CN114500339A - Node bandwidth monitoring method and device, electronic equipment and storage medium - Google Patents
Node bandwidth monitoring method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114500339A CN114500339A CN202210116825.4A CN202210116825A CN114500339A CN 114500339 A CN114500339 A CN 114500339A CN 202210116825 A CN202210116825 A CN 202210116825A CN 114500339 A CN114500339 A CN 114500339A
- Authority
- CN
- China
- Prior art keywords
- time period
- node
- detected
- bandwidth
- resource consumption
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
- H04L43/0894—Packet rate
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/16—Threshold monitoring
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present disclosure provides a node bandwidth monitoring method, apparatus, electronic device and storage medium, which relate to the technical field of internet, and in particular, to the technical fields of content distribution network node bandwidth monitoring, machine learning, and the like. The specific implementation scheme is as follows: the method comprises the steps of obtaining operation data of a CDN node to be detected in a current time period, and updating a predetermined flow-resource consumption model and a model error index by using the operation data of the CDN node to be detected in the current time period; determining a bandwidth value which can be borne by the CDN node to be detected when the resource usage reaches a threshold value based on a flow-resource consumption model, and obtaining a node single machine bandwidth value of the CDN node to be detected; and determining the monitoring bandwidth of the CDN node to be detected according to the node single machine bandwidth value of the CDN node to be detected and the model error index. The embodiment of the disclosure realizes the monitoring of the node bandwidth.
Description
Technical Field
The present disclosure relates to the field of internet technologies, and in particular, to the field of content distribution network node bandwidth monitoring and machine learning technologies, and in particular, to a node bandwidth monitoring method and apparatus, an electronic device, and a storage medium.
Background
A CDN (Content Delivery Network) is a Network system for caching and delivering internet resource files, and caches various internet resources (such as documents, pictures, videos, and the like) on an edge node server close to a user, so as to improve the speed at which the user accesses the internet resources. The bandwidth that the CDN node server can carry is closely related to the constraints such as the hardware of the node server.
Disclosure of Invention
The disclosure provides a node bandwidth monitoring method, a node bandwidth monitoring device, electronic equipment and a storage medium.
According to an aspect of the present disclosure, a node bandwidth monitoring method is provided, including:
obtaining operation data of a CDN node to be detected in a current time period, wherein the operation data comprises flow characteristic data and resource consumption data of the CDN node to be detected;
updating a predetermined flow-resource consumption model and a model error index by using the operation data of the CDN node to be detected in the current time period;
determining a bandwidth value which can be borne by the CDN node to be detected when the resource usage reaches a threshold value based on a flow-resource consumption model, and obtaining a node single machine bandwidth value of the CDN node to be detected;
and determining the monitoring bandwidth of the CDN node to be detected according to the node single machine bandwidth value of the CDN node to be detected and the model error index.
According to another aspect of the present disclosure, there is provided a node bandwidth monitoring apparatus, including:
the system comprises a data acquisition module, a resource consumption module and a resource management module, wherein the data acquisition module is used for acquiring operation data of a CDN node to be detected in a current time period, and the operation data comprises flow characteristic data and resource consumption data of the CDN node to be detected;
the model updating module is used for updating a predetermined flow-resource consumption model and a model error index by using the operation data of the CDN node to be detected in the current time period;
the bandwidth prediction module is used for determining a bandwidth value which can be borne by the CDN node to be detected when the resource usage reaches a threshold value based on a flow-resource consumption model, so as to obtain a node single machine bandwidth value of the CDN node to be detected;
and the bandwidth monitoring module is used for determining the monitoring bandwidth of the CDN node to be detected according to the node single machine bandwidth value of the CDN node to be detected and the model error index.
According to another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a node bandwidth monitoring method of any of the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the node bandwidth monitoring method of any one of the present disclosure.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the node bandwidth monitoring method of any one of the present disclosure.
The embodiment of the disclosure realizes the monitoring of the node bandwidth.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram of a node bandwidth monitoring method according to the present disclosure;
FIG. 2 is a schematic diagram of one acquisition of a traffic-resource consumption model according to the present disclosure;
FIG. 3 is a schematic diagram of a node standalone bandwidth value determination approach according to the present disclosure;
FIG. 4 is a schematic illustration of a node monitoring bandwidth determination in accordance with the present disclosure;
FIG. 5 is a schematic diagram of a node bandwidth monitoring apparatus according to the present disclosure;
fig. 6 is a block diagram of an electronic device for implementing a node bandwidth monitoring method according to an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The CDN is a network system for caching and delivering internet resource files, and is limited by hardware of a CDN edge node server and the like, and the service capability of the CDN edge node server is limited. The service capacity of a server is usually measured by using the maximum bandwidth that the server can carry, and the maximum bandwidth that the server can carry can be called as a stand-alone bandwidth capacity. The accumulation of the single-machine bandwidth capabilities of all servers under a certain CDN edge node is the available bandwidth of the CDN node. And then the CDN flow scheduling system can schedule the user requests which do not exceed the available bandwidth of each CDN node to the CDN node according to the available bandwidth of each CDN node.
The single-machine bandwidth capability of the server under the CDN node is closely related to the traffic use scene on the CDN node and the hardware configuration of the server. Under different traffic scenarios, the difference between the single-machine bandwidth capabilities of the servers is large, for example, because the larger the file is, the smaller the corresponding request number is, under the same bandwidth, and further when the user accesses the large file, the single-machine bandwidth capability of the server is higher.
In the related art, a pressure measurement method is used to obtain the single-machine bandwidth capability of a server, specifically, a bandwidth value borne by the server may be continuously increased until the hardware utilization rate of the server reaches a threshold, and a corresponding bearing bandwidth value when the hardware utilization rate of the server reaches the threshold is determined as the single-machine bandwidth capability of the server. However, the single-machine bandwidth capability of the server is obtained by using the pressure measurement method, and the accuracy of the single-machine bandwidth capability of the server in a corresponding traffic scene can only be ensured in pressure measurement, but the accuracy of the single-machine bandwidth capability of the server in other traffic scenes cannot be ensured.
