CN112532459A - Bandwidth resource adjusting method, device and equipment - Google Patents
Bandwidth resource adjusting method, device and equipment Download PDFInfo
- Publication number
- CN112532459A CN112532459A CN202011418772.9A CN202011418772A CN112532459A CN 112532459 A CN112532459 A CN 112532459A CN 202011418772 A CN202011418772 A CN 202011418772A CN 112532459 A CN112532459 A CN 112532459A
- Authority
- CN
- China
- Prior art keywords
- information
- bandwidth
- network
- resource
- adjusting
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000013499 data model Methods 0.000 claims abstract description 32
- 238000013135 deep learning Methods 0.000 claims abstract description 23
- 238000004891 communication Methods 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000014509 gene expression Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005314 correlation function Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- 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
- H04L41/08—Configuration management of networks or network elements
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- 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
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Mathematical Optimization (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Biology (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
Abstract
The invention discloses a bandwidth resource adjusting method, which comprises the steps of receiving network resource information; inputting the network resource information into a pre-trained traffic data model to obtain bandwidth traffic prediction information; the traffic data model is a deep learning network model; and adjusting bandwidth resources according to the bandwidth flow prediction information. According to the method and the device, the bandwidth flow corresponding to each network resource information is learned through the flow prediction model, the accuracy of the bandwidth flow prediction information can be greatly improved by utilizing a computer deep learning technology, the bandwidth resource adjustment in the network is guided according to the bandwidth flow prediction information, and the possibility of network blockage caused by the vacancy of the bandwidth resource or insufficient bandwidth is further reduced. The invention also provides a bandwidth resource adjusting device, equipment and a computer readable storage medium with the beneficial effects.
Description
Technical Field
The present invention relates to the field of network resource allocation, and in particular, to a method, an apparatus, a device, and a computer-readable storage medium for adjusting bandwidth resources.
Background
The Internet of things can comprehensively sense information, rapid networking can be realized, and convenience and flexibility are achieved. However, such a huge amount of terminal devices of the internet of things are accessed into the network, so that various excellent efficiencies are realized, and meanwhile, a new demand is inevitably put on the calculation of network resources, so as to prevent the network from being blocked or the system from being crashed due to insufficient allocated bandwidth when the flow rate rises.
In the prior art, the prediction of the traffic is usually performed only by allocating the network bandwidth according to the personal experience of an operator, or by simply calculating the average value and the maximum value of the traffic, or by statistically predicting the traffic trend of the traffic in a certain past time period, the communication bandwidth of the power grid is predicted. However, since the traffic distribution conditions of different services in the same day are not always the same, the accuracy of this method is not high, and in the current network service, there are still a lot of network congestion caused by too low traffic prediction, or a lot of waste caused by resource vacancy caused by too high traffic prediction.
Therefore, how to solve the problem of low accuracy of bandwidth resource prediction in the prior art is a problem to be urgently solved by the technical staff in the field.
Disclosure of Invention
The invention aims to provide a bandwidth resource adjusting method, a bandwidth resource adjusting device, bandwidth resource adjusting equipment and a computer readable storage medium, which are used for solving the problem that in the prior art, the flow prediction accuracy is low, so that the network is blocked or resources are vacant too much.
In order to solve the above technical problem, the present invention provides a bandwidth resource adjusting method, including:
receiving network resource information;
inputting the network resource information into a pre-trained traffic data model to obtain bandwidth traffic prediction information; the traffic data model is a deep learning network model;
and adjusting bandwidth resources according to the bandwidth flow prediction information.
Optionally, in the bandwidth resource adjustment method, the receiving network resource information includes:
receiving network state information and time period information;
correspondingly, inputting the network state information and the time period information into the traffic data model to obtain time point bandwidth traffic prediction information corresponding to each moment in the time period information;
and correspondingly, adjusting the bandwidth resources according to the time point bandwidth flow prediction information.
Optionally, in the bandwidth resource adjustment method, the receiving network state information includes:
receiving at least one of communication packet number information, communication byte number information, communication retransmission number information, communication delay information and packet loss rate information.
Optionally, in the method for adjusting bandwidth resources, the method further includes:
acquiring total amount information of available resources;
judging whether the bandwidth flow prediction information is not less than the total amount information of the available resources;
and when the bandwidth flow prediction information is not less than the total amount information of the available resources, sending alarm information.
A bandwidth resource adjustment apparatus, comprising:
the receiving module is used for receiving the network resource information;
the prediction module is used for inputting the network resource information into a pre-trained traffic data model to obtain bandwidth traffic prediction information; the traffic data model is a deep learning network model;
and the adjusting module is used for adjusting the bandwidth resources according to the bandwidth flow prediction information.
Optionally, in the bandwidth resource adjusting apparatus, the receiving module includes:
the time interval receiving unit is used for receiving the network state information and the time interval information;
correspondingly, the prediction module comprises a time interval prediction unit, and the time interval prediction unit is used for inputting the network state information and the time interval information into the traffic data model to obtain time point bandwidth traffic prediction information corresponding to each moment in the time interval information;
correspondingly, the adjusting module includes a time point adjusting unit, configured to adjust the bandwidth resource according to the time point bandwidth flow prediction information.
Optionally, in the bandwidth resource adjusting apparatus, the receiving module includes:
and the complex information receiving unit is used for receiving at least one of communication packet number information, communication byte number information, communication retransmission number information, communication delay information and packet loss rate information.
Optionally, in the bandwidth resource adjusting apparatus, the apparatus further includes:
the total amount acquisition module is used for acquiring total amount information of available resources;
the flow judgment module is used for judging whether the bandwidth flow prediction information is not less than the total amount information of the available resources;
and the alarm module is used for sending alarm information when the bandwidth flow prediction information is not less than the total amount information of the available resources.
A bandwidth resource adjustment apparatus comprising:
a memory for storing a computer program;
a processor, configured to implement the steps of the bandwidth resource adjustment method according to any one of the above descriptions when the computer program is executed.
A computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the bandwidth resource adjustment method according to any one of the preceding claims.
The bandwidth resource adjusting method provided by the invention receives the network resource information; inputting the network resource information into a pre-trained traffic data model to obtain bandwidth traffic prediction information; the traffic data model is a deep learning network model; and adjusting bandwidth resources according to the bandwidth flow prediction information. According to the method and the device, the bandwidth flow corresponding to each network resource information is learned through the flow prediction model, the accuracy of the bandwidth flow prediction information can be greatly improved by utilizing a computer deep learning technology, the bandwidth resource adjustment in the network is guided according to the bandwidth flow prediction information, and the possibility of network blockage caused by the vacancy of the bandwidth resource or insufficient bandwidth is further reduced. The invention also provides a bandwidth resource adjusting device, equipment and a computer readable storage medium with the beneficial effects.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a bandwidth resource adjustment method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of another embodiment of a bandwidth resource adjustment method according to the present invention;
fig. 3 is a flowchart illustrating a bandwidth resource adjustment method according to another embodiment of the present invention;
fig. 4 is a schematic structural diagram of an embodiment of a bandwidth resource adjusting apparatus according to the present invention.
Detailed Description
Deep learning allows a computational model composed of multiple processing layers to learn expressions with multiple levels of abstract data, and the method is widely applied to many fields, such as visual object recognition, voice recognition, object detection and the like, and simultaneously plays a role in promoting new medicine discovery and new genomics development. Deep learning utilizes back-propagation algorithms to find the inherently complex structure of large data, and then the BP algorithm will instruct the machine how to change its internal parameters at each layer using the expressions obtained from the previous layer. The essence of deep learning is to use massive training data (which can be label-free data) to learn more useful characteristic data by constructing a multi-hidden-layer model, so that the data classification effect is improved, and the accuracy of a prediction result is improved. The "deep learning model" is a means and the "feature learning" is a purpose.
The single or shallow learning algorithm has insufficient prediction accuracy on the bandwidth flow, and has low utilization rate and long running time on a large amount of bandwidth flow data. The deep learning model basically has no oversaturation state when facing increasingly huge data volume, better learning effect can be obtained when the data is more, and the advantage of large data volume can be exerted to the greatest extent.
In the current flow prediction, a poisson model proposed according to the characteristics of telephone service is widely applied because the poisson model can accurately describe the service characteristics in a telephone network. However, the model is more applicable to the conventional telephone switching network, and the poisson model is not suitable for data network traffic analysis because the data communication traffic is bursty. An autoregressive Moving Average Model (ARMA) based on a research statistical rule is based on an autoregressive Model (AR Model) and a Moving Average Model (MA Model), and a future value is estimated by adopting a historical value. But the method has low sensitivity to the development of the service, and cannot better reflect the influence of the service change on the network bandwidth.
The real-time data volume of the Internet of things is large, the prediction accuracy of a single or shallow learning algorithm on the bandwidth flow is not enough, and meanwhile, the utilization rate of a large amount of bandwidth flow data is not high, and the running time is long. The deep learning model basically has no oversaturation state when facing increasingly huge data volume, better learning effect can be obtained when the data is more, and the advantage of large data volume can be exerted to the greatest extent.
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The core of the present invention is to provide a method for adjusting bandwidth resources, a flowchart of one embodiment of which is shown in fig. 1, and is referred to as a first embodiment, and the method includes:
s101: network resource information is received.
S102: inputting the network resource information into a pre-trained traffic data model to obtain bandwidth traffic prediction information; the traffic data model is a deep learning network model.
The pre-training process of deep learning is an unsupervised learning process, initial weights of an algorithm can be obtained by using a pre-training network, and greedy optimization is performed layer by layer to obtain a training strategy. The visual layer of the RBM is v and the hidden layer is h, and meanwhile, the nodes in the layers are opposite to each other, and all the nodes in the layers are connected with each other. The energy function and probability distribution function of the RBM stochastic model can be expressed as:
(the above formula is an energy function, and the following formula is a probability distribution function)
In the formula, viThe node state is a visible layer node state; h isiThe state is a hidden node state; a isi、biBiasing the corresponding layer node; omegaijThe connection weight between the nodes is obtained; θ ═ { W, a, b } is the network weight, i.e. the parameter to be optimized at this stage; z is a normalized coefficient of the coefficient,the expression is as follows:
(normalization factor)
Through the above process, an output similar to the input data distribution can be obtained. Through preferentially training the RBM at the lowest layer and taking the number of influencing factors as input, the expression h of the bandwidth flow is obtained1Then by h1As input, the second tier RBM is trained, and so on. The output layer is a Softmax classifier, and the output layer weight omega is randomly initialized through sample comparison.
S103: and adjusting bandwidth resources according to the bandwidth flow prediction information.
The bandwidth resource adjusting method provided by the invention receives the network resource information; inputting the network resource information into a pre-trained traffic data model to obtain bandwidth traffic prediction information; the traffic data model is a deep learning network model; and adjusting bandwidth resources according to the bandwidth flow prediction information. According to the method and the device, the bandwidth flow corresponding to each network resource information is learned through the flow prediction model, the accuracy of the bandwidth flow prediction information can be greatly improved by utilizing a computer deep learning technology, the bandwidth resource adjustment in the network is guided according to the bandwidth flow prediction information, and the possibility of network blockage caused by the vacancy of the bandwidth resource or insufficient bandwidth is further reduced.
On the basis of the first specific embodiment, the input quantity of the flow data model is further improved to obtain a second specific embodiment, a flow diagram of which is shown in fig. 2, and includes:
s201: and receiving the network state information and the time period information.
The network state information comprises at least one of communication packet number information, communication byte number information, communication retransmission number information, communication delay information and packet loss rate information, wherein the communication packet number information comprises uplink packet number information, downlink packet number information, uplink bad packet number information and downlink bad packet number information, the communication byte number information comprises uplink byte number information and downlink byte number information, and the communication retransmission number information comprises uplink retransmission number information and downlink retransmission number information.
S202: and inputting the network state information and the time period information into the traffic data model to obtain time point bandwidth traffic prediction information corresponding to each moment in the time period information.
The time point bandwidth flow prediction information in this step refers to bandwidth flow prediction information combined with time characteristics, which includes bandwidth flow prediction information at each time, and of course, each time may be a time with a minimum unit of every second, every minute, or every ten minutes.
S203: and adjusting bandwidth resources according to the time point bandwidth flow prediction information.
In traffic prediction, one key point is to find a functional relationship between bandwidth traffic, user number and time, assuming that y is a certain traffic, x is the number of users simultaneously using the service, and t is a certain time period of the day, then:
y＝f(x)·t
(service broadband flow function)
The traffic flow y is a correlation function consisting of time t and number of users x. Meanwhile, the number x of users using the service is a correlation function consisting of the total number a of users and time t:
X＝g(A)·t
(number of users)
According to statistical analysis, the total number of users is constant in a certain time, and can be regarded as a constant, namely x is only a function related to time t. Therefore, in a certain time, the traffic at a certain interface is the accumulation of various service traffic at the interface, that is:
(interface flow)
The deep learning method is mainly used for finding out a relation equation of original data and time in the bandwidth flow prediction process.
According to the technical scheme in the specific embodiment, after a time period and predicted service details are given, the system can calculate the total predicted usage flow of the internet of things in the time period according to the process. By the total amount, the autonomous flow management of the network is realized, and data support is provided for the application of the network in service by analyzing real-time data such as running state, efficiency, quality and the like. Meanwhile, the data can be used for cooperating with the operation III so as to solve the problem of congestion and overload brought to an access network by a large number of burst connections of the Internet of things in a planned way.
On the basis of the second specific embodiment, the bandwidth resource adjustment method is further improved to obtain a third specific embodiment, a flow diagram of which is shown in fig. 3, and includes:
s301: and receiving the network state information and the time period information.
S302: and inputting the network state information and the time period information into the traffic data model to obtain time point bandwidth traffic prediction information corresponding to each moment in the time period information.
S303: and adjusting bandwidth resources according to the time point bandwidth flow prediction information.
S304: and acquiring the total amount information of the available resources.
The total amount of available resources refers to the maximum available bandwidth of the system, and it should be noted that there is no precedence relationship between step S304 and the above steps S301 to S303, and this application places this step after S303 as a specific implementation, which may be adjusted accordingly in practical applications according to specific situations.
S305: and judging whether the bandwidth flow prediction information is not less than the total amount information of the available resources.
S306: and when the bandwidth flow prediction information is not less than the total amount information of the available resources, sending alarm information.
In the specific embodiment, a step of acquiring the total bandwidth scheduled by the system internal medicine, namely the total available resource information is further added, when the predicted required bandwidth exceeds the total available resource information, it is indicated that the predicted flow exceeds the upper limit of the system load, a worker needs to be reminded in time, and a certain processing time is reserved, so that the system paralysis caused by impact of a large amount of flow on the system without early warning is avoided.
In the following, the bandwidth resource adjusting apparatus provided in the embodiments of the present invention is introduced, and the bandwidth resource adjusting apparatus described below and the bandwidth resource adjusting method described above may be referred to correspondingly.
Fig. 4 is a block diagram of a bandwidth resource adjustment apparatus according to an embodiment of the present invention, which is referred to as a fourth specific implementation, where, referring to fig. 4, the bandwidth resource adjustment apparatus may include:
a receiving module 100, configured to receive network resource information;
the prediction module 200 is used for inputting the network resource information into a pre-trained traffic data model to obtain bandwidth traffic prediction information; the traffic data model is a deep learning network model;
and an adjusting module 300, configured to adjust bandwidth resources according to the bandwidth traffic prediction information.
As a preferred embodiment, the receiving module 100 includes:
the time interval receiving unit is used for receiving the network state information and the time interval information;
correspondingly, the prediction module 200 includes a time period prediction unit, configured to input the network state information and the time period information into the traffic data model, so as to obtain time point bandwidth traffic prediction information corresponding to each time in the time period information;
accordingly, the adjusting module 300 includes a time point adjusting unit, configured to adjust bandwidth resources according to the time point bandwidth traffic prediction information.
As a preferred embodiment, the receiving module 100 includes:
and the complex information receiving unit is used for receiving at least one of communication packet number information, communication byte number information, communication retransmission number information, communication delay information and packet loss rate information.
As a preferred embodiment, the method further comprises:
the total amount acquisition module is used for acquiring total amount information of available resources;
the flow judgment module is used for judging whether the bandwidth flow prediction information is not less than the total amount information of the available resources;
and the alarm module is used for sending alarm information when the bandwidth flow prediction information is not less than the total amount information of the available resources.
The bandwidth resource adjusting apparatus of this embodiment is configured to implement the foregoing bandwidth resource adjusting method, and therefore specific implementations of the bandwidth resource adjusting apparatus can be seen in the foregoing embodiments of the bandwidth resource adjusting method, for example, the receiving module 100, the predicting module 200, and the adjusting module 300, which are respectively configured to implement steps S101, S102, and S103 in the foregoing bandwidth resource adjusting method, so that the specific implementations thereof may refer to descriptions of corresponding embodiments of each part, and are not described herein again.
The bandwidth resource adjusting device provided by the invention is used for receiving network resource information through the receiving module 100; the prediction module 200 is used for inputting the network resource information into a pre-trained traffic data model to obtain bandwidth traffic prediction information; the traffic data model is a deep learning network model; and an adjusting module 300, configured to adjust bandwidth resources according to the bandwidth traffic prediction information. According to the method and the device, the bandwidth flow corresponding to each network resource information is learned through the flow prediction model, the accuracy of the bandwidth flow prediction information can be greatly improved by utilizing a computer deep learning technology, the bandwidth resource adjustment in the network is guided according to the bandwidth flow prediction information, and the possibility of network blockage caused by the vacancy of the bandwidth resource or insufficient bandwidth is further reduced.
A bandwidth resource adjustment apparatus comprising:
a memory for storing a computer program;
a processor, configured to implement the steps of the bandwidth resource adjustment method according to any one of the above descriptions when the computer program is executed. The bandwidth resource adjusting method provided by the invention receives the network resource information; inputting the network resource information into a pre-trained traffic data model to obtain bandwidth traffic prediction information; the traffic data model is a deep learning network model; and adjusting bandwidth resources according to the bandwidth flow prediction information. According to the method and the device, the bandwidth flow corresponding to each network resource information is learned through the flow prediction model, the accuracy of the bandwidth flow prediction information can be greatly improved by utilizing a computer deep learning technology, the bandwidth resource adjustment in the network is guided according to the bandwidth flow prediction information, and the possibility of network blockage caused by the vacancy of the bandwidth resource or insufficient bandwidth is further reduced.
A computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the bandwidth resource adjustment method according to any one of the preceding claims. The bandwidth resource adjusting method provided by the invention receives the network resource information; inputting the network resource information into a pre-trained traffic data model to obtain bandwidth traffic prediction information; the traffic data model is a deep learning network model; and adjusting bandwidth resources according to the bandwidth flow prediction information. According to the method and the device, the bandwidth flow corresponding to each network resource information is learned through the flow prediction model, the accuracy of the bandwidth flow prediction information can be greatly improved by utilizing a computer deep learning technology, the bandwidth resource adjustment in the network is guided according to the bandwidth flow prediction information, and the possibility of network blockage caused by the vacancy of the bandwidth resource or insufficient bandwidth is further reduced.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It is to be noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The method, apparatus, device and computer readable storage medium for adjusting bandwidth resources provided by the present invention are described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (10)
1. A method for adjusting bandwidth resources, comprising:
receiving network resource information;
inputting the network resource information into a pre-trained traffic data model to obtain bandwidth traffic prediction information; the traffic data model is a deep learning network model;
and adjusting bandwidth resources according to the bandwidth flow prediction information.
2. The bandwidth resource adjustment method of claim 1, wherein the receiving network resource information comprises:
receiving network state information and time period information;
correspondingly, inputting the network state information and the time period information into the traffic data model to obtain time point bandwidth traffic prediction information corresponding to each moment in the time period information;
and correspondingly, adjusting the bandwidth resources according to the time point bandwidth flow prediction information.
3. The bandwidth resource adjustment method of claim 2, wherein the receiving network state information comprises:
receiving at least one of communication packet number information, communication byte number information, communication retransmission number information, communication delay information and packet loss rate information.
4. The method for bandwidth resource adjustment according to claim 1, further comprising:
acquiring total amount information of available resources;
judging whether the bandwidth flow prediction information is not less than the total amount information of the available resources;
and when the bandwidth flow prediction information is not less than the total amount information of the available resources, sending alarm information.
5. A bandwidth resource adjusting apparatus, comprising:
the receiving module is used for receiving the network resource information;
the prediction module is used for inputting the network resource information into a pre-trained traffic data model to obtain bandwidth traffic prediction information; the traffic data model is a deep learning network model;
and the adjusting module is used for adjusting the bandwidth resources according to the bandwidth flow prediction information.
6. The bandwidth resource adjustment apparatus of claim 5, wherein the receiving module comprises:
the time interval receiving unit is used for receiving the network state information and the time interval information;
correspondingly, the prediction module comprises a time interval prediction unit, and the time interval prediction unit is used for inputting the network state information and the time interval information into the traffic data model to obtain time point bandwidth traffic prediction information corresponding to each moment in the time interval information;
correspondingly, the adjusting module includes a time point adjusting unit, configured to adjust the bandwidth resource according to the time point bandwidth flow prediction information.
7. The bandwidth resource adjustment apparatus of claim 5, wherein the receiving module comprises:
and the complex information receiving unit is used for receiving at least one of communication packet number information, communication byte number information, communication retransmission number information, communication delay information and packet loss rate information.
8. The bandwidth resource adjustment apparatus of claim 5, further comprising:
the total amount acquisition module is used for acquiring total amount information of available resources;
the flow judgment module is used for judging whether the bandwidth flow prediction information is not less than the total amount information of the available resources;
and the alarm module is used for sending alarm information when the bandwidth flow prediction information is not less than the total amount information of the available resources.
9. A bandwidth resource adjustment apparatus, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the bandwidth resource adjustment method according to any one of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the bandwidth resource adjustment method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011418772.9A CN112532459A (en) | 2020-12-07 | 2020-12-07 | Bandwidth resource adjusting method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011418772.9A CN112532459A (en) | 2020-12-07 | 2020-12-07 | Bandwidth resource adjusting method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112532459A true CN112532459A (en) | 2021-03-19 |
Family
ID=74997886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011418772.9A Pending CN112532459A (en) | 2020-12-07 | 2020-12-07 | Bandwidth resource adjusting method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112532459A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114039870A (en) * | 2021-09-27 | 2022-02-11 | 河海大学 | Deep learning-based real-time bandwidth prediction method for video stream application in cellular network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018068558A1 (en) * | 2016-10-14 | 2018-04-19 | 腾讯科技（深圳）有限公司 | Network service scheduling method and device, and storage medium and program product |
| CN108449286A (en) * | 2018-03-01 | 2018-08-24 | 北京邮电大学 | Network bandwidth resources distribution method and device |
| CN108881967A (en) * | 2018-08-01 | 2018-11-23 | 广发证券股份有限公司 | A kind of video method for uploading, device and equipment based on machine learning |
| CA3117707A1 (en) * | 2018-10-26 | 2020-04-30 | Hughes Network Systems, Llc | Monitoring a communication network |
| CN111866953A (en) * | 2019-04-26 | 2020-10-30 | 中国移动通信有限公司研究院 | Network resource allocation method, device and storage medium |
-
2020
- 2020-12-07 CN CN202011418772.9A patent/CN112532459A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018068558A1 (en) * | 2016-10-14 | 2018-04-19 | 腾讯科技（深圳）有限公司 | Network service scheduling method and device, and storage medium and program product |
| CN108449286A (en) * | 2018-03-01 | 2018-08-24 | 北京邮电大学 | Network bandwidth resources distribution method and device |
| CN108881967A (en) * | 2018-08-01 | 2018-11-23 | 广发证券股份有限公司 | A kind of video method for uploading, device and equipment based on machine learning |
| CA3117707A1 (en) * | 2018-10-26 | 2020-04-30 | Hughes Network Systems, Llc | Monitoring a communication network |
| CN111866953A (en) * | 2019-04-26 | 2020-10-30 | 中国移动通信有限公司研究院 | Network resource allocation method, device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 新井纪子: "《当人工智能考上名校（深度剖析AI本质）》", 民主与建设出版社, pages: 19 - 20 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114039870A (en) * | 2021-09-27 | 2022-02-11 | 河海大学 | Deep learning-based real-time bandwidth prediction method for video stream application in cellular network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tan et al. | Intelligent sharing for LTE and WiFi systems in unlicensed bands: A deep reinforcement learning approach | |
| US10091675B2 (en) | System and method for estimating an effective bandwidth | |
| CN103685072A (en) | Method for quickly distributing network flow | |
| CN111614754B (en) | Fog-calculation-oriented cost-efficiency optimized dynamic self-adaptive task scheduling method | |
| CN111711666A (en) | Internet of vehicles cloud computing resource optimization method based on reinforcement learning | |
| CN102662764A (en) | Dynamic cloud computing resource optimization allocation method based on semi-Markov decision process (SMDP) | |
| CN113543160B (en) | 5G slice resource allocation method, device, computing equipment and computer storage medium | |
| Kim et al. | Mathematical model of operation of a cell of a mobile communication network with adaptive modulation schemes and handover of mobile users | |
| CN112200665A (en) | Method and device for determining credit limit | |
| CN113194040A (en) | Intelligent control method for instantaneous high-concurrency server thread pool congestion | |
| CN112532459A (en) | Bandwidth resource adjusting method, device and equipment | |
| CN111682975A (en) | Network state prediction method and device, electronic equipment and storage medium | |
| CN111901134B (en) | Method and device for predicting network quality based on recurrent neural network model (RNN) | |
| CN116385857A (en) | Calculation power distribution method based on AI intelligent scheduling | |
| CN109688065B (en) | Parameter processing method and device and storage medium | |
| CN114064394A (en) | Safety monitoring method and device based on edge calculation and terminal equipment | |
| CN113271221B (en) | Network capacity opening method and system and electronic equipment | |
| CN116566696B (en) | Security assessment system and method based on cloud computing | |
| CN110012507B (en) | Internet of vehicles resource allocation method and system with priority of user experience | |
| CN112104730A (en) | Scheduling method and device of storage tasks and electronic equipment | |
| Håkansson et al. | Cost-aware dual prediction scheme for reducing transmissions at IoT sensor nodes | |
| CN114615705B (en) | Single-user resource allocation strategy method based on 5G network | |
| CN111683133B (en) | Service flow limiting method based on micro-service architecture and related device | |
| US9032119B2 (en) | Adaptive polling of information from a device | |
| CN116109058A (en) | Substation inspection management method and device based on deep reinforcement learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210319 |
|
| RJ01 | Rejection of invention patent application after publication |