CN111585824B

CN111585824B - Resource distribution method, device and system and electronic equipment

Info

Publication number: CN111585824B
Application number: CN202010436302.9A
Authority: CN
Inventors: 张强; 贾鹏
Original assignee: Beijing QIYI Century Science and Technology Co Ltd
Current assignee: Beijing QIYI Century Science and Technology Co Ltd
Priority date: 2020-05-21
Filing date: 2020-05-21
Publication date: 2022-10-25
Anticipated expiration: 2040-05-21
Also published as: CN111585824A

Abstract

The embodiment of the invention provides a resource distribution method, a device, a system and electronic equipment, which are used for collecting the outlet bandwidth of IDCs in real time, predicting the predicted outlet bandwidth of the IDCs in the next sampling time length on the basis of the historical outlet bandwidth of the IDCs for each IDC in the IDCs, updating the highest bandwidth available time length of the IDCs in the current charging period in real time for each IDC in the IDCs by comparing the outlet bandwidth of the IDCs with the first preset bandwidth, selecting the IDCs in the IDCs, the predicted outlet bandwidth of which is greater than the first preset bandwidth and the highest bandwidth available time length of which is greater than the preset time length, as the highest bandwidth available time lengths, calling the highest bandwidth available IDCs to distribute resources according to the outlet bandwidth upper limit in the next sampling time length, and improving the efficiency of resource distribution without increasing charge flow when the resources are distributed according to the outlet bandwidth upper limit of the IDCs in the next sampling time length.

Description

Resource distribution method, device and system and electronic equipment

Technical Field

The present invention relates to the field of resource distribution network technologies, and in particular, to a method, an apparatus, a system, and an electronic device for resource distribution.

Background

With the development of Internet technology, more and more users obtain resource services through the Internet, and in order to better provide resource services for users, resource servers often build a CDN (Content Delivery Network) by self-building an IDC (Internet Data Center) and renting an IDC.

An operator mainly collects the flow charge of IDC by a 95 bandwidth peak value charging mode, in a simple word, aiming at an IDC, the real-time bandwidth of the IDC is monitored, in a charging period, the bandwidth peak value of the IDC in the sampling period is collected at intervals of sampling time length and is used as the bandwidth sampling value of the IDC in the sampling time length, after a charging period is finished, the first 5% of the bandwidth sampling values with the maximum bandwidth value are removed from all the collected bandwidth sampling values, the bandwidth sampling value with the maximum bandwidth value is selected from the remaining 95% of the bandwidth sampling values and is used as the charging bandwidth value of the charging period, and finally the flow charge in the charging period is calculated according to the charging bandwidth value of the charging period.

Therefore, it can be seen that the traffic cost in the 95 bandwidth peak charging mode depends on a portion with a higher bandwidth value, and when a bandwidth is abnormally increased in a charging period, the traffic cost in the charging period is increased, and during the operation of a CDN, resource distribution is an important reason for the abnormally increased bandwidth, where resource distribution refers to that after a resource service provider obtains a new resource, in order to enable the new resource to be normally obtained by a required user, the new resource is often required to be distributed to each IDC of the CDN as soon as possible, so if bandwidth control is not performed in the resource distribution process, the bandwidth of each node is abnormally increased in the resource distribution process, and the traffic cost is increased.

In order to solve the problem of bandwidth abnormality caused by resource distribution, in the prior art, a mode of setting a threshold value to limit the resource distribution amount is adopted, so that abnormal increase of the egress bandwidth is avoided.

The inventor finds that the prior art at least has the following problems in the process of implementing the invention:

in a time period with a smaller resource demand of a user, a mode of setting a threshold value to limit the distribution amount is still adopted, so that new resources cannot be distributed to each IDC in time, and the resource distribution efficiency is low.

Disclosure of Invention

The embodiment of the invention aims to provide a resource distribution method, a resource distribution device, a resource distribution system and electronic equipment so as to reduce the flow cost of a resource service provider. The specific technical scheme is as follows:

in a first aspect of the present invention, there is provided a resource distribution method, including:

collecting the outlet bandwidth of each IDC in real time;

for each IDC in the IDCs, predicting the predicted outlet bandwidth of the IDC in the next sampling time length based on the historical outlet bandwidth of the IDC;

for each IDC in each IDC, updating the highest bandwidth available time length of the IDC in the current charging period in real time by comparing the size of the outlet bandwidth of the IDC with a first preset bandwidth, wherein the highest bandwidth available time length of one IDC is the time length difference between a specified time length and the peak bandwidth used time length of the IDC, the peak bandwidth used time length of one IDC is the time length when the outlet bandwidth of the IDC is greater than the first preset bandwidth in the current charging period, the specified time length is the product of the time length of the current charging period and a specified ratio, and the specified ratio is not greater than the ratio removed when the bandwidth cost is settled;

selecting IDCs with predicted outlet bandwidths larger than a first preset bandwidth and with highest bandwidth available duration larger than a preset duration from the IDCs as highest bandwidth available IDCs;

and calling the IDC with the highest available bandwidth to distribute resources according to the upper limit of the outlet bandwidth in the next sampling time length.

Further, before the invoking the highest bandwidth available IDC to distribute the resource according to the upper bound of the outlet bandwidth, the method further includes:

calculating a difference value of an outlet bandwidth upper limit of the IDC with the highest bandwidth and a predicted outlet bandwidth of the IDC with the highest bandwidth as a first bandwidth difference;

taking the product of the first bandwidth difference and the next sampling time length as a first distribution flow;

within the next sampling duration, the calling the highest bandwidth available IDC to distribute resources according to the upper limit of the outlet bandwidth includes:

and calling a resource distribution task with the data size of the IDC processing resource with the highest bandwidth available and the size of the first distribution flow being the same in the next sampling time length.