In practical application, flow scenes on different CDN nodes are usually different, correspondingly, the single-machine bandwidth capability of each CDN node is also different, and the single-machine bandwidth capability obtained by pressure measurement on a certain CDN node at a certain time cannot represent the single-machine bandwidth capability of the CDN node at all times, so that if the single-machine bandwidth capability of the CDN node obtained by using the pressure measurement method is used, the available bandwidth of each CDN node is calculated, which may cause inaccuracy of the available bandwidth of each CDN node, thereby causing unbalanced requests to be scheduled to each CDN node, and affecting load balancing among the CDN nodes.
In order to implement monitoring of node bandwidth, an embodiment of the present disclosure provides a node bandwidth monitoring method, with reference to fig. 1, including: s101, obtaining operation data of a CDN node to be detected in a current time period, wherein the operation data comprises flow characteristic data and resource consumption data of the CDN node to be detected; s102, updating a predetermined flow-resource consumption model and a model error index by using the operation data of the CDN node to be detected in the current time period; s103, determining a bandwidth value which can be borne by the CDN node to be detected when the resource usage reaches a threshold value based on a flow-resource consumption model, and obtaining a node single machine bandwidth value of the CDN node to be detected; and S104, determining the monitoring bandwidth of the CDN node to be detected according to the node single machine bandwidth value of the CDN node to be detected and the model error index.
In the embodiment of the disclosure, the predetermined flow-resource consumption model and model error index are updated by using the operating data of the CDN node to be detected in the current time period, so that the flow-resource consumption model can more accurately describe the corresponding relationship between the flow and the resource consumption in the current time period, further, based on the flow-resource consumption model, the bandwidth value that the CDN node to be detected can bear when the resource usage reaches the threshold is determined, a more accurate node single machine bandwidth value of the CDN node to be detected is obtained, the monitoring bandwidth of the CDN node to be detected is determined according to the node single machine bandwidth value of the node to be detected and the model error index, the bandwidth monitoring of the CDN node to be detected can be more accurately realized, and further, a more accurate node available bandwidth can be provided for the CDN scheduling system, thereby realizing load balancing among the CDN nodes, and the resource utilization rate of each CDN node is improved.
The node bandwidth monitoring method provided by the embodiment of the disclosure can be applied to electronic equipment, such as terminal equipment, server equipment and the like. The node bandwidth monitoring method provided by the embodiment of the disclosure can be applied to application scenarios such as CDN node bandwidth monitoring, CDN node load balancing, CDN node flow scheduling and the like. The following describes the node bandwidth monitoring method provided by the present disclosure in detail by using specific embodiments.
First, a flow-resource consumption model acquisition method in the present disclosure will be described. In a possible embodiment, an obtaining manner of the traffic-resource consumption model according to an embodiment of the present disclosure, referring to fig. 2, includes:
s201, collecting operation data in the historical time period of the CDN node to be detected so as to obtain the operation data in the historical time period of the CDN node to be detected.
The collection frequency of the operation data can be set in a customized manner according to actual conditions, and can be 30 seconds, 1 minute, 2 minutes and the like.
The operation data comprises flow characteristic data of the CDN node to be detected, resource consumption data and the like. In an example, the traffic characteristic data may be a carried bandwidth value, or the number of received requests, and the resource consumption data may be a Central Processing Unit (CPU) resource, or a disk resource, or a network card resource. In an example, the obtained operation data of the CDN node to be detected in the historical time period may further include: the time attribute corresponding to the flow characteristic data and the time attribute corresponding to the resource consumption data.
The historical time period may be a time period in any historical data, in one example, taking the historical time period as a first time period, traffic characteristic data and resource consumption data of the CDN node to be detected in the historical time period may be obtained, so that the traffic characteristic data and the resource consumption data in the historical time period are used to train the algorithm model, and the traffic-resource consumption model is obtained. The historical time period can also be a plurality of time periods in historical data before the current time period, and flow characteristic data and resource consumption data in the time periods are obtained to train the algorithm model to obtain the flow-resource consumption model. Wherein a time period may be a period, which may be, for example, 12 hours, or 1 day, or 2 days, etc.
S202, after obtaining the operation data in the historical time period of the CDN node to be detected, sample data construction can be carried out, when the sample data is constructed, the flow characteristic data in the historical time period is used as the sample input characteristic of the algorithm model, the resource consumption data in the historical time period is used as the sample output characteristic of the algorithm model, and the flow characteristic data and the resource consumption data corresponding to the same time attribute in the historical time period are combined into the sample data to obtain the sample data in the historical time period.
In one example, the algorithm model may be any regression algorithm model, such as a polynomial regression algorithm model, a logistic regression algorithm model, etc., or other algorithm models capable of determining the corresponding relationship between the flow and the resource consumption according to the operation data in the historical time period.
In a possible implementation manner, after the sample data in the historical time period is obtained, the sample data in the historical time period may be further filtered to obtain the sample data after filtering, and the sample data after filtering may be subjected to dimension conversion to obtain the sample data for algorithm model training.
The filtering process performed on the sample data in the historical time period may be a process of filtering (for example, deleting) an abnormal sample in the sample data, where the abnormal sample may be, for example, sample data with missing data. Sample data in the historical time period is directed at the CDN node to be detected, and the CDN node to be detected may include multiple servers, so performing dimension conversion on the sample data after filtering may be to convert the sample data after filtering the node dimension into sample data of the server dimension. In an example, the sample data after filtering may be divided by the number of servers under the CDN node to be detected, so as to convert the sample data of the node dimension into the sample data of the server dimension.
In the embodiment of the disclosure, after the sample data in the historical time period is obtained, the sample data in the historical time period is filtered, and the dimension conversion is performed on the filtered sample data, so that the accuracy of the sample data can be improved, the obtained sample data for algorithm model training is more accurate, and the accuracy of the traffic-resource consumption model obtained by training is further improved.
