Prediction method, prediction device, chip, communication network system and storage medium

Abstract

The invention discloses a prediction method, a prediction device, a chip, a communication network system and a storage medium. The traffic prediction method for the communication network comprises the following steps: acquiring first state information of terminal equipment in the communication network at a first moment, first position information of an emergency and a time-varying parameter of the emergency; determining second position information according to the first position information and the time varying parameter; determining second state information of the terminal equipment at a second moment according to the second position information and the first state information; and determining a second prediction value according to the second state information. According to the traffic prediction method of the communication network provided by the embodiment of the invention, the emergencies influencing the network traffic are set as the emergencies with the propagation speed, so that the designed traffic model is more in line with an actual application scene, the accuracy of the predicted network traffic is improved, and the traffic prediction efficiency is improved. The technical problem that the network traffic predicted by the traffic model in the related technology is inaccurate is solved.

Description

Technical Field

[0001] The present application relates to the field of communication network traffic technology, and more specifically, to a prediction method, a prediction device, a chip, a communication network system and a storage medium. Background Art

[0002] In related technologies, the machine type communication (MTC) traffic model does not focus on the impact of the propagation rate of emergencies on the dynamics of the entire network traffic. It assumes that emergencies are stationary and ignores the importance of propagation speed in building traffic models. This does not conform to actual application scenarios, resulting in inaccurate network traffic prediction based on the MTC traffic model. Summary of the invention

[0003] An embodiment of the present application provides a method for predicting traffic in a communication network, including: obtaining first state information of a terminal device in the communication network at a first moment, first position information of an emergency event, and a time-varying parameter of the emergency event, wherein the first position information is configured to identify the position of the emergency event at the first moment; determining second position information according to the first position information and the time-varying parameter, wherein the second position information is configured to identify the position of the emergency event at a second moment; determining second state information of the terminal device at a second moment according to the second position information and the first state information; and determining a second prediction value according to the second state information to determine a network traffic prediction value of the communication network at the second moment.

[0004] In this way, the traffic prediction method for the communication network provided in the implementation mode of the present application sets the emergency events that affect the network traffic as emergency events with a propagation speed, so that the designed traffic model is more in line with the actual application scenario, improves the accuracy of the predicted network traffic, and solves the technical problem of inaccurate network traffic predicted by the traffic model in the related technology.

[0005] In some embodiments, determining the second status information of the terminal device at the second moment based on the second location information and the first status information includes: obtaining the location information of each of the terminal devices; determining the distance information of each of the terminal devices based on the location information of each of the terminal devices and the second location information, the distance information being configured to identify the distance between the terminal device and the emergency; and determining the second status information of each of the terminal devices based on the distance information of each of the terminal devices and the first status information of each of the terminal devices.

[0006] In this way, the impact of the emergency event on each terminal device can be determined according to the distance between the emergency event and each terminal device, and then the second state information of each terminal device can be determined.

[0007] In some embodiments, the second status information of each terminal device is determined based on the distance information of each terminal device and the first status information of each terminal device, including: when the distance between the terminal device and the emergency event is less than or equal to a specific distance, the first status information of the terminal device is consistent with the second status information.

[0008] In this way, when the distance between the terminal device and the emergency event is less than or equal to a specific distance, there is no need to additionally calculate the impact factor of the emergency event on the terminal device, which reduces the amount of calculation of the traffic model and the complexity of the traffic model operation.

[0009] In some embodiments, determining the second status information of each terminal device based on the distance information of each terminal device and the first status information of each terminal device includes: when the distance between the terminal device and the emergency event is higher than a specific distance, obtaining the first spatial-related parameter of each terminal device, the first spatial-related parameter being the spatial-related parameter of the emergency event to the terminal device at the first moment; determining the second spatial-related parameter of each terminal device based on the first spatial-related parameter of each terminal device, a normal distribution model and the distance information of each terminal device, the second spatial-related parameter being the spatial-related parameter of the emergency event to the terminal device at the second moment; determining the second status information of each terminal device based on the second spatial-related parameter of each terminal device and the first status information of each terminal device.

[0010] In this way, when the distance between the terminal device and the emergency event is higher than a specific distance, the state change of the terminal device can be determined according to the spatial correlation parameters while taking the spatial correlation of the terminal device into consideration.

[0011] In some implementations, the first related parameter of each of the terminal devices is the same.

[0012] In this way, the first related parameters of each of the terminal devices can be set to the same parameters, which reduces the amount of calculation of the traffic model and reduces the complexity of the operation of the traffic model.

[0013] In certain embodiments, the specific distance is determined based on a standard deviation parameter of the normal distribution model.

[0014] In this way, by determining and setting a specific distance according to the standard deviation parameter of the normal distribution model, it is possible to accurately determine whether the terminal device has spatial correlation based on the specific distance.

[0015] In some embodiments, the standard deviation parameter is determined based on the first spatial correlation parameter.

[0016] In this way, by determining to set a specific distance according to the first spatial correlation parameter, it is possible to accurately determine whether the terminal device has spatial correlation based on the specific distance.

[0017] In certain embodiments, after determining the second space-related parameter corresponding to the terminal device, the method includes: obtaining a second time-related parameter, the second time-related parameter being the time-related parameter of the emergency event for the terminal device at the second moment; determining the second status information of each terminal device based on the second time-related parameter, the second space-related parameter of each terminal device and the first status information of each terminal device.

[0018] In this way, taking into account the spatial correlation and time correlation of the terminal device, the state change of the terminal device can be determined according to the spatial correlation parameters and the time correlation.

[0019] In some embodiments, obtaining the second time-related parameter includes: obtaining quantity information and period information, the quantity information is configured to identify the number of the terminal devices in the communication network, and the period information is configured to identify a sampling period of the communication network, and within one sampling period, each of the terminal devices in the communication network is sampled; determining the second time-related parameter based on the quantity information, the period information and the Beta distribution model.

[0020] In this way, the second time-related parameter can be determined based on the Beta distribution model, and then the time correlation of each terminal device at the second moment can be determined.

[0021] In some embodiments, determining the second position information based on the first position information and the time-varying parameters includes: determining the speed and / or acceleration of the sudden event based on the time-varying parameters, and obtaining the sampling interval; determining the displacement of the sudden event based on the sudden event and the sampling interval; determining the second position based on the first position and the displacement of the sudden event.

[0022] In this way, the second position can be calculated and determined according to the time-varying parameter and the first position.

[0023] In some embodiments, the time-varying parameter includes preset speed information and / or acceleration information, the speed information is configured to identify the speed of the emergency event, and the acceleration information is configured to identify the acceleration of the emergency event.

