Method for generating business data with time correlation

Abstract

The invention discloses a method for generating business data with time correlation, and relates to the field of communication network simulation. The method comprises the following steps: synthesizing first variable data obeying normal distribution based on sine waves with different frequencies, and synthesizing second variable data which is mutually orthogonal to the first variable data and obeying normal distribution based on cosine waves; based on the first variable data and the second variable data, establishing data obeying the target distribution combination; and selecting target business data from the data obeying the target distribution combination, the first variable data and / or the second variable data according to the business scene, and establishing a business flow model. Compared with the prior art, under the condition that a real flow data set is lacked, the method can generate service data with time correlation for different service types, can more accurately and effectively simulate actual user flow data, is adaptive to multi-service scenes, can be used for tasks of flow analysis, service classification, service prediction and the like, and reduces the research cost.

Description

Technical Field

[0001] The present invention relates to the technical field of communication network simulation, and more specifically, to a method for generating business data with time correlation. Background Art

[0002] With the rapid development of mobile communication technology and the widespread application of technologies such as the Internet of Things (IoT), cloud computing, and virtual reality, the data and traffic of mobile communications have exploded. In order to meet the soaring user demand and reduce operating costs, cell-level traffic prediction plays a vital role in mobile networks. Many mobile applications rely on real-time or near real-time wireless access network traffic analysis. Accurately predicting the future traffic load of multiple base stations can help base stations implement sleep strategies to reduce energy consumption, help optimize network resources to better allocate network resources, improve resource utilization, enable the network to automatically adapt to changes in business traffic, enhance network flexibility and the ability to respond to emergencies, and improve the service experience of mobile users. Therefore, the importance of traffic prediction is becoming increasingly apparent.

[0003] At present, intelligent machine learning methods can achieve good prediction accuracy for traffic prediction. Machine learning models rely on a large number of data sets to complete training and verification. However, the difficulty and cost of collecting traffic data are relatively high. In the mobile network environment, the collection of traffic data not only requires high-precision equipment and complex technical support, but may also involve user privacy and data security issues, which to a certain extent limits the acquisition and use of data. At present, there are relatively few public live network traffic data sets, especially for the business data of the new generation of mobile communication technology - 5G. Such data sets are even more scarce.

[0004] Therefore, most industry research generates simulation data based on the distribution of different services as a simulation of actual data, reducing research costs and improving development efficiency. The existing methods for generating simulated traffic data mainly use Monte Carlo to generate a large number of random numbers based on the variables and parameters of different business models to simulate the corresponding business distribution. For example, simple discrete random distributions are usually generated using the inverse transformation method, that is, solving the inverse function of the cumulative distribution function of the target distribution. For complex distribution functions, the rejection sampling method is usually used to sample random numbers from the reference distribution, and decide whether to accept the sampled value by comparing the probability density function of the target distribution, and finally simulate the corresponding probability density function. Although this method can quickly generate data that conforms to a certain business statistical distribution, these data lack time correlation. In actual applications, mobile network traffic has obvious spatiotemporal dependence, that is, traffic patterns in different time periods and different geographical locations may be significantly different. Therefore, the existing methods of using random numbers to generate simulated business traffic data cannot serve traffic prediction, and it is necessary to simulate the time correlation of existing network traffic data more closely. Summary of the invention

[0005] In order to overcome the defect that the method of generating simulated business traffic data using random numbers described in the above-mentioned prior art cannot serve traffic prediction, the present invention provides a method for generating business data with time correlation.

[0006] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0007] In a first aspect, a method for generating time-related business data includes:

[0008] Synthesize first variable data that obeys normal distribution based on sine waves of different frequencies, and synthesize second variable data that obeys normal distribution and is orthogonal to the first variable data based on cosine waves;

[0009] Based on the first variable data and the second variable data, establishing data that obeys a target distribution combination;

[0010] According to the business scenario, target business data is selected from the data that obeys the target distribution combination, the first variable data and / or the second variable data to establish a business traffic model.

[0011] In a second aspect, a computer-readable storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by a processor to implement the method described in the first aspect.

[0012] In a third aspect, a computer program product comprises a computer program or computer executable instructions, wherein when the computer program or computer executable instructions are executed by a processor, the method described in the first aspect is implemented.

[0013] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0014] The present invention provides a method for generating business data with time correlation, which synthesizes first variable data and second variable data that obey normal distribution based on sine waves of different frequencies, thereby establishing data that obeys target distribution combination, and selects target business data according to business scenarios to establish a business traffic model. Compared with the prior art, the present invention can generate business data with time correlation for different business types in the absence of a real traffic data set, can simulate actual user traffic data more accurately and effectively, adapt to multiple business scenarios, and can be used for tasks such as traffic analysis, business classification, and business prediction, reducing research costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1This is a flow chart of a method for generating time-related business data in Example 1 of the present application.

[0016] Figure 2 This is another flowchart of a method for generating time-related business data in Example 1 of the present application.

[0017] Figure 3 Schematic diagram of normal distribution with time correlation in Example 1 of the present application.

[0018] Figure 4 This is a schematic diagram of a normal distribution without time correlation in Example 1 of the present application.

[0019] Figure 5 This is a schematic diagram of the 8K UHD wireless screen projection service traffic model established in Example 1 of the present application.

[0020] Figure 6 This is a schematic diagram of the packet layer traffic model for the shared bicycle communication service established in Example 1 of the present application. DETAILED DESCRIPTION

[0021] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged in appropriate cases, which is only to describe the distinction mode adopted by the objects of the same attributes in the embodiments of the present application when describing. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment containing a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment. The term "determine" widely covers various actions, and may include acquisition, calculation, calculation, processing, derivation, investigation, search (for example, search in a table, database or other data structure), ascertainment, and similar actions, and may also include reception (for example, receiving information), access (for example, accessing data in a memory) and similar actions, and may also include generation, creation, establishment and similar actions, as well as parsing, selection, selection and similar actions, etc. The relevant definitions of other terms will be given in the following description.

[0022] It should be noted that when an element is considered to be "connected" to another element, it can be directly connected to the other element, or connected to the other element through an intermediate element. In addition, the "connection" in the following embodiments should be understood as "electrical connection", "communication connection", etc. if there is transmission of electrical signals or data between the connected objects.

[0023] The drawings are for illustrative purposes only and should not be construed as limiting the present patent;

[0024] In order to better illustrate the present embodiment, some parts in the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0025] It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0026] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0027] Example 1

[0028] This embodiment provides a method for generating time-related business data. Figure 1 ,include:

[0029] Synthesize first variable data that obeys normal distribution based on sine waves of different frequencies, and synthesize second variable data that obeys normal distribution and is orthogonal to the first variable data based on cosine waves;

[0030] Based on the first variable data and the second variable data, establishing data that obeys a target distribution combination;

[0031] According to the business scenario, target business data is selected from the data that obeys the target distribution combination, the first variable data and / or the second variable data to establish a business traffic model.

[0032] In some preferred embodiments, the synthesis of first variable data obeying normal distribution based on sine waves of different frequencies, and the synthesis of second variable data obeying normal distribution mutually orthogonal to the first variable data based on cosine waves, include:

[0033] Set the maximum frequency f m It is used to characterize the periodic characteristics of the data and is used in (0,f m ) randomly select N-1 frequencies within the frequency range, and the highest frequency f m Together they form N base frequencies; at a certain time granularity, the highest frequency f m It is reflected in the relevance of business data. Low frequency indicates strong relevance of business data, while high frequency indicates weak relevance.

[0034] Randomly select N phases;

[0035] Based on the central limit theorem, using the selected N reference frequencies and N phases, construct N sine waves with random frequencies and random phases and corresponding N cosine waves;

[0036] Set the time granularity ts The data sampling interval used to characterize a specific service is based on the time granularity t s and the preset duration of the service to be simulated, sampling and synthesizing the first variable data of approximately normal distribution on the N sine waves, sampling and synthesizing the second variable data on the N cosine waves; these two normally distributed data already have time correlation.

[0037] It should be noted that the temporal correlation of business data is affected by multiple factors such as user behavior habits, time, space, weather, major events, etc. Usually, this time series data can be divided into three components: trend items, seasonal items, and random items. For seasonal items, they are mainly affected by the rhythmicity of crowd activities, that is, they have a certain periodicity, and random items mainly reflect the short-term activity patterns of users. This embodiment draws on the method of simulating Rayleigh channels using Jakes'Model, reflects seasonal items through the highest frequency of sine waves, uses a combination of sine waves with multiple random frequencies and random phases to characterize random items, and uses the central limit theorem to synthesize a normal distribution through multiple random phases and random frequency sine waves, and then uses parameter transformation, acceptance sampling (rejection sampling) methods, etc. to obtain data that obeys target distributions such as Weibull distribution and mean distribution, thereby simulating business data with certain time correlation.

[0038] In some specific implementations, eight sine waves of different frequencies are used for synthesis to obtain a variable v with an approximate normal distribution. 1 That is, the first variable data; the highest frequency determines the strength of data correlation. The greater the frequency, the weaker the data correlation of the same time length. The normal distribution data obtained is as follows Figure 3 In contrast, the normally distributed random numbers generated using the classical method are as follows Figure 4 As shown, it can be seen that the latter has no temporal correlation and is difficult to use for prediction tasks.

[0039] Use cosine waves with the same frequency combination to synthesize and get the same value as v in step 1 1 Mutually orthogonal variables v 2 That is the second variable data.

[0040] In some preferred embodiments, the target distribution combination includes at least one of exponential distribution, uniform distribution, Weibull distribution, Gumel distribution (largest extreme value distribution, also called Largest Extreme Value distribution), lognormal distribution, Pareto distribution, Gamma distribution and Poisson distribution.

[0041] In some optional embodiments, obtaining data that obeys exponential distribution and / or uniform distribution based on the Box-Muller transformation method includes:

[0042] The first variable data and the second variable data can be regarded as mutually orthogonal standard normal distributions. The first variable data and the second variable data are respectively used as two bases of the complex plane, and the amplitude is squared to obtain data that obeys an exponential distribution, and / or the phase angle is taken to obtain data that obeys a uniform distribution.

[0043] Furthermore, using the data that obeys the exponential distribution and / or uniform distribution, based on the parameter transformation method, data that obeys the Weibull distribution, Gumel distribution, lognormal distribution and / or Pareto distribution are obtained, and based on the rejection sampling method, data that obeys the Gamma distribution and / or Poisson distribution are obtained.

[0044] Furthermore, when the service scenario is an eMBB service traffic scenario, the service traffic model includes one or more of an 8K UHD wireless projection service traffic model, a video stream packet layer traffic model, a video stream session layer traffic model, a Gaming downlink service packet layer traffic model, and a Gaming uplink service packet layer traffic model;

[0045] The step of selecting target business data from the data that obeys the target distribution combination, the first variable data, and / or the second variable data according to the business scenario to establish a business traffic model includes:

[0046] Performing parameter transformation on the first variable data or the second variable data that obeys a normal distribution, and then truncating the maximum value to obtain the 8K UHD wireless projection service traffic model;

[0047] Determine the packet interval based on data that obeys the Gamma distribution and satisfies preset distribution parameters, and establish the video stream packet layer traffic model according to the preset packet size; wherein the data that obeys the Gamma distribution is obtained by performing rejection sampling (also called "rejection-acceptance sampling" or "acceptance-rejection sampling") on data that obeys the uniform distribution and the first variable data or the second variable data that obeys the normal distribution;

[0048] Determine the frame data size based on data that obeys Weibull distribution, and establish the video stream session layer traffic model in combination with a preset frame time interval; wherein the data that obeys Weibull distribution is obtained by performing parameter transformation on data that obeys exponential distribution;

[0049] After scaling the data that obeys the uniform distribution, the data is used as the initial arrival time interval of the Gaming downlink service data packet. The data that obeys the uniform distribution is parameterized to obtain the data that obeys the Gumel distribution and used as the subsequent arrival time interval and data packet size of the data packet, respectively. Combined with the initial arrival time interval of the Gaming downlink service data packet, the Gaming downlink service packet layer traffic model is established;

[0050] and / or,

[0051] The data that obeys the uniform distribution is scaled and transformed to serve as the initial arrival time interval of the Gaming uplink service data packets. The data that obeys the uniform distribution is parameterized to obtain data that obeys the Gumel distribution and used as the subsequent arrival time interval and data packet size of the data packets respectively. Combined with the initial arrival time interval of the Gaming uplink service data packets, the Gaming uplink service packet layer traffic model is established.

[0052] In some specific implementations, for the 8K UHD wireless screen projection service, the service grouping interval is fixed at 1 / 16200s, and the data packet size follows a normal distribution with a mean of 36.76Kbytes and a standard deviation of 1.35Kbytes, and the maximum value is truncated to 368.640Kbytes. The data that follows the standard normal distribution (i.e., the first variable data or the second variable data) is used for parameter transformation, and then the maximum value is truncated to obtain the data of the service. The corresponding 8K UHD wireless screen projection service traffic model is as follows: Figure 5 shown.

[0053] In some specific implementation processes, for the video stream service packet layer (BV6, 15.6Mbps), the data packet size is fixed at 500 bytes, the data packet interval time is Gamma distribution, the distribution coefficient is k = 0.2463, theta = 60.227, and the data obeying the corresponding distribution can be obtained from the standard uniform distribution and the standard normal distribution using the rejection-acceptance sampling method; for the video stream service session layer, the frame time interval is fixed at 400ms, and the frame data size is sampled from the data obeying the Weibull distribution to establish a video stream session layer traffic model.

[0054] Furthermore, when the service scenario is a uRLLC service traffic scenario, the service traffic model includes one or more of a substation automatic detection service packet layer traffic model, a substation maintenance service traffic model, an ambulance and hospital two-way video service packet layer traffic model, an ambulance and hospital medical equipment interconnection communication packet layer traffic model, and an enhanced driving event triggered service packet layer traffic model;

[0055] The step of selecting target business data from the data obeying the target distribution combination, the first variable data and / or the second variable data according to the business scenario to establish a business traffic model includes:

[0056] The uniformly distributed data is scaled as the packet size of the group, and a periodic arrival model is established as the traffic model of the substation automatic detection service packet layer in combination with the preset grouping interval size;

[0057] Based on data that obeys Pareto distribution or uniform distribution and satisfies preset distribution parameters, parameter transformation is performed to establish a substation maintenance service session layer flow model in the on state, and the corresponding session duration is determined based on the data that obeys Pareto distribution; based on data that obeys Poisson distribution, a substation maintenance service packet layer flow model is established, the packet size is constant, and the packet time interval is obtained based on data that obeys exponential distribution; the substation maintenance service session layer flow model and the substation maintenance service packet layer flow model are combined into a substation maintenance service flow model;

[0058] Based on the acceptance-rejection sampling method, sampling and fitting the data that obeys the uniform distribution is performed to obtain the packet layer traffic model of the two-way video service between the ambulance and the hospital, the corresponding packet time interval is determined based on the data that obeys the exponential distribution, and the packet data packet size is determined based on the data that obeys the Gamma distribution;

[0059] Determine the packet time interval based on data that follows an exponential distribution and meets a preset mean, determine the packet data packet size based on a preset fixed value, and establish a packet layer traffic model for interconnected communication between ambulances and hospital medical equipment;

[0060] and / or,

[0061] The packet time interval is determined based on data that obeys exponential distribution and a fixed additional preset bias is added. The packet size is determined based on data that obeys uniform distribution, and an enhanced driving event-triggered service packet layer traffic model is established.

[0062] In some specific implementations, the traffic model of the substation automatic detection service packet layer is a periodic arrival model, the fixed packet interval is 2s, and the packet size of the packet is determined from data that obeys a uniform distribution.

[0063] In some specific implementation processes, for substation maintenance services, the session layer is divided into on / off states. The on state obeys the Pareto distribution with distribution parameters of (1.6, 1.6), and the session duration also obeys the Pareto distribution; the packet layer obeys the Poisson arrival model, the packet size is constant at 85 bytes, and the packet time interval is determined based on data that obeys the exponential distribution.

[0064] In some specific implementations, for the packet layer traffic model of the interconnection communication between an ambulance and hospital medical equipment, the packet time interval is determined based on data obeying an exponential distribution with a mean of 60 seconds, and the packet data size is 85 bytes.

[0065] In some specific implementations, for the enhanced driving event triggered service packet layer traffic model, the packet time interval follows an exponential distribution with a mean of 50 ms, and a fixed additional 50 ms bias, and the packet size is [200:200:2000] bytes evenly distributed.

[0066] Furthermore, when the service scenario is an mMTC service traffic scenario, the service traffic model includes one or more of a smart grid triggered service packet layer traffic model, a wireless retail service packet layer traffic model, and a shared bicycle communication service packet layer traffic model;

[0067] The step of selecting target business data from the data that obeys the target distribution combination, the first variable data, and / or the second variable data according to the business scenario to establish a business traffic model includes:

[0068] Based on data that follows an exponential distribution and satisfies a preset mean, a grouping time interval is determined through a scale transformation; a smart grid triggered service grouping layer traffic model is established based on the preset grouping size and the determined grouping time interval;

[0069] Determine a packet period based on data that obeys a Pareto distribution and satisfies preset distribution parameters, determine a packet size based on data that obeys a uniform distribution, and establish a wireless retail service packet layer traffic model based on the determined packet period and packet size;

[0070] and / or,

[0071] The packet time interval is determined based on the data that obeys the uniform distribution, the packet size is determined based on the data that obeys the Pareto distribution, and a packet layer traffic model for the shared bicycle communication service is established.

[0072] In some specific implementations, for the packet layer traffic model of smart grid triggered services, the packet time interval is an exponential distribution with a mean of 1 / 60s, which can be generated by scaling data that obeys the exponential distribution. The packet size is always 135 bytes, which is a uniform distribution.

[0073] In some specific implementations, for the packet layer traffic model of wireless retail services, the packet period is determined based on data satisfying a Pareto distribution with parameters (shape=10, minium=1), and the packet size is determined based on data obeying a uniform distribution.

[0074] In some specific implementations, a shared bicycle communication service packet layer traffic model is established for the shared bicycle communication service packet layer traffic. Figure 6 As shown, the time intervals of grouping are evenly distributed and the sizes are Pareto distributed.

[0075] Example 2

[0076] This embodiment provides a computer-readable storage medium, on which is stored at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor, so that the processor executes part or all of the steps of the method provided in Example 1 of the present application.

[0077] It is understood that the storage medium may be transient or non-transient. Exemplarily, the storage medium includes, but is not limited to, 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, and other media that can store program codes.

[0078] Exemplarily, the processor may be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA).

[0079] Exemplarily, the read-only memory includes but is not limited to MASK ROM, PROM, EPROM, EEPROM, Flash, etc.

[0080] Exemplarily, the random access memory includes but is not limited to DRAM, SRAM, SDRAM, DDR SDRAM, etc.

[0081] In some examples, a computer program product is provided, which can be implemented in hardware, software or a combination thereof. As a non-limiting example, the computer program product can be embodied as the storage medium, or as a software product, such as an SDK (Software Development Kit).

[0082] As a non-limiting example, a computer program product is provided, the computer program product includes a computer program or a computer executable instruction, the computer program or the computer executable instruction is stored in a computer-readable storage medium. A processor of an electronic device reads the computer program or the computer executable instruction from the computer-readable storage medium, and the processor executes the computer executable instruction, so that the electronic device performs some or all steps of the method described in the embodiment of the present application.

[0083] In some examples, a computer program is provided, comprising a computer-readable code, and when the computer-readable code is run in a computer device, a processor in the computer device executes a part or all of the steps in the method.

[0084] This embodiment also proposes an electronic device, including a memory and a processor, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and when the processor executes the at least one instruction, at least one program, a code set or an instruction set, it implements part or all of the steps of the method described in Example 1.

[0085] In some examples, a hardware entity of the electronic device is provided, including: a processor, a memory and a communication interface; wherein the processor generally controls the overall operation of the electronic device; the communication interface is used to enable the electronic device to communicate with other terminals or servers through a network; the memory is configured to store instructions and applications executable by the processor, and can also cache data to be processed or processed by the processor and various modules in the electronic device (including but not limited to image data, audio data, voice communication data and video communication data), which can be implemented by flash memory (FLASH), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or random access memory (RAM).

[0086] The processor may include one or more processing elements. Thus, the processor may include one or more integrated circuits (ICs) configured to perform the functions of the processor. In addition, each integrated circuit may include a circuit (e.g., a first circuit, a second circuit, and other circuits, etc.) configured to perform the functions of the processor.

[0087] Furthermore, data may be transmitted between the processor, the communication interface and the memory via a bus, which may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together.

[0088] It can be understood that the options in the above-mentioned embodiment 1 are also applicable to this embodiment, so they will not be described again here.

[0089] The same or similar reference numerals correspond to the same or similar components;

[0090] The terms used to describe the positional relationship in the drawings are only used for illustrative purposes and should not be construed as limiting the present application;

[0091] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application may be combined with each other.

[0092] In different specific implementations, the method or system described in the present application can be implemented in software, hardware or a combination thereof. In addition, the order of the steps of the method can be changed, and various elements can be added, reordered, combined, omitted, modified, etc.

[0093] Obviously, the above-mentioned embodiments of the present application are merely examples for clearly illustrating the present application, and are not intended to limit the implementation methods of the present application, and are not intended to limit the present application. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. Each discrete structure / function module or unit can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part, and the structure and function of the discrete components can be implemented as a combined structure or component. It is not necessary and impossible to enumerate all the implementation methods here. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the claims of the present application.

Claims

1. A method for generating time-related business data, characterized in that: include: Synthesize first variable data that obeys normal distribution based on sine waves of different frequencies, and synthesize second variable data that obeys normal distribution and is orthogonal to the first variable data based on cosine waves; Based on the first variable data and the second variable data, establishing data that obeys a target distribution combination; According to the business scenario, target business data is selected from the data that obeys the target distribution combination, the first variable data and / or the second variable data to establish a business traffic model.

2. The method for generating time-correlated business data according to claim 1, characterized in that: The method of synthesizing first variable data that obeys normal distribution based on sine waves of different frequencies, and synthesizing second variable data that obeys normal distribution and is orthogonal to the first variable data based on cosine waves, includes: Set the maximum frequency f m It is used to characterize the periodic characteristics of the data and is used in (0,f m ) randomly select N-1 frequencies within the frequency range, and the highest frequency f m Together they form N reference frequencies; Randomly select N phases; Based on the central limit theorem, using the selected N reference frequencies and N phases, construct N sine waves with random frequencies and random phases and corresponding N cosine waves; Set the time granularity t s The data sampling interval used to characterize a specific service is based on the time granularity t s and the preset service duration to be simulated, sampling and synthesizing the first variable data of approximately normal distribution on the N sine waves, and sampling and synthesizing the second variable data on the N cosine waves.

3. The method for generating time-correlated business data according to claim 1, characterized in that: The target distribution combination includes at least one of exponential distribution, uniform distribution, Weibull distribution, Gumel distribution, lognormal distribution, Pareto distribution, Gamma distribution and Poisson distribution.

4. The method for generating time-correlated business data according to claim 3, characterized in that: Based on the Box-Muller transformation method, data that follows exponential distribution and / or uniform distribution are obtained, including: The first variable data and the second variable data are respectively used as two bases of the complex plane, and the square of the amplitude is taken to obtain data that obeys the exponential distribution, and / or the phase angle is taken to obtain data that obeys the uniform distribution.

5. The method for generating time-correlated business data according to claim 4, characterized in that: Utilizing the data that obey exponential distribution and / or uniform distribution, data that obey Weibull distribution, Gumel distribution, lognormal distribution and / or Pareto distribution are obtained based on parameter transformation method, and data that obey Gamma distribution and / or Poisson distribution are obtained based on rejection sampling method.

6. The method for generating time-correlated business data according to claim 5, characterized in that: When the service scenario is an eMBB service traffic scenario, the service traffic model includes one or more of an 8K UHD wireless projection service traffic model, a video stream packet layer traffic model, a video stream session layer traffic model, a gaming downlink service packet layer traffic model, and a gaming uplink service packet layer traffic model; The step of selecting target business data from the data that obeys the target distribution combination, the first variable data, and / or the second variable data according to the business scenario to establish a business traffic model includes: Performing parameter transformation on the first variable data or the second variable data that obeys a normal distribution, and then truncating the maximum value to obtain the 8K UHD wireless projection service traffic model; Determine the packet interval based on data that obeys the Gamma distribution and satisfies preset distribution parameters, and establish the video stream packet layer traffic model according to the preset packet size; wherein the data that obeys the Gamma distribution is obtained by rejecting the data that obeys the uniform distribution and the first variable data or the second variable data that obeys the normal distribution; Determine the frame data size based on data that obeys Weibull distribution, and establish the video stream session layer traffic model in combination with a preset frame time interval; wherein the data that obeys Weibull distribution is obtained by performing parameter transformation on data that obeys exponential distribution; Performing a scale transformation on the data that obeys the uniform distribution as the initial arrival time interval of the Gaming downlink service data packet, performing a parameter transformation on the data that obeys the uniform distribution to obtain the data that obeys the Gumel distribution and using them as the subsequent arrival time interval of the data packet and the data packet size respectively, and combining the initial arrival time interval of the Gaming downlink service data packet to establish the Gaming downlink service packet layer traffic model; and / or, The data that obeys the uniform distribution is scaled and transformed to serve as the initial arrival time interval of the Gaming uplink service data packets. The data that obeys the uniform distribution is parameterized to obtain data that obeys the Gumel distribution and used as the subsequent arrival time interval and data packet size of the data packets respectively. Combined with the initial arrival time interval of the Gaming uplink service data packets, the Gaming uplink service packet layer traffic model is established.

7. The method for generating time-correlated business data according to claim 5, characterized in that: When the service scenario is a uRLLC service traffic scenario, the service traffic model includes one or more of a substation automatic detection service packet layer traffic model, a substation maintenance service traffic model, an ambulance and hospital two-way video service packet layer traffic model, an ambulance and hospital medical equipment interconnection communication packet layer traffic model, and an enhanced driving event triggered service packet layer traffic model; The step of selecting target business data from the data that obeys the target distribution combination, the first variable data, and / or the second variable data according to the business scenario to establish a business traffic model includes: The uniformly distributed data is scaled as the packet size of the group, and a periodic arrival model is established as the traffic model of the substation automatic detection service packet layer in combination with the preset grouping interval size; Based on data that obeys Pareto distribution or data that obeys uniform distribution and satisfies preset distribution parameters, parameter transformation is performed to establish a substation maintenance service session layer traffic model in the on state, and the corresponding session duration is determined based on the data that obeys Pareto distribution; based on data that obeys Poisson distribution, a substation maintenance service packet layer traffic model is established, the packet size is constant, and the packet time interval is obtained based on data that obeys exponential distribution; the substation maintenance service session layer traffic model and the substation maintenance service packet layer traffic model are combined into a substation maintenance service traffic model; Based on the rejection sampling method, sampling and fitting the data that obeys the uniform distribution is performed to obtain the packet layer traffic model of the two-way video service between the ambulance and the hospital, the corresponding packet time interval is determined based on the data that obeys the exponential distribution, and the packet data packet size is determined based on the data that obeys the Gamma distribution; Determine the packet time interval based on data that follows an exponential distribution and satisfies a preset mean, determine the packet data packet size based on a preset fixed value, and establish a packet layer traffic model for interconnection communication between ambulances and hospital medical equipment; and / or, The packet time interval is determined based on data that obeys exponential distribution and a fixed additional preset bias is added. The packet size is determined based on data that obeys uniform distribution, and an enhanced driving event-triggered service packet layer traffic model is established.

8. The method for generating time-correlated business data according to claim 5, characterized in that: When the service scenario is an mMTC service traffic scenario, the service traffic model includes one or more of a smart grid triggered service packet layer traffic model, a wireless retail service packet layer traffic model, and a shared bicycle communication service packet layer traffic model; The step of selecting target business data from the data that obeys the target distribution combination, the first variable data, and / or the second variable data according to the business scenario to establish a business traffic model includes: Based on data that follows an exponential distribution and satisfies a preset mean, a grouping time interval is determined through a scale transformation; a smart grid triggered service grouping layer traffic model is established based on the preset grouping size and the determined grouping time interval; Determine a packet period based on data that obeys a Pareto distribution and satisfies preset distribution parameters, determine a packet size based on data that obeys a uniform distribution, and establish a wireless retail service packet layer traffic model based on the determined packet period and packet size; and / or, The packet time interval is determined based on the data that obeys the uniform distribution, the packet size is determined based on the data that obeys the Pareto distribution, and a packet layer traffic model for the shared bicycle communication service is established.

9. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by the processor to implement the method as described in any one of claims 1-8.

10. A computer program product comprising a computer program or computer executable instructions, characterized in that: When the computer program or computer executable instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images