In a possible implementation manner, after the dimension conversion is performed on the sample data after the filtering processing, the normalization processing may be performed on the sample data after the dimension conversion, so as to increase the training speed of the algorithm model.
S203, after sample data used for algorithm model training is obtained, training the algorithm model by using the sample data in the historical time period to obtain a flow-resource consumption model and a model error index.
The trained traffic-resource consumption model can represent the corresponding relation between the node traffic and the node resource consumption, and the model error index can represent the accuracy of the corresponding relation between the node traffic and the node resource consumption in the trained traffic-resource consumption model.
Because the traffic carried by each CDN node is different, in the embodiment of the present disclosure, different traffic-resource consumption models may be trained for each CDN node. In the embodiment of the present disclosure, the traffic-resource consumption model and the model error index trained by using the operation data in the historical data may also be updated by using the operation data in the time period in different time periods, so as to more accurately represent the corresponding relationship between the node traffic and the node resource consumption in different time periods.
In the embodiment of the disclosure, a training sample is determined by using operating data in a historical time period of a CDN node to be detected, an algorithm model is trained to obtain a flow-resource consumption model and a model error index, so that a correspondence between node flow and node resource consumption in different flow scenarios and a corresponding error index thereof can be accurately obtained, and the stand-alone bandwidth capability of the CDN node to be detected can be accurately predicted based on the flow-resource consumption model.
Referring to fig. 1, an implementation process of a node bandwidth monitoring method according to an embodiment of the present disclosure includes:
s101, collecting operation data of the CDN node to be detected in the current time period to obtain the operation data of the CDN node to be detected in the current time period.
In one example, the current time period may be the current latest time period. Illustratively, a time period represents a day, and accordingly, the current time period may be the latest day before the current time, and so on.
S102, after the operation data in the current time period of the CDN node to be detected is obtained, the operation data in the current time period and the operation data in the historical time period before the current time period can be used for retraining the algorithm model so as to update the predetermined flow-resource consumption model and the model error index, and the updated flow-resource consumption model and the model error index are obtained.
The updated flow-resource consumption model can more accurately represent the corresponding relation between the node flow and the node resource consumption in the current time period. The predetermined flow-resource consumption model and the model error index may be obtained by training an algorithm model according to the operation data in the historical time period.
And S103, after the flow-resource consumption model is updated, predicting a bandwidth value which can be borne by the CDN node to be detected when the resource usage amount reaches a threshold value by using the updated flow-resource consumption model based on the flow characteristic data in the current time period, and determining the bandwidth value as a node single machine bandwidth value of the CDN node to be detected.
The method is used for predicting a bandwidth value that a CDN node to be detected can bear when the resource usage reaches a threshold, where the traffic feature data in the current time period may be an average of all traffic feature data acquired in the current time period, or an average of all traffic feature data acquired in a specified time period in the current time period, and the specified time period may be a time period corresponding to a traffic usage peak period, or the like. The resource usage amount of the CDN nodes to be detected may be hardware resource usage amount of the CDN nodes to be detected, and the threshold of the resource usage amount of the CDN nodes to be detected may be set according to actual conditions of each CDN node to be detected.
And S104, after determining the node single machine bandwidth value and the model error index of the CDN node to be detected, further determining the monitoring bandwidth of the CDN node to be detected according to the node single machine bandwidth value and the model error index of the CDN node to be detected.
The model error index can represent the accuracy of the corresponding relation between the node flow and the node resource consumption in the trained flow-resource consumption model, the smaller the model error index is, the higher the accuracy of the corresponding relation between the node flow and the node resource consumption is, and further the monitoring bandwidth of the CDN node to be detected can be accurately predicted under the condition that the model error index is smaller.
In an example, the determined node single-machine bandwidth value of the CDN node to be detected may be determined as a monitoring bandwidth of the CDN node to be detected, and the model error index may be determined as an error of the monitoring bandwidth; the weighted average value of the node single-machine bandwidth values and the model error indexes in the multiple different historical time periods and the current time period can be determined as the monitoring bandwidth of the CDN node to be detected and the like according to the node single-machine bandwidth values of the CDN node to be detected in the multiple different historical time periods and the current time period and the model error indexes corresponding to the node single-machine bandwidth values and the model error indexes.
In the embodiment of the disclosure, the predetermined flow-resource consumption model and model error index are updated by using the operating data of the CDN node to be detected in the current time period, so that the flow-resource consumption model can more accurately describe the corresponding relationship between the flow and the resource consumption in the current time period, further, based on the flow-resource consumption model, the bandwidth value that the CDN node to be detected can bear when the resource usage reaches the threshold is determined, a more accurate node single machine bandwidth value of the CDN node to be detected is obtained, the monitoring bandwidth of the CDN node to be detected is determined according to the node single machine bandwidth value of the node to be detected and the model error index, the bandwidth monitoring of the CDN node to be detected can be more accurately realized, and further, a more accurate node available bandwidth can be provided for the CDN scheduling system, thereby realizing load balancing among the CDN nodes, and the resource utilization rate of each CDN node is improved.
In a possible implementation manner, the implementation manner of determining the node standalone bandwidth value of the CDN node to be detected in step S103 may include:
step one, collecting traffic characteristic data of a designated time period in a current time period of a CDN node to be detected so as to obtain the traffic characteristic data of the designated time period in the current time period of the CDN node to be detected.
The specified time period may be a time period corresponding to a peak period of the latest flow usage in the current time period, and the flow characteristic data of the specified time period may be an average value of all flow characteristic data acquired in the specified time period. The latest flow use peak period in the current time period represents a scene corresponding to the maximum flow demand in the current time period, and by using the flow characteristic data in the scene, the bandwidth value which can be borne by the CDN node to be detected when the resource use amount reaches the threshold value can be predicted more quickly.
For example, the current time period may be the latest day before the current time, and the traffic characteristic data for the specified time period may be an average of the traffic characteristic data for the late peaks 20:00-21:00 during the current time period.
