CN106936733B

CN106936733B - Bandwidth resource allocation method and device

Info

Publication number: CN106936733B
Application number: CN201511029265.5A
Authority: CN
Inventors: 李全峰
Original assignee: Beijing Kingsoft Cloud Network Technology Co Ltd; Beijing Kingsoft Cloud Technology Co Ltd
Current assignee: Beijing Kingsoft Cloud Network Technology Co Ltd; Beijing Kingsoft Cloud Technology Co Ltd
Priority date: 2015-12-31
Filing date: 2015-12-31
Publication date: 2020-08-28
Anticipated expiration: 2035-12-31
Also published as: CN106936733A

Abstract

The embodiment of the application discloses a method and a device for allocating bandwidth resources, which relate to the technical field of networks, wherein the method comprises the following steps: obtaining the estimated peak bandwidth of a target client and the estimated shared bandwidth of the target client; obtaining peak bandwidth of each machine room and shared bandwidth of each machine room; selecting a target machine room of the target client from each machine room according to the estimated peak bandwidth of the target client, the estimated shared bandwidth of the target client, the peak bandwidth of each machine room and the shared bandwidth of each machine room; and allocating bandwidth resources to the target client according to the bandwidth resources of the target computer room. By applying the scheme provided by the embodiment of the application to allocate the bandwidth resources, the bandwidth resources of the computer room can be fully utilized.

Description

Bandwidth resource allocation method and device

Technical Field

The present application relates to the field of network technologies, and in particular, to a method and an apparatus for allocating bandwidth resources.

Background

With the rapid development of network technology, networks are becoming an indispensable part of people's work and life. In practical application, when a client wants to construct a network, the client needs to determine which machine room of a network service provider the bandwidth resource needed by the client is allocated, and then can construct the network according to the bandwidth resource allocated by the machine room to access the network.

In the prior art, when determining which computer room the bandwidth resource required by the client is allocated, the bandwidth resource is generally randomly selected, and one computer room is randomly selected from currently available computer rooms to allocate the bandwidth resource required by the client to the client. Although the bandwidth resource allocation can be realized by applying the method, the peak bandwidth of each client in an individual computer room may be concentrated due to the random selection when selecting the computer room, for example, the peak bandwidth is too high for a period of time, and the peak bandwidth is too low for a period of time, and thus the bandwidth resource in the computer room is not fully utilized.

Disclosure of Invention

The embodiment of the application discloses a method and a device for allocating bandwidth resources, which are used for fully utilizing the bandwidth resources of a computer room.

In order to achieve the above object, an embodiment of the present application discloses a method for allocating bandwidth resources, where the method includes:

obtaining the estimated peak bandwidth of a target client and the estimated shared bandwidth of the target client;

obtaining peak bandwidth of each machine room and shared bandwidth of each machine room;

selecting a target machine room of the target client from each machine room according to the estimated peak bandwidth of the target client, the estimated shared bandwidth of the target client, the peak bandwidth of each machine room and the shared bandwidth of each machine room;

and allocating bandwidth resources to the target client according to the bandwidth resources of the target computer room.

In a specific implementation manner of the present application, in a case that the target client includes a plurality of clients, selecting a target machine room of the target client from each machine room according to the estimated peak bandwidth of the target client, the estimated shared bandwidth of the target client, the peak bandwidth of each machine room, and the shared bandwidth of each machine room includes:

according to the peak bandwidth of each machine room and the shared bandwidth of each machine room, calculating the machine room peak-to-peak ratio of each machine room, wherein the machine room peak-to-peak ratio is as follows: a ratio between a peak bandwidth of a room and a shared bandwidth of the room;

according to the machine room peak sharing ratio of each machine room, selecting the target machine room of each client in the target clients from the machine rooms according to the following mode:

estimating the machine room peak-to-peak ratio of each machine room after the client U is respectively added into each machine room according to the estimated peak bandwidth of the client U and the estimated shared bandwidth of the client U, wherein the client U is any one of the target clients;

determining the machine room peak sharing number meeting a first relation, wherein the first relation is as follows: the estimated machine room peak common ratio of the machine room is larger than the machine room peak common ratio of the machine room before estimation;

judging whether the machine room peak common ratio quantity is larger than a preset quantity threshold value or not;

if so, selecting a target machine room of the client U from machine rooms corresponding to the machine room peak ratio obtained by the estimation meeting the first relational expression;

and if not, selecting the target machine room of the client U from all the machine rooms according to the machine room peak sharing ratio obtained by estimation.

In a specific implementation manner of the present application, the selecting a target machine room of the client U from machine rooms corresponding to the estimated machine room peak-to-peak ratio satisfying the first relation includes:

calculating the ratio between the machine room peak common ratio obtained by the estimation which meets the first relational expression and the machine room peak common ratio before the estimation based on the same machine room;

and selecting the machine room corresponding to the ratio with the largest value in the calculated ratios as the target machine room of the client U.

In a specific implementation manner of the present application, the selecting a target machine room of the client U from each machine room according to the machine room peak-to-peak ratio obtained by estimation includes:

calculating the ratio of the estimated machine room peak common ratio to the machine room peak common ratio before estimation based on the same machine room;

In a specific implementation manner of the present application, after selecting a target machine room of the client U from each machine room according to the estimated machine room peak-to-peak ratio, the method further includes:

and marking the client U as a client of the changeable computer room.

In a specific implementation manner of the present application, in a case that the target client includes one client, the selecting a target machine room of the target client from each machine room according to the estimated peak bandwidth of the target client, the estimated shared bandwidth of the target client, the peak bandwidth of each machine room, and the shared bandwidth of each machine room includes:

estimating the machine room peak sharing ratio of each machine room after the target client is added into each machine room according to the estimated peak bandwidth of the target client and the estimated shared bandwidth of the target client, wherein the machine room peak sharing ratio is as follows: a ratio between a peak bandwidth of a room and a shared bandwidth of the room;

and selecting a target machine room for the target client according to the machine room peak sharing ratio obtained by estimation.

In a specific implementation manner of the present application, the selecting a target machine room for the target customer according to the machine room peak-to-peak ratio obtained by estimation includes:

calculating the client peak-to-peak ratio of the target client according to the estimated peak bandwidth of the target client and the estimated shared bandwidth of the target client, wherein the client peak-to-peak ratio is as follows: a ratio between the estimated peak bandwidth of the target client and the estimated shared bandwidth of the target client;

judging whether the customer peak ratio of the target customer is greater than a preset customer peak ratio threshold value or not;

if so, selecting the machine room corresponding to the machine room peak common ratio with the maximum value in the machine room peak common ratios obtained by estimation as the target machine room of the target client;

and if not, selecting the target machine room of the target client from machine rooms corresponding to the machine room peak ratio which is not lower than the machine room peak ratio obtained by estimation of the machine room peak ratio before estimation.

In a specific implementation manner of the present application, after selecting the target machine room of the target client from the machine rooms corresponding to the machine room peak-to-peak ratios obtained from the estimation that is not lower than the machine room peak-to-peak ratio before estimation, the method further includes:

and marking the target client as a client of the changeable computer room.

judging whether a client marked as a changeable computer room exists or not;

if yes, carrying out client merging processing on the target client and the client marked as the changeable computer room to obtain a merged client;

and selecting a target machine room for the merging client according to the estimated machine room peak sharing ratio, determining the target machine room as the target machine room of the target client, and changing the client marked as the changeable machine room from the machine room in which the client is currently located to the target machine room.

In a specific implementation manner of the present application, the bandwidth resource allocation method further includes:

selecting a customer value calculation rule aiming at the target customer from a preset customer value calculation rule base according to the customer peak sharing ratio of the target customer;

and calculating the customer value of the target customer according to the selected customer value calculation rule.

In order to achieve the above object, an embodiment of the present application discloses a bandwidth resource allocation apparatus, including:

the first bandwidth information acquisition module is used for acquiring the estimated peak bandwidth of a target client and the estimated shared bandwidth of the target client;

the second bandwidth information obtaining module is used for obtaining the peak bandwidth of each machine room and the shared bandwidth of each machine room;

the target machine room selection module is used for selecting the target machine room of the target client from each machine room according to the estimated peak bandwidth of the target client, the estimated shared bandwidth of the target client, the peak bandwidth of each machine room and the shared bandwidth of each machine room;

and the bandwidth resource allocation module is used for allocating bandwidth resources to the target client according to the bandwidth resources of the target computer room.

In a specific implementation manner of the present application, in a case that the target client includes a plurality of clients, the target machine room selecting module includes:

and the machine room peak sharing ratio calculation submodule is used for calculating the machine room peak sharing ratio of each machine room according to the peak bandwidth of each machine room and the shared bandwidth of each machine room, wherein the machine room peak sharing ratio is as follows: a ratio between a peak bandwidth of a room and a shared bandwidth of the room;

the first target machine room selection submodule is used for selecting a target machine room of each client in the target clients from each machine room according to the machine room peak sharing ratio of each machine room;

wherein, the first target machine room selection submodule includes:

the computer room peak sharing ratio estimation unit is used for estimating the computer room peak sharing ratio of each computer room after the client U is added into each computer room respectively according to the estimated peak bandwidth of the client U and the estimated shared bandwidth of the client U, wherein the client U is any one of the target clients;

the computer room peak ratio number determining unit is used for determining the computer room peak ratio number meeting a first relational expression, wherein the first relational expression is as follows: the estimated machine room peak common ratio of the machine room is larger than the machine room peak common ratio of the machine room before estimation;

the machine room peak common ratio number judging unit is used for judging whether the machine room peak common ratio number is larger than a preset number threshold value or not;

the first target machine room selection unit is used for selecting a target machine room of the client U from the machine rooms corresponding to the machine room peak sharing ratio obtained by the estimation of the first relational expression under the condition that the judgment result of the machine room peak sharing ratio quantity judgment unit is yes;

and the second target machine room selecting unit is used for selecting the target machine room of the client U from each machine room according to the machine room peak sharing ratio obtained by estimation under the condition that the judgment result of the machine room peak sharing ratio quantity judging unit is negative.

In a specific implementation manner of the present application, the first target equipment room selecting unit includes:

the first ratio operator unit is used for calculating the ratio between the machine room peak common ratio obtained by the estimation which meets the first relational expression and the machine room peak common ratio before the estimation based on the same machine room;

and the first target machine room selection subunit is used for selecting the machine room corresponding to the ratio with the largest value in the calculated ratios as the target machine room of the client U.

In a specific implementation manner of the present application, the second target equipment room selecting unit includes:

the second ratio operator unit is used for calculating the ratio between the machine room peak ratio obtained by estimation and the machine room peak ratio before estimation based on the same machine room;

and the second target machine room selecting subunit is used for selecting the machine room corresponding to the ratio with the largest value in the calculated ratios as the target machine room of the client U.

In a specific implementation manner of the present application, the first target machine room selection sub-module further includes:

and the client marking unit is used for marking the client U as a client of the changeable machine room after the second target machine room selecting unit selects the target machine room.

In a specific implementation manner of the present application, in a case that the target client includes one client, the target machine room selecting module includes:

a machine room peak sharing ratio estimation submodule, configured to estimate a machine room peak sharing ratio of each machine room after the target client is added to each machine room according to the estimated peak bandwidth of the target client and the estimated shared bandwidth of the target client, where the machine room peak sharing ratio is: a ratio between a peak bandwidth of a room and a shared bandwidth of the room;

and the second target machine room selection submodule is used for selecting a target machine room for the target client according to the machine room peak common ratio obtained by estimation.

In a specific implementation manner of the present application, the second target machine room selecting submodule includes:

a client peak-to-peak ratio calculating unit, configured to calculate a client peak-to-peak ratio of the target client according to the estimated peak bandwidth of the target client and the estimated shared bandwidth of the target client, where the client peak-to-peak ratio is: a ratio between the estimated peak bandwidth of the target client and the estimated shared bandwidth of the target client;

the client peak-to-peak ratio judging unit is used for judging whether the client peak-to-peak ratio of the target client is larger than a preset client peak-to-peak ratio threshold value or not;

a third target machine room selecting unit, configured to select, when the determination result of the client peak-to-peak ratio determining unit is yes, a machine room corresponding to the machine room peak-to-peak ratio with the largest value in the estimated machine room peak-to-peak ratios as a target machine room of the target client;

and the fourth target machine room selecting unit is used for selecting the target machine room of the target client from machine rooms corresponding to the machine room peak-to-peak ratio which is not lower than the machine room peak-to-peak ratio obtained by estimation of the machine room peak-to-peak ratio before estimation under the condition that the judgment result of the client peak-to-peak ratio judging unit is negative.

In a specific implementation manner of the present application, the bandwidth resource allocation apparatus further includes:

and the client marking module is used for marking the target client as a client of the changeable machine room after the fourth target machine room selecting unit selects the target machine room.

a marked client judging unit for judging whether a client marked as a changeable room exists;

a client merging processing unit, configured to, if the judgment result of the marked client judgment unit is yes, perform client merging processing on the target client and the client marked as the changeable room to obtain a merged client;

and the fifth target machine room selecting unit is used for selecting a target machine room for the merged client according to the machine room peak common ratio obtained by estimation, determining the target machine room as the target machine room of the target client, and changing the client marked as the changeable machine room from the machine room where the client is currently located to the target machine room.

a client peak-to-peak ratio calculation module, configured to calculate a client peak-to-peak ratio of the target client according to the estimated peak bandwidth of the target client and the estimated shared bandwidth of the target client, where the client peak-to-peak ratio is: a ratio between the estimated peak bandwidth of the target client and the estimated shared bandwidth of the target client;

the calculation rule selection module is used for selecting a client value calculation rule aiming at the target client from a preset client value calculation rule base according to the client peak-to-peak ratio of the target client;

and the client value calculation module is used for calculating the client value of the target client according to the selected client value calculation rule.

As can be seen from the above, in the scheme provided in the embodiment of the present application, when a target machine room is selected for a target client, factors such as an estimated peak bandwidth of the target client, an estimated shared bandwidth of the target client, a peak bandwidth of each machine room, and a shared bandwidth of each machine room are considered, so that machine room selection can be performed by synthesizing characteristics of each machine room, bandwidth resources can be allocated for the target client according to bandwidth resources of the target machine room, and then bandwidth resources of the machine room can be fully utilized, which is beneficial to solving the bandwidth pricing problem of the client, and is beneficial to reasonable collocation between clients, improving the utilization rate of the machine room, solving the scheduling of new clients, and further improving the profitability of the machine room.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flowchart of a first method for allocating bandwidth resources according to an embodiment of the present application;

fig. 2 is a schematic flowchart of a method for selecting a target machine room according to an embodiment of the present disclosure;

fig. 3 is a flowchart illustrating a second method for allocating bandwidth resources according to an embodiment of the present application;

fig. 4 is a flowchart illustrating a third bandwidth resource allocation method according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of a first bandwidth resource allocation apparatus according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of an apparatus for selecting a target machine room according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of a second bandwidth resource allocation apparatus according to an embodiment of the present application;

fig. 8 is a schematic mechanism diagram of a third bandwidth resource allocation apparatus according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The concepts involved in the embodiments of the present application are introduced first:

for a multi-IP (Internet Protocol) client, the peak bandwidth refers to the sum of the bandwidth peaks of the respective IPs of the client up to the calculation day; the shared bandwidth refers to the maximum value of the shared bandwidth of each IP of the client by the calculation day.

For a multi-client multi-IP computer room, the peak bandwidth refers to the sum of the shared bandwidths of all the IPs of each client by the calculation day; shared bandwidth refers to the maximum egress bandwidth of the room by the day of computation.

Customer peak-to-peak ratio, refers to the ratio between the peak bandwidth of a customer and the shared bandwidth of that customer.

Theoretically, the customer peak-to-peak ratio is always equal to or greater than 1, and the smaller the customer peak-to-peak ratio, the less profit the customer contributes to the network service provider on the bandwidth, and conversely, the larger the customer peak-to-peak ratio, the more profit the customer contributes to the network service provider on the bandwidth.

The machine room peak-to-peak ratio refers to a ratio between a peak bandwidth of one machine room and a shared bandwidth of the machine room.

Fig. 1 is a schematic flowchart of a first method for allocating bandwidth resources according to an embodiment of the present application, where the method includes:

s101: and obtaining the estimated peak bandwidth of the target client and the estimated shared bandwidth of the target client.

In practical application, the estimated peak bandwidth and the estimated shared bandwidth may be provided by the target client according to actual needs of the target client, and may have a certain error with the actual peak bandwidth and the actual shared bandwidth of the target client in practical application.

In addition, in order to improve user experience, the network service provider may sometimes provide trial service to the client, and in this case, the estimated peak bandwidth and the estimated shared bandwidth may be obtained according to data generated in a trial service stage of the target client, which is not limited in this application.

It should be noted that the target client may include only one client, and may also include a plurality of clients.

S102: and obtaining the peak bandwidth of each machine room and the shared bandwidth of each machine room.

S103: and selecting the target machine room of the target client from each machine room according to the estimated peak bandwidth of the target client, the estimated shared bandwidth of the target client, the peak bandwidth of each machine room and the shared bandwidth of each machine room.

Since the customer peak ratio of a customer can reflect the profit degree that the customer can bring to the service provider when using the bandwidth provided by the network service provider to a certain extent, or can reflect whether the customer can contribute more profits to the network service provider on the allocated bandwidth, and since the bandwidth resources of each machine room of the network service provider are limited, from the viewpoint of maximizing the profit of the network service provider, the customer can be placed in different machine rooms by adopting the principle of peak error in combination with the factors of the estimated peak bandwidth of the target customer, the estimated shared bandwidth of the target customer, the peak bandwidth of each machine room, and the shared bandwidth of each machine room, for example, the customer with the lower customer peak ratio and the customer with the higher customer peak ratio are matched into one machine room, the situation that customers with high peak-to-peak ratio or customers with low peak-to-peak ratio appear in the same machine room is avoided.

S104: and allocating the bandwidth resources for the target client according to the bandwidth resources of the target computer room.

As can be seen from the foregoing description, the customer peak ratio of a customer can reflect the profit that the customer may bring to the network service provider to some extent, so in an alternative implementation of the present application, the bandwidth allocation method may further include:

and calculating the client peak-to-peak ratio of the target client according to the estimated peak bandwidth of the target client and the estimated shared bandwidth of the target client, then selecting a client value calculation rule aiming at the target client from a preset client value calculation rule base according to the client peak-to-peak ratio of the target client, and calculating the client value of the target client according to the selected client value calculation rule.

In this optional implementation, the customer peak ratio is: a ratio between the estimated peak bandwidth of the target client and the estimated shared bandwidth of the target client.

In particular, the customer value may be understood to be specific to the network service provider, for example, the customer value may be: the target customer can be profits brought to the network service provider, etc.

The preset customer value calculation rule base may include a plurality of customer value calculation rules, and the customer value calculation rules may be calculation rules related to customer peak sharing of customers.

In a specific implementation manner of the present application, when the peak-to-peak ratio of a customer is greater than a preset peak-to-peak ratio threshold, the customer may be considered as a peak-to-peak ratio customer, the customer value calculation rule may be a rule for calculating profits according to a peak bandwidth of the customer, and further, a rule for calculating profits by using a step discount according to the peak-to-peak ratio of the customer on the basis of calculating profits according to the peak bandwidth of the customer; when the peak-to-common ratio of the client is smaller than the preset peak-to-common ratio threshold, the client can be considered as a low-peak-to-common ratio client, and the client value calculation rule can be a rule for calculating profits according to the shared bandwidth of the client, or a rule for calculating profits according to the fixed bandwidth.

For example, the preset peak-to-peak ratio threshold may be 2.

When calculating the profit according to the magnitude of the peak-to-peak ratio of the client based on the profit calculated according to the peak bandwidth of the client by taking a step discount, the range of the peak-to-peak ratio of the client and the calculated discount can be specifically shown in the following table 1.

TABLE 1

It should be noted that, the present application is only described as an example, and the preset peak-to-peak ratio threshold, the range of the client peak-to-peak ratio and the value of the calculated discount in practical application are not limited thereto.

Further, the network service provider may formulate a sales strategy based on the customer peak sharing ratio described above.

For example, when the customer peak is small (e.g., close to 1), the customer may be advised to use a "shared bandwidth" settlement approach, which may make the customer feel a greater incentive without significantly impacting the profits of the network service provider.

When the customer peak is large in total, the customer can be advised to use a settlement mode of 'peak bandwidth', taking the customer 'Jinshan' as an example, the peak ratio of 'Jinshan' in 4 months and 16 days exceeds 10, and if the settlement is carried out by 'peak bandwidth', the amount of money is consumed in 4 months and 16 days by 33K; if the amount of 3K is consumed 4 months and 16 days if settlement is performed with the "shared bandwidth", even if settlement is performed with the "peak bandwidth" of 1 discount, the income is better than the settlement with the "shared bandwidth". Therefore, when the peak of the customer is larger in total, the settlement is carried out by combining the peak bandwidth and the discount, not only can the maximum preferential strength be given to the customer, but also the technical scheme of the embodiment can ensure that more profits can be left for the network service provider for a relatively rude processing scheme.

Further, the network service provider may specify the operation policy according to the customer peak sharing ratio.

For the client with larger peak total, the wide profit margin brought by the network service provider can be higher, so the client can be put in any computer room to cooperate with any other client. For the client with smaller peak, the client can be put into the machine room with the shared bandwidth at different time points, so as to reduce the cost and increase the benefit.

In addition, the network service provider can establish two types of machine rooms of 'peak-to-peak ratio' or 'low peak-to-peak ratio' according to different bandwidth costs and outlet bandwidth upper limits, and the machine rooms are used for placing clients with different client peak-to-peak ratios in different types of machine rooms, so that existing resources are fully utilized, and the defects of the machine rooms are overcome.

In the foregoing description, the target client may include multiple clients or may include only one client, and the bandwidth resource allocation method provided in the embodiment of the present application is described in the following cases.

Specifically, when the target client includes a plurality of clients, the target machine room of the target client is selected from the machine rooms according to the estimated peak bandwidth of the target client, the estimated shared bandwidth of the target client, the peak bandwidth of each machine room and the shared bandwidth of each machine room, the machine room peak ratio of each machine room may be calculated according to the peak bandwidth of each machine room and the shared bandwidth of each machine room, and then the target machine room of each client in the target client is selected from each machine room according to the machine room peak ratio of each machine room.

Wherein, the machine room peak ratio is as follows: the ratio between the peak bandwidth of one room and the shared bandwidth of that room.

In a specific implementation manner of the present application, referring to fig. 2, a flow diagram of a method for selecting a target machine room is provided, where the method includes:

s201: and estimating the machine room peak-to-peak ratio of each machine room after the client U is respectively added into each machine room according to the estimated peak bandwidth of the client U and the estimated shared bandwidth of the client U.

Wherein the client U is any one of the target clients.

Of course, the machine room peak sharing ratio of each machine room after the client U is added to each machine room is estimated in this step, which can be understood as that the client U is supposed to be added to each machine room respectively, and then the machine room peak sharing ratio of each machine room after the client U is supposed to be added to each machine room is estimated.

Specifically, suppose the machine room peak sharing ratio of the current machine room F is S1/O1, where S1 represents the peak bandwidth of the current machine room F, and O1 represents the shared bandwidth of the current machine room F.

The room peak-to-peak ratio P of the room F after the client U is added to the room F can be estimated according to the following expression,

P＝(S1+S2)/(O1+O2)

where S2 represents the predicted peak bandwidth of client U and O2 represents the predicted shared bandwidth of client U.

S202: and determining the machine room peak ratio number meeting the first relation.

The first relational expression is:

and the machine room peak ratio of the machine room obtained by estimation is larger than the machine room peak ratio of the machine room before estimation.

S203: and judging whether the machine room peak common ratio number is greater than a preset number threshold, if so, executing S204, otherwise, executing S205.

The preset number may be a number related to the number of available rooms that the network service provider can provide.

For example, if the number of available machine rooms that can be provided by the network service provider is 4, the preset number may be 3, and so on.

S204: and selecting a target machine room of the client U from machine rooms corresponding to the machine room peak ratio obtained by estimation meeting the first relational expression.

In an optional implementation manner of the present application, when the target machine room of the client U is selected from the machine rooms corresponding to the machine room peak-to-peak ratios obtained by the estimation satisfying the first relational expression, a ratio between the machine room peak-to-peak ratios obtained by the estimation satisfying the first relational expression and the machine room peak-to-peak ratios before the estimation may be calculated based on the same machine room, and then the machine room corresponding to the ratio with the largest value among the calculated ratios is selected as the target machine room of the client U.

Assuming that 4 available rooms can be provided by the network service provider, assuming that the client U is added to the 4 rooms, the estimated room peak-to-peak ratio, and the ratio therebetween are shown in table 2 below.

TABLE 2

As can be seen from the above table, the ratio corresponding to the machine room 4 is the largest, so that it can be determined that the machine room 4 is the target machine room of the client U.

In another optional implementation manner of the present application, when the target machine room of the client U is selected from the machine rooms corresponding to the machine room peak-to-peak ratios obtained through estimation satisfying the first relational expression, the machine room corresponding to the machine room peak-to-peak ratio with the largest value may be directly selected from the machine room peak-to-peak ratios obtained through estimation satisfying the first relational expression, and the machine room corresponding to the machine room peak-to-peak ratio with the largest value may be used as the target machine room of the client U.

For example, it can be seen from table 2 that the peak-to-peak ratio of the machine room 4 is the largest among the estimated peak-to-peak ratios, and therefore, it can be determined that the machine room 4 is the target machine room of the client U.

S205: and selecting a target machine room of the client U from each machine room according to the estimated machine room peak-to-peak ratio.

Similar to the optional implementation manner given in S204 above, in an optional implementation manner of the present application, when the target machine room of the client U is selected from each machine room according to the estimated machine room peak common ratio, a ratio between the estimated machine room peak common ratio and the machine room peak common ratio before estimation may be calculated based on the same machine room, and then the machine room corresponding to the ratio with the largest value among the calculated ratios is selected as the target machine room of the client U.

In another optional implementation manner of the application, when the target machine room of the client U is selected from each machine room according to the machine room peak ratio obtained through estimation, the machine room corresponding to the machine room peak ratio with the largest value can be directly selected from the machine room peak ratios obtained through estimation to serve as the target machine room of the client U, and then the client U is allocated to the target machine room.

When the number of the machine room peak sharing ratios is smaller than the preset number threshold, it is stated that after the client U is placed in each machine room, for most of the machine rooms, not only the gains of the machine rooms are not increased, but also the gains of the machine rooms are possibly decreased. However, for the merchant, in consideration of the principle of preferentially providing the customers with the premium services, the target machine room may be determined for the customers U in the manner provided in S205, and the bandwidth resources may be allocated to the customers U from the determined target machine room. Further, considering that a subsequent customer applies for service from the network service provider, the customer peak ratio of the subsequent customer applying for service may be higher, and certainly may also be lower, so that the customer may be placed in the same machine room in cooperation with the customer U to improve the overall profit of each machine room of the network service provider.

In view of the above, in a preferred implementation of the present application, after selecting a target machine room of the client U from each machine room according to the estimated machine room peak-to-peak ratio, the client U may be further marked as a client of the changeable machine room.

When the client U is marked as a client that can change the machine room, it indicates that the machine room that allocates bandwidth resources to the client U can be changed from the current machine room to another machine room, and of course, the operation of changing the machine room can be performed in the background without affecting the normal service use of the client.

In addition, when the client U is combined with the client who applies for the subsequent service to determine a new target machine room and the combined client consisting of the client U and the client who applies for the subsequent service is not marked as the client who can change the machine room after the new target machine room is determined, the changeable machine room mark of the client U is eliminated.

In a specific implementation manner of the present application, referring to fig. 3, a flowchart of a second bandwidth resource allocation method is provided, and compared with the foregoing embodiment, in this embodiment, a target client includes only one client, and a target computer room of the target client is selected from among the computer rooms according to an estimated peak bandwidth of the target client, an estimated shared bandwidth of the target client, a peak bandwidth of each computer room, and a shared bandwidth of each computer room (S103), including:

S103A: and estimating the machine room peak-to-peak ratio of each machine room after the target client is added into each machine room according to the estimated peak bandwidth of the target client and the estimated shared bandwidth of the target client.

It should be noted that, in this step, the machine room peak to peak ratio of each machine room after the target is added to each machine room is estimated, which may be understood as assuming that the target is added to each machine room respectively, and then estimating the machine room peak to peak ratio of each machine room after the target client is assumed to be added to each machine room.

Specifically, suppose that the machine room peak-to-peak ratio of the current machine room H is S3/O3, where S3 represents the peak bandwidth of the current machine room H, and O3 represents the shared bandwidth of the current machine room H.

The room peak-to-peak ratio P of the room H after the target client is added to the room H can be estimated according to the following expression,

P＝(S3+S4)/(O3+O4)

where S4 represents the predicted peak bandwidth of the target client and O4 represents the predicted shared bandwidth of the target client.

S103B: and selecting a target machine room for the target client according to the machine room peak sharing ratio obtained by estimation.

In an optional implementation manner of the present application, when selecting a target machine room for a target client according to an estimated machine room peak ratio obtained by estimation, a client peak ratio of the target client may be calculated according to an estimated peak bandwidth of the target client and an estimated shared bandwidth of the target client, and then it is determined whether the client peak ratio of the target client is greater than a preset client peak ratio threshold, if it is determined that the client peak ratio of the target client is greater than the preset client peak ratio threshold, a machine room corresponding to the machine room peak ratio with the largest value in the estimated machine room peak ratios is selected as the target machine room of the target client, and if it is determined that the client peak ratio of the target client is not greater than the preset client peak ratio threshold, the target machine room of the target client is selected from machine rooms corresponding to the machine room peak ratios obtained by estimation of the machine room peak ratios before estimation.

Based on the optional implementation manner, in another optional implementation manner of the present application, if it is determined that the customer peak-to-peak ratio of the target customer is greater than the preset customer peak-to-peak ratio threshold, a ratio between the machine room peak-to-peak ratio obtained by estimation satisfying the second relation and the machine room peak-to-peak ratio before estimation may be calculated first, and then the machine room corresponding to the ratio with the largest value in the calculated ratios is selected as the target machine room of the target customer; if the client peak-to-peak ratio of the target client is judged to be not greater than the preset client peak-to-peak ratio threshold, the ratio between the estimated machine room peak-to-peak ratio and the machine room peak-to-peak ratio before estimation can be calculated first, and then the machine room corresponding to the ratio with the largest value in the calculated ratio is selected as the target machine room of the target client.

The second relational expression is:

In a preferred implementation manner of the present application, after selecting a target machine room of a target client from machine rooms corresponding to machine room peak-to-peak ratios obtained from estimation that are not lower than the machine room peak-to-peak ratios before estimation, the method further includes:

the target customer is marked as a customer of the changeable room.

In a specific implementation manner of the present application, referring to fig. 4, a flowchart of a third bandwidth resource allocation method is provided, and compared with the embodiment shown in fig. 3, in this embodiment, according to an estimated machine room peak-to-peak ratio, a target machine room is selected for a target client (S103B), including:

S103B 1: it is determined whether or not there is a client marked as a changeable room, and if so, execution proceeds to S103B 2.

S103B 2: and carrying out client merging processing on the target client and the client marked as the changeable computer room to obtain a merged client.

S103B 3: and selecting a target machine room for the merged client according to the estimated machine room peak-to-peak ratio, determining the target machine room as the target machine room of the target client, and changing the client marked as the changeable machine room from the machine room in which the client is currently located to the target machine room.

It should be noted that the process of selecting the target machine room for the merging client is similar to the scheme provided in the embodiment shown in fig. 3, and is not described herein again.

In this step, after the target machine room is determined as the target machine room of the target client, bandwidth resources can be allocated to the target client from the target machine room, and in addition, after the client marked as the changeable machine room is changed from the current machine room to the target machine room, the bandwidth resources are allocated to the client marked as the changeable machine room by the target machine room, and meanwhile, the client marked as the changeable machine room does not use the bandwidth resources of the current machine room. Therefore, a plurality of clients can be matched to allocate bandwidth resources, and the whole bandwidth utilization rate of each machine room is improved.

As can be seen from the above, in the solutions provided in the above embodiments, when selecting a target machine room for a target client, factors such as an estimated peak bandwidth of the target client, an estimated shared bandwidth of the target client, a peak bandwidth of each machine room, and a shared bandwidth of each machine room are considered, so that the machine room can be selected by synthesizing characteristics of each machine room, and bandwidth resources are allocated to the target client according to the bandwidth resources of the target machine room, so that the bandwidth resources of the machine rooms can be fully utilized.

Corresponding to the bandwidth resource allocation method, the embodiment of the application also provides a bandwidth resource allocation device.

Fig. 5 is a schematic structural diagram of a first bandwidth resource allocation apparatus according to an embodiment of the present application, where the apparatus includes:

a first bandwidth information obtaining module 501, configured to obtain an estimated peak bandwidth of a target client and an estimated shared bandwidth of the target client;

a second bandwidth information obtaining module 502, configured to obtain a peak bandwidth of each equipment room and a shared bandwidth of each equipment room;

a target machine room selection module 503, configured to select a target machine room of the target client from each machine room according to the estimated peak bandwidth of the target client, the estimated shared bandwidth of the target client, the peak bandwidth of each machine room, and the shared bandwidth of each machine room;

a bandwidth resource allocation module 504, configured to allocate bandwidth resources to the target client according to the bandwidth resources of the target computer room.

Optionally, the bandwidth resource allocation apparatus may further include:

Specifically, in a case where the target client includes a plurality of clients, the target equipment room selecting module includes:

and the first target machine room selection submodule is used for selecting the target machine room of each client in the target clients from each machine room according to the machine room peak sharing ratio of each machine room.

In a specific implementation manner of the present application, referring to fig. 6, there is provided a mechanism diagram of an apparatus for selecting a target machine room, in which the first target machine room selection submodule includes:

a machine room peak sharing ratio estimation unit 601, configured to estimate a machine room peak sharing ratio of each machine room after a client U is added to each machine room respectively according to an estimated peak bandwidth of the client U and an estimated shared bandwidth of the client U, where the client U is any one of the target clients;

a machine room peak ratio number determining unit 602, configured to determine a machine room peak ratio number that satisfies a first relation, where the first relation is: the estimated machine room peak common ratio of the machine room is larger than the machine room peak common ratio of the machine room before estimation;

a machine room peak common ratio number judging unit 603, configured to judge whether the machine room peak common ratio number is greater than a preset number threshold;

a first target machine room selecting unit 604, configured to select a target machine room of the client U from the machine rooms corresponding to the machine room peak-to-peak ratio obtained through estimation that satisfies the first relation, if the determination result of the machine room peak-to-peak ratio number determining unit 603 is yes;

a second target machine room selecting unit 605, configured to select a target machine room of the client U from each machine room according to the machine room peak sharing ratio obtained through estimation if the determination result of the machine room peak sharing ratio number determining unit 603 is negative.

Specifically, the first target equipment room selecting unit 604 may include:

Specifically, the second target equipment room selecting unit 605 may include:

Preferably, the first target equipment room selection sub-module may further include:

In a specific implementation manner of the present application, referring to fig. 7, a schematic structural diagram of a second bandwidth resource allocation apparatus is provided, and compared with the foregoing embodiment, in this embodiment, when the target client includes one client, the target machine room selecting module 503 includes:

a machine room peak sharing ratio estimation submodule 503A, configured to estimate a machine room peak sharing ratio of each machine room after the target client is added to each machine room according to the estimated peak bandwidth of the target client and the estimated shared bandwidth of the target client, where the machine room peak sharing ratio is: a ratio between a peak bandwidth of a room and a shared bandwidth of the room;

and a second target machine room selecting submodule 503B, configured to select a target machine room for the target client according to the machine room peak-to-peak ratio obtained through estimation.

Specifically, the second target equipment room selecting submodule 503B may include:

Preferably, the bandwidth resource allocation apparatus may further include:

In a specific implementation manner of the present application, referring to fig. 8, a schematic structural diagram of a third bandwidth resource allocation apparatus is provided, and compared with the foregoing embodiment, in this embodiment, the second target machine room selection sub-module 503B includes:

a marked client judging unit 503B1 for judging whether there is a client marked as a changeable room;

a client merge processing unit 503B2, configured to, if the judgment result of the marked client judgment unit 503B1 is yes, perform client merge processing on the target client and the client marked as a changeable room to obtain a merged client;

a fifth target machine room selecting unit 503B3, configured to select a target machine room for the merged client according to the estimated machine room peak-to-peak ratio, determine the target machine room as the target machine room of the target client, and change the client marked as a changeable machine room from the machine room currently located to the target machine room.

For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

Those skilled in the art will appreciate that all or part of the steps in the above method embodiments may be implemented by a program to instruct relevant hardware to perform the steps, and the program may be stored in a computer-readable storage medium, which is referred to herein as a storage medium, such as: ROM/RAM, magnetic disk, optical disk, etc.

The above description is only for the preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. A method for allocating bandwidth resources, the method comprising:

selecting a target machine room of the target client from each machine room by adopting a peak staggering principle according to the estimated peak bandwidth of the target client, the estimated shared bandwidth of the target client, the peak bandwidth of each machine room and the shared bandwidth of each machine room;

2. The method of claim 1, wherein in a case that the target client comprises a plurality of clients, selecting the target room of the target client from the rooms according to the estimated peak bandwidth of the target client, the estimated shared bandwidth of the target client, the peak bandwidth of each room, and the shared bandwidth of each room by adopting a peak shifting principle comprises:

determining the machine room peak sharing number meeting a first relation, wherein the first relation is as follows: the estimated machine room peak common ratio of the machine room is larger than the machine room peak common ratio of the machine room before estimation; the machine room peak sharing quantity is the quantity of the machine rooms meeting the first relational expression;

3. The method of claim 2, wherein selecting the target room for the client U from rooms corresponding to the estimated room-peak-to-peak ratio satisfying the first relation comprises:

4. The method of claim 2, wherein selecting the target room of the client U from the rooms according to the estimated room-to-peak ratio comprises:

5. The method of claim 2, further comprising, after selecting the target room for the client U from the rooms according to the estimated room-to-peak ratio, the method further comprising:

and marking the client U as a client of the changeable computer room.

6. The method of claim 1, wherein in the case that the target client comprises a client, selecting the target room of the target client from the rooms according to the estimated peak bandwidth of the target client, the estimated shared bandwidth of the target client, the peak bandwidth of each room, and the shared bandwidth of each room by adopting a peak shifting principle comprises:

7. The method of claim 6, wherein selecting a target room for the target customer based on the estimated peak-to-peak ratio comprises:

8. The method of claim 7, wherein after selecting the target room of the target customer from the rooms corresponding to the room peak-to-peak ratios that are not lower than the estimated room peak-to-peak ratio before estimation, further comprising:

and marking the target client as a client of the changeable computer room.

9. The method of claim 8, wherein selecting a target room for the target customer based on the estimated peak-to-peak ratio comprises:

judging whether a client marked as a changeable computer room exists or not;

10. The method of claim 1, further comprising:

11. An apparatus for allocating bandwidth resources, the apparatus comprising:

the target machine room selection module is used for selecting the target machine room of the target client from each machine room by adopting a peak staggering principle according to the estimated peak bandwidth of the target client, the estimated shared bandwidth of the target client, the peak bandwidth of each machine room and the shared bandwidth of each machine room;

12. The apparatus of claim 11, wherein in the case that the target customer comprises a plurality of customers, the target room selection module comprises:

wherein, the first target machine room selection submodule includes:

the computer room peak ratio number determining unit is used for determining the computer room peak ratio number meeting a first relational expression, wherein the first relational expression is as follows: the estimated machine room peak common ratio of the machine room is larger than the machine room peak common ratio of the machine room before estimation; the machine room peak sharing quantity is the quantity of the machine rooms meeting the first relational expression;

13. The apparatus of claim 12, wherein the first target room selection unit comprises:

14. The apparatus of claim 12, wherein the second target room selection unit comprises:

15. The apparatus of claim 12, wherein the first target room selection sub-module further comprises:

16. The apparatus of claim 11, wherein in the case where the target customer comprises a customer, the target room selection module comprises:

17. The apparatus of claim 16, wherein the second target room selection submodule comprises:

18. The apparatus of claim 17, further comprising:

19. The apparatus of claim 18, wherein the second target room selection submodule comprises:

20. The apparatus of claim 11, further comprising: