Data service flow prediction method, device, electronic device and storage medium

Abstract

Embodiments of the present invention provide a data service flow prediction method, apparatus, electronic device, and storage medium, including: establishing a mobile internet data service model based on preset data service assumptions; solving the mobile internet data service model to obtain a flow-time relationship equation; and, based on the flow-time relationship equation, obtaining a prediction result for any cell that will experience network congestion at any point in time. By establishing a mobile internet data service model applicable to mobile cellular networks and predicting the flow of data services, the embodiments of the present invention can more accurately determine the cells and time points where network congestion will occur in the future, effectively guiding network expansion and optimization efforts.

Description

Technical Field

[0001] The present invention relates to the field of mobile Internet technology, and in particular to a data service flow prediction method, device, electronic device and storage medium. Background Art

[0002] Data model prediction is a difficult task in the mobile Internet field, and there has been no good solution. This has led to a lack of systematic methods for network planning, network expansion optimization, and expansion guidance.

[0003] The current business model for predicting network data is commonly used to model the circuit domain business data based on the Markov random process. The characteristics of the Markov model are exclusive channels, each channel is independent and does not affect each other. It is assumed that the arrival of calls follows a Poisson process, the duration of each call follows a negative exponential distribution of parameters, and the system has a trunk number "S". If there is no idle trunk, the new call will be rejected, such as Figure 1 The queuing model in this scenario is as follows Figure 2 As shown, during the birth and death process, the service rate and arrival rate are as follows:

[0004]

[0005]

[0006] The stable distribution of the birth and death process is:

[0007]

[0008]

[0009] Normalized by probability:

[0010]

[0011] Compared to the traditional circuit-domain model, the data service model of a mobile cellular network is completely different. Circuit-domain models are typically analyzed using discrete-state Markov models. Actual mobile network data models must consider the fact that data services share physical channels and migrate between cells, leading to varying cell loads. Summary of the Invention

[0012] The embodiments of the present invention provide a data service flow prediction method, device, electronic device and storage medium to address the defect in the prior art that there is no systematic model for predicting data services for mobile cellular networks.

[0013] In a first aspect, an embodiment of the present invention provides a data service flow prediction method, comprising:

[0014] Establish a mobile Internet data service model based on preset data service assumptions;

[0015] Solving the mobile Internet data service model to obtain a relationship between traffic and time;

[0016] According to the relationship between traffic and time, a prediction result of any cell that may experience network congestion at any time point is obtained.

[0017] Furthermore, the establishment of a mobile Internet data service model based on the preset data service assumptions specifically includes:

[0018] Assuming that within a preset time range, the overall data traffic volume to be transmitted of the cellular network to be predicted remains unchanged, and the traffic volume to be transmitted of each cell in the cellular network to be predicted is differentiable;

[0019] The Euler gas flow equation is obtained, the spatial dimension of the Euler gas flow equation is expanded, and a matrix partial differential equation system is established.

[0020] Furthermore, the matrix partial differential equation system includes dynamic equations, boundary conditions and initial conditions; wherein:

[0021] The dynamic equation represents the performance characteristics and service characteristics of the cellular network to be predicted;

[0022] The boundary condition indicates that the total amount of service demand in the cell cluster remains unchanged;

[0023] The initial condition represents the traffic volume in the cell cluster at the initial moment.

[0024] Furthermore, the dynamic equation includes a flow matrix, a velocity matrix and a probability transfer matrix; wherein:

[0025] The traffic matrix represents the traffic in the cell cluster, including the traffic volume maintained by any current cell, the traffic volume migrated from any current cell to any other cell, and the number of cells in the cell cluster;

[0026] The speed matrix represents the rate in the cell cluster, including the rate of any current cell and the transfer rate from any current cell to any other cell;

[0027] The probability transfer matrix represents a rate transfer matrix, including the rate migration probability from any current cell to any other cell.

[0028] Furthermore, solving the mobile Internet data service model to obtain a flow rate and time relationship equation specifically includes:

[0029] Substituting the velocity matrix and the probability transfer matrix into the flow matrix to obtain a flow equation;

[0030] The flow equation is solved to obtain the flow and time relationship equation.

[0031] Furthermore, substituting the velocity matrix and the probability transfer matrix into the flow matrix to obtain the flow equation specifically includes:

[0032] The flow equation is obtained by substituting the inter-cell peak rate, the threshold matrix, the threshold flow and the flow of any cell into the flow matrix.

[0033] Furthermore, the flow equation is solved to obtain the flow and time relationship, which specifically includes:

[0034] The flow equation is solved as a first-order nonlinear differential equation and decomposed into a Taylor series to obtain the flow-time relationship equation.

[0035] In a second aspect, an embodiment of the present invention further provides a data service flow prediction device, comprising:

[0036] Establishing a module for establishing a mobile Internet data service model based on preset data service assumptions;

[0037] A solution module, configured to solve the mobile Internet data service model and obtain a flow-time relationship equation;

[0038] The prediction module is used to obtain a prediction result of any cell that will experience network congestion at any time point based on the relationship between traffic and time.

[0039] In a third aspect, an embodiment of the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-described data service flow prediction methods are implemented.

[0040] In a fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-described data service flow prediction methods.

[0041] The data service flow prediction method, device, electronic device and storage medium provided in the embodiments of the present invention predict the flow of data services by establishing a mobile Internet data service model suitable for mobile cellular networks. This can more accurately determine the cells and time points where network congestion will occur in the future, and effectively guide network expansion and optimization work. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 It is a circuit domain service data model based on Markov random process provided by existing technology;

[0044] Figure 2 This is a schematic diagram of a queuing model in a circuit domain scenario provided by the prior art;

[0045] Figure 3 This is a schematic diagram of data traffic flow between cells provided by an embodiment of the present invention;

[0046] Figure 4 Schematic diagram of traffic migration in a cellular network provided by an embodiment of the present invention;

[0047] Figure 5 1 is a schematic diagram of rate migration in a cellular network provided by an embodiment of the present invention;

[0048] Figure 6 1 is a flow chart of a data service flow prediction method provided by an embodiment of the present invention;

[0049] Figure 7 This is a schematic diagram of the Euler gas flow equation provided by an embodiment of the present invention;

[0050] Figure 8 This is a schematic diagram of service migration in a certain cell provided by an embodiment of the present invention;

[0051] Figure 9 This is a schematic diagram of cellular network data migration provided by an embodiment of the present invention;

[0052] Figure 10 Schematic diagram of the relationship between the flow and rate of cell j provided in an embodiment of the present invention;

[0053] Figure 11 It is a structural diagram of a data service flow prediction device provided by an embodiment of the present invention;

[0054] Figure 12 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0056] To address the problem that there is no established data service model for mobile cellular networks in the prior art, the present invention proposes a new data service flow prediction model to predict data service flow in mobile cellular networks. This model assumes that the traffic of all cells in a cluster remains constant over a certain period of time and can migrate from one cell to another. Based on the above assumptions, a mathematical model of matrix differential equations is established. The schematic diagram of data service flow between cells is shown in the figure below. Figure 3 The figure shows the dynamic service characteristics of mobile cellular networks. Users are constantly migrating in adjacent areas. Figure 4 and Figure 5 The traffic migration diagram and rate migration diagram of a cellular network are shown, respectively. The currently transmitted service Q migrates with the user and is continuously transmitted in adjacent areas. The unit is bits. When the amount of traffic to be transmitted exceeds a threshold, the cell is congested. The cell rate V migrates with the user and is continuously transmitted in adjacent areas. The unit is bits per second. V represents the available or achievable rate when data is being transmitted, not the average rate of traffic over a period of time. When the rate falls below the threshold, the cell is congested.

[0057] The core idea of the embodiment of the present invention is to build a connection between Q and V. Figure 6 FIG. 1 is a flow chart of a data service flow prediction method provided by an embodiment of the present invention. Figure 6 Shown, including:

[0058] 101. Establish a mobile Internet data service model based on preset data service assumptions;

[0059] 102. Solve the mobile Internet data service model to obtain a relationship between traffic and time;

[0060] 103. Obtain a prediction result of any cell that may experience network congestion at any time point based on the relationship between traffic and time.

[0061] Specifically, we first assume certain preset conditions based on the characteristics of the mobile cellular network and establish a mobile Internet data service model. Then, we solve the model based on parameters such as the traffic and speed of the cells in the mobile cellular network to obtain the relationship between traffic and time. Using this relationship between traffic and time, we can predict the changes in traffic in the cellular network over time, and thus predict which cells will experience congestion at certain time points in the future.

[0062] The embodiments of the present invention establish a mobile Internet data service model applicable to mobile cellular networks to predict the flow of data services, which can more accurately determine the cells and time points where network congestion will occur in the future, and effectively guide network expansion and optimization work.

[0063] Based on the above embodiment, step 101 in the method specifically includes:

[0064] Assuming that within a preset time range, the overall data traffic volume to be transmitted of the cellular network to be predicted remains unchanged, and the traffic volume to be transmitted of each cell in the cellular network to be predicted is differentiable;

[0065] The Euler gas flow equation is obtained, the spatial dimension of the Euler gas flow equation is expanded, and a matrix partial differential equation system is established.

[0066] The matrix partial differential equation system includes dynamic equations, boundary conditions and initial conditions; wherein:

[0067] The dynamic equation represents the performance characteristics and service characteristics of the cellular network to be predicted;

[0068] The boundary condition indicates that the total amount of service demand in the cell cluster remains unchanged;

[0069] The initial condition represents the traffic volume in the cell cluster at the initial moment.

[0070] The dynamic equation includes a flow matrix, a velocity matrix, and a probability transfer matrix; wherein:

[0071] The traffic matrix represents the traffic in the cell cluster, including the traffic volume maintained by any current cell, the traffic volume migrated from any current cell to any other cell, and the number of cells in the cell cluster;

[0072] The speed matrix represents the rate in the cell cluster, including the rate of any current cell and the transfer rate from any current cell to any other cell;

[0073] The probability transfer matrix represents a rate transfer matrix, including the rate migration probability from any current cell to any other cell.

[0074] Specifically, the embodiment of the present invention is based on the Euler gas flow equation and expands its dimension, such as Figure 7 shown.

[0075] ρ(x, t) represents the gas density at position x and time t. v(x, t) represents the gas velocity at position x and time t. The net mass change between the two segments during Δt is approximately given by the following formula:

[0076]

[0077] Dividing by ΔxΔt and then using ΔxΔt to reach the limit of zero gives ρ t +(ρv) x =0.

[0078] Based on the one-dimensional gas equation, we expand the dimension and establish the equation relationship between time t and space x. The method for establishing the mobile Internet data service model is as follows:

[0079] First, based on two assumptions:

[0080] 1) From time t0=0 to T0, the total amount of data traffic to be transmitted remains unchanged;

[0081] 2) The traffic volume to be transmitted in each cell is differentiable.

[0082] Among them, the business migration of a certain cell is as follows: Figure 8 As shown, data migration in cellular networks is as follows Figure 9 shown.

[0083] Although traffic will migrate between different cells, the traffic within a cluster remains constant over a certain period of time. This can be described using a matrix by expanding the spatial dimension. The details are as follows:

[0084] DE:Q t +(V) c =0;t o <t<To

[0085]

[0086]

[0087] The above is a matrix partial differential equation system, DE is the dynamic equation, BC is the boundary condition, and IC is the initial condition. DE represents the performance characteristics and service characteristics of the communication system, BC indicates that the total service demand in the cell cluster remains unchanged, and IC represents the traffic flow in the cell cluster at the initial moment. Compared with the gas equation, (V) c and ((ρv) x There is a formal difference between them, but if information is regarded as quality, this difference will be eliminated and the two will be consistent.

[0088] Based on any of the above embodiments, step 102 in the method specifically includes:

[0089] Substituting the velocity matrix and the probability transfer matrix into the flow matrix to obtain a flow equation;

[0090] The flow equation is solved to obtain the flow and time relationship equation.

[0091] Substituting the velocity matrix and the probability transfer matrix into the flow matrix to obtain the flow equation specifically includes:

[0092] The flow equation is obtained by substituting the inter-cell peak rate, the threshold matrix, the threshold flow and the flow of any cell into the flow matrix.

[0093] The flow equation is solved to obtain the flow-time relationship, which specifically includes:

[0094] The flow equation is solved as a first-order nonlinear differential equation and decomposed into a Taylor series to obtain the flow-time relationship equation.

[0095] Specifically, the traffic matrix Q(t) is first defined as:

[0096]

[0097] Q(t) represents the traffic within the cluster. ii (t)) represents the traffic volume maintained in cell i, q ij (t) represents the traffic volume migrating from cell i to cell j; x represents the number of cells in the cluster.

[0098] The second step is to define the rate matrix V:

[0099]

[0100] V represents the rate in the cell cluster, v ii represents the rate that cell i can achieve, v ij It represents the transfer rate that can be achieved from cell i to cell j. V needs to take into account the interaction between neighboring cells. High traffic will reduce the network SNR, which will lead to low rate. More advanced communication systems will have better performance. Figure 10 It shows the relationship between the traffic and rate of cell j.

[0101] It is understandable that when q jj ≤q jj1 hour, When q jj >q jj1 ,v jj =v jj1 .vjj1 is the minimum guaranteed rate of cell j, v jj_max is the maximum rate of cell j. According to the actual situation, in different scenarios, v jj_max ,q jj1 and v jj1 is different. Expanded to matrix form, such as:

[0102] V=V max +((V1-V max ). / Q1) T Q

[0103] Among them, “. / ” represents dot division, and matrix Q1 is the threshold traffic. When the cell traffic of Q is greater than Q1, the cell is congested. The threshold matrix V1 is the minimum rate matrix guaranteed between cells when congestion occurs. Matrix V max is the peak rate that can be achieved between cells, V1, V max and Q1 represent the performance mechanism of communication, which has a mapping relationship with the actual parameters in the network, which establishes the association between rate V and traffic Q.

[0104] Then define the probability transfer matrix P:

[0105] (*) c The meaning is P T ×(*), where:

[0106] is the rate transfer matrix, p ij is the rate migration probability from cell i to cell j, and It is implied here that the traffic of cell j is the inflow of cell j minus the outflow of cell j, so P is a symmetric matrix.

[0107] Then V and (*) c =P T Substituting ×(*) into DE part, it can be simplified to:

[0108] DE:Q t =-P T V max -HQ

[0109] Where H = P T (V1-V max ). / Q1) T The final form of the equation is:

[0110] DE:Q t =-P T V max -HQ,t o <t<To

[0111]

[0112]

[0113] Using a first-order nonlinear differential equation, we can obtain the following results:

[0114]

[0115]

[0116]

[0117]

[0118] pass The Taylor series of can be used to obtain the following flow rate and time relationship:

[0119]

[0120] Where H = P T (V1-V max ). / Q1) T .

[0121] After obtaining the final flow and time relationship Q(t), the flow changes in the cellular network can be predicted. For example, the rate of cell j reaches the guaranteed rate v at a certain time t in the future. jj (t) = v jj1 (t), congestion occurs.

[0122] The embodiment of the present invention uses a data service model to predict the flow change of a cell and determine the congestion standard, that is, some cells are judged to be congested when the flow threshold is reached at a certain moment in the future.

[0123] The data service flow prediction device provided by an embodiment of the present invention is described below. The data service flow prediction device described below and the data service flow prediction method described above can be referenced to each other.

[0124] Figure 11 FIG. 1 is a schematic diagram of the structure of a data service flow prediction device provided by an embodiment of the present invention. Figure 11 As shown, it includes: an establishment module 1101, a solution module 1102 and a prediction module 1103; wherein:

[0125] The establishment module 1101 is used to establish a mobile Internet data service model based on preset data service assumptions; the solution module 1102 is used to solve the mobile Internet data service model to obtain a flow and time relationship equation; the prediction module 1103 is used to obtain a prediction result of any cell that will experience network congestion at any time point based on the flow and time relationship equation.

[0126] The embodiments of the present invention establish a mobile Internet data service model applicable to mobile cellular networks to predict the flow of data services, which can more accurately determine the cells and time points where network congestion will occur in the future, and effectively guide network expansion and optimization work.

[0127] Figure 12 An example of a physical structure diagram of an electronic device is shown below. Figure 12 As shown, the electronic device may include: a processor 1210, a communication interface 1220, a memory 1230, and a communication bus 1240, wherein the processor 1210, the communication interface 1220, and the memory 1230 communicate with each other via the communication bus 1240. The processor 1210 may invoke logic instructions in the memory 1230 to execute a data service flow prediction method, which includes: establishing a mobile Internet data service model based on preset data service assumptions; solving the mobile Internet data service model to obtain a flow-time relationship equation; and obtaining a prediction result for any cell that will experience network congestion at any point in time based on the flow-time relationship equation.

[0128] In addition, the logic instructions in the above-mentioned memory 1230 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0129] On the other hand, an embodiment of the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the data service flow prediction method provided by the above-mentioned method embodiments, the method including: establishing a mobile Internet data service model based on preset data service assumptions; solving the mobile Internet data service model to obtain a flow and time relationship equation; and obtaining a prediction result of any cell that will experience network congestion at any time point based on the flow and time relationship equation.

[0130] On the other hand, an embodiment of the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the data service flow prediction method provided by the above-mentioned embodiments. The method includes: establishing a mobile Internet data service model based on preset data service assumptions; solving the mobile Internet data service model to obtain a flow and time relationship equation; and obtaining a prediction result of any cell that will experience network congestion at any time point based on the flow and time relationship equation.

[0131] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0132] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A data traffic flow prediction method, characterized in that: include: Establish a mobile Internet data service model based on preset data service assumptions; Solving the mobile Internet data service model to obtain a relationship between traffic and time; According to the relationship between traffic and time, a prediction result of any cell that will experience network congestion at any time point is obtained; The establishment of a mobile Internet data service model based on preset data service assumptions specifically includes: Assuming that within a preset time range, the overall data traffic volume to be transmitted of the cellular network to be predicted remains unchanged, and the traffic volume to be transmitted of each cell in the cellular network to be predicted is differentiable; Obtaining the Euler gas flow equation, performing spatial dimension expansion on the Euler gas flow equation, and establishing a matrix partial differential equation system; The matrix partial differential equation system includes dynamic equations, boundary conditions and initial conditions; wherein: The dynamic equation represents the performance characteristics and service characteristics of the cellular network to be predicted; The boundary condition indicates that the total amount of service demand in the cell cluster remains unchanged; The initial condition represents the traffic volume in the cell cluster at the initial moment; The dynamic equation includes a flow matrix, a velocity matrix and a probability transfer matrix; wherein: The traffic matrix represents the traffic in the cell cluster, including the traffic volume maintained by any current cell, the traffic volume migrated from any current cell to any other cell, and the number of cells in the cell cluster; The speed matrix represents the rate in the cell cluster, including the rate of any current cell and the transfer rate from any current cell to any other cell; The probability transfer matrix represents a rate transfer matrix, including the rate migration probability from any current cell to any other cell; The dynamic equation is: ; in, , P is the probability transfer matrix, matrix V1 is the minimum rate matrix guaranteed between cells when congestion occurs, matrix is the peak rate that can be achieved between cells, matrix Q1 is the threshold flow, and Q is the flow matrix; ; is the rate migration probability from cell i to cell j; Solving the mobile Internet data service model to obtain a flow-time relationship equation specifically includes: Substituting the velocity matrix and the probability transfer matrix into the flow matrix to obtain a flow equation; The flow equation is solved to obtain the flow and time relationship equation.

2. The data traffic flow prediction method according to claim 1, characterized in that: Substituting the velocity matrix and the probability transfer matrix into the flow matrix to obtain the flow equation specifically includes: The flow equation is obtained by substituting the inter-cell peak rate, the threshold matrix, the threshold flow and the flow of any cell into the flow matrix.

3. The data traffic flow prediction method according to claim 1, characterized in that: Solving the flow equation to obtain the flow-time relationship specifically includes: The flow equation is solved by first-order nonlinear differential equation and Taylor series decomposition to obtain the flow and time relationship equation.

4. A data traffic flow prediction device, characterized in that: include: Establishing a module for establishing a mobile Internet data service model based on preset data service assumptions; A solution module, configured to solve the mobile Internet data service model to obtain a flow rate and time relationship equation; A prediction module, configured to obtain a prediction result of any cell that will experience network congestion at any point in time based on the relationship between traffic and time; The establishment of a mobile Internet data service model based on preset data service assumptions specifically includes: Assuming that within a preset time range, the overall data traffic volume to be transmitted of the cellular network to be predicted remains unchanged, and the traffic volume to be transmitted of each cell in the cellular network to be predicted is differentiable; Obtaining the Euler gas flow equation, performing spatial dimension expansion on the Euler gas flow equation, and establishing a matrix partial differential equation system; The matrix partial differential equation system includes dynamic equations, boundary conditions and initial conditions; wherein: The dynamic equation represents the performance characteristics and service characteristics of the cellular network to be predicted; The boundary condition indicates that the total amount of service demand in the cell cluster remains unchanged; The initial condition represents the traffic volume in the cell cluster at the initial moment; The dynamic equation includes a flow matrix, a velocity matrix and a probability transfer matrix; wherein: The traffic matrix represents the traffic in the cell cluster, including the traffic volume maintained by any current cell, the traffic volume migrated from any current cell to any other cell, and the number of cells in the cell cluster; The speed matrix represents the rate in the cell cluster, including the rate of any current cell and the transfer rate from any current cell to any other cell; The probability transfer matrix represents a rate transfer matrix, including the rate migration probability from any current cell to any other cell; The dynamic equation is: ; in, , P is the probability transfer matrix, matrix V1 is the minimum rate matrix guaranteed between cells when congestion occurs, matrix is the peak rate that can be achieved between cells, matrix Q1 is the threshold flow, and Q is the flow matrix; ; is the rate migration probability from cell i to cell j; Solving the mobile Internet data service model to obtain a flow-time relationship equation specifically includes: Substituting the velocity matrix and the probability transfer matrix into the flow matrix to obtain a flow equation; The flow equation is solved to obtain the flow and time relationship equation.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the data service flow prediction method according to any one of claims 1 to 3 are implemented.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the data service flow prediction method according to any one of claims 1 to 3 are implemented.

Images