The traffic characteristic data in the appointed time period is used as a prediction sample for predicting the bandwidth value which can be borne by the CDN node to be detected when the resource usage reaches the threshold value, and the proportional relation between the traffic characteristic data in the prediction sample is consistent with the proportional relation between the traffic characteristic data of the CDN node to be detected when the resource usage reaches the threshold value, so that the bandwidth value which can be borne by the CDN node to be detected when the resource usage reaches the threshold value can be more accurately predicted. In one example, the proportional relationship between the flow characteristic data may include: the proportional relation between the bandwidth value borne by the CDN node and the number of received requests, or the proportional relation between the exit bandwidth and the entry bandwidth of the CDN node, and the like.
And secondly, after the flow characteristic data of the CDN node to be detected in the current time period in the appointed time period is obtained, predicting a bandwidth value which can be borne by the CDN node to be detected when the resource usage amount reaches a threshold value by using a flow-resource consumption model based on the flow characteristic data of the appointed time period, so as to obtain a node single machine bandwidth value of the CDN node to be detected.
In the embodiment of the disclosure, the latest flow use peak period in the current time period represents a scene corresponding to the maximum flow demand in the current time period, and by using the flow characteristic data in the scene, the bandwidth value that the CDN node to be detected can bear when the resource usage reaches the threshold can be predicted more quickly, so that the node single-machine bandwidth value of the CDN node to be detected can be obtained quickly.
In a possible implementation manner, the predicting, based on the traffic characteristic data of the specified time period and using the traffic-resource consumption model, a bandwidth value that can be borne by the CDN node to be detected when the resource usage reaches the threshold to obtain a node-to-node bandwidth value of the CDN node to be detected, with reference to fig. 3, may include:
s301, inputting the acquired flow characteristic data of the specified time period into a flow-resource consumption model, and predicting resource consumption data corresponding to the flow characteristic data of the specified time period by using the flow-resource consumption model to obtain an output of the flow-resource consumption model, namely a target resource consumption value.
S302, judging whether the obtained target resource consumption value reaches a threshold value of the resource usage amount of the CDN node to be detected, if so, executing the step S303; if not, step S304 is performed.
And if the target resource consumption value reaches the threshold of the resource usage of the CDN node to be detected, the target resource consumption value is the bandwidth value which can be borne by the CDN node to be detected when the resource usage reaches the threshold. If the target resource consumption value does not reach the threshold of the resource usage of the CDN node to be detected, the target resource consumption value is not a bandwidth value that the CDN node to be detected can bear when the resource usage reaches the threshold, and at this time, it is necessary to further determine a bandwidth value that the CDN node to be detected can bear when the resource usage reaches the threshold.
And S303, if the target resource consumption value reaches the threshold value of the resource usage amount of the CDN node to be detected, determining the target resource consumption value as a node single machine bandwidth value of the CDN node to be detected.
And S304, if the target resource consumption value does not reach the threshold of the CDN node resource usage amount to be detected, zooming the traffic characteristic data of the specified time period by using a preset zooming proportion, updating the zoomed traffic characteristic data into the traffic characteristic data of the specified time period, and returning to execute the step S301.
The preset scaling ratio can be set according to actual requirements, such as scaling by 1 time, 2 times or 3 times. In an example, when the target resource consumption value does not reach the threshold of the resource usage amount of the CDN node to be detected, the traffic feature data of the specified time period may be enlarged to 1 time, 2 times, or 3 times, the enlarged traffic feature data is used as the input of the traffic-resource consumption model again, the corresponding output (target resource consumption value) is predicted, whether the target resource consumption value reaches the threshold of the resource usage amount of the CDN node to be detected is further determined until the target resource consumption value reaches the threshold of the resource usage amount of the node to be detected, and a bandwidth value that the node to be detected can bear when the resource usage amount of the CDN reaches the threshold is determined.
In the embodiment of the disclosure, the target resource consumption value is predicted by using the flow characteristic data of the specified time period and the flow-resource consumption model, and the target resource consumption value reaching the threshold of the resource usage amount of the CDN node to be detected is further determined as the node single machine bandwidth value of the CDN node to be detected, so that the prediction of the node single machine bandwidth value of the CDN node to be detected is realized.
In a possible implementation manner, in the embodiment of the present disclosure, the model error index and the node individual bandwidth value of the CDN node to be detected may also be stored.
In the embodiment of the present disclosure, in different time periods or under different flow scenarios, the flow-resource consumption model and the model error index trained by using the operation data in the historical data may be updated by using the operation data in the time period, so that the flow-resource consumption model and the model error index corresponding to different time periods are different, and further, the node single-machine bandwidth values of the CDN node to be detected, which are determined based on the flow-resource consumption model and the model error index, are also different.
In an example, the model error index and the node single-machine bandwidth value of the CDN node to be detected in different time periods may be stored in the database, or may be stored in other places.
In the embodiment of the disclosure, model error indexes in different time periods and node single machine bandwidth values of CDN nodes to be detected are stored, so that the CDN flow scheduling system can read and use the model error indexes in different time periods and node single machine bandwidth values of the CDN nodes to be detected, or the monitoring bandwidth of the CDN nodes to be detected is determined based on the stored model error indexes in different time periods and node single machine bandwidth values of the CDN nodes to be detected.
In a possible implementation manner, the determining the monitoring bandwidth of the CDN node to be detected according to the node standalone bandwidth value of the CDN node to be detected and the model error index may include, with reference to fig. 4:
s401, reading the node single machine bandwidth values and model error indexes of the stored CDN nodes in different historical time periods to obtain the node single machine bandwidth values and model error indexes of the CDN nodes to be detected in different historical time periods.
In an example, a time period represents one day, traffic carried by the CDN node is dynamic every day, and correspondingly, a single-machine bandwidth capability value (i.e., a node single-machine bandwidth value) of the CDN node is also dynamic, so that the node single-machine bandwidth value of the CDN node can be predicted in a period of days, and the predicted node single-machine bandwidth value of the CDN node is matched with the traffic carried by the current CDN node. The CDN traffic scheduling system usually does not allow the exit bandwidth of each CDN node to change too severely, which needs to determine the monitoring bandwidth of the CDN node by comprehensively considering the historically predicted CDN node individual bandwidth value, so as to reduce fluctuation of the CDN node individual bandwidth value.
For example, a node single-machine bandwidth value and a model error index of the CDN node to be detected in the historical time period corresponding to each day of monday, tuesday, friday may be obtained, and the monitoring bandwidth of the CDN node to be detected is further determined based on the node single-machine bandwidth value and the model error index.
S402, after model error indexes of the CDN node to be detected in different historical time periods are obtained, based on the sizes of the model error indexes in the historical time periods and the current time period and/or the single degree of operation data, the confidence coefficients of the single bandwidth values of the nodes in the historical time periods and the current time period are respectively determined.
The larger the model error index is, the lower the accuracy of the corresponding relationship between the node flow and the node resource consumption is shown, that is, the lower the accuracy of the flow-resource consumption model is, which may result in the low accuracy of the predicted bandwidth value of the node single machine in the corresponding time period, and at this time, the confidence that the corresponding bandwidth value of the node single machine may be set is low.
And determining the confidence of the single bandwidth values of the nodes in each historical time period and the current time period according to the single degree of the operation data in each historical time period and the current time period, namely the richness of the operation data participating in the training or updating of the traffic-resource consumption model. The more single the running data is, the lower the accuracy of the obtained traffic-resource consumption model is, which may result in that the accuracy of the predicted node single machine bandwidth value in the corresponding time period is not high, and at this time, the confidence of the corresponding node single machine bandwidth value may be set to be low.
In an example, the value range of the resource consumption data in the operation data may be used to measure whether the operation data is single, for example, when the value range of the resource consumption data is smaller, such as between 10% and 20%, or between 10% and 30%, the more single the operation data is determined.
And S403, after the confidence degrees of the single-machine bandwidth values of the nodes in each historical time period and the current time period are determined, determining the weight coefficients of the single-machine bandwidth values of the nodes in each historical time period and the current time period according to the positive correlation between the confidence degrees and the weight coefficients.
The confidence degrees of the node single machine bandwidth values in each historical time period and the current time period can represent the accuracy of the node single machine bandwidth value prediction, and the accuracy corresponding to the low confidence degree is low, so that a smaller weight coefficient can be set for the node single machine bandwidth value corresponding to the low confidence degree, or the weight coefficient is directly set to 0 and does not participate in the determination of the monitoring bandwidth of the CDN node to be detected.
In a possible implementation manner, the weighting coefficients of the node single machine bandwidth values in each historical time period and the current time period may also be set according to the hardware resource consumption utilization rates corresponding to the operation data in each historical time period and the current time period, or the time difference between each time period and the current time, and the like.
S404, after determining the weighting coefficients of the node single machine bandwidth values in each historical time period and the current time period, calculating a weighted average of the node single machine bandwidth values and the weighting coefficients thereof in each historical time period and the current time period, and determining the weighted average as the monitoring bandwidth of the CDN node to be detected.
In the embodiment of the disclosure, node single-machine bandwidth values in each historical time period and current time period and confidence degrees of the node single-machine bandwidth values in each historical time period and current time period are comprehensively considered, and the monitoring bandwidth of the CDN node is determined, so that excessively severe changes in the bandwidth of the CDN node outlet are avoided, and fluctuations in the node single-machine bandwidth values of the CDN node to be detected are reduced.
The embodiment of the present disclosure further provides a node bandwidth monitoring device, referring to fig. 5, the device includes:
the data obtaining module 501 is configured to obtain operation data of the CDN node to be detected in the current time period, where the operation data includes traffic characteristic data and resource consumption data of the CDN node to be detected;
the model updating module 502 is configured to update a predetermined flow-resource consumption model and model error indexes by using operation data of the CDN node to be detected in the current time period;
the bandwidth prediction module 503 is configured to determine, based on a traffic-resource consumption model, a bandwidth value that can be borne by the CDN node to be detected when the resource usage reaches a threshold, and obtain a node-individual bandwidth value of the CDN node to be detected;
and the bandwidth monitoring module 504 is configured to determine the monitoring bandwidth of the CDN node to be detected according to the node standalone bandwidth value of the CDN node to be detected and the model error index.
In the embodiment of the disclosure, the predetermined flow-resource consumption model and model error index are updated by using the operating data of the CDN node to be detected in the current time period, so that the flow-resource consumption model can more accurately describe the corresponding relationship between the flow and the resource consumption in the current time period, further, based on the flow-resource consumption model, the bandwidth value that the CDN node to be detected can bear when the resource usage reaches the threshold is determined, a more accurate node single machine bandwidth value of the CDN node to be detected is obtained, the monitoring bandwidth of the CDN node to be detected is determined according to the node single machine bandwidth value of the node to be detected and the model error index, the bandwidth monitoring of the CDN node to be detected can be more accurately realized, and further, a more accurate node available bandwidth can be provided for the CDN scheduling system, thereby realizing load balancing among the CDN nodes, and the resource utilization rate of each CDN node is improved.
In a possible embodiment, the above apparatus further comprises:
the historical data acquisition module is used for acquiring operation data of the CDN node to be detected within a historical time period;
the sample data determining module is used for taking the flow characteristic data in the historical time period as the sample input characteristic of the algorithm model and taking the resource consumption data in the historical time period as the sample output characteristic of the algorithm model to obtain the sample data in the historical time period;
and the model training module is used for training the algorithm model by using the sample data in the historical time period to obtain a flow-resource consumption model and a model error index.
In a possible embodiment, the above apparatus further comprises:
the data filtering module is used for filtering the sample data in the historical time period to obtain the filtered sample data;
and the data conversion module is used for performing dimension conversion on the filtered sample data to obtain the sample data for algorithm model training.
In a possible implementation manner, the bandwidth prediction module 503 includes:
the data acquisition submodule is used for acquiring flow characteristic data of the CDN node to be detected in a specified time period in the current time period; the specified time period is a time period corresponding to the latest flow use peak period in the current time period;
and the bandwidth prediction submodule is used for predicting a bandwidth value which can be borne by the CDN node to be detected when the resource usage reaches a threshold value by using a flow-resource consumption model based on the flow characteristic data of the specified time period to obtain a node single machine bandwidth value of the CDN node to be detected.
In a possible implementation manner, the bandwidth prediction sub-module is specifically configured to:
taking the flow characteristic data of the specified time period as the input of a flow-resource consumption model, and predicting the resource consumption data corresponding to the flow characteristic data of the specified time period by using the flow-resource consumption model to obtain a target resource consumption value;
judging whether the target resource consumption value reaches a threshold value of the resource usage amount of the CDN node to be detected;
if so, determining the target resource consumption value as a node single machine bandwidth value of the CDN node to be detected;
if not, zooming the flow characteristic data of the specified time period by using a preset zooming proportion, updating the zoomed flow characteristic data into the flow characteristic data of the specified time period, returning to execute the step of taking the flow characteristic data of the specified time period as the input of a flow-resource consumption model, and predicting the resource consumption data corresponding to the flow characteristic data of the specified time period by using the flow-resource consumption model to obtain a target resource consumption value.
In a possible implementation manner, the bandwidth monitoring module 504 is specifically configured to:
acquiring node single machine bandwidth values and model error indexes of CDN nodes to be detected in different historical time periods;
respectively determining the confidence coefficients of the node single machine bandwidth values in each historical time period and the current time period based on the model error indexes and the operation data in each historical time period and the current time period;
determining the weight coefficients of the node single machine bandwidth values in each historical time period and the current time period based on the confidence coefficients of the node single machine bandwidth values in each historical time period and the current time period;
and determining the monitoring bandwidth of the CDN node to be detected according to the node single machine bandwidth values and the weight coefficients thereof in each historical time period and the current time period.
In a possible embodiment, the above apparatus further comprises:
and the data storage module is used for storing the model error index and the node single machine bandwidth value of the CDN node to be detected.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
Wherein, electronic equipment includes:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any of the present disclosure.
A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of the present disclosure.
A computer program product comprising a computer program which, when executed by a processor, implements the method of any of the present disclosure.
In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user all conform to the regulations of related laws and regulations, and do not violate the requirements of public order and good custom, it is noted that the head model in the embodiment is not a head model for a specific user, and cannot reflect the personal information of the specific user. It should be noted that the two-dimensional face image in the present embodiment is from a public data set.
FIG. 6 illustrates a schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the apparatus 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, or the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The computing unit 601 performs the various methods and processes described above, such as the node bandwidth monitoring method. For example, in some embodiments, the node bandwidth monitoring method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the node bandwidth monitoring method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the node bandwidth monitoring method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (17)
1. A node bandwidth monitoring method comprises the following steps:
obtaining operation data of a CDN node to be detected in a current time period, wherein the operation data comprises flow characteristic data and resource consumption data of the CDN node to be detected;
updating a predetermined flow-resource consumption model and a model error index by using the operation data of the CDN node to be detected in the current time period;
determining a bandwidth value which can be borne by the CDN node to be detected when the resource usage reaches a threshold value based on a flow-resource consumption model, and obtaining a node single machine bandwidth value of the CDN node to be detected;
and determining the monitoring bandwidth of the CDN node to be detected according to the node single machine bandwidth value of the CDN node to be detected and the model error index.
2. The method of claim 1, further comprising:
acquiring operation data of the CDN node to be detected in a historical time period;
taking the flow characteristic data in the historical time period as a sample input characteristic of an algorithm model, and taking the resource consumption data in the historical time period as a sample output characteristic of the algorithm model to obtain sample data in the historical time period;
and training the algorithm model by using the sample data in the historical time period to obtain a flow-resource consumption model and a model error index.
3. The method of claim 2, before training an algorithm model with the sample data in the historical time period to obtain a traffic-resource consumption model and a model error indicator, the method further comprising:
filtering the sample data in the historical time period to obtain the filtered sample data;
and carrying out dimension conversion on the sample data after the filtering processing to obtain the sample data for algorithm model training.
4. The method according to claim 1, wherein the determining, based on the traffic-resource consumption model, a bandwidth value that the CDN node to be detected can bear when the resource usage reaches a threshold to obtain a node-individual bandwidth value of the CDN node to be detected includes:
acquiring flow characteristic data of the CDN node to be detected in a specified time period in the current time period; the specified time period is a time period corresponding to the latest flow use peak period in the current time period;
and predicting a bandwidth value which can be borne by the CDN node to be detected when the resource usage reaches a threshold value by using the flow-resource consumption model based on the flow characteristic data of the specified time period to obtain a node single machine bandwidth value of the CDN node to be detected.
5. The method according to claim 4, wherein the predicting, based on the traffic characteristic data of the specified time period and using the traffic-resource consumption model, a bandwidth value that the CDN node to be detected can bear when the resource usage reaches a threshold to obtain a node-individual bandwidth value of the CDN node to be detected includes:
taking the flow characteristic data of the specified time period as the input of the flow-resource consumption model, and predicting the resource consumption data corresponding to the flow characteristic data of the specified time period by using the flow-resource consumption model to obtain a target resource consumption value;
judging whether the target resource consumption value reaches a threshold value of the resource usage amount of the CDN node to be detected;
if so, determining the target resource consumption value as a node single machine bandwidth value of the CDN node to be detected;
if not, zooming the flow characteristic data of the specified time period by using a preset zooming proportion, updating the zoomed flow characteristic data into the flow characteristic data of the specified time period, returning to execute the step of taking the flow characteristic data of the specified time period as the input of the flow-resource consumption model, and predicting the resource consumption data corresponding to the flow characteristic data of the specified time period by using the flow-resource consumption model to obtain a target resource consumption value.
6. The method according to claim 1, wherein the determining the monitoring bandwidth of the CDN node to be detected according to the node standalone bandwidth value of the CDN node to be detected and the model error index includes:
obtaining node single machine bandwidth values and the model error indexes of the CDN node to be detected in different historical time periods;
respectively determining the confidence coefficients of the node single machine bandwidth values in each historical time period and the current time period based on the model error indexes and the operation data in each historical time period and the current time period;
determining the weight coefficients of the node single machine bandwidth values in each historical time period and the current time period based on the confidence coefficients of the node single machine bandwidth values in each historical time period and the current time period;
and determining the monitoring bandwidth of the CDN node to be detected according to the node single machine bandwidth values and the weight coefficients thereof in each historical time period and the current time period.
7. The method of claim 1, further comprising:
and storing the model error index and the node single machine bandwidth value of the CDN node to be detected.
8. A node bandwidth monitoring apparatus, comprising:
the system comprises a data acquisition module, a resource consumption module and a resource management module, wherein the data acquisition module is used for acquiring operation data of a CDN node to be detected in a current time period, and the operation data comprises flow characteristic data and resource consumption data of the CDN node to be detected;
the model updating module is used for updating a predetermined flow-resource consumption model and a model error index by using the operation data of the CDN node to be detected in the current time period;
the bandwidth prediction module is used for determining a bandwidth value which can be borne by the CDN node to be detected when the resource usage reaches a threshold value based on a flow-resource consumption model, so as to obtain a node single machine bandwidth value of the CDN node to be detected;
and the bandwidth monitoring module is used for determining the monitoring bandwidth of the CDN node to be detected according to the node single machine bandwidth value of the CDN node to be detected and the model error index.
9. The apparatus of claim 8, the apparatus further comprising:
the historical data acquisition module is used for acquiring the operating data of the CDN node to be detected within a historical time period;
the sample data determining module is used for taking the flow characteristic data in the historical time period as the sample input characteristic of the algorithm model and taking the resource consumption data in the historical time period as the sample output characteristic of the algorithm model to obtain the sample data in the historical time period;
and the model training module is used for training the algorithm model by using the sample data in the historical time period to obtain a flow-resource consumption model and a model error index.
10. The apparatus of claim 9, the apparatus further comprising:
the data filtering module is used for filtering the sample data in the historical time period to obtain the filtered sample data;
and the data conversion module is used for carrying out dimension conversion on the filtered sample data to obtain the sample data for algorithm model training.
11. The apparatus of claim 8, wherein the bandwidth prediction module comprises:
the data acquisition submodule is used for acquiring traffic characteristic data of the CDN node to be detected in a specified time period in the current time period; the specified time period is a time period corresponding to the latest flow use peak period in the current time period;
and the bandwidth prediction submodule is used for predicting a bandwidth value which can be borne by the CDN node to be detected when the resource usage reaches a threshold value by utilizing the flow-resource consumption model based on the flow characteristic data of the specified time period, so as to obtain a node single machine bandwidth value of the CDN node to be detected.
12. The apparatus of claim 11, wherein the bandwidth predictor sub-module is specifically configured to:
taking the flow characteristic data of the specified time period as the input of the flow-resource consumption model, and predicting the resource consumption data corresponding to the flow characteristic data of the specified time period by using the flow-resource consumption model to obtain a target resource consumption value;
judging whether the target resource consumption value reaches a threshold value of the resource usage amount of the CDN node to be detected;
if so, determining the target resource consumption value as a node single machine bandwidth value of the CDN node to be detected;
if not, zooming the flow characteristic data of the specified time period by using a preset zooming proportion, updating the zoomed flow characteristic data into the flow characteristic data of the specified time period, returning to execute the step of taking the flow characteristic data of the specified time period as the input of the flow-resource consumption model, and predicting the resource consumption data corresponding to the flow characteristic data of the specified time period by using the flow-resource consumption model to obtain a target resource consumption value.
13. The apparatus according to claim 8, wherein the bandwidth monitoring module is specifically configured to:
obtaining node single machine bandwidth values and the model error indexes of the CDN node to be detected in different historical time periods;
respectively determining the confidence coefficient of the single node bandwidth value in each historical time period and the current time period based on the model error index and the operation data in each historical time period and the current time period;
determining the weight coefficients of the node single machine bandwidth values in each historical time period and the current time period based on the confidence coefficients of the node single machine bandwidth values in each historical time period and the current time period;
and determining the monitoring bandwidth of the CDN node to be detected according to the node single machine bandwidth values and the weight coefficients thereof in each historical time period and the current time period.
14. The apparatus of claim 8, the apparatus further comprising:
and the data storage module is used for storing the model error index and the node single machine bandwidth value of the CDN node to be detected.
15. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-7.
17. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210116825.4A CN114500339B (en) | 2022-02-07 | 2022-02-07 | Node bandwidth monitoring method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210116825.4A CN114500339B (en) | 2022-02-07 | 2022-02-07 | Node bandwidth monitoring method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114500339A true CN114500339A (en) | 2022-05-13 |
| CN114500339B CN114500339B (en) | 2023-07-04 |
Family
ID=81478939
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210116825.4A Active CN114500339B (en) | 2022-02-07 | 2022-02-07 | Node bandwidth monitoring method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114500339B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114945024A (en) * | 2022-05-19 | 2022-08-26 | 东北林业大学 | Server load balancing optimization method based on long-term and short-term memory network |
| CN115086244A (en) * | 2022-06-16 | 2022-09-20 | 平安付科技服务有限公司 | Bandwidth allocation method and device, computer equipment and storage medium |
| CN117827710A (en) * | 2024-03-06 | 2024-04-05 | 上海燧原智能科技有限公司 | DMA bandwidth determining method, device, equipment and medium based on AI chip |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180302296A1 (en) * | 2016-10-14 | 2018-10-18 | Tencent Technology (Shenzhen) Company Limited | Network service scheduling method and apparatus, storage medium, and program product |
| CN110474852A (en) * | 2019-08-01 | 2019-11-19 | 网宿科技股份有限公司 | A kind of bandwidth scheduling method and device |
| CN111464323A (en) * | 2019-01-18 | 2020-07-28 | 北京沃东天骏信息技术有限公司 | Node bandwidth scheduling method and scheduling device |
| US20210120078A1 (en) * | 2018-07-10 | 2021-04-22 | Wangsu Science & Technology Co., Ltd. | Method, device, and scheduling server for network resource acquisition |
| CN112714029A (en) * | 2021-02-09 | 2021-04-27 | 北京金山云网络技术有限公司 | Method, device and equipment for scheduling content distribution network bandwidth |
| CN113132479A (en) * | 2021-04-16 | 2021-07-16 | 北京百度网讯科技有限公司 | Traffic switching method, traffic switching apparatus, traffic model generating method, traffic model generating apparatus, traffic model generating |
| US20210303985A1 (en) * | 2020-03-25 | 2021-09-30 | EMC IP Holding Company LLC | Machine learning based resource availability prediction |
| CN113691398A (en) * | 2021-08-13 | 2021-11-23 | 北京金山云网络技术有限公司 | Node bandwidth prediction method and device, electronic equipment and storage medium |
| CN113839795A (en) * | 2020-06-23 | 2021-12-24 | 北京金山云网络技术有限公司 | Peak eliminating processing method and device for CDN node, electronic equipment and storage medium |
-
2022
- 2022-02-07 CN CN202210116825.4A patent/CN114500339B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180302296A1 (en) * | 2016-10-14 | 2018-10-18 | Tencent Technology (Shenzhen) Company Limited | Network service scheduling method and apparatus, storage medium, and program product |
| US20210120078A1 (en) * | 2018-07-10 | 2021-04-22 | Wangsu Science & Technology Co., Ltd. | Method, device, and scheduling server for network resource acquisition |
| CN111464323A (en) * | 2019-01-18 | 2020-07-28 | 北京沃东天骏信息技术有限公司 | Node bandwidth scheduling method and scheduling device |
| CN110474852A (en) * | 2019-08-01 | 2019-11-19 | 网宿科技股份有限公司 | A kind of bandwidth scheduling method and device |
| US20210303985A1 (en) * | 2020-03-25 | 2021-09-30 | EMC IP Holding Company LLC | Machine learning based resource availability prediction |
| CN113839795A (en) * | 2020-06-23 | 2021-12-24 | 北京金山云网络技术有限公司 | Peak eliminating processing method and device for CDN node, electronic equipment and storage medium |
| CN112714029A (en) * | 2021-02-09 | 2021-04-27 | 北京金山云网络技术有限公司 | Method, device and equipment for scheduling content distribution network bandwidth |
| CN113132479A (en) * | 2021-04-16 | 2021-07-16 | 北京百度网讯科技有限公司 | Traffic switching method, traffic switching apparatus, traffic model generating method, traffic model generating apparatus, traffic model generating |
| CN113691398A (en) * | 2021-08-13 | 2021-11-23 | 北京金山云网络技术有限公司 | Node bandwidth prediction method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| BABANGIDA ALBABA ABUBAKAR; MILTOS PETRIDIS; DESHINDER SINGH GILL; SAEED MALEKSHAHI GHEYTASSI: "Adaptive CDN-based bandwidth conserving algorithm for Mobile IPTV", 2016 EIGHTH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTATIONAL INTELLIGENCE (ICACI) * |
| 林春莺: "一种基于强化学习的CDN流量调度系统设计方法", 集美大学学报(自然科学版) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114945024A (en) * | 2022-05-19 | 2022-08-26 | 东北林业大学 | Server load balancing optimization method based on long-term and short-term memory network |
| CN115086244A (en) * | 2022-06-16 | 2022-09-20 | 平安付科技服务有限公司 | Bandwidth allocation method and device, computer equipment and storage medium |
| CN117827710A (en) * | 2024-03-06 | 2024-04-05 | 上海燧原智能科技有限公司 | DMA bandwidth determining method, device, equipment and medium based on AI chip |
| CN117827710B (en) * | 2024-03-06 | 2024-05-24 | 上海燧原智能科技有限公司 | DMA bandwidth determining method, device, equipment and medium based on AI chip |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114500339B (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109697522B (en) | Data prediction method and device | |
| CN114500339B (en) | Node bandwidth monitoring method and device, electronic equipment and storage medium | |
| CN108923996B (en) | Capacity analysis method and device | |
| US20180352020A1 (en) | Perfect application capacity analysis for elastic capacity management of cloud-based applications | |
| CN111198808A (en) | Method, device, storage medium and electronic equipment for predicting performance index | |
| CN113407426A (en) | Server cluster capacity evaluation method and device, electronic equipment and storage medium | |
| CN108459905B (en) | Resource pool capacity planning method and server | |
| CN112527598A (en) | Method, apparatus, device, storage medium and program product for monitoring data | |
| CN110766184A (en) | Order quantity prediction method and device | |
| CN112506619A (en) | Job processing method, apparatus, electronic device, storage medium, and program product | |
| CN114818913A (en) | Decision generation method and device | |
| CN114301803A (en) | Network quality detection method and device, electronic equipment and storage medium | |
| CN116756522B (en) | Probability forecasting method and device, storage medium and electronic equipment | |
| CN113159453A (en) | Resource data prediction method, device, equipment and storage medium | |
| WO2023029680A1 (en) | Method and apparatus for determining usable duration of magnetic disk | |
| CN114257521B (en) | Traffic prediction method, traffic prediction device, electronic equipment and storage medium | |
| CN113556394B (en) | Cloud product network usage processing method, device, equipment, storage medium and product | |
| CN115619170A (en) | Method, device, equipment, computer medium and program product for adjusting electric quantity load | |
| CN114520773A (en) | Service request response method, device, server and storage medium | |
| CN114999665A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN115225543A (en) | Flow prediction method and device, electronic equipment and storage medium | |
| CN114612212A (en) | Business processing method, device and system based on risk control | |
| CN113961797A (en) | Resource recommendation method and device, electronic equipment and readable storage medium | |
| CN113411390B (en) | Scheduling method and device of content distribution network and electronic equipment | |
| CN113225228B (en) | Data processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |