report is:
step 4.1, calculating the energy consumption reduction value ERI of each server:
ERi＝(Pi a -Pi h )×Ti h -(Pi a-h ×Ci a-h )-Pi h-a ×Ci h-a ，
where ERI is the power consumption reduction value of the ith server, pi a : power consumption, pi, of the ith server in the working mode h : power consumption of the ith server in Low Power mode, ti h : duration of the ith server in Low Power consumption mode, pi a-h : power consumption of the ith server in switching from the operating mode to the low power consumption mode, ci a-h : number of times of switching the ith server from the operating mode to the low power mode, pi h-a : power consumption for switching the ith server from the low power consumption mode to the active mode, ci h-a : switching the ith server from the low power consumption mode to the working mode for times;
step 4.2, calculating the energy consumption reduction values GER of all servers:
in the formula, GEr% is the rate of energy consumption reduction of all servers, the range is [0%,100% ], GEr is the energy consumption reduction value GEr of all servers obtained in step 4.2, and GE is the total power consumption GE of all servers.
An energy consumption monitoring system for an IDC data center room, the system comprising:
each server is directly connected with the energy consumption management terminal, the server distribution terminal and the power consumption detection module through a network;
the server manages the terminal: the system is used for managing the servers in batches, distributing tasks and acquiring the states of the servers, wherein the states comprise the current load and the current mode of the servers;
energy consumption management terminal: the energy consumption information acquisition module is used for acquiring energy consumption information and transmitting the energy consumption information to the server management terminal;
the server distributes the terminal: for assigning tasks to each server;
the power consumption detection module: the power consumption monitoring system is used for monitoring the power consumption of all the servers and sending power consumption data to the server management terminal. Compared with the prior art, the invention has the following beneficial technical effects:
compared with the traditional method for simply regulating and controlling the server, the method has the advantages that the waiting time before the working mode of the server is changed is introduced, the times of state conversion of the server are reduced, the energy consumption during state switching is saved, and the service availability is ensured by setting a certain number of servers which always work.
Drawings
The foregoing and other features of the present invention will become more apparent to those skilled in the art from the following detailed description of the embodiments taken in conjunction with the accompanying drawings, in which like reference characters designate the same or similar elements, and in which it is apparent that the drawings described below are merely exemplary of the invention and that other drawings may be derived therefrom without the inventive faculty, to those skilled in the art, and in which:
fig. 1 is a flowchart of an energy consumption monitoring method for an IDC data center room according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clear, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. The specific embodiments described herein are merely illustrative of the invention and are not intended to be limiting.
It is also to be understood that the following examples are illustrative of the present invention and are not to be construed as limiting the scope of the invention, and that certain insubstantial modifications and adaptations of the invention by those skilled in the art in light of the foregoing description are intended to be included within the scope of the invention. The specific process parameters and the like of the following examples are also only one example within a suitable range, i.e., those skilled in the art can select the appropriate range through the description herein, and are not limited to the specific values exemplified below.
The following exemplarily illustrates an energy consumption monitoring method for an IDC data center room provided by the present invention. Fig. 1 is a flowchart of an energy consumption monitoring method for an IDC data center room, and the following describes an energy consumption monitoring method for an IDC data center room according to an embodiment of the present invention with reference to fig. 1, where the method includes the following steps:
step 1, acquiring historical load and energy consumption information of a server;
step 2, acquiring a task list;
step 3, performing task allocation and setting a server working mode;
and 4, outputting an energy consumption report.
Further, in step 1, the substep of obtaining the historical load and energy consumption information of the server is:
step 1.1, acquiring device information of a server 30 days before the current time of a system through a server management terminal, wherein the device information comprises an average load and an average energy consumption of the server, carrying out dimension removal processing on the average load and taking a value of the average load, and the average load is recorded as a set L = { L1, L2, \8230 \ 8230:, ln }, lx is the average load of the x-th server, the average energy consumption is recorded as E = { E1, E2, \8230; \ 8230, en }, ex is the average energy consumption of the x-th server, and n is the number of the servers;
the average energy consumption is the electric energy consumption of the server in the last 30 days;
step 1.2, acquiring a preset service priority of each server, and recording the service priority as a service priority set P = { P1, P2, P3, \8230 \ 8230;, pn }, wherein Px is the service priority of the xth server;
the service priority is sorted from small to large according to the average load of the server in the last 30 days, and the sorted serial number is used as a preset service priority;
step 1.3, energy consumption information of each server is obtained through an energy consumption management terminal and is transmitted to the server management terminal, a relation LT (L0) between the traffic and the energy consumption information is established, and the L0 is an instant load of the server;
step 1.4, obtaining a load value Le of the lowest point of the energy consumption and the load through the relation LT (L0) of the average load and the energy consumption obtained in the step 1.3, wherein the average load and the load value are expressed in percentage, and the load range is [0%,100% ].
The load value is the average load of the CPU for 10 minutes.
Further, in step 2, the substep of obtaining the task list is:
a task list J and a desired elapsed time Te for the task list are obtained.
For example, task list J is: the rendering method comprises the steps of processing a rendering task of three-dimensional image data, averagely dividing the imported three-dimensional image data into a plurality of pieces of sub three-dimensional image data with the same size, rendering each piece of three-dimensional image data to be used as a processing task M, and using a sequence formed by each processing task to be used as a task list J.
The expected elapsed time Te for the task list is the average time required to complete each processing task.
Further, in step 3, the substeps of performing task allocation and setting the server operating mode are:
step 3.1, the number U of servers always in the working mode is set AL Number of servers U in the initial state in the operating mode i The number of servers in the low power consumption mode is n-U i N is the number of servers;
the working mode of the server is as follows: the server starts to process tasks, and the CPU of the server is in a running state.
The low power consumption mode (or called as low power consumption mode) of the server is as follows: the CPU of the server is in a dormant state, and is converted into a working mode after waiting for external interruption.
3.2, refreshing the current task list, calculating the time T0 for the server in the current working mode to finish the current task list, if T0 is more than Te and the value of T0-Te is more than a set delay tolerance value delta, skipping to the step 3.3, if T0 is less than Te and the value of Te-T0 is less than a second threshold value, skipping to the step 3.4, and if not, waiting for a second time interval T2 and re-executing the step 3.2;
step 3.3, if the number U of servers in the working mode currently i If the number of the servers in the low power consumption mode is less than n, switching the x servers in the low power consumption mode to the working mode, and if the number of the servers in the working mode is U i The sum of x and n is greater than or equal to the number of servers, x is U i + x-n, otherwise, keeping x unchanged, and counting the number U of the servers in the current working mode i Is set as U i + x, skipping to step 3.2 after a set first time interval T1; the substep of switching x servers in the low power consumption mode to the working mode is to obtain the x servers according to the value of the service priority set P of the servers, and specifically comprises the following steps:
sorting the elements in the service priority set P from high to low, sequentially selecting the servers corresponding to the sub-elements in the sorted set P, if the selected server is in the working mode, selecting the server corresponding to the next element in the sorted set P to judge whether the server is in the working mode, and switching the selected x servers to the working mode until x servers in the low power consumption mode are found;
step 3.4, wait for the second timeThe interval T2 is set, whether a new task exists in the task list is monitored, if the new task exists, the difference between the time T0 of the current task list completed by the current server in the working mode and the expected consumed time Te of the current task list is calculated, if the value of T0-Te is larger than the set delay tolerance value delta, the step 3.3 is skipped, if T0 is larger than Te and the value of Te-T0 is smaller than a second threshold value, the y servers in the working mode are switched to the low power consumption mode, and the number U of the servers in the working mode is set i Set the value to U i -y，C h-a Is set to C h-a Y, if U i The value of-y is less than the number of servers U always on AL Then y is equal to U i -U AL Waiting for a first time interval T1, and skipping to the step 3.2;
the substep of switching y servers in the working mode to the low power consumption mode is to obtain the y servers according to the value of the service priority set P of the servers, and specifically comprises the following steps:
and sequencing the elements in the service priority set P according to the low to high sequence, sequentially selecting the servers corresponding to the sub-elements in the sequenced set P, if the selected server is in the working mode, selecting the server corresponding to the next element in the sequenced set P to judge whether the server is in the working mode, and switching the selected y servers to the low power consumption mode until y servers in the working mode are found.
In one embodiment, the server type is HTTP servers, the number of servers is 1000, and the number of servers in the working mode is U AL 64, number of servers U in the initial state in the operating mode i 132, a delay tolerance delta of 100ms, and x is given a value of [10, 50%]And y has a value of [10, 40 ]]The first time interval T1 is 10s, the second time interval T2 is 15s, and the second threshold is 200ms.
In one embodiment, the server type is GPU server, the number of servers is 200, and the number of servers in the working mode is U AL 10, number of servers in the initial state in the operating mode U i 20, the delay tolerance delta is 10s, x is taken as [2,5%]And y has a value of [4, 10]The first time interval T1 is120s, a second time interval T2 of 150s and a second threshold of 5s.
In one embodiment, the server type is archive server, the number of servers is 500, and the number of servers in the working mode is U AL 15, number of servers in initial state in operating mode U i 20, the delay tolerance value delta is 5s, x is [6, 20 ]]And y has a value of [8, 15 ]]The first time interval T1 is 10s, the second time interval T2 is 15s, and the second threshold is 5s.
Preferably, the value of x can also be determined by the following sub-steps:
x＝((T0-Te)/Te)×(|Lavg-Le|)×1.2×(n-U i )；
in the formula, T0 is the time T0 of the current working mode server to complete the current task list, te is the expected time consumption Te of the current task list, | Lavg-Le | is the absolute value of the difference between the average load and the energy consumption of the current working mode server and the load value Le at the lowest point of the load, | Lavg-Le | is the number of servers, U is the number of the servers i The number of servers currently in the operating mode.
Preferably, the value of y can also be determined by the following sub-steps:
y＝((Te-T0)/Te)×(|Lavg-Le|)×1.4×U i ；
in the formula, T0 is the time T0 when the current working mode server completes the current task list, te is the expected time consumption Te of the current task list, | Lavg-Le | is the absolute value of the difference between the average load and the load value Le of the lowest point of the energy consumption and the load of the current working mode server, and U i The number of servers currently in the operating mode. Further, in step 4, the sub-step of outputting the energy consumption report is:
step 4.1, calculating the energy consumption reduction value ERI of each server:
ERi＝(Pi a -Pi h )×Ti h -(Pi a-h ×Ci a-h )-Pi h-a ×Ci h-a ，
where ERI is the power consumption reduction value of the ith server, pi a : power consumption of the ith server in the working mode, pi h : work of ith server in low power consumption modeConsuming Ti h : duration of the ith server in Low Power consumption mode, pi a-h : power consumption of the ith server in switching from the operating mode to the low power consumption mode, ci a-h : number of times of switching the ith server from the operating mode to the low power mode, pi h-a : power consumption for switching the ith server from the low power consumption mode to the active mode, ci h-a : switching the ith server from the low power consumption mode to the working mode for times;
step 4.2, calculating energy consumption reduction values GER of all servers:
in the formula, GEr% is the rate of energy consumption reduction of all servers, the range is [0%,100% ], GEr is the energy consumption reduction value GEr of all servers obtained in step 4.2, and GE is the total power consumption GE of all servers.
An energy consumption monitoring system for an IDC data center room, the system comprising:
each server is directly connected with the energy consumption management terminal, the server distribution terminal and the power consumption detection module through a network;
the server manages the terminal: the system is used for managing the servers in batches, distributing tasks and acquiring the states of the servers, wherein the states comprise the current load and the current mode of the servers;
energy consumption management terminal: the energy consumption information is acquired and transmitted to the server management terminal;
the server distributes the terminal: for assigning tasks to each server;
the power consumption detection module: the power consumption monitoring system is used for monitoring the power consumption of all the servers and sending power consumption data to the server management terminal. The energy consumption monitoring system for the IDC data center machine room can be operated in computing equipment such as a desktop computer, a notebook computer, a palm computer and a cloud server. The energy consumption monitoring system for the IDC data center room can operate by comprising a processor and a memory. Those skilled in the art will appreciate that the example is merely an example of an energy consumption monitoring system for an IDC data center room and does not constitute a limitation of an energy consumption monitoring system for an IDC data center room and may include more or less components than a proportion, or some components in combination, or different components, for example, the energy consumption monitoring system for the IDC data center room may further include input and output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, the processor is the control center of the energy consumption monitoring system operation system for the IDC data center room, and various interfaces and lines are utilized to connect various parts of the whole energy consumption monitoring system operation system for the IDC data center room.
The memory can be used for storing the computer program and/or the module, and the processor realizes various functions of the energy consumption monitoring system for the IDC data center room by running or executing the computer program and/or the module stored in the memory and calling data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Although the description of the present invention has been presented in considerable detail and with reference to a few illustrated embodiments, it is not intended to be limited to any such detail or embodiment or any particular embodiment so as to effectively encompass the intended scope of the invention. Furthermore, the foregoing describes the invention in terms of embodiments foreseen by the inventor for which an enabling description was available, notwithstanding that insubstantial modifications of the invention, not presently foreseen, may nonetheless represent equivalent modifications thereto.
In the description of the present specification, reference to the description of "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (4)
1. An energy consumption monitoring method for an IDC data center machine room is characterized by comprising the following steps:
step 1, acquiring historical load and energy consumption information of a server;
step 2, acquiring a task list;
step 3, distributing tasks and setting a server working mode;
step 4, outputting an energy consumption report;
in step 3, the substeps of performing task allocation and setting the working mode of the server are as follows:
step 3.1, the number U of servers always in the working mode is set AL Number of servers U in the initial state in the operating mode i The number of servers in the low power consumption mode is n-U i N is the number of servers;
step 3.2, refreshing the current task list, calculating the time T0 of the current working mode server for completing the current task list, if T0 is more than Te and the value of T0-Te is more than a set delay tolerance value delta, skipping to step 3.3, if T0 is more than Te and the value of Te-T0 is less than a second threshold value, skipping to step 3.4, otherwise waiting for a second time interval T2 and re-executing step 3.2;
wherein Te is expected time consumption of the task list;
step 3.3, if the number U of the servers currently in the working mode i If the number of the servers in the low power consumption mode is less than n, switching the x servers in the low power consumption mode to the working mode, and if the number of the servers in the working mode is U i If the sum of the sum x is more than or equal to the number n of the servers, x is Ui + x-n, otherwise, x is unchanged, and the number U of the servers in the current working mode is set i Is set as U i + x, skipping to step 3.2 after a set first time interval T1;
the substep of switching x servers in the low power consumption mode to the working mode is to obtain the x servers according to the value of the service priority set P of the servers, and specifically comprises the following steps:
sorting the elements in the service priority set P from high to low, sequentially selecting the servers corresponding to the sub-elements in the sorted set P, if the selected server is in the working mode, selecting the server corresponding to the next element in the sorted set P to judge whether the server is in the working mode, and switching the selected x servers to the working mode until x servers in the low power consumption mode are found;
step 3.4, waiting for a second time interval T2, monitoring whether a new task exists in the task list, if the new task exists, calculating the difference between the time T0 for the current server in the working mode to complete the current task list and the expected consumed time Te of the current task list, if the value of T0-Te is greater than a set delay tolerance value delta, skipping to step 3.3, if T0 is greater than Te and the value of Te-T0 is less than a second threshold value, switching y servers in the working mode to a low power consumption mode, and counting the number of the servers in the working mode, namely U i Set the value to U i -y，C h-a Is set to C h-a Y, if U i The value of-y is less than the number of servers U always on AL Then y has a value of U i -U AL Waiting for a first time interval T1, and skipping to the step 3.2;
the substep of switching y servers in the working mode to the low power consumption mode is to acquire the y servers according to the value of the service priority set P of the servers, and specifically comprises the following steps:
and sequencing the elements in the service priority set P according to the low to high sequence, sequentially selecting the servers corresponding to the sub-elements in the sequenced set P, if the selected server is in the working mode, selecting the server corresponding to the next element in the sequenced set P to judge whether the server is in the working mode, and switching the selected y servers to the low power consumption mode until y servers in the working mode are found.
2. The energy consumption monitoring method for the IDC data center room as claimed in claim 1, wherein in step 1, the substep of obtaining the historical load and energy consumption information of the server is:
step 1.1, acquiring device information of a server within 30 days before the current time of a system through a server management terminal, wherein the device information comprises an average load and an average energy consumption of the server, carrying out dimensionless processing on the average load and taking a numerical value of the average load, and the average load is recorded as a set L = { L1, L2, \8230:, ln }, lx is the average load of an x-th server, the average energy consumption is recorded as E = { E1, E2, \82308230, 8230, en }, ex is the average energy consumption of the x-th server, and n is the number of servers;
the average energy consumption is the electric energy consumption of the server in the last 30 days;
step 1.2, acquiring a preset service priority of each server, and recording the service priority as a service priority set P = { P1, P2, P3, \8230 \ 8230;, pn }, wherein Px is the service priority of the xth server;
step 1.3, energy consumption information of each server is obtained through an energy consumption management terminal and is transmitted to the server management terminal, a relation LT (L0) between the traffic and the energy consumption information is established, and the L0 is an instant load of the server;
step 1.4, obtaining a load value Le of the lowest point of the energy consumption and the load through the relation LT (L0) of the average load and the energy consumption obtained in the step 1.3, wherein the average load and the load value are expressed in percentage, and the load range is [0%,100% ]; the load value is the CPU 10 minute average load.
3. The method for monitoring the energy consumption of the IDC data center room according to claim 1, wherein in the step 2, the sub-step of obtaining the task list comprises the following steps:
a task list J and a desired elapsed time Te for the task list are obtained.
4. The method for monitoring energy consumption of the IDC data center room, according to claim 1, wherein in step 4, the sub-step of outputting the energy consumption report is:
step 4.1, calculating the energy consumption reduction value ERI of each server:
ERi=（Pi a -Pi h ）×Ti h -（Pi a-h ×Ci a-h ）-Pi h-a ×Ci h-a ，
where ERI is the energy consumption reduction value of the ith server, pi a : power consumption of the ith server in the working mode, pi h : power consumption of the ith server in Low Power consumption mode, ti h : duration of the ith server in Low Power consumption mode, pi a-h : the ith server is switched from the working mode to the low power consumptionPower consumption of the pattern, ci a-h : number of times of switching the ith server from the operating mode to the low power mode, pi h-a : power consumption for switching the ith server from the low power consumption mode to the active mode, ci h-a : switching the ith server from the low power consumption mode to the working mode for times;
step 4.2, calculating the energy consumption reduction values GER of all servers:
in the formula, n is the number of servers, and ERi is the energy consumption reduction value ERi of the ith server obtained in the step 4.1;
step 4.3, obtaining the total power consumption GE of all servers, and calculating the power consumption reduction ratio GER%:
GEr%=(GEr/(GEr+GE))×100%，
in the formula, GEr% is the rate of energy consumption reduction of all servers, the range is [0%,100% ], GEr is the energy consumption reduction value GEr of all servers obtained in step 4.2, and GE is the total power consumption GE of all servers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110960636.0A CN113821339B (en) | 2021-08-20 | 2021-08-20 | Energy consumption monitoring method and device for IDC data center machine room |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110960636.0A CN113821339B (en) | 2021-08-20 | 2021-08-20 | Energy consumption monitoring method and device for IDC data center machine room |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113821339A CN113821339A (en) | 2021-12-21 |
| CN113821339B true CN113821339B (en) | 2022-11-08 |
Family
ID=78922965
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110960636.0A Active CN113821339B (en) | 2021-08-20 | 2021-08-20 | Energy consumption monitoring method and device for IDC data center machine room |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113821339B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114780332A (en) * | 2022-03-25 | 2022-07-22 | 利德世普科技有限公司 | Energy consumption monitoring method for IDC data center machine room |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927231A (en) * | 2014-03-31 | 2014-07-16 | 华中科技大学 | Data-oriented processing energy consumption optimization dataset distribution method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063327B (en) * | 2010-12-15 | 2013-07-24 | 中国科学院深圳先进技术研究院 | Application service scheduling method with power consumption consciousness for data center |
| US8937822B2 (en) * | 2011-05-08 | 2015-01-20 | Paul Wilkinson Dent | Solar energy conversion and utilization system |
| CN109739332B (en) * | 2019-01-25 | 2022-05-03 | 华侨大学 | Multi-task general energy consumption optimization method |
-
2021
- 2021-08-20 CN CN202110960636.0A patent/CN113821339B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927231A (en) * | 2014-03-31 | 2014-07-16 | 华中科技大学 | Data-oriented processing energy consumption optimization dataset distribution method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113821339A (en) | 2021-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101320289B (en) | A method, system, and apparatus for improving multi-core processor performance | |
| CN105893148B (en) | A kind of accidental task low energy consumption dispatching method based on RM strategy | |
| CN103037109B (en) | Multicore equipment energy consumption management method and device | |
| JP2007336796A (en) | Peak-shift management server and power demand peak-shift method | |
| CN111245732B (en) | Flow control method, device and equipment | |
| CN113821339B (en) | Energy consumption monitoring method and device for IDC data center machine room | |
| CN105847385B (en) | A kind of cloud computing platform dispatching method of virtual machine based on operation duration | |
| CN109039342B (en) | Compression method and system and decompression method and system of output data | |
| WO2022135440A1 (en) | Llc resonant circuit control method and control apparatus, and terminal device | |
| CN105450784B (en) | The device and method of message distribution consumption node into MQ | |
| CN101819459B (en) | Heterogeneous object memory system-based power consumption control method | |
| CN116167581A (en) | Battery demand estimation method and device, scheduling method and computer equipment | |
| CN108415766B (en) | Rendering task dynamic scheduling method | |
| CN108549296B (en) | Automatic control method and device for industrial robot work saturation | |
| CN105100505B (en) | A kind of method and system that battery capacity is distributed for terminal applies | |
| CN115373860B (en) | Scheduling method, device and equipment of GPU (graphics processing Unit) tasks and storage medium | |
| CN110689175A (en) | Energy consumption optimization method for distributed green cloud data center with chaotic multiple universes | |
| CN113922411A (en) | Method and device for determining distributed photovoltaic absorption capacity | |
| CN108767883A (en) | A kind of response processing method of Demand-side | |
| CN111211615B (en) | Medium-voltage intelligent load control method and system for large-scale data center | |
| CN107748711A (en) | Method, terminal device and the storage medium of Automatic Optimal Storm degree of parallelisms | |
| CN112398172A (en) | Source-grid-load coordinated operation control method and related device | |
| CN111143055A (en) | Virtual cloud host pre-allocation method and device, readable storage medium and electronic equipment | |
| CN117040029B (en) | Power distribution network power dispatching method, device, computer equipment and storage medium | |
| CN116449935B (en) | Cluster energy-saving management method, electronic equipment and computer storage medium |
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 |