Further, the method further comprises:

selecting IDCs with predicted outlet bandwidth not greater than a first preset bandwidth or with highest bandwidth available duration not greater than preset duration from the IDCs as bandwidth limiting IDCs;

and calling the bandwidth limiting IDC to distribute resources according to the first preset bandwidth within the next sampling time length.

Further, before the invoking the bandwidth limitation IDC to distribute the resources according to the first preset bandwidth, the method further includes:

calculating a difference value between the first preset bandwidth and a predicted exit bandwidth of the bandwidth limiting IDC to serve as a second bandwidth difference;

taking the product of the second bandwidth difference and the next sampling duration as a second distribution flow;

within the next sampling duration, calling the bandwidth limiting IDC to distribute resources according to the first preset bandwidth, and further including:

and calling a resource distribution task with the data size of the bandwidth limiting IDC processing resource being the same as the second distribution flow size in the next sampling time length.

Further, the collecting the egress bandwidth of each IDC in real time includes:

collecting egress traffic for each of the IDCs and determining an egress bandwidth for each of the IDCs based on the egress traffic for each of the IDCs; and/or the presence of a gas in the gas,

and acquiring each outlet bandwidth through the API of each IDC.

In a second aspect of the present invention, there is further provided a resource distribution apparatus, including:

the bandwidth collection module is used for collecting the outlet bandwidth of each IDC in real time;

the bandwidth prediction module is used for predicting the predicted outlet bandwidth of each IDC in the IDCs in the next sampling time length based on the historical outlet bandwidth of the IDC;

an available duration updating module, configured to update, in real time, a maximum bandwidth available duration of the IDC in a current charging period by comparing an outlet bandwidth of the IDC with a first preset bandwidth for each IDC, where the maximum bandwidth available duration of one IDC is a difference between a specified duration and a peak bandwidth used duration of the IDC, the peak bandwidth used duration of one IDC is a duration in which the outlet bandwidth of the IDC is greater than the first preset bandwidth in the current charging period, the specified duration is a product of the duration of the current charging period and a specified proportion, and the specified proportion is not greater than a proportion removed when a bandwidth cost is settled;

the selection module is used for selecting IDCs with predicted outlet bandwidths larger than a first preset bandwidth and with highest bandwidth available duration larger than preset duration from the IDCs as the highest bandwidth available IDCs;

and the IDC calling module is used for calling the IDC with the highest available bandwidth to distribute resources according to the upper limit of the outlet bandwidth in the next sampling time length.

Further, the apparatus further comprises:

a first distribution traffic determining module, configured to calculate, before the IDC invoking module performs the invoking of the highest bandwidth available IDC for resource distribution according to an outlet bandwidth upper limit, a difference between the outlet bandwidth upper limit of the highest bandwidth available IDC and a predicted outlet bandwidth of the highest bandwidth available IDC as a first bandwidth difference, and use a product of the first bandwidth difference and the next sampling duration as a first distribution traffic;

the IDC calling module is specifically configured to call a resource distribution task in which the data size of the highest bandwidth available IDC processing resource is the same as the first distribution traffic size within the next sampling duration.

Further, the selecting module is further configured to select, from the IDCs, an IDC whose predicted outlet bandwidth is not greater than a first preset bandwidth or whose maximum bandwidth available duration is not greater than a preset duration as a bandwidth limiting IDC;

the IDC calling module is further configured to call the bandwidth limiting IDC to distribute resources according to the first preset bandwidth within the next sampling duration.

Further, the method also comprises the following steps:

a second distribution traffic determining module, configured to calculate, before the IDC invoking module executes the invoking of the bandwidth limitation IDC to perform resource distribution according to the first preset bandwidth, a difference between the first preset bandwidth and a predicted outlet bandwidth of the bandwidth limitation IDC as a second bandwidth difference, and use a product of the second bandwidth difference and the next sampling duration as a second distribution traffic;

the IDC invoking module is specifically further configured to invoke a resource distribution task in which the data size of the bandwidth-limited IDC processing resource is the same as the second distribution traffic size within the next sampling duration.

Further, the bandwidth collection module is specifically configured to collect egress traffic of each IDC, and determine an egress bandwidth of each IDC based on the egress traffic of each IDC; and/or, obtaining each said egress bandwidth through an API of each said IDC.

In a third aspect of the present invention, there is also provided a resource distribution system, including: data server, charging server, flow control server and distribution server, wherein:

the data server is used for collecting the outlet bandwidth of each IDC in real time, predicting the predicted outlet bandwidth of each IDC in the next sampling time length based on the historical outlet bandwidth of the IDC for each IDC in the IDCs, sending the collected real-time bandwidth to the charging server and sending the predicted outlet bandwidth to the flow control server;

the charging server is used for updating the highest bandwidth available time length of the IDC in the current charging period in real time by comparing the size of the outlet bandwidth of the IDC with a first preset bandwidth for each IDC in the IDCs, and sending the highest bandwidth available time length of each IDC to the flow control server, wherein the highest bandwidth available time length of one IDC is the time length difference between a specified time length and the peak bandwidth used time length of the IDC, the peak bandwidth used time length of one IDC is the time length when the outlet bandwidth of the IDC is greater than the first preset bandwidth in the current charging period, the specified time length is the product of the time length of the current charging period and a specified duty ratio, and the specified duty ratio is not greater than the duty ratio removed during bandwidth cost settlement;

the flow control server is used for selecting IDCs with predicted exit bandwidth larger than a first preset bandwidth and highest bandwidth available duration larger than preset duration from the IDCs as highest bandwidth available IDCs, and sending the information of the highest bandwidth available IDCs to the distribution server;

and the distribution server is used for calling the highest bandwidth available IDC to distribute resources according to the upper limit of the outlet bandwidth according to the information of the highest bandwidth available IDC.

Further, the distribution server is specifically configured to calculate, according to the information of the highest bandwidth available IDC, a difference between an upper limit of an outlet bandwidth of the highest bandwidth available IDC and a predicted outlet bandwidth of the highest bandwidth available IDC as a first bandwidth difference, use a product of the first bandwidth difference and the next sampling duration as a first distribution traffic, and call a resource distribution task in which a data size of processing resources of the highest bandwidth available IDC is the same as the first distribution traffic within the next sampling duration.

Further, the traffic control server is further configured to select, from the IDCs, an IDC whose predicted outlet bandwidth is not greater than a first preset bandwidth or whose maximum bandwidth available duration is not greater than a preset duration as a bandwidth limiting IDC, and send information of the bandwidth limiting IDC to the distribution server;

and the distribution server is further configured to call the bandwidth limitation IDC to distribute resources according to the first preset bandwidth within the next sampling duration.

Further, the distribution server is specifically configured to calculate a difference between the first preset bandwidth and the predicted exit bandwidth of the bandwidth limiting IDC as a second bandwidth difference, and use a product of the second bandwidth difference and the next sampling time duration as a second distribution traffic, and call a resource distribution task in which the data size of the processing resource of the bandwidth limiting IDC is the same as the second distribution traffic in the next sampling time duration.

Further, the data server is specifically configured to collect egress traffic of each IDC, and determine an egress bandwidth of each IDC based on the egress traffic of each IDC; and/or, obtaining each said egress bandwidth through an API of each said IDC.

In yet another aspect of the present invention, there is also provided a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to execute any of the above-described resource distribution methods.

In yet another aspect of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any of the above-described resource distribution methods.

The method, the device, the system and the electronic equipment for distributing resources provided by the embodiment of the invention have the advantages that the specified duration is the product of the duration of the current charging period and the specified duty, and the specified duty is not more than the duty removed during bandwidth cost settlement, so the specified duration of an IDC represents the available non-ingress traffic cost of the IDC in the charging period and is more than the use duration of the egress bandwidth of the charging bandwidth, further, the used peak bandwidth duration of the IDC represents the duration that the egress bandwidth of the IDC in the current charging period is more than a first preset bandwidth, therefore, the used peak bandwidth duration of the IDC represents the accumulated use duration that the egress bandwidth in the current charging period is more than the charging bandwidth before the current time, further, the available duration of the highest bandwidth calculated by the specified duration and the used peak bandwidth duration represents the available duration after the current time, the available non-ingress traffic cost in the current charging period and the available duration of the egress bandwidth which is more than the charging bandwidth after the current time, therefore, the available peak bandwidth determined based on the available bandwidth is not used as the egress bandwidth which can be higher than the charging bandwidth, and the sampling duration of the IDC is increased in the next IDC, and the resource distribution efficiency is not increased according to the next IDC.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below.

Fig. 1 is a schematic structural diagram of a resource distribution system according to an embodiment of the present invention;

FIG. 2 is an interaction diagram provided by one embodiment of the present invention;

FIG. 3 is a flowchart of a resource distribution method according to an embodiment of the present invention;

fig. 4 is a flowchart of a resource distribution method according to another embodiment of the present invention;

FIG. 5 is a flowchart of a resource distribution method according to another embodiment of the present invention;

fig. 6 is a schematic structural diagram of a resource distribution apparatus according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of a resource distribution system according to another embodiment of the present invention;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order to provide a scheme for improving efficiency of resource distribution without increasing traffic cost, embodiments of the present invention provide a method, an apparatus, a system, and an electronic device for resource distribution, and the following describes embodiments of the present invention with reference to the accompanying drawings. And the embodiments and features of the embodiments in the present application may be combined with each other without conflict.

In order to more clearly illustrate the embodiments of the present invention, the following technical concept of the present invention will be briefly described. For the 95 bandwidth peak charging mode, the outlet bandwidth corresponding to the removed proportion during cost settlement is not taken as the charging bandwidth value, so that for a charging period, a free peak bandwidth usage duration, namely a specified duration, exists.

Illustratively, one billing cycle is one month (30 days), the sampling duration is 5 minutes, then 12 bandwidth samples are taken for 1 hour, 12 × 24 × 30=8640 bandwidth samples are taken for one month, the first 5% is 8640 × 5% =432 bandwidth samples correspond to 432 × 5=2160 minutes (36 hours), i.e., the specified duration is 36 hours, which indicates that there is a maximum bandwidth usage accounting cost of 36 hours in one month.

Because the 95 bandwidth peak charging mode is to remove the 5% bandwidth sampling value with the highest bandwidth, select the largest value from the remaining 95% bandwidth sampling values as the charging bandwidth value, and the charging bandwidth value of an IDC often appears in a time period with a higher bandwidth resource demand, when the bandwidth resource demand is higher at the current moment, the prior art allocates resource requests to IDCs according to the weight scheduling strategy, and according to the weight of each IDC, the higher bandwidth resource demand is evenly allocated to each IDC, so that the bandwidth sampling value of each IDC is higher, and finally the calculated traffic cost is higher.

In the prior art, the situation that the outlet bandwidth is abnormally increased is avoided by setting a threshold to limit the resource distribution amount, but the resource distribution amount also needs to be limited in a time period with a small bandwidth requirement by adopting the cutting mode, so that the resource distribution efficiency is low.

In order to improve the efficiency of resource distribution without increasing the traffic cost, in the embodiment of the present invention, the highest bandwidth available duration of each IDC may be determined through the outlet bandwidth of each IDC collected in real time, and since the highest bandwidth available duration represents the non-charging traffic cost that can be used in the current charging period after the current time and is greater than the available duration of the outlet bandwidth of the charging bandwidth, the highest bandwidth available IDC determined based on the highest bandwidth available duration is an IDC that can use the outlet bandwidth that is greater than the charging bandwidth without charging the traffic cost, so when the resource distribution is performed according to the outlet bandwidth upper limit of the IDC in the next sampling duration, the efficiency of resource distribution is improved without increasing the traffic cost.

The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

In an embodiment of the present invention, a resource distribution system is provided, as shown in fig. 1, the system includes a data server 101, a charging server 102, a traffic control server 103, and a distribution server 104, where the data server 101 and the distribution server 104 are respectively connected to a CDN during actual use, and the CDN includes multiple IDCs.

As shown in fig. 2, an interaction diagram of a resource distribution system is provided for one embodiment of the present invention, which includes:

step 201: the data server collects the outlet bandwidth of the IDCs in real time and predicts, for each of the IDCs, a predicted outlet bandwidth for the IDC within a next sampling duration based on the historical outlet bandwidth of the IDC.

Step 202: and the data server sends the collected real-time bandwidth to the charging server.

Step 203: and the data server sends the predicted outlet bandwidth of each IDC to the flow control server.

Step 204: and aiming at each IDC in each IDC, the charging server updates the highest bandwidth available time length of the IDC in the current charging period in real time by comparing the size of the outlet bandwidth of the IDC with the first preset bandwidth.

Step 205: and the charging server sends the highest bandwidth available time of each IDC to the flow control server.

Step 206: and the flow control server selects IDCs with predicted exit bandwidth larger than a first preset bandwidth and highest bandwidth available time longer than a preset time from the IDCs as highest bandwidth available IDCs.

Step 207: the flow control server sends the information of the highest bandwidth available IDC to the distribution server.

Step 208: and the distribution server calls the highest bandwidth available IDC to distribute resources according to the upper limit of the outlet bandwidth according to the information of the highest bandwidth available IDC.

In the above steps, the data server 101 may collect the egress bandwidth of each IDC in the CDN in real time, where, as known to those skilled in the art, the real-time collection indicates that the real-time collection duration is obtained every other real-time collection duration, where the real-time collection duration may be 1s.

An exemplary real-time bandwidth to collect IDC _1 at 12 hours, 27 minutes, 45 seconds, 1 month, 15 months, 2020 is 2.5Mbps, and IDC _1 at 27 minutes, 46 seconds, 1 month, 15 days, 2020 is 2.7Mbps.

After collecting the egress bandwidth of each IDC, the data server 101 aggregates the collected egress bandwidth of each IDC, and sends the aggregated data to the charging server 102.

Further, the data server 101 may also predict, for each IDC of the IDCs, a predicted exit bandwidth of the IDC within the next sampling duration based on the historical exit bandwidth of the IDC.

Alternatively, the data server 101 may calculate a change rate of the egress bandwidth at the current time based on the historical egress bandwidth, and determine a predicted egress bandwidth for the IDC within the next sampling duration based on the change rate and the egress bandwidth.

After the data server 101 determines the predicted egress bandwidth, the predicted egress bandwidth of each IDC may be sent to the traffic control server 103 for subsequent use by the traffic control server 103.

Optionally, to avoid frequent interaction to save resources, the data server 101 may periodically send the aggregated data of the egress bandwidth of each IDC to the charging server 102 and periodically send the aggregated data of the predicted egress bandwidth of each IDC to the traffic control server 103, for example, send the aggregated data to the charging server 102 and the traffic control server 103 every 1 minute.

After the charging server 102 receives the egress bandwidth of each IDC sent by the data server 101, the maximum bandwidth available duration of the IDC in the current charging cycle may be updated based on the egress bandwidth of one IDC.

Optionally, the maximum bandwidth available duration of one IDC is a duration difference between the specified duration and the peak bandwidth used duration of the IDC, the peak bandwidth used duration of one IDC is a duration in which the exit bandwidth of the IDC is greater than a first preset bandwidth in the current charging period, the specified duration is a product of the duration of the current charging period and a specified proportion, and the specified proportion is not greater than the proportion removed when the bandwidth cost is settled.

For example, in the conventional 95 bandwidth peak charging method, the removed proportion during the bandwidth cost settlement is 5%, so the specified proportion is less than or equal to 5%, for example, the specified proportion is 5%, and if the charging period is 1 month (30 days), the specified duration can be calculated to be 36 hours.

Optionally, the first preset bandwidth may be determined based on historical bandwidth data and experience, for example, if the charging bandwidth value of IDC _2 in month 2 is 3Mbps, the charging bandwidth value in month 3 is 3.2Mbps, and the charging bandwidth value in month 4 is 2.8Mbps, then the average value of the charging bandwidth values in month 2, month 3, and month 4 of 3Mbps may be taken as the first preset bandwidth in month 5, and the charging bandwidth value in this month may also be predicted by combining data such as holidays and the like as the first preset bandwidth.

After receiving the exit bandwidth of each IDC, the charging server 102 compares the exit bandwidth of the IDC with a first preset bandwidth for each IDC, and if the exit bandwidth is greater than the first preset bandwidth, the used time of the peak bandwidth of the IDC is counted.

Illustratively, the first preset bandwidth is 5Mbps, the charging server 102 receives that the real-time bandwidth of IDC _3 collected by the data server 101 from 27 minutes and 45 seconds at 12 days 1, 15, 2020 to 28 minutes and 45 seconds at 12 days 1, 15, 2020 is 5.5Mbps, and then the charging server 102 increases the elapsed time of the peak bandwidth of IDC _3 by 1 minute.

After determining the peak bandwidth elapsed time for each IDC, the billing server 102 may calculate a maximum bandwidth availability time duration for each IDC based on the peak bandwidth elapsed time duration, the maximum bandwidth availability time duration for one IDC being a time duration difference between the specified time duration for the IDC and the peak bandwidth elapsed time duration for the IDC.

Illustratively, the specified duration of IDC _4 is 36 hours, the peak bandwidth used duration is 10 hours, and the highest bandwidth available duration of IDC _4 is 36-10=26 hours.

After the charging server 102 determines the highest bandwidth available duration of each IDC, the highest bandwidth available duration of each IDC may be aggregated and sent to the traffic control server 103.

After receiving the maximum bandwidth available duration of each IDC sent by the charging server 102 and the predicted exit bandwidth of each IDC sent by the data server 101, the traffic control server 103 selects, as the maximum bandwidth available IDC, the IDC whose predicted exit bandwidth is greater than the first preset bandwidth and whose maximum bandwidth available duration is greater than the preset duration from each IDC.

Optionally, the preset time period may be determined empirically or according to requirements, for example, may be 10 hours, where the highest bandwidth available IDC is the IDC with the highest bandwidth available time period longer than 10 hours, and the predicted outlet bandwidth is greater than the first preset bandwidth.

For example, if the highest bandwidth available duration of the highest bandwidth available IDC _1 is 15 hours and the preset duration is 10 hours, the highest bandwidth available IDC _1 may continue to be used for 5 hours.

Optionally, the preset time period in the current charging cycle may be a time period with a high bandwidth demand, such as a late peak, a weekend, a holiday, a summer holiday, and the like.

In an embodiment of the present invention, a resource distribution method is provided, as shown in fig. 3, including:

s301: the egress bandwidth of each IDC is collected in real time.

S302: for each of the IDCs, a predicted exit bandwidth for the IDC is predicted for a next sampling duration based on historical exit bandwidths of the IDC.

S303: aiming at each IDC in each IDC, updating the highest bandwidth available time length of the IDC in the current charging period in real time by comparing the size of the outlet bandwidth of the IDC with the first preset bandwidth, wherein the highest bandwidth available time length of one IDC is the time length difference between the specified time length and the peak bandwidth used time length of the IDC, the peak bandwidth used time length of one IDC is the time length when the outlet bandwidth of the IDC is larger than the first preset bandwidth in the current charging period, the specified time length is the product of the time length of the current charging period and the specified ratio, and the specified ratio is not larger than the ratio removed when the bandwidth cost is settled.

S304: selecting IDCs with predicted outlet bandwidths larger than a first preset bandwidth and with highest bandwidth available duration larger than a preset duration from the IDCs as highest bandwidth available IDCs;

s305: and calling the highest bandwidth available IDC to distribute the resources according to the upper limit of the outlet bandwidth in the next sampling time length.

In the resource distribution method as shown in fig. 3 provided in the embodiment of the present invention, since the specified duration is a product of a duration of a current charging period and the specified duty, and the specified duty is not greater than the duty removed in bandwidth cost settlement, the specified duration of an IDC represents a non-accounted traffic charge available for the IDC in the charging period and a usage duration of an egress bandwidth greater than the charging bandwidth, further, a used peak bandwidth duration of an IDC represents a duration of the egress bandwidth of the IDC in the current charging period greater than a first preset bandwidth, and therefore, the used peak bandwidth duration of an IDC represents an accumulated usage duration of the egress bandwidth in the current charging period before the current time, and further, after the current time, an available maximum bandwidth duration calculated by the specified duration and the used peak bandwidth duration represents an available duration of the egress bandwidth that is greater than the charging bandwidth and that is not accounted for the currently available traffic charge in the charging period, and an available egress bandwidth duration of the egress bandwidth that is greater than the charging bandwidth is not accounted before the current time, and therefore, when the sampling of the IDC increases the egress bandwidth in the next IDC, the resource distribution efficiency is not increased according to the upper limit of the IDC.

In one embodiment, the resource distribution method shown in fig. 3 may be applied to any device in the scheduling system, such as a data server and a scheduling server, or the server may be separately configured to perform the above steps.

For the step S301, the exit bandwidth of each IDC in the CDN may be collected in real time, where, as known to those skilled in the art, the real-time collection indicates that the exit bandwidth is obtained every other collection duration.

For the step S302, optionally, the highest bandwidth available duration of an IDC is a duration difference between a specified duration and a peak bandwidth used duration of the IDC, the peak bandwidth used duration of an IDC is a duration in which the exit bandwidth of the IDC is greater than a first preset bandwidth in the current charging period, the specified duration is a product of the duration of the current charging period and a specified duty ratio, and the specified duty ratio is not greater than the duty ratio removed during the bandwidth cost settlement.

For the above step S303, optionally, the highest bandwidth available IDC is used to distribute the resources according to the upper bound of the egress bandwidth.

Specifically, the implementation manner of the above steps is the same as or similar to that of the above interaction embodiment, and is not described herein again.

Optionally, the step S301 may be implemented in any one of the following two ways, where:

the first mode is as follows: the egress traffic for each IDC is collected and an egress bandwidth for each IDC is determined based on the egress traffic for each IDC.

Optionally, the first method may be executed for an IDC built by a resource provider, and the egress bandwidth of the IDC may be obtained through aggregation calculation based on the traffic of the egress of the acquisition switch.

The second mode is as follows: the egress bandwidth of each is obtained through the API of each IDC.

Optionally, the second method may be executed for an IDC in a commercial CDN leased by a resource service provider, and since the commercial CDN leased by the resource service provider does not have a right to acquire traffic of an outlet of the switch, the outlet bandwidth of the IDC may be acquired in an API (Application Programming Interface) manner, it needs to be noted that there is a time delay, generally about 15 minutes, when the outlet bandwidth of the IDC is acquired in the API manner.

In another embodiment of the present invention, a resource distribution method is provided, as shown in fig. 4, including:

s401: the egress bandwidth of each IDC is collected in real time.

S402: for each of the IDCs, a predicted outlet bandwidth for the IDC is predicted for a next sampling duration based on historical outlet bandwidths of the IDC.

S403: and aiming at each IDC in each IDC, updating the highest bandwidth available time length of the IDC in the current charging period in real time by comparing the size of the outlet bandwidth of the IDC with the first preset bandwidth.

S404: and selecting the IDC with the predicted outlet bandwidth larger than the first preset bandwidth and the highest bandwidth available duration larger than the preset duration from the IDCs as the highest bandwidth available IDC.

The steps S401 to 404 are the same as or similar to the steps S301 to S304, and are not described herein again.

S405: and calculating the difference value of the outlet bandwidth upper limit of the IDC with the highest bandwidth and the predicted outlet bandwidth of the IDC with the highest bandwidth as a first bandwidth difference.

In this step, in order to determine the data size of the resource distribution task that can be allocated to each IDC with the highest bandwidth, the size of the remaining available bandwidth after the outlet bandwidth for maintaining the IDC function is calculated first, because the resource distribution task is the next sampling duration, the resource distribution task is used to replace the outlet bandwidth required to actually maintain the IDC function in the next sampling duration, and because the IDC with the highest bandwidth can maintain the upper limit of the outlet bandwidth without increasing the traffic cost, in order to improve the efficiency of resource distribution, the IDC with the highest bandwidth is used to operate according to the upper limit of the outlet bandwidth, so that the first bandwidth difference indicates the largest outlet bandwidth for resource distribution in the next sampling duration.

S406: and taking the product of the first bandwidth difference and the next sampling time length as the first distribution flow.

In this step, the product of the first bandwidth difference and the next sampling duration identifies the amount of data that can be distributed when the device operates in the next sampling duration according to the first bandwidth difference.

S407: and calling a resource distribution task with the data size of the highest bandwidth available IDC processing resource being the same as the first distribution flow size in the next sampling time length.

In this step, a resource distribution task having the same data size as the first distribution traffic may be created, and then the highest bandwidth available IDC is called to process the resource distribution task.

In the resource distribution method shown in fig. 4 provided in the embodiment of the present invention, because the highest bandwidth available IDC determined based on the highest bandwidth available duration is the IDC that can use the outlet bandwidth higher than the charging bandwidth without counting the traffic cost, when the resource is distributed according to the outlet bandwidth upper limit of the IDC in the next sampling duration, the efficiency of resource distribution is improved without increasing the traffic cost.

Further, on the basis of the resource distribution method shown in fig. 4, as shown in fig. 5, the method may further include the following steps:

s408: and selecting IDCs with predicted exit bandwidth not larger than a first preset bandwidth or with highest bandwidth available duration not larger than preset duration from the IDCs as bandwidth limiting IDCs.

S409: and calculating the difference value of the first preset bandwidth and the predicted outlet bandwidth of the bandwidth limiting IDC as a second bandwidth difference.

S410: and taking the product of the second bandwidth difference and the next sampling time length as a second distribution flow.

S411: and calling the bandwidth limitation IDC to distribute the resources according to the first preset bandwidth in the next sampling time length.

And in the next sampling time length, calling a resource distribution task with the data size of the bandwidth limiting IDC processing resource being the same as the size of the second distribution flow.

In the resource distribution method shown in fig. 5 provided in the embodiment of the present invention, since the bandwidth limitation IDC may be called, and the resource distribution is performed according to the first preset bandwidth, the efficiency of resource distribution is improved without increasing traffic cost.

Based on the same inventive concept, according to the resource distribution method provided in the embodiment of the present invention, the embodiment of the present invention further provides a resource distribution apparatus, as shown in fig. 6, the apparatus includes:

a bandwidth collecting module 601, configured to collect the egress bandwidth of each IDC in real time;

a bandwidth prediction module 602, configured to predict, for each IDC in the IDCs, a predicted outlet bandwidth of the IDC within a next sampling duration based on a historical outlet bandwidth of the IDC;

an available duration updating module 603, configured to update, in real time, a maximum bandwidth available duration of the IDC in a current charging period by comparing an exit bandwidth of the IDC with a first preset bandwidth for each IDC, where the maximum bandwidth available duration of one IDC is a difference between a specified duration and a peak bandwidth used duration of the IDC, the peak bandwidth used duration of one IDC is a duration in which the exit bandwidth of the IDC is greater than the first preset bandwidth in the current charging period, the specified duration is a product of the duration of the current charging period and a specified proportion, and the specified proportion is not greater than the proportion removed when the bandwidth cost is settled;

a selecting module 604, configured to select, as a highest bandwidth available IDC, an IDC whose predicted exit bandwidth is greater than a first preset bandwidth and whose highest bandwidth available duration is greater than a preset duration from among the IDCs;

an IDC invoking module 605, configured to invoke the highest bandwidth available IDC to distribute the resources according to the upper limit of the egress bandwidth in the next sampling duration.

Further, the apparatus further comprises:

a first distribution flow determining module, configured to calculate, before the IDC calling module performs resource distribution by calling the highest-bandwidth available IDC according to the upper limit of the outlet bandwidth within the next sampling duration and before the IDC calling module calls the highest-bandwidth available IDC to perform resource distribution, a difference between the upper limit of the outlet bandwidth of the highest-bandwidth available IDC and a predicted outlet bandwidth of the highest-bandwidth available IDC, as a first bandwidth difference, and take a product of the first bandwidth difference and the next sampling duration as a first distribution flow;

and the IDC calling module is specifically used for calling a resource distribution task with the data size of the highest bandwidth available IDC processing resource being the same as the first distribution flow size in the next sampling time length.

Further, the selection module is further configured to select, as the bandwidth limitation IDC, the IDC whose predicted exit bandwidth is not greater than the first preset bandwidth or whose maximum bandwidth available duration is not greater than the preset duration from among the IDCs;

and the IDC calling module is also used for calling the bandwidth limiting IDC to distribute resources according to the first preset bandwidth in the next sampling time length.

Further, the method also comprises the following steps:

a second distribution flow determining module, configured to calculate, before the IDC calling module performs resource distribution according to the first preset bandwidth within the next sampling duration and calls the bandwidth limitation IDC, a difference between the first preset bandwidth and a predicted exit bandwidth of the bandwidth limitation IDC as a second bandwidth difference, and take a product of the second bandwidth difference and the next sampling duration as a second distribution flow;

the IDC calling module is specifically used for calling a resource distribution task with the same data size of the bandwidth limitation IDC processing resource as the second distribution flow size in the next sampling time length.

Further, the bandwidth collection module is specifically configured to collect the egress traffic of each IDC, and determine the egress bandwidth of each IDC based on the egress traffic of each IDC; and/or, obtaining the egress bandwidth of each IDC through the API of each IDC.

In the resource distribution apparatus shown in fig. 6 provided in the embodiment of the present invention, since the specified duration is a product of a duration of the current charging period and the specified duty, and the specified duty is not greater than the duty removed in the bandwidth cost settlement, the specified duration of an IDC represents a non-accounted traffic charge available for the IDC in the charging period and a usage duration of an egress bandwidth greater than the charging bandwidth, further, a used peak bandwidth duration of an IDC represents a duration of the egress bandwidth greater than a first preset bandwidth in the current charging period, and therefore, the used peak bandwidth duration of an IDC represents an accumulated usage duration of the egress bandwidth greater than the charging bandwidth in the current charging period before the current time, and further, after the current time, the available ingress traffic charge available for the IDC in the current charging period and an available egress bandwidth greater than the charging bandwidth are represented by the maximum bandwidth available duration calculated by the specified duration and the used peak bandwidth duration, and the available duration of the egress bandwidth in the current charging period, and therefore, when the IDC increases the sampling rate of the egress bandwidth in the next IDC according to the upper limit of the bandwidth, the resource distribution efficiency is not increased.

Based on the same inventive concept, according to the resource distribution method provided in the embodiment of the present invention, the embodiment of the present invention further provides a resource distribution system, as shown in fig. 7, including: data server 701, charging server 702, flow control server 703 and distribution server 704, wherein:

a data server 701, configured to collect the outlet bandwidth of each IDC in real time, predict, for each IDC in each IDC, a predicted outlet bandwidth of the IDC within a next sampling duration based on a historical outlet bandwidth of the IDC, and send the collected real-time bandwidth to a charging server 702 and send the predicted outlet bandwidth to a traffic control server 703;

the charging server 702 is configured to update, in real time, a maximum bandwidth available duration of the IDC in a current charging period for each IDC by comparing an exit bandwidth of the IDC with a first preset bandwidth, and send the maximum bandwidth available duration of each IDC to the traffic control server 703, where the maximum bandwidth available duration of one IDC is a duration difference between a specified duration and a peak bandwidth used duration of the IDC, the peak bandwidth used duration of one IDC is a duration in which the exit bandwidth of the IDC is greater than the first preset bandwidth in the current charging period, the specified duration is a product of the duration of the current charging period and a specified proportion, and the specified proportion is not greater than a proportion removed when the bandwidth cost is settled;

the traffic control server 703 is configured to select, from the IDCs, an IDC whose predicted exit bandwidth is greater than a first preset bandwidth and whose maximum bandwidth available duration is greater than a preset duration as a maximum bandwidth available IDC, and send information of the maximum bandwidth available IDC to the distribution server 704;

and the distribution server 704 is used for calling the IDC with the highest bandwidth availability to distribute the resources according to the upper limit of the outlet bandwidth according to the information of the IDC with the highest bandwidth availability.

Further, the distributing server 704 is specifically configured to calculate, according to the information of the highest bandwidth available IDC, a difference between an upper limit of an outlet bandwidth of the highest bandwidth available IDC and a predicted outlet bandwidth of the highest bandwidth available IDC as a first bandwidth difference, and use a product of the first bandwidth difference and a next sampling duration as a first distributing traffic, and call, in the next sampling duration, a resource distributing task in which a data size of the highest bandwidth available IDC processing resource is the same as the first distributing traffic.

Further, the traffic control server 703 is further configured to select, as a bandwidth limitation IDC, an IDC whose predicted exit bandwidth is not greater than a first preset bandwidth or whose maximum bandwidth availability duration is not greater than a preset duration from among the IDCs, and send information of the bandwidth limitation IDC to the distribution server;

the distributing server 704 is further configured to invoke the bandwidth limitation IDC to distribute the resources according to the first preset bandwidth in the next sampling duration.

Further, the distribution server 704 is specifically configured to calculate a difference between the first preset bandwidth and the predicted outlet bandwidth of the bandwidth limiting IDC as a second bandwidth difference, and use a product of the second bandwidth difference and a next sampling duration as a second distribution traffic, and call a resource distribution task in which the data size of the processing resource of the bandwidth limiting IDC is the same as the second distribution traffic in the next sampling duration.

Further, the data server 701 is specifically configured to collect egress traffic of each IDC, and determine an egress bandwidth of each IDC based on the egress traffic of each IDC; and/or, obtaining the egress bandwidth of each IDC through the API of each IDC.

In the resource distribution system shown in fig. 7 provided in the embodiment of the present invention, since the specified duration is a product of a duration of the current charging period and the specified duty, and the specified duty is not greater than the duty removed when the bandwidth cost is settled, the specified duration of one IDC represents a non-charging traffic charge that the IDC can use in the charging period and a usage duration of an outlet bandwidth that is greater than the charging bandwidth, further, a used peak bandwidth duration of one IDC represents a duration that the outlet bandwidth of the IDC is greater than a first preset bandwidth in the current charging period, and therefore, the used peak bandwidth duration of one IDC represents a cumulative usage duration that the outlet bandwidth is greater than the charging bandwidth in the current charging period before the current time, and further, a used maximum bandwidth duration calculated by the specified duration and the used peak bandwidth duration represents a usable maximum bandwidth duration that the IDC can use the outlet bandwidth that is greater than the charging bandwidth after the current time, the non-charging traffic charge that can be used in the current charging period and an available duration that is greater than the outlet bandwidth of the charging bandwidth is greater than the charging bandwidth, therefore, when the IDC increases the sampling traffic charge in the next bandwidth, the resource distribution efficiency is not increased.

An embodiment of the present invention further provides an electronic device, as shown in fig. 8, which includes a processor 801, a communication interface 802, a memory 803, and a communication bus 804, where the processor 801, the communication interface 802, and the memory 803 complete mutual communication through the communication bus 804,

a memory 803 for storing a computer program;

the processor 801 is configured to implement the following steps when executing the program stored in the memory 803:

collecting the outlet bandwidth of each IDC in real time;

In the electronic device shown in fig. 8 according to the embodiment of the present invention, since the specified duration is a product of a duration of a current charging period and the specified duty, and the specified duty is not greater than a duty removed in a bandwidth cost settlement, the specified duration of an IDC represents a usage duration of an egress bandwidth that is greater than a charging bandwidth and is usable in the charging period, and further, a used peak bandwidth duration of an IDC represents a duration that is greater than a first preset bandwidth and is usable in the charging period, and therefore, the used peak bandwidth duration of an IDC represents an accumulated usage duration that is greater than the charging bandwidth and is usable in the charging period before the current time, and further, an available maximum bandwidth duration calculated by specifying the duration and the used peak bandwidth duration represents an available ingress bandwidth that is usable after the current time, and is greater than the charging bandwidth in the charging period, and is usable in the egress bandwidth of the charging bandwidth, and is not usable in the charging period, and therefore, when an IDC is used in the next sampling bandwidth, the sampling rate is increased, and the egress bandwidth is not used as a resource.

It should be noted that other embodiments of the filtering method implemented by the electronic device are the same as the filtering method mentioned in the foregoing method embodiment, and are not described herein again.

The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this is not intended to represent only one bus or type of bus.

The communication interface is used for communication between the electronic equipment and other equipment.

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

The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components.

In yet another embodiment of the present invention, a computer-readable storage medium is further provided, which has instructions stored therein, and when the instructions are executed on a computer, the instructions cause the computer to execute the resource distribution method described in any of the above embodiments.

In a further embodiment of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the resource distribution method of any of the above embodiments.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), among others.

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 phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on differences from other embodiments. In particular, for the apparatus, the system, the electronic device, the computer-readable storage medium, and the computer program embodiment, since they are substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims

1. A method for resource distribution, comprising:

collecting the outlet bandwidth of each IDC in real time;

2. The method according to claim 1, wherein prior to said invoking said highest bandwidth available IDC for distribution of resources by egress bandwidth capping, said method further comprises:

3. The method according to claim 1 or 2, characterized in that the method further comprises:

selecting IDCs with predicted exit bandwidth not larger than a first preset bandwidth or with highest bandwidth available time not larger than preset time from IDCs as bandwidth limiting IDCs;

4. The method according to claim 3, wherein before said invoking said bandwidth limiting IDC for resource distribution according to said first preset bandwidth, said method further comprises:

and calling a resource distribution task with the data size of the bandwidth limiting IDC processing resource being the same as the second distribution flow in the next sampling time length.

5. The method according to any of claims 1-2 or 4, wherein the collecting in real time the egress bandwidth of each IDC comprises:

and acquiring each outlet bandwidth through the API of each IDC.

6. A resource distribution apparatus, comprising:

the selection module is used for selecting IDCs with predicted outlet bandwidths larger than a first preset bandwidth and with highest bandwidth available duration larger than preset duration from the IDCs as highest bandwidth available IDCs;

7. A resource distribution system, the system comprising: data server, charging server, flow control server and distribution server, wherein:

8. The system according to claim 7, wherein the distribution server is specifically configured to calculate, according to the information of the highest bandwidth-available IDC, a difference between an upper bound of an egress bandwidth of the highest bandwidth-available IDC and a predicted egress bandwidth of the highest bandwidth-available IDC as a first bandwidth difference, and take a product of the first bandwidth difference and the next sampling duration as a first distribution traffic, and invoke, in the next sampling duration, a resource distribution task in which a data size of the highest bandwidth-available IDC processing resource is the same as the first distribution traffic.

9. The system according to claim 7 or 8, wherein the traffic control server is further configured to select, as a bandwidth limitation IDC, an IDC with a predicted egress bandwidth not greater than a first preset bandwidth or a highest bandwidth availability time not greater than a preset time among the IDCs, and send information of the bandwidth limitation IDC to the distribution server;

and the distribution server is further configured to call the bandwidth limiting IDC to distribute resources according to the first preset bandwidth within the next sampling duration.

10. The system according to claim 9, wherein said distribution server is specifically configured to calculate a difference between said first preset bandwidth and a predicted exit bandwidth of said bandwidth-limited IDC as a second bandwidth difference, and take a product of said second bandwidth difference and said next sampling duration as a second distribution traffic, and within said next sampling duration, invoke a resource distribution task in which a data size of said bandwidth-limited IDC processing resource is the same as a size of said second distribution traffic.

11. The system according to any of claims 7-8 or 10, wherein said data server, in particular, is configured to collect egress traffic for each of said IDCs and determine an egress bandwidth for each of said IDCs based on the egress traffic for each of said IDCs; and/or obtaining each said egress bandwidth through an API of each said IDC.

12. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing the communication between the processor and the memory through the communication bus;

a memory for storing a computer program;

a processor for implementing the method steps of any one of claims 1 to 5 when executing a program stored in the memory.

13. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of the claims 1-5.