CN114744649A

CN114744649A - Control method, device, equipment, medium and program product of cloud computing unit

Info

Publication number: CN114744649A
Application number: CN202210437362.1A
Authority: CN
Inventors: 石启铮
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2022-04-19
Filing date: 2022-04-19
Publication date: 2022-07-12

Abstract

The disclosure provides a control method, device, equipment, medium and program product of a cloud computing unit, and relates to the technical field of computers, in particular to the technical field of cloud computing. The specific implementation scheme is as follows: detecting whether load balance exists between at least two line units included in a power supply line; under the condition of unbalanced load, selecting at least two unbalanced abnormal line units from the power supply line; and carrying out data migration on the abnormal cloud computing unit hooked by the abnormal line unit. The embodiment of the disclosure maintains load balance among the line units in a data migration mode.

Description

Control method, device, equipment, medium and program product of cloud computing unit

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, a medium, and a program product for controlling a cloud computing unit.

Background

The cloud computing data center is provided with massive cloud computing units and used for providing software and hardware resources of the cloud computing units to user computers and other equipment as required. The cloud computing units have different use conditions and different corresponding powers.

When power is supplied to the cloud computing data center, three-phase four-wire or three-phase five-wire is generally adopted, and a certain number of cloud computing units are connected to each phase of circuit in an articulated mode. The cloud computing units are different in power, so that the load of each phase of circuit is different. The load imbalance among the circuits of each phase can cause the loss of the power grid line. Therefore, it is important to ensure load balance of each phase during power supply.

Disclosure of Invention

The disclosure provides a control method, device, equipment, medium and program product for a cloud computing unit.

According to an aspect of the present disclosure, there is provided a control method of a cloud computing unit, including:

detecting whether load balance exists between at least two line units included in a power supply line;

under the condition of unbalanced load, selecting at least two unbalanced abnormal line units from the power supply line;

and carrying out data migration on the abnormal cloud computing unit hooked by the abnormal line unit.

According to another aspect of the present disclosure, there is provided a control apparatus of a cloud computing unit, including:

the load balancing detection module is used for detecting whether the load between at least two line units included in the power supply line is balanced or not;

the abnormal line unit selection module is used for selecting at least two unbalanced abnormal line units from the power supply line under the condition of unbalanced load;

and the data migration module is used for performing data migration on the abnormal cloud computing unit hooked by the abnormal line unit.

According to another aspect of the present disclosure, there is provided an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of controlling a cloud computing unit of any of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method of controlling a cloud computing unit according to any one of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of controlling a cloud computing unit of any of the embodiments of the present disclosure.

The load balance of the line unit is kept through the data migration mode.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1a is a schematic diagram of a control method of a cloud computing unit according to an embodiment of the present disclosure;

fig. 1b is an architecture diagram of a cloud computing center provided in accordance with an embodiment of the present disclosure;

fig. 1c is a schematic diagram of a power supply line provided according to an embodiment of the present disclosure to supply power to a cloud computing unit;

fig. 2 is a schematic diagram of a control method of a cloud computing unit according to an embodiment of the present disclosure;

fig. 3 is a schematic diagram of a control method of a cloud computing unit according to an embodiment of the present disclosure;

fig. 4 is a schematic diagram of a control method of a cloud computing unit according to an embodiment of the present disclosure;

fig. 5 is a schematic diagram of a control apparatus of a cloud computing unit provided according to an embodiment of the present disclosure;

fig. 6 is a block diagram of an electronic device to implement a control method of a cloud computing unit according to an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1a is a flowchart of a control method for a cloud computing unit according to an embodiment of the present disclosure, which may be applied to a case where load balancing between line units is guaranteed through data migration. The method of the embodiment may be executed by a control device of a cloud computing unit, where the device may be implemented in a software and/or hardware manner, and is specifically configured in an electronic device with a certain data operation capability, where the electronic device may be a client device or a server device, and the client device may be, for example, a mobile phone, a tablet computer, a vehicle-mounted terminal, a desktop computer, and the like.

S110, whether load balance exists between at least two line units included in a power supply line is detected.

The power supply circuit is used for supplying power to the cloud computing unit, and comprises a neutral line and at least one phase line, wherein one phase line is called a line unit. At least one cloud computing unit is connected in each line unit in an articulated mode, and the line units supply power to the connected cloud computing units.

The cloud computing unit is equipment for providing software and hardware resources for cloud computing unit users in the cloud computing center. The architecture of the cloud computing center is shown in fig. 1b, and comprises a cloud computing management center and a plurality of cloud computing units. The cloud computing management center is communicated with the cloud computing units and the cloud computing units through the internal local area network. The cloud computing management center can receive a cloud computing unit allocation request initiated by a user through a network, and allocate the cloud computing units to the user according to the cloud computing unit allocation request.

Illustratively, the power supply line is a three-phase four-wire circuit or a three-phase five-wire circuit. Fig. 1C shows that a three-phase four-wire power supply line is adopted to supply power to the cloud computing units, wherein the three-phase four-wire power supply line comprises line units A, B and C and a center line, the line units a are connected with cloud computing units a1, a2, A3 and … AN in a hanging manner, the line units B are connected with cloud computing units B1, B2, B3 and … BN in a hanging manner, and the line units C are connected with cloud computing units C1, C2, C3 and … CN in a hanging manner.

The cloud computing units connected with the line units have larger operating power difference, so that the loads of different line units are unbalanced. When the loads of the line units are unbalanced, current flows through the neutral line, so that loss of the neutral line is generated, namely loss of a power supply line is increased. In addition, when the loads of the line units are unbalanced, the loss of the distribution transformer is increased.

In the embodiment of the present disclosure, in order to maintain load balancing among line units in a power supply line, it is first required to detect whether load balancing exists among at least two line units included in the power supply line. Specifically, for one line unit, the current flowing through the line unit is measured through an ammeter, and the voltage of each cloud computing unit connected in the line unit is measured through a voltmeter. And then calculating the operating power of each cloud computing unit according to the measured current and voltage, and calculating the load value of each line unit according to the operating power of each cloud computing unit. Finally, the load value of the line units can be calculated, the unbalance rate among the line units is calculated, and under the condition that the unbalance rate is larger than a set threshold value, the load unbalance among the line units is determined. Where the imbalance ratio between line units is (maximum load value-minimum load value)/maximum load value, for example, if the power supply line is a three-phase four-wire circuit in which the load values of 3 line units are 10W, 5W, and 9W, respectively, the imbalance ratio between line units is (10-5)/10 is 0.5.

In addition, the operating power of the cloud computing units can be calculated according to the utilization rate of each component in the cloud computing units, and the load value of each line unit is calculated according to the operating power of each cloud computing unit. And finally, calculating the unbalance rate among the line units according to the load values of the line units, and determining the load unbalance among the line units under the condition that the unbalance rate is greater than a set threshold value. Wherein, through the rate of utilization of each part in the cloud computing unit, calculate cloud computing unit's operating power, specifically do: and calculating the product of the maximum power and the utilization rate of each part in the cloud computing unit to obtain the operating power of the current part, and summing the operating powers of the parts to obtain the operating power of the current cloud computing unit.

It should be noted that, in order to improve the accuracy of determining load balancing, the operating power of the cloud computing unit may be calculated multiple times within a set time period, an average value of the operating power of the cloud computing unit is obtained, and whether load balancing is performed between the line units is determined according to the average value.

In a specific example, the main components of the cloud computing Unit include a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a memory. The maximum power of each component can be obtained when the cloud computing unit is shipped, for example, the maximum power of the cloud computing unit CPU is 10W, the maximum power of the GPU is 30W, and the maximum power of the memory is 25W. At a certain collection time point, the usage rate of the CPU is 20%, the usage rate of the GPU is 30%, and the usage rate of the memory is 50%, and then at the collection time point, the operating power of the cloud computing unit is 10 × 20% + 30% +25 × 50% + 23.5W.

Furthermore, the utilization rate of each component of the cloud computing unit can be obtained according to a set time interval, the operating power is calculated, the obtained operating power is averaged, and the average value is used as the operating power of the cloud computing unit. For example, for a certain cloud computing unit, the operating power is acquired every 10 minutes, and 5 times in total are acquired, and then the average value of the 5 acquired operating powers is obtained as the operating power of the cloud computing unit.

Further, the load value of each line unit is calculated according to the running power of the cloud computing unit connected with each line unit in a hanging mode. For example, 3 cloud computing units are hung on the line unit a, the operating powers are 30W, 20W and 35W respectively, and the load value of the line unit a is the sum of the three, namely 85W. Similarly, the load values of other line units are calculated, the imbalance rate among the line units is calculated according to the load values, and whether the load is balanced or not is determined according to the imbalance rate.

And S120, selecting at least two unbalanced abnormal line units from the power supply line when the loads are unbalanced.

In the embodiment of the disclosure, under the condition of unbalanced load among a plurality of line units of a power supply line, at least two unbalanced abnormal line units are selected from the power supply line so as to adjust the load of the at least two abnormal line units, thereby realizing the load balance among the line units. Specifically, the line unit with the largest load value and the line unit with the smallest load value are acquired among the line units as abnormal line units. Of course, in the case where the power supply line includes a large number of line units, it is also possible to select a plurality of abnormal line units depending on the load values of the line units, for example, to select the line unit having the largest and the next largest load values and the line unit having the smallest and the next smallest load values as the abnormal line units.

In one specific example, where the power supply line is a three-phase four-wire system, including line cells A, B and C, the load values are 153W, 39W, and 89W, respectively. In the case of load imbalance, the line unit a with the highest load value and the line unit B with the lowest load value may be regarded as abnormal line units.

And S130, performing data migration on the abnormal cloud computing unit hooked by the abnormal line unit.

After the abnormal line units are determined in the power supply line, in order to keep load balance among the line units, data migration is carried out on the abnormal cloud computing units connected with the abnormal line units in a hanging mode. Specifically, after the abnormal line unit is determined, the abnormal cloud computing unit is further determined in at least one cloud computing unit hooked on the abnormal line unit, the cloud computing unit with the highest operating power in the abnormal line unit with the higher load is used as the abnormal cloud computing unit, and the cloud computing unit in the idle state in the abnormal line unit with the lower load is used as the abnormal cloud computing unit. And finally, transferring the user data contained in the abnormal cloud computing unit of the abnormal line unit with the higher load to the abnormal cloud computing unit of the abnormal line unit with the lower load. The user data includes configuration data and storage data when the user uses the cloud computing unit, for example, the configuration data includes font size, notification bar type, whether the configuration data is in a night mode, time and date format or default input method, and the storage data may include a document created by the user or a file downloaded through a network.

In one particular example, the supply line includes line cells A, B and C, with load values of 153W, 39W, and 89W, respectively. The line unit A is connected with 4 cloud computing units in a hanging mode, and the load values are 46W, 28W, 47W and 32W respectively; the line unit B is hung with 4 cloud computing units, the load values are 6W, 5W, 6W and 22W respectively, and the first two cloud computing units are not distributed with users. In the case of load imbalance, the line unit a with the highest load value and the line unit B with the lowest load value are regarded as abnormal line units. Further, the cloud computing unit with the highest power in the line unit a is determined as an abnormal cloud computing unit, that is, the cloud computing unit with the power of 47W in the line unit a is determined as an abnormal cloud computing unit. And randomly selecting one of the cloud computing units in the unallocated state in the line unit B as an abnormal cloud computing unit. Finally, the user data of the abnormal cloud computing unit in the line unit a can be migrated to the abnormal cloud computing unit in the line unit B.

In another specific example, the supply line includes line cells A, B and C, with load values of 153W, 39W, and 89W, respectively. The line unit A is connected with 4 cloud computing units in a hanging mode, the 4 cloud computing units are all in an allocated state, and the corresponding last user data migration time is 1 month, 5 days, 1 month, 3 days, 1 month, 1 day and 1 month, 6 days; the line unit B is connected with 4 cloud computing units in a hanging mode, wherein the line unit B comprises two cloud computing units in an unallocated state, and the last migration time of the cloud computing units in the unallocated state is 1 month, 8 days and 1 month, 1 day respectively. In the case of load imbalance, the line unit a with the highest load value and the line unit B with the lowest load value are regarded as abnormal line units. Further, the cloud computing unit in the allocated state is determined in the line unit a, and the cloud computing unit with the last migration time farthest from the current time is determined as the abnormal cloud computing unit in the allocated cloud computing unit, that is, the cloud computing unit with the last migration time of 1 month and 1 day is determined as the abnormal cloud computing unit. Meanwhile, the cloud computing unit in the unallocated state is determined in the line unit B, and the cloud computing unit with the last migration time farthest from the current migration time is determined in the unallocated cloud computing unit as the abnormal cloud computing unit. And finally, migrating the user data of the abnormal cloud computing unit in the line unit A to the abnormal cloud computing unit in the line unit B.

It is noted that more than one pair of abnormal cloud computing units may be determined in line unit a and line unit B, and after determining the first pair of abnormal cloud computing units, the next pair of abnormal cloud computing units may continue to be determined in line units a and B until the imbalance ratio between line units a and B is below the set threshold.

According to the technical scheme of the embodiment of the disclosure, whether at least two line units included in the power supply line are in load balance is detected, under the condition of unbalanced load, at least two unbalanced abnormal line units are selected from the power supply line, data migration is carried out on the abnormal cloud computing units hung on the abnormal line units, line unit switching is achieved through a data migration mode, power failure of the abnormal cloud computing units is not needed, and the cost of power supply line switching is reduced.

Fig. 2 is a schematic diagram of a control method of a cloud computing unit in the embodiment of the present disclosure, which is further refined on the basis of the embodiment described above, and provides specific steps for performing data migration on an abnormal cloud computing unit hooked by an abnormal line unit. A control method of a cloud computing unit provided in an embodiment of the present disclosure is described below with reference to fig. 2, where the method includes the following steps:

s210, detecting whether load balance exists between at least two line units included in a power supply line.

And S220, under the condition of unbalanced load, selecting at least two unbalanced abnormal line units from the power supply line.

And S230, determining an overload line unit and a light load line unit from the abnormal line units according to the load values of the abnormal line units.

In the embodiment of the disclosure, after the abnormal line unit is determined in the power supply line, the abnormal line unit may be divided into the overload line unit and the light-load line unit according to the load value of the abnormal line unit. Specifically, a line unit with a large load value in the abnormal line units is used as an overload line unit, and a line unit with a small load value is used as a light-load line unit.

In one specific example, line cells A, B and C are included in the supply line, with load values of 153W, 39W, and 89W, respectively. And determining load imbalance among the line units in the power supply line by calculating the imbalance rate among the line units, and taking the line unit A with the highest load value and the line unit B with the highest load value as abnormal line units. Furthermore, the line unit a with a higher load value in the abnormal line units is taken as an overload line unit, and the line unit B with a smaller load value is taken as a light load line unit.

And S240, carrying out data migration on the abnormal cloud computing units hooked by the overload line unit and the light load line unit.

After the overload line unit and the light-load line unit are determined, one or more abnormal cloud computing units can be determined in the cloud computing units connected with the overload line unit according to the operating power of the cloud computing units. And meanwhile, one or more cloud computing units in an idle state (namely cloud computing units without users) are selected from the cloud computing units connected with the light-load line units in an attached mode to serve as abnormal cloud computing units. And finally, migrating the user data of the abnormal cloud computing unit in the overload line unit to the abnormal cloud computing unit in the light load line. Load balance among the line units is achieved only through transferring user data, power failure and manual carrying of the cloud computing units are not needed, labor cost for maintaining load balance is reduced, and meanwhile influences on use of users can be reduced.

In a specific example, the overload line unit and the light-load line unit are respectively connected with 3 cloud computing units in a hanging manner, the cloud computing unit with the highest operating power can be selected from the overload line unit as the abnormal cloud computing unit, and one cloud computing unit in an idle state can be selected from the light-load line unit as the abnormal cloud computing unit. And finally, migrating the user data of the abnormal cloud computing unit in the overload line unit to the abnormal cloud computing unit in the light-load line unit.

In another specific example, the overload line unit and the light-load line unit are respectively connected with 3 cloud computing units, at least one first candidate cloud computing unit in an allocated state can be determined in the overload line unit, and the cloud computing unit with the longest last migration time and the longest current migration time is selected as the abnormal cloud computing unit in the first candidate cloud computing units. Meanwhile, the cloud computing unit in the unallocated state is determined to be used as a second candidate cloud computing unit in the light load line unit, and the cloud computing unit with the longest last migration time and the longest current time is selected as an abnormal cloud computing unit in the second candidate cloud computing unit. And finally, migrating the user data of the abnormal cloud computing unit in the overload line unit to the abnormal cloud computing unit in the light-load line unit.

Optionally, the data migration of the abnormal cloud computing unit hooked by the overload line unit and the light-load line unit includes:

acquiring at least one distributed cloud computing unit in a distributed state from an overload line unit, and determining a first abnormal cloud computing unit in the distributed cloud computing units according to the last migration time associated with the distributed computing units;

acquiring at least one unallocated cloud computing unit in an unallocated state from the light-load line unit, and determining a second abnormal cloud computing unit in the unallocated cloud computing unit according to the last migration time associated with the unallocated cloud computing unit;

and migrating the user data in the first abnormal cloud computing unit to a second abnormal cloud computing unit.

In this optional embodiment, a specific manner of performing data migration on the abnormal cloud computing unit hooked by the overload line unit and the light-load line unit is provided: firstly, at least one distributed cloud computing unit in a distributed state is obtained from an overload line unit, and a first abnormal cloud computing unit is determined in the distributed cloud computing unit according to the last migration time associated with the distributed cloud computing unit. Meanwhile, at least one unallocated cloud computing unit in an unallocated state is obtained from the light-load line unit, and a second abnormal cloud computing unit is determined in the unallocated cloud computing unit according to the last migration time associated with the unallocated cloud computing unit. And finally, migrating the user data in the first abnormal cloud computing unit to the second abnormal cloud computing unit, and emptying the user data in the first abnormal cloud computing unit.

Specifically, in the overload line unit, the cloud computing unit with the last migration time farthest from the current time may be selected as the first abnormal cloud computing unit from among the allocated cloud computing units according to the last migration time associated with the allocated computing unit. Similarly, in the light load line unit, according to the last migration time associated with the unallocated computing units, the cloud computing unit with the last migration time farthest from the current time is selected from the unallocated cloud computing units as the second abnormal cloud computing unit. The abnormal cloud computing unit is determined according to the last migration time of the cloud computing unit, so that frequent migration of the cloud computing unit can be avoided, and damage to a memory of the cloud computing unit caused by frequent large-batch reading and writing is avoided.

It should be noted that in this alternative embodiment, more than one first abnormal cloud computing unit may be determined in the overloaded line unit, and also, more than one second abnormal cloud computing unit may be determined in the lightly loaded line unit, that is, a plurality of pairs of the first abnormal cloud computing unit and the second abnormal cloud computing unit may be determined. Specifically, after the first abnormal cloud computing unit and the second abnormal cloud computing unit are determined, the next group of the first abnormal cloud computing unit and the second abnormal cloud computing unit may be selected from the overloaded line unit and the lightly loaded line unit respectively according to the last migration time, and the selection mode is the same as the first selection mode, and is not described here again.

In a specific example, the power supply line includes 3 line units A, B and C, where 4 cloud computing units are respectively hung in the line units A, B and C, and specific information of each cloud computing unit is as shown in table 1, where the specific information includes a line unit to which the cloud computing unit belongs, power of the cloud computing unit, users allocated to the cloud computing unit, and last data migration time.

TABLE 1

From the power of the cloud computing unit, the load of line unit a is 153W, the load of line unit B is 6+5+6+22 is 39W, and the load of line unit C is 45+33+5+6 is 89W. The imbalance ratio between the line units in the power supply line is (153-39)/153-74.5%, and the imbalance ratio is greater than a set threshold value (50%). At this time, the line unit a with the largest load value and the line unit B with the smallest load value may be determined as abnormal line units, and the line unit a is an overloaded line unit and the line unit B is a light-loaded line unit.

Further, at least one allocated cloud computing unit 01, 02, 03, and 04 in an allocated state is determined in line unit a, and at least one unallocated cloud computing unit 05 and 06 in an unallocated state is determined in line unit B. Further, the cloud computing unit 03 with the last data migration time farthest from the current time may be selected as a first abnormal cloud computing unit from among the allocated cloud computing units hooked by the line unit a, and the cloud computing unit 06 with the last data migration time farthest from the current time may be selected as a second abnormal cloud computing unit from among the unallocated cloud computing units hooked by the line unit B.

After the first and second anomalous cloud computing units are determined, the next group of first and second anomalous cloud computing units may continue to be selected in line unit a and line unit B until the following conditions are satisfied:

a. the unbalance rate between the line units is lower than a set threshold value;

b. the unassigned cloud computing unit does not exist in the line unit B;

c. the number of the abnormal cloud computing units exceeds a set number threshold.

According to the technical scheme of the embodiment of the disclosure, whether load balance exists between at least two line units included in a power supply line is detected, at least two unbalanced abnormal line units are selected from the power supply line under the condition of unbalanced load, further, an overloaded line unit and a lightly loaded line unit are determined from the abnormal line units according to the load values of the abnormal line units, data migration is finally carried out on the abnormal cloud computing units connected with the overloaded line units and the lightly loaded line units, power supply line switching is achieved through a data migration mode, power failure of the abnormal cloud computing units is not needed, and the cost for maintaining the load balance can be reduced.

Fig. 3 is a schematic diagram of a control method of a cloud computing unit in an embodiment of the present disclosure, which is further detailed on the basis of the above embodiment, and provides a specific step of detecting whether load balancing exists between at least two line units included in a power supply line. A control method of a cloud computing unit provided in the embodiment of the present disclosure is described below with reference to fig. 3, where the method includes the following steps:

s310, acquiring the load values of the line units, and determining the load unbalance rate between at least two line units according to the load values.

In the embodiment of the disclosure, the load values of the line units are obtained, and then the imbalance rate of at least two line units is determined according to the load value of each line unit, so as to determine whether the load between the line units included in the power supply line is balanced or not according to the imbalance rate. Specifically, the utilization rates of all parts of the cloud computing unit in the line unit can be obtained, the power of the cloud computing unit is further determined according to the utilization rates, and further, the load value of the line unit is obtained according to the sum of the power of the cloud computing units connected with the line unit in a hanging mode. Finally, the unbalance rate between the line units can be calculated according to the highest load value and the lowest load value in the line units of the power supply line.

Illustratively, the supply line includes line cells A, B and C, with load values of 10W, 5W and 9W, respectively. The imbalance ratio between the line units in the power supply line is (10-5)/10 is 0.5.

Optionally, obtaining the load value of the line unit includes:

determining the power of the cloud computing unit according to the utilization rate of working components in the cloud computing unit;

and determining the load value of the line unit according to the power of the cloud computing unit.

In this optional embodiment, the utilization rates of the working components in the cloud computing unit, for example, the utilization rates of the CPU, the GPU and the memory, are obtained, and the power of the cloud computing unit is calculated based on the maximum power and the utilization rates of the components. And then summing the power of the cloud computing units hung on the same line unit to obtain the load value of the line unit. The power of the cloud computing unit is computed through the utilization rate of the working parts of the cloud computing unit, measuring equipment such as a power meter, an ammeter or a voltmeter and the like do not need to be connected to the line unit externally, and the hardware cost and the line installation complexity are reduced.

It is noted that before calculating the load value of the power supply line unit, the user login and new user allocation request functions of the cloud computing unit may be disabled to avoid the situation that the load of the line unit changes during the calculation process.

And S320, determining that the load is unbalanced between at least two line units when the load imbalance ratio reaches a set threshold value.

In the embodiment of the disclosure, the load imbalance of at least two line units is determined when the load imbalance rate reaches a set threshold. For example, the power supply line includes line cells A, B and C, the load values are 153W, 39W, and 89W, respectively, and the threshold is set to 50%. And calculating the unbalance rate (153-39)/153-74.5% according to the load values of the line units, and obviously determining the load unbalance between at least two line units in the power supply line if the unbalance rate is higher than a set threshold value. By calculating the load unbalance rate and comparing the unbalance rate with a set threshold value, whether the line unit is in load balance or not is determined, balance between load balance and migration frequency can be realized by setting the threshold value, and line loss caused by overhigh migration frequency or extremely unbalanced long-term load is avoided.

And S330, selecting at least two unbalanced abnormal line units from the power supply line under the condition of unbalanced load.

And S340, performing data migration on the abnormal cloud computing unit hooked by the abnormal line unit.

According to the technical scheme of the embodiment of the disclosure, the load values of the line units are obtained, the load unbalance rate between the at least two line units is determined according to the load values, and the load unbalance between the at least two line units is determined under the condition that the load unbalance rate reaches the set threshold value. Furthermore, at least two unbalanced abnormal line units are selected from the power supply line, data migration is carried out on the abnormal cloud computing units connected with the abnormal line units in a hanging mode, and load balance of the line units can be maintained under the condition that the abnormal cloud computing units are not powered off.

Fig. 4 is a schematic diagram of a control method of a cloud computing unit in an embodiment of the present disclosure, which is further refined on the basis of the above embodiment, and provides specific steps before detecting whether load balancing exists between at least two line units included in a power supply line. A control method of a cloud computing unit provided in the embodiment of the present disclosure is described below with reference to fig. 4, which includes the following steps:

s410, determining the number of online users at the acquisition time of at least two candidate data according to historical operation data of the cloud computing unit.

In the embodiment of the disclosure, in order to avoid a great influence on users of the cloud computing unit caused by data migration, the number of online users at the time of collecting at least two candidate data may be determined according to historical operating data of the cloud computing unit, so as to obtain the time when the number of online users is minimum. The number of online users refers to the number of all users using the cloud computing unit at the data acquisition time.

In a specific example, the number of online users at each integral point in a day may be obtained according to historical operating data of the cloud computing unit within 1 month, and then an average value of the number of online users at each integral point within 1 month is calculated as a final number of online users at each integral point. For example, the number of online users of 0:00 per day for 1 month is obtained, and the average value is taken as the final number of online users of 0: 00.

And S420, taking the candidate data acquisition time with the least number of online users as the load balancing detection time.

In the embodiment of the present disclosure, after the number of online users at each candidate data acquisition time is obtained, the candidate data acquisition time with the smallest number of online users may be used as load balancing detection, so as to reduce the influence of data migration on the users. For example, at 0:00 the minimum number of online users, then 0:00 is used as the load balance detection time.

And S430, detecting whether the load of at least two line units included in the power supply line is balanced at the moment of detecting the load balance.

After the load balancing detection time is determined, whether the load between at least two line units included in the power supply line is balanced or not can be detected at the load balancing detection time, the time when the number of online users is large can be avoided, and the influence of data migration on the use of the users is avoided.

And S440, selecting at least two unbalanced abnormal line units from the power supply line when the loads are unbalanced.

And S450, performing data migration on the abnormal cloud computing unit hooked by the abnormal line unit.

Optionally, the embodiment of the present disclosure further includes:

responding to a cloud computing unit distribution request, and determining a line unit to be distributed according to the load value of the line unit;

and selecting the cloud computing units in the unallocated state from the line units to be allocated for allocation.

In this optional embodiment, after receiving a cloud computing unit allocation request initiated by a new user, the to-be-allocated line unit is determined according to the load value of the line unit, and then the cloud computing unit in the non-allocated state is selected from the to-be-allocated line units and allocated to the user. The cloud computing units are distributed according to the load values of the line units, so that load balance among the cloud computing units is further promoted.

In one particular example, the supply line includes line cells A, B and C, with load values of 153W, 39W, and 89W, respectively. After receiving a cloud computing unit allocation request initiated by a new user, selecting a line unit B with the smallest load value as a line to be allocated, and further randomly selecting one cloud computing unit from at least one cloud computing unit in an unallocated state in the line units B to allocate to the new user.

According to the technical scheme of the embodiment of the disclosure, the number of online users at the time of collecting at least two candidate data is determined according to historical operating data of the cloud computing unit, and the candidate data collecting time with the minimum number of online users is used as the load balancing detection time. Further, at the time of detecting load balancing, whether load balancing exists between at least two line units included in the power supply line is detected. And under the condition of unbalanced load, selecting at least two unbalanced abnormal line units from the power supply line, and performing data migration on the abnormal cloud computing units connected with the abnormal line units in a hanging mode.

According to an embodiment of the present disclosure, fig. 5 is a structural diagram of a control device of a cloud computing unit in an embodiment of the present disclosure, and the embodiment of the present disclosure is applied to a case where load balance between line units is ensured by data migration. The device is realized by software and/or hardware and is specifically configured in electronic equipment with certain data operation capacity.

A control apparatus 500 of a cloud computing unit shown in fig. 5 includes: a load balancing detection module 510, an abnormal line unit selection module 520 and a data migration module 530; wherein the content of the first and second substances,

a load balancing detection module 510, configured to detect whether load balancing exists between at least two line units included in a power supply line;

an abnormal line unit selecting module 520, configured to select at least two abnormal line units that are unbalanced from the power supply line when the loads are unbalanced;

and the data migration module 530 is configured to perform data migration on the abnormal cloud computing unit hooked by the abnormal line unit.

According to the technical scheme of the embodiment of the disclosure, whether at least two line units included in the power supply line are in load balance is detected, under the condition of unbalanced load, at least two unbalanced abnormal line units are selected from the power supply line, data migration is carried out on the abnormal cloud computing units hung on the abnormal line units, power supply line switching is achieved through a data migration mode, power failure of the abnormal cloud computing units is not needed, and the cost of power supply line switching is reduced.

Further, the data migration module 530 includes:

the overload circuit unit determining unit is used for determining an overload circuit unit and a light load circuit unit from the abnormal circuit unit according to the load value of the abnormal circuit unit;

and the data migration unit is used for performing data migration on the abnormal cloud computing unit connected with the overload line unit and the light load line unit in a hanging mode.

Further, the data migration unit is specifically configured to:

acquiring at least one distributed cloud computing unit in a distributed state from the overload line unit, and determining a first abnormal cloud computing unit from the distributed cloud computing units according to the last migration time associated with the distributed cloud computing units;

and migrating the user data in the first abnormal cloud computing unit to the second abnormal cloud computing unit.

Further, the load balancing detection module 510 includes:

the imbalance rate determining unit is used for acquiring the load values of the line units and determining the load imbalance rate between at least two line units according to the load values;

and the load balance detection unit is used for determining the load imbalance between the at least two line units under the condition that the load imbalance rate reaches a set threshold value.

Further, the imbalance rate determining unit is specifically configured to:

Further, the cloud computing unit control apparatus further includes:

the user number determining module is used for determining the number of online users at the acquisition moments of at least two candidate data according to historical operating data of the cloud computing unit before detecting whether load balance exists between at least two line units included in the power supply line;

the detection moment determining module is used for taking the candidate data acquisition moment with the least number of online users as the load balancing detection moment;

the load balancing detection module 510 is specifically configured to:

and detecting whether the load between at least two line units included in the power supply line is balanced at the load balance detection moment.

Further, the cloud computing unit control apparatus further includes:

the to-be-distributed line determining module is used for responding to the distribution request of the cloud computing unit and determining the to-be-distributed line unit according to the load value of the line unit;

and the cloud computing unit distribution module is used for selecting the cloud computing units in the unallocated state from the line units to be distributed for distribution.

The cloud computing unit control device provided by the embodiment of the disclosure can execute the method of the cloud computing unit control device provided by any embodiment of the disclosure, and has corresponding functional modules and beneficial effects of the execution method.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 6 illustrates a schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the apparatus 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, or the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The computing unit 601 executes the respective methods and processes described above, such as the control method of the cloud computing unit. For example, in some embodiments, the control method of the cloud computing unit may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of a computer program may be loaded onto and/or installed onto device 600 via ROM 602 and/or communications unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the control method of the cloud computing unit described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured by any other suitable means (e.g., by means of firmware) to perform the cloud computing unit's control method.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A control method of a cloud computing unit includes:

2. The method of claim 1, wherein the performing data migration on the abnormal cloud computing unit hooked by the abnormal line unit comprises:

determining an overload line unit and a light-load line unit from the abnormal line units according to the load values of the abnormal line units;

and carrying out data migration on the abnormal cloud computing units hooked by the overload line units and the light load line units.

3. The method of claim 2, wherein the migrating data of the abnormal cloud computing units hooked by the overloaded and the lightly loaded line units comprises:

migrating the user data in the first abnormal cloud computing unit to the second abnormal cloud computing unit.

4. The method of claim 1, wherein the detecting whether the load is balanced between at least two line units included in the power supply line comprises:

acquiring load values of the line units, and determining the load unbalance rate between at least two line units according to the load values;

and determining the load imbalance between the at least two line units under the condition that the load imbalance rate reaches a set threshold value.

5. The method of claim 4, wherein the obtaining a load value of a line unit comprises:

6. The method of claim 1, further comprising, prior to detecting whether load balancing is occurring between at least two line units included in the power supply line:

determining the number of online users at the acquisition moments of at least two candidate data according to historical operating data of the cloud computing unit;

taking the candidate data acquisition time with the least number of online users as the load balancing detection time;

detecting whether load balance exists between at least two line units included in a power supply line, including:

7. The method of claim 1, further comprising:

and selecting the cloud computing units in the unallocated state from the to-be-allocated line units for allocation.

8. A control apparatus of a cloud computing unit, comprising:

9. The apparatus of claim 8, wherein the data migration module comprises:

10. The apparatus according to claim 9, wherein the data migration unit is specifically configured to:

11. The apparatus of claim 8, wherein the load balancing detection module comprises:

12. The apparatus of claim 11, wherein the imbalance rate determining unit is specifically configured to:

13. The apparatus of claim 8, further comprising:

the load balancing detection module is specifically configured to:

14. The apparatus of claim 8, further comprising:

and the cloud computing unit distribution module is used for selecting the cloud computing units in the unallocated state from the to-be-distributed line units for distribution.

15. An electronic device, comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of controlling the cloud computing unit of any of claims 1-7.

16. A non-transitory computer readable storage medium storing computer instructions for causing the computer to execute the method of controlling the cloud computing unit according to any one of claims 1-7.

17. A computer program product comprising computer programs/instructions which, when executed by a processor, implement the method of controlling a cloud computing unit according to any of claims 1-7.