[0024] In this way, time-varying parameters can be pre-set according to the characteristics of the emergency, so that the designed traffic model is more in line with the actual application scenario.

[0025] In some embodiments, the second moment is determined based on the first moment and a sampling interval, and the sampling interval is a preset time interval.

[0026] In this way, the traffic prediction method can update the determined network traffic prediction value based on the preset sampling interval.

[0027] In some embodiments, after determining the second prediction value, the method further includes: updating the second moment to the first moment, and repeatedly executing the step of obtaining the first state information, the first location information and the time-varying parameter to determine the second prediction value based on the second state information, so as to determine multiple second prediction values; and determining the network traffic prediction value of the communication network within a sampling period based on the multiple second prediction values.

[0028] In this way, the traffic prediction method can obtain multiple second prediction values, and then determine the network traffic prediction value within a sampling period.

[0029] In some embodiments, the number of times the steps of obtaining the first state information, the first location information, and the time-varying parameter to determining the second predicted value based on the second state information are performed is determined based on the time interval, the sampling period, and the number of the terminal devices.

[0030] In this way, a theoretical analysis is conducted on the computational complexity, and the use of piecewise function calculation based on the cutoff distance to reduce the complexity has obvious advantages for communication networks with a larger total number of terminal devices.

[0031] In some implementations, the emergency event is an event that affects the communication device to switch from a normal state to an alarm state.

[0032] In this way, the communication device to be alerted can be determined based on the impact of the emergency, thereby predicting the traffic of the communication network.

[0033] In some embodiments, the first state information is configured to determine a first state matrix of the terminal device at the first moment, and whether the terminal device is in a normal state or an alarm state at the first moment is determined based on the first state matrix; the second state information is configured to determine a second state matrix of the terminal device at the second moment, and whether the terminal device is in a normal state or an alarm state at the second moment is determined based on the second state matrix.

[0034] In this way, based on the first state matrix and the second state matrix, it can be determined whether the terminal device is in a normal state or an alarm state.

[0035] In some embodiments, determining the second state information of the terminal device at the second moment based on the second position information and the first state information includes: determining a conversion matrix based on the second position information; and determining the second state matrix based on the conversion matrix and the first state matrix to determine the second state information.

[0036] In this way, the second state matrix can be determined based on the first state matrix and the transition matrix.

[0037] In some embodiments, determining the conversion matrix based on the second position information includes: determining an impact factor based on the second position information, the impact factor being an impact factor of the emergency event on the terminal device at the second moment; obtaining a first standard matrix and a second standard matrix, the first standard matrix being a completely correlated state transfer matrix, and the second standard matrix being a completely uncorrelated state transfer matrix; determining the conversion matrix based on the first standard matrix, the second standard matrix, and the impact factor.

[0038] In this way, the conversion matrix can be determined according to the first standard matrix, the second standard matrix and the influencing factor, and then the working state corresponding to each terminal device can be determined.

[0039] In some embodiments, determining the impact factor based on the second location information includes: obtaining the location information of the terminal device; determining the distance information of the terminal device based on the location information of the terminal device and the second location information, the distance information being configured to identify the distance between the terminal device and the emergency event; when the distance between the terminal device and the emergency event is less than or equal to a specific distance, the impact factor is zero, so that the conversion matrix is ​​the second standard matrix.

[0040] In this way, when the distance between the terminal device and the emergency event is less than or equal to a specific distance, there is no need to additionally calculate the conversion matrix, which reduces the amount of calculation of the traffic model and the complexity of the operation of the traffic model.

[0041] In certain embodiments, determining the impact factor based on the second location information includes: when the distance between the terminal device and the emergency event is higher than the specific distance, obtaining a first spatial-related parameter of the terminal device, the first spatial-related parameter being the spatial-related parameter of the emergency event on the terminal device at the first moment; determining a second spatial-related parameter of the terminal device based on the first spatial-related parameter of the terminal device, a normal distribution model and the distance information of the terminal device, the second spatial-related parameter being the spatial-related parameter of the emergency event on the terminal device at the second moment; and determining the impact factor based on the second spatial-related parameter.

[0042] In this way, when the distance between the terminal device and the emergency event is higher than a specific distance, the corresponding conversion matrix can be determined according to the spatial correlation calculation of the terminal device.

[0043] In some embodiments, determining the impact factor based on the second location information includes: when the distance between the terminal device and the emergency event is higher than the specific distance, obtaining a first spatial-related parameter of the terminal device, the first spatial-related parameter being the spatial-related parameter of the emergency event on the terminal device at the first moment; determining a second spatial-related parameter of the terminal device based on the first spatial-related parameter of the terminal device, a normal distribution model and the distance information of the terminal device, the second spatial-related parameter being the spatial-related parameter of the emergency event on the terminal device at the second moment; obtaining a second time-related parameter, the second time-related parameter being the time-related parameter of the emergency event on the terminal device at the second moment; and determining the impact factor based on the second spatial-related parameter and the second time-related parameter.

[0044] In this way, when the distance between the terminal device and the emergency event is higher than a specific distance, the corresponding conversion matrix can be calculated and determined according to the spatial correlation and temporal correlation of the terminal device.

[0045] In some embodiments, the second state information is configured to identify the normal or alarm state of the terminal device in the second state, and determining the second prediction value based on the second state information includes: the second prediction value is determined based on the number of the terminal devices that are in the normal state at the second moment, and the number of the terminal devices that are in the alarm state at the second moment.

[0046] In this way, the corresponding traffic prediction value can be determined according to the working status of multiple terminal devices.

[0047] An embodiment of the present application provides a traffic prediction device for a communication network, the device comprising an acquisition module and a determination module. The acquisition module is configured to acquire first state information of a terminal device in the communication network at a first moment, first location information of an emergency event, and a time-varying parameter of the emergency event, the first location information being configured to identify the location of the emergency event at the first moment. The determination module is configured to determine second location information based on the first location information and the time-varying parameter, the second location information being configured to identify the location of the emergency event at a second moment, the determination module is configured to determine second state information of the terminal device at the second moment based on the second location information and the first state information, and the determination module is configured to determine a second prediction value based on the second state information to determine the network traffic prediction value of the communication network at the second moment.

[0048] In some embodiments, the acquisition module is configured to acquire location information of each of the terminal devices. The determination module is configured to determine distance information of each of the terminal devices according to the location information of each of the terminal devices and the second location information. The distance information is configured to identify the distance between the terminal device and the emergency event, and the determination module is further configured to determine the second status information of each of the terminal devices according to the distance information of each of the terminal devices and the first status information of each of the terminal devices.

[0049] In some implementations, when the distance between the terminal device and the emergency event is less than or equal to a specific distance, the determination module determines that the first state information of the terminal device is consistent with the second state information.

[0050] In some embodiments, the acquisition module is configured to acquire a first spatial correlation parameter of each terminal device when the distance between the terminal device and the emergency event is higher than a specific distance, the first spatial correlation parameter being the spatial correlation parameter of the emergency event to the terminal device at the first moment. The determination module is configured to determine a second spatial correlation parameter of each terminal device based on the first spatial correlation parameter of each terminal device, a normal distribution model, and the distance information of each terminal device, the second spatial correlation parameter being the spatial correlation parameter of the emergency event to the terminal device at the second moment. The determination module is also configured to determine the second state information of each terminal device based on the second spatial correlation parameter of each terminal device and the first state information of each terminal device.

[0051] In some embodiments, the acquisition module is further configured to acquire a second time-related parameter, where the second time-related parameter is a time-related parameter of the emergency event on the terminal device at the second moment. The determination module is further configured to determine the second state information of each of the terminal devices according to the second time-related parameter, the second space-related parameter of each of the terminal devices, and the first state information of each of the terminal devices.

[0052] An embodiment of the present application provides a chip, which includes a memory and a processor. The memory is configured to store a computer program, and the processor implements the traffic prediction method of the above embodiment when executing the computer program.

[0053] An embodiment of the present application provides a communication network system, which includes: a base station, a plurality of terminal devices located within the coverage area of ​​the base station, and the prediction device or chip of the above embodiment.

[0054] In some embodiments, the terminal device is a machine type communication device.

[0055] In this way, the traffic model constructed based on emergencies can better predict the working status of MTC devices and further predict the traffic of the communication network.

[0056] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by one or more processors, the traffic prediction method of the above embodiment is implemented.

[0057] The embodiments of the present application provide a prediction method, a prediction device, a chip, a communication network system and a storage medium. Among them, the traffic prediction method of the communication network includes: obtaining the first state information of the terminal device in the communication network at the first moment, the first position information of the emergency event and the time-varying parameters of the emergency event, the first position information is configured to identify the position of the emergency event at the first moment; determining the second position information according to the first position information and the time-varying parameters, the second position information is configured to identify the position of the emergency event at the second moment; determining the second state information of the terminal device at the second moment according to the second position information and the first state information; determining the second prediction value according to the second state information to determine the network traffic prediction value of the communication network at the second moment. The traffic prediction method of the communication network provided in the embodiments of the present application sets the emergency event that affects the network traffic as an emergency event with a propagation speed, so that the designed traffic model is more in line with the actual application scenario, improves the accuracy of the predicted network traffic, and solves the technical problem of inaccurate network traffic predicted by the traffic model in the related technology.

[0058] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0060] Figure 1 It is a flow chart of a flow prediction method according to an embodiment of the present application;

[0061] Figure 2 is a schematic diagram of a flow prediction device according to an embodiment of the present application;

[0062] Figure 3 is a schematic diagram of a communication network system according to an embodiment of the present application;

[0063] Figure 4 is a schematic diagram of a Markov modulated Poisson process of a traffic model according to an embodiment of the present application;

[0064] Figure 5 It is a flow chart of a flow prediction method according to an embodiment of the present application;

[0065] Figure 6 It is a schematic diagram of spatial flow predicted by flow models in the relevant technical field;

[0066] Figure 7 It is a schematic diagram of spatial traffic predicted by the traffic model according to the implementation mode of the present application. DETAILED DESCRIPTION

[0067] The embodiments of the present application are described in detail below, and the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0068] In related technologies, the machine type communication (MTC) traffic model does not focus on the impact of the propagation rate of emergencies on the dynamics of the entire network traffic. It assumes that emergencies are stationary and ignores the importance of propagation speed in building traffic models. This does not conform to actual application scenarios, resulting in inaccurate network traffic prediction based on the MTC traffic model.

[0069] Reference Figure 1 The present application embodiment provides a method for predicting traffic in a communication network, including:

[0070] 01: Acquire first state information of a terminal device in a communication network at a first moment, first location information of an emergency event, and a time-varying parameter of the emergency event, wherein the first location information is configured to identify a location of the emergency event at the first moment;

[0071] 02: Determine second location information according to the first location information and the time-varying parameter, where the second location information is configured to identify the location of the emergency at a second moment;

[0072] 03: Determine the second state information of the terminal device at the second moment according to the second location information and the first state information;

[0073] 04: Determine a second prediction value according to the second state information to determine a network traffic prediction value of the communication network at the second moment.

[0074] Reference Figure 2 , the embodiment of the present application also provides a traffic prediction device 10 for a communication network. The traffic prediction method of the embodiment of the present application can be implemented by the traffic prediction device 10 of the embodiment of the present application. Specifically, the traffic prediction device 10 includes an acquisition module 11 and a determination module 12. Among them, the acquisition module 11 can obtain the first state information of the terminal device in the communication network at the first moment, the first position information of the emergency event and the time-varying parameters of the emergency event, and the first position information is configured to identify the position of the emergency event at the first moment. The determination module 12 is configured to determine the second position information according to the first position information and the time-varying parameters. The second position information is configured to identify the position of the emergency event at the second moment. The determination module 12 is configured to determine the second state information of the terminal device at the second moment according to the second position information and the first state information. The determination module 12 is configured to determine the second prediction value according to the second state information to determine the network traffic prediction value of the communication network at the second moment.

[0075] The flow prediction device 10 can be widely used in the technical fields of equipment status monitoring in smart grids, remote video monitoring, retail logistics distribution systems, etc. It can be implemented in products such as smart meters, equipment monitoring sensors, urban public monitoring equipment, RFID equipment, etc.

[0076] The embodiment of the present application also provides a chip, and the traffic prediction method of the embodiment of the present application can be implemented by the chip of the embodiment of the present application. Specifically, the chip includes a memory and a processor, the memory is configured to store a computer program, and when the processor executes the computer program, it realizes obtaining the first state information of the terminal device in the communication network at the first moment, the first position information of the emergency event, and the time-varying parameters of the emergency event, determining the second position information according to the first position information and the time-varying parameters, determining the second state information of the terminal device at the second moment according to the second position information and the first state information, and determining the second prediction value according to the second state information, so as to determine the network traffic prediction value of the communication network at the second moment.

[0077] Reference Figure 3 The embodiment of the present application also provides a communication network system 100. Specifically, the communication network system 100 includes a traffic prediction device 10 or chip of the embodiment of the present application, a base station 30, and multiple terminal devices 20 located within the coverage of the base station 30. The traffic prediction device 10 or chip of the embodiment of the present application can predict the network traffic of multiple terminal devices 20 located within the coverage of the base station 30.

[0078] Specifically, with the rapid development of 5G technology, data traffic has exploded, massive devices have been connected, and new businesses have emerged. Human-to-human (H2H)-based communications have been expanded to machine-to-machine (M2M) communications. The terminal device 20 can be set as a human type communication (HTC) device or a machine type communication (MTC) device.

[0079] In step 01 and step 02, the location of the emergency event can be set to X(t), and the state information of the terminal device 20 can be set to S(t). The first time can be set to t1, and the second time can be set to t2. The first state information of the terminal device 20 can be set to S(t1), and the second state information of the terminal device 20 can be set to S(t2). The first location can be set to X(t1), and the second location can be set to X(t2).

[0080] The sudden event has a corresponding propagation speed, and the time-varying parameter of the sudden event can be set as the propagation speed of the sudden event. The position of the sudden event can be changed in real time, that is, the first position X(t1) and the second position X(t2) can be inconsistent. The sudden event can be set as an event that affects the working state of the terminal device 20, and the network traffic can be determined based on multiple terminal devices 20 in the communication network. The different positions of the sudden event make the sudden event have different effects on the terminal device 20, that is, the sudden event has different effects on the terminal device 20 at the first moment t1 and the second moment t2.

[0081] In step 03 and step 04, after determining the first position X(t1) and the second position X(t2), the impact factor of the sudden event from the first moment t1 to the second moment t2 on the terminal device 20 can be determined, and then the first state information S(t2) can be determined based on the impact factor of the sudden event from the first moment t1 to the second moment t2 on the terminal device 20 and the first state information S(t1).

[0082] It can be understood that the traffic prediction method for the communication network provided in the implementation mode of the present application sets the emergency events that affect the network traffic as emergency events with a propagation speed, so that the designed traffic model is more in line with the actual application scenario, improves the accuracy of the predicted network traffic, and solves the technical problem of inaccurate network traffic predicted by the traffic model in the related technology.

[0083] In some embodiments, the terminal device 20 is a machine type communication device.

[0084] Specifically, all devices in the M2M scenario have similar behaviors. MTC devices are homogeneous, while HTC devices are heterogeneous. At the same time, in small-scale time, MTC devices respond to emergencies in a synchronized manner, but HTC devices do not have this feature. Therefore, the HTC traffic model cannot be directly applied to the M2M scenario.

[0085] Coupled Markov Modulated Poisson Process (CMMPP) can be used to describe the traffic model applied to M2M scenarios. CMMPP uses a random process to describe emergencies (such as extreme weather and network congestion). Emergencies can affect the working status of all MTC devices in time and space, and construct a traffic model.

[0086] Reference Figure 4 , the Poisson process arrival rate is determined by the Markov chain state modulation. Where Sn is the Markov chain state value of the nth device, λ n,t is the packet arrival rate of the nth device at time t, p i,jis the transition probability from state j to state i. The sudden event can affect the corresponding p of all MTC devices in time and space. i,j , thus affecting the working status of all MTC devices.

[0087] In this way, the traffic model constructed based on emergencies can better predict the working status of MTC devices and further predict the traffic of the communication network.

[0088] Reference Figure 5 In some embodiments, step 03: determining the second state information of the terminal device 20 at the second moment based on the second location information and the first state information, includes: obtaining the location information of each terminal device 20; determining the distance information of each terminal device 20 based on the location information and the second location information of each terminal device 20, the distance information being configured to identify the distance between the terminal device 20 and the emergency event; determining the second state information of each terminal device 20 based on the distance information of each terminal device 20 and the first state information of each terminal device 20.

[0089] In some embodiments, the acquisition module 11 may acquire the location information of each terminal device 20. The determination module 12 may determine the distance information of each terminal device 20 according to the location information of each terminal device 20 and the second location information. The determination module 12 may also determine the second status information of each terminal device 20 according to the distance information of each terminal device 20 and the first status information of each terminal device 20.

[0090] In some embodiments, the processor can obtain the location information of each terminal device 20; determine the distance information of each terminal device 20 based on the location information of each terminal device 20 and the second location information; determine the second status information of each terminal device 20 based on the distance information of each terminal device 20 and the first status information of each terminal device 20.

[0091] Specifically, the communication network may include m terminal devices 20, and n may be set to any integer from 1 to m. Sn may be set to the status information of the nth device, the first status information of the nth terminal device 20 may be set to Sn(t1), the second status information of the nth terminal device 20 may be set to Sn(t2), Xn may be set to the position of the nth terminal, and dn may be set to the difference between X(t2) and Xn.

[0092] Furthermore, the position X(t2) of the emergency at the second moment can be set as the horizontal position x e (t) and the vertical position y e (t), the position of the nth terminal can be set to the horizontal position x n and the vertical position y n, dn can be expressed as

[0093] The location information X1-Xm of the m terminal devices 20 can be obtained. The distances d1-dm of the m terminal devices 20 are determined based on the location information X1-Xm of the m terminal devices 20 and the location X(t2) of the emergency at the second moment.

[0094] It is understandable that the impact of an emergency on each terminal device 20 can be determined by the distance between the emergency and the terminal device 20. The farther the distance between the emergency and the terminal device 20, the smaller the impact of the emergency on the terminal device 20, and the closer the distance between the emergency and the terminal device 20, the greater the impact of the emergency on the terminal device 20.

[0095] The second state information Sn(t2) of the nth terminal device 20 may be determined according to the distance dn of the nth terminal device 20 and the first state information Sn(t1) of the nth terminal device 20.

[0096] In this way, the impact of the emergency event on each terminal device 20 can be determined according to the distance between the emergency event and each terminal device 20, and then the second state information of each terminal device 20 can be determined.

[0097] Reference Figure 5 In some embodiments, the second state information of each terminal device 20 is determined based on the distance information of each terminal device 20 and the first state information of each terminal device 20, including: when the distance between the terminal device 20 and the emergency event is less than or equal to a specific distance, the first state information of the terminal device 20 is consistent with the second state information.

[0098] In some implementations, the determination module 12 may determine that the first state information of the terminal device 20 is consistent with the second state information when the distance between the terminal device 20 and the emergency event is less than or equal to a specific distance.

[0099] In some implementations, the processor may determine that the first state information of the terminal device 20 is consistent with the second state information when the distance between the terminal device 20 and the emergency event is less than or equal to a specific distance.

[0100] Specifically, the farther the distance between the emergency and the terminal device 20 is, the smaller the impact of the emergency on the terminal device 20 is. The specific distance can be set to dth, and when the distance dn between the nth terminal device 20 and the emergency is less than or equal to the specific distance dth, the nth terminal device 20 can be considered to be non-correlated. At this time, the emergency will not affect the terminal device 20, and the working state of the nth terminal device 20 can remain unchanged, that is, the first state information Sn(t1) of the nth terminal device 20 is consistent with the second state information Sn(t2) of the nth terminal device 20.

[0101] In this way, when the distance between the terminal device 20 and the emergency event is less than or equal to a specific distance, there is no need to additionally calculate the impact factor of the emergency event on the terminal device 20, which reduces the amount of calculation of the traffic model and reduces the complexity of the traffic model operation.

[0102] Reference Figure 5 In some embodiments, the second state information of each terminal device 20 is determined based on the distance information of each terminal device 20 and the first state information of each terminal device 20, including: when the distance between the terminal device 20 and the emergency event is higher than a specific distance, obtaining the first space-related parameter of each terminal device 20, the first space-related parameter being the space-related parameter of the emergency event on the terminal device 20 at the first moment; determining the second space-related parameter of each terminal device 20 based on the first space-related parameter of each terminal device 20, a normal distribution model and the distance information of each terminal device 20, the second space-related parameter being the space-related parameter of the emergency event on the terminal device 20 at the second moment; determining the second state information of each terminal device 20 based on the second space-related parameter of each terminal device 20 and the first state information of each terminal device 20.

[0103] In some embodiments, the acquisition module 11 may acquire the first space-related parameter of each terminal device 20 when the distance between the terminal device 20 and the emergency event is higher than a specific distance. The determination module 12 may determine the second space-related parameter of each terminal device 20 according to the first space-related parameter of each terminal device 20, the normal distribution model, and the distance information of each terminal device 20. The determination module 12 may also determine the second state information of each terminal device 20 according to the second space-related parameter of each terminal device 20 and the first state information of each terminal device 20.

[0104] In some embodiments, the processor may obtain a first spatial-related parameter of each terminal device 20 when the distance between the terminal device 20 and the emergency event is higher than a specific distance; determine a second spatial-related parameter of each terminal device 20 based on the first spatial-related parameter of each terminal device 20, a normal distribution model and the distance information of each terminal device 20; and determine the second state information of each terminal device 20 based on the second spatial-related parameter of each terminal device 20 and the first state information of each terminal device 20.

[0105] Specifically, when the distance dn between the nth terminal device 20 and the emergency event is higher than a specific distance dth, the nth terminal device 20 can be considered to be non-correlated. In this case, it is necessary to calculate and determine the impact factor of the emergency event on the nth terminal device 20.

[0106] The first space-related parameter can be set to δ, and the second space-related parameter corresponding to the nth terminal device 20 can be set to δ n , the distance information corresponding to the nth terminal device 20 can be set as d(n), δ n It can be expressed as The spatial correlation parameter may be a parameter that indicates the impact of an emergency on the working state of the terminal device 20 in space. When the spatial correlation of the terminal device 20 is taken into consideration, the state change of the terminal device 20 may be determined according to the spatial correlation parameter. n The first state information Sn(t1) of the n-th terminal device 20 can determine the second state information Sn(t2) of the n-th terminal device 20.

[0107] In this way, when the distance between the terminal device 20 and the emergency event is higher than a specific distance, the state change of the terminal device 20 can be determined according to the spatial correlation parameters while considering the spatial correlation of the terminal device 20 .

[0108] In some implementations, the first related parameter of each terminal device 20 is the same.

[0109] Specifically, the first moment can be set as the initial moment of the emergency, the first space-related parameter δ can be set as the initial intensity of the emergency center, and the first space-related parameter δ corresponding to each terminal device 20 can be the same parameter, so that the second space parameter δ n Calculation.

[0110] In this way, the first related parameters of each terminal device 20 can be set to the same parameters, which reduces the amount of calculation of the traffic model and reduces the complexity of the operation of the traffic model.

[0111] In certain embodiments, a specific distance is determined based on a standard deviation parameter of a normal distribution model.

[0112] Specifically, the specific distance dth may be set to 2δ. n It can be expressed as When d(n) is greater than dth, δ n Less than δ n Small, δ can be ignored n As for the impact on the n-th terminal device 20, it can be considered that the n-th terminal device 20 is irrelevant.

[0113] When d(n) is less than or equal to dth, δ n Greater than or equal to δ cannot be ignored n The impact on the nth terminal device 20, at this time, it can be considered that the nth terminal device 20 has relevance, and needs to be determined according to δ n The second state information Sn(t2) of the n-th terminal device 20 is calculated and determined.

[0114] In this way, by determining and setting the specific distance according to the standard deviation parameter of the normal distribution model, it is possible to accurately determine whether the terminal device 20 has spatial correlation based on the specific distance.

[0115] In certain embodiments, a standard deviation parameter is determined based on a first spatially correlated parameter.

[0116] Specifically, the first spatial correlation parameter δ can be set as the initial intensity of the emergency center, and δ can be the standard deviation parameter of the normal distribution model. At the same time, the specific distance is determined according to the standard deviation parameter of the normal distribution model, that is, the specific distance can be determined according to the first spatial correlation parameter.

[0117] The larger the first space-related parameter δ is, the higher the initial intensity of the emergency center is, and the larger the value of the specific distance dth needs to be set. The smaller the first space-related parameter δ is, the lower the initial intensity of the emergency center is, and the smaller the value of the specific distance dth needs to be set.

[0118] In this way, by determining to set the specific distance according to the first spatial correlation parameter, it is possible to accurately determine whether the terminal device 20 has spatial correlation based on the specific distance.

[0119] Reference Figure 5In some embodiments, after determining the second space-related parameter corresponding to the terminal device 20, the method includes: obtaining a second time-related parameter, the second time-related parameter being the time-related parameter of the emergency event on the terminal device 20 at the second moment; determining the second state information of each terminal device 20 according to the second time-related parameter, the second space-related parameter of each terminal device 20 and the first state information of each terminal device 20.

[0120] In some embodiments, the acquisition module 11 may acquire the second time-related parameter after determining the second space-related parameter corresponding to the terminal device 20. The determination module 12 may determine the second state information of each terminal device 20 according to the second time-related parameter, the second space-related parameter of each terminal device 20, and the first state information of each terminal device 20.

[0121] In some embodiments, the processor may obtain a second time-related parameter; and determine the second state information of each terminal device 20 based on the second time-related parameter, the second space-related parameter of each terminal device 20, and the first state information of each terminal device 20.

[0122] Specifically, the time-related parameter may be a parameter that the emergency event affects the working state of the terminal device 20 in time. The time-related parameter may be set to θ(t), the second time-related parameter of the terminal device 20 at the second moment t2 may be set to θ(t2), and the second time-related parameter of the nth terminal device 20 may be set to θ(t2).

[0123] In the case of considering the spatial correlation and time correlation of the terminal device 20, the state change of the terminal device 20 can be determined according to the spatial correlation parameter and the time correlation. n , the second time-related parameter θ(t2) of the nth terminal device 20, and the first state information Sn(t1) of the nth terminal device 20 can determine the second state information Sn(t2) of the nth terminal device 20.

[0124] In this way, taking into account the spatial correlation and temporal correlation of the terminal device 20, the state change of the terminal device 20 can be determined according to the spatial correlation parameters and the temporal correlation.

[0125] Reference Figure 5In some embodiments, obtaining a second time-related parameter includes: obtaining quantity information and period information, the quantity information is configured to identify the number of terminal devices 20 in the communication network, and the period information is configured to identify a sampling period of the communication network. Within a sampling period, each terminal device 20 in the communication network is sampled; determining the second time-related parameter based on the quantity information, the period information and the Beta distribution model.

[0126] In some implementations, the acquisition module 11 may acquire quantity information and period information. The determination module 12 may determine the second time-related parameter according to the quantity information, period information and the Beta distribution model.

[0127] In some implementations, the processor may obtain quantity information and period information; and determine the second time-related parameter according to the quantity information, period information, and a Beta distribution model.

[0128] Specifically, the communication network may include m terminal devices 20, and the sampling period may be set to T. In a sampling period T, all the m terminal devices 20 in the communication network are sampled. θ(t2) can be expressed as α can be 3 and β can be 4.

[0129] In this way, the second time-related parameter can be determined based on the Beta distribution model, and then the time correlation of each terminal device 20 at the second moment can be determined.

[0130] Reference Figure 5 In some embodiments, step 02: determining the second position information based on the first position information and the time-varying parameters, including: determining the speed and / or acceleration of the sudden event based on the time-varying parameters, and obtaining the sampling interval; determining the displacement of the sudden event based on the sudden event and the sampling interval; determining the second position based on the first position and the displacement of the sudden event.

[0131] In some implementations, the acquisition module 11 may acquire the sampling interval. The determination module 12 may determine the displacement of the sudden event according to the sudden event and the sampling interval; and determine the second position according to the first position and the displacement of the sudden event.

[0132] In some embodiments, the processor can determine the speed and / or acceleration of the sudden event based on time-varying parameters, and obtain a sampling interval; determine the displacement of the sudden event based on the sudden event and the sampling interval; determine the second position based on the first position and the displacement of the sudden event.

[0133] Specifically, the second position X(t2) can be calculated and determined according to the time-varying parameter and the first position X(t1). From the first moment t1 to the second moment t2, the speed of the sudden event can be set to v, the speed of the sudden event can be set to a, and the time interval from the first moment t1 to the second moment t2 is set to t.

[0134] Furthermore, the horizontal speed of the sudden event can be set as v x , the speed of the emergency can be set to a x , the horizontal speed of the sudden event can be set as v y , the speed of the emergency can be set to a y , the time interval from the first moment t1 to the second moment t2 is set to t, and the position X(t1) of the emergency at the first moment can be set to the horizontal position x o and the vertical position y o The position of the incident at the second moment X(t2) can be set to the horizontal position x e (t) and the vertical position y e (t),

[0135] In this way, the second position can be calculated and determined according to the time-varying parameter and the first position.

[0136] In some embodiments, the time-varying parameter includes preset speed information and / or acceleration information, the speed information is configured to identify the speed of the sudden event, and the acceleration information is configured to identify the acceleration of the sudden event.

[0137] Specifically, the time-varying parameters can be pre-set according to the characteristics of the emergency event. Before predicting the network traffic, the time-varying parameters can be determined according to the characteristics of the emergency event.

[0138] Reference Figure 6 , Figure 6 (a) is a schematic diagram of spatial flow showing the duration of emergency event A for 10 seconds. Figure 6 (b) A schematic diagram of spatial flow showing the duration of event A for 20 seconds. Event A can be set as a stationary event. In this case, the speed and acceleration of the event in different directions can be set to zero. Figure 6 (a) and Figure 6 (b) It can be determined that the center point of the high flow area of ​​the CMMPP flow model does not change over time, but the range of the high flow area increases over time.

[0139] Reference Figure 7 , Figure 7 (a) is a schematic diagram of spatial flow showing the duration of the emergency event B for 10 seconds. Figure 7 (b) shows the spatial flow diagram of the sudden event B that lasts for 20 seconds. The sudden event B can be set as a moving event, and the speed v of the sudden event B in the horizontal direction is x is 10m / s, and the vertical velocity v y is 10m / s. Figure 7 (a) and Figure 7 (b) It can be determined that the range of the high-flow area in the CMMPP flow model not only gradually increases with time, but also the center point of the high-flow area changes with time, which is time-varying.

[0140] Figure 7 (c) shows the spatial flow diagram of the sudden event C that lasts for 20 seconds. The sudden event C can be set as a moving event, and the speed v of the sudden event C in the horizontal direction is x is -20m / s, the vertical velocity v y is 20m / s. Both emergency events B and C can be set as emergency events with a central initial intensity of δ. Figure 7 (b) and Figure 7 (c) It can be determined that the center of the high-flow area in the CMMPP flow model is related to the magnitude and direction of the propagation speed of the emergency.

[0141] Figure 7 (d) shows the spatial flow diagram of the sudden event D that lasts for 20 seconds. The sudden event C can be set as a moving event, and the speed v of the sudden event C in the horizontal direction is x is -20m / s, the vertical velocity v y is 20m / s, and the sudden event D can be set as a sudden event with a central initial intensity of δ / 2. Figure 7 (c) and Figure 7 (d) It can be determined that the high-flow area of ​​the CMMPP flow model is related to the intensity of emergency transmission. The greater the intensity, the larger the high-flow area.

[0142] Furthermore, the emergency event can also be set as an emergency event E with acceleration. The moving speed of the center point of the high-flow area of ​​the emergency event E changes with time, and the center point of the high-flow area changes with time, which is time-varying.

[0143] In this way, time-varying parameters can be pre-set according to the characteristics of the emergency, so that the designed traffic model is more in line with the actual application scenario.

[0144] In some implementations, the second moment is determined based on the first moment and a sampling interval, where the sampling interval is a preset time interval.

[0145] Specifically, the sampling interval may be set to Δt, t2=t1+Δt. Δt may be a preset time period, so that the traffic prediction method updates the obtained network traffic prediction value based on the impact of the emergency event within the Δt time period.

[0146] For example, Δt may be set to 1 / 60s. After the traffic prediction method determines the network traffic prediction value at time t1, steps 01 to 04 are executed, and a new network traffic prediction value is determined at time t1.

[0147] In this way, the traffic prediction method can update the determined network traffic prediction value based on the preset sampling interval.

[0148] In some embodiments, after determining the second prediction value, the method also includes: updating the second moment to the first moment, and repeatedly executing the step of obtaining the first state information, the first position information, and the time-varying parameters to determine the second prediction value based on the second state information to determine multiple second prediction values; determining the network traffic prediction value of the communication network within a sampling period based on the multiple second prediction values.

[0149] In some implementations, after determining the second prediction value, the traffic prediction device 10 may repeatedly execute steps 01 to 04 multiple times.

[0150] In some implementations, after determining the second prediction value, the processor may repeatedly execute steps 01 to 04 multiple times.

[0151] Specifically, the time of a sampling cycle can be set to T. For the nth terminal device 20, when the steps of obtaining the first state information, the first position information and the time-varying parameter to determining the second prediction value according to the second state information are executed for the first time, t1 can be set to t0, and t2 can be set to t0+Δt, so as to determine the network traffic prediction value at t0+Δt, and then t1 can be set to t0+Δt, and t2 can be set to t0+2Δt, so as to determine the network traffic prediction value of t0+2Δt, until t1 is set to t0+T-Δt, t2 is set to t0+T, and the network traffic prediction value of t0+T is determined.

[0152] In this way, the traffic prediction method can obtain multiple second prediction values, and then determine the network traffic prediction value within a sampling period.

[0153] In some embodiments, the number of times the steps of acquiring the first state information, the first position information and the time-varying parameter to determining the second prediction value according to the second state information are performed is determined according to the time interval, the sampling period and the number of terminal devices 20.

[0154] Specifically, the communication network may include m terminal devices 20. In one sampling period, each terminal device 20 needs to determine T / Δt second network traffic prediction values, that is, it needs to execute T / Δt steps 01 to 04. When the second network traffic prediction values ​​of all terminal devices 20 are determined, it is necessary to execute (T / Δt) m Step 01 to Step 04.

[0155] Theoretical analysis of computational complexity shows that the proposed model mainly uses piecewise function calculation based on the cutoff distance to reduce the complexity. The computational complexity advantage is mainly related to the location of the MTC device. If the distance between all device locations and the center of the emergency is less than the cutoff distance, the computational complexity of the proposed model is the same as that of the traditional CMMPP model. If the distance between the locations of M devices and the center of the emergency is greater than the cutoff distance, the proposed model can reduce (T / Δt) compared to the traditional CMMPP model. M Complex multiplications are performed, and as the total number of terminal devices 20 increases, the probability of M increasing, and the computational complexity advantage of the proposed model becomes more obvious.

[0156] Thus, a theoretical analysis is conducted on the computational complexity, and it is found that reducing the complexity by using piecewise function calculation based on the cut-off distance has obvious advantages for communication networks with a greater total number of terminal devices 20 .

[0157] In some implementations, an emergency event is an event that affects the communication device to switch from a normal state to an alarm state.

[0158] Specifically, an emergency event has a propagation speed. If an emergency event occurs, the working state of the MTC devices near the center point will change.

[0159] Reference Figure 6 , Figure 6 (a) is a schematic diagram of spatial flow showing the duration of emergency event A for 10 seconds. Figure 6 (b) is a schematic diagram of spatial flow when the emergency event A lasts for 20 seconds. Figure 6 (a) and Figure 6 (b) It can be determined that the high-traffic area is only increasing over time, causing the number of communication devices in an alarm state to increase over time.

[0160] Reference Figure 7 , Figure 7 (a) is a schematic diagram of spatial flow showing the duration of the emergency event B for 10 seconds. Figure 7 (b) A schematic diagram of spatial flow showing the duration of the sudden event B for 20 seconds. The sudden event B can be set as a moving event. Figure 7 (a) and Figure 7(b) It can be determined that the range of the high-flow area of ​​the CMMPP traffic model not only gradually increases with time, but also the center point of the high-flow area changes with time, causing the location of the communication equipment in the alarm state to change with time.

[0161] In this way, the communication device to be alerted can be determined based on the impact of the emergency, thereby predicting the traffic of the communication network.

[0162] In some embodiments, the first state information is configured to determine a first state matrix of the terminal device 20 at a first moment, and whether the terminal device 20 is in a normal state or an alarm state at the first moment is determined based on the first state matrix; the second state information is configured to determine a second state matrix of the terminal device 20 at a second moment, and whether the terminal device 20 is in a normal state or an alarm state at the second moment is determined based on the second state matrix.

[0163] Specifically, each terminal device 20 corresponds to a Markov chain, and the terminal device 20 has a state distribution vector π, based on which it can be determined whether the terminal device 20 is in a normal state or an alarm state. At the first moment t1, the state distribution vector π is set as a first state matrix, and at the first moment t2, the state distribution vector π is set as a second state matrix.

[0164] In this way, based on the first state matrix and the second state matrix, it can be determined whether the terminal device 20 is in a normal state or an alarm state.

[0165] In some embodiments, step 03: determining the second state information of the terminal device 20 at the second moment based on the second position information and the first state information includes: determining the conversion matrix based on the second position information; determining the second state matrix based on the conversion matrix and the first state matrix to determine the second state information.

[0166] In some implementations, the determination module 12 may determine a conversion matrix according to the second position information; and determine a second state matrix according to the conversion matrix and the first state matrix to determine the second state information.

[0167] In some implementations, the processor may determine a conversion matrix based on the second position information; and determine a second state matrix based on the conversion matrix and the first state matrix to determine the second state information.

[0168] Specifically, each terminal device 20 has a state transfer matrix P and a state distribution vector π, and the relationship between the two is πP=π in a steady state. The state transfer matrix P from the first time t1 to the first time t2 can be set as a conversion matrix, and the second state matrix can be updated and determined according to the first state matrix and the state transfer matrix P.

[0169] In this way, the second state matrix can be determined based on the first state matrix and the transition matrix.

[0170] In some embodiments, determining a conversion matrix based on the second position information includes: determining an impact factor based on the second position information, the impact factor being the impact factor of the emergency event on the terminal device 20 at the second moment; obtaining a first standard matrix and a second standard matrix, the first standard matrix being a completely correlated state transfer matrix, and the second standard matrix being a completely uncorrelated state transfer matrix; determining a conversion matrix based on the first standard matrix, the second standard matrix, and the impact factor.

[0171] In some implementations, the acquisition module 11 may acquire a first standard matrix and a second standard matrix. The determination module 12 may determine a conversion matrix according to the first standard matrix, the second standard matrix and the influencing factor.

[0172] In some implementations, the processor may obtain a first standard matrix and a second standard matrix, and determine a conversion matrix according to the first standard matrix, the second standard matrix, and the influencing factor.

[0173] Specifically, the impact factor can be set as θn(t), θn(t) = δ n ×θ(t), in the case of considering the spatial correlation of the terminal device 20, the state change of the terminal device 20 can be determined according to the spatial correlation parameter, that is, according to δ n The size of θn(t) is determined. The specific process may refer to the above implementation.

[0174] The state transition matrix of the nth communication device can be set as P n (t), P C represents the state transition matrix of the relevant terminal device 20, P U represents the state transition matrix of the completely non-correlated terminal device 20, P n (t) = θn(t)P C +[1-θn(t)]P U For a 2-state Markov chain, the working states are "normal" and "warning". The above formula indicates that the relevant terminal device 20 triggers the "alarm" working state once within a time period, and the non-relevant terminal device 20 maintains the "normal" working state and does not trigger the "alarm".

[0175] In this way, the conversion matrix can be determined according to the first standard matrix, the second standard matrix and the influencing factor, and then the corresponding working state of each terminal device 20 can be determined.

[0176] Reference Figure 4After calculating and determining the state transfer matrix of the n-th communication device, the Markov chain state value Sn of the n-th device can be determined based on the Markov modulated Poisson process. It can be set as the packet arrival rate of the nth device at time t, is the state distribution vector of the nth device at time t.

[0177] The Markov chain state values ​​Sn of n communication devices at time t can be set to values ​​from 1 to 1 in sequence. n,t It can be set as the corresponding data packet arrival rate of n devices at time t, λ n,t It is determined based on the packet arrival rate of each device at time t and the state distribution vector of each device at time t.

[0178] In some embodiments, determining the impact factor based on the second location information includes: obtaining the location information of the terminal device 20; determining the distance information of the terminal device 20 based on the location information of the terminal device 20 and the second location information, the distance information being configured to identify the distance between the terminal device 20 and the emergency event; when the distance between the terminal device 20 and the emergency event is less than or equal to a specific distance, the impact factor is zero, so that the conversion matrix is ​​a second standard matrix.

[0179] Specifically, the farther the distance between the emergency event and the terminal device 20 is, the smaller the impact of the emergency event on the terminal device 20. When the distance between the terminal device 20 and the emergency event is less than or equal to a specific distance, it can be considered that the nth terminal device 20 has no correlation, the impact factor is zero, and the conversion matrix is ​​expressed as a state transfer matrix of completely non-correlated terminal devices 20.

[0180] In this way, when the distance between the terminal device 20 and the emergency event is less than or equal to a specific distance, there is no need to additionally calculate the conversion matrix, which reduces the amount of calculation of the traffic model and the complexity of the operation of the traffic model.

[0181] In some embodiments, determining the impact factor based on the second location information includes: when the distance between the terminal device 20 and the emergency is higher than a specific distance, obtaining a first spatial-related parameter of the terminal device 20, the first spatial-related parameter being the spatial-related parameter of the emergency on the terminal device 20 at the first moment; determining a second spatial-related parameter of the terminal device 20 based on the first spatial-related parameter of the terminal device 20, a normal distribution model and the distance information of the terminal device 20, the second spatial-related parameter being the spatial-related parameter of the emergency on the terminal device 20 at the second moment; and determining the impact factor based on the second spatial-related parameter.

[0182] Specifically, when the distance between the terminal device 20 and the emergency event is less than or equal to a specific distance, the nth terminal device 20 can be considered to be non-correlated. At this time, the conversion matrix needs to be calculated and determined, and the calculation process can refer to the above implementation.

[0183] In this way, when the distance between the terminal device 20 and the emergency event is higher than a specific distance, the corresponding conversion matrix can be determined according to the spatial correlation calculation of the terminal device 20 .

[0184] In some embodiments, determining the impact factor based on the second location information includes: when the distance between the terminal device 20 and the emergency is higher than a specific distance, obtaining a first spatial-related parameter of the terminal device 20, the first spatial-related parameter being the spatial-related parameter of the emergency on the terminal device 20 at the first moment; determining a second spatial-related parameter of the terminal device 20 based on the first spatial-related parameter of the terminal device 20, a normal distribution model and the distance information of the terminal device 20, the second spatial-related parameter being the spatial-related parameter of the emergency on the terminal device 20 at the second moment; obtaining a second time-related parameter, the second time-related parameter being the time-related parameter of the emergency on the terminal device 20 at the second moment; and determining the impact factor based on the second spatial-related parameter and the second time-related parameter.

[0185] Specifically, the impact factor can be set as θn(t), θn(t) = δ n ×θ(t), considering the spatial correlation and time correlation of the terminal device 20, the state change of the terminal device 20 can be determined according to the spatial correlation parameters and the time correlation parameters, that is, according to δ n and θ(t) determine the size of θn(t), and the specific process can refer to the above implementation method.

[0186] In this way, when the distance between the terminal device 20 and the emergency event is higher than a specific distance, the corresponding conversion matrix can be calculated and determined according to the spatial correlation and temporal correlation of the terminal device 20 .

[0187] In some embodiments, the second state information is configured to identify the normal or alarm state of the terminal device 20 in the second state, and the second prediction value is determined based on the second state information, including: the second prediction value is determined based on the number of terminal devices 20 that are in a normal state at the second moment, and the number of terminal devices 20 that are in an alarm state at the second moment.

[0188] Specifically, the traffic of the communication network is determined according to the number of terminal devices 20 in a normal state and the number of terminal devices 20 in an alarm state at the second moment. It can be understood that in the "normal" state, the terminal devices 20 generate data asynchronously, and in the "alarm" state, the terminal devices 20 generate a large amount of data, and the determined second prediction value is larger.

[0189] In this way, according to the working status of the plurality of terminal devices 20, the corresponding traffic prediction value can be determined.

[0190] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by one or more processors, the traffic prediction method of the above embodiment is implemented.

[0191] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples" or "some examples" means that the specific features, deconstructions, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0192] In addition, the term "connection" should be understood in a broad sense, for example, it can include fixed connection, detachable connection, or integral connection; it can include direct connection, indirect connection through an intermediate medium, and internal communication between two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0193] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0194] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0195] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for predicting traffic in a communication network, characterized in that: The method comprises: Acquire first state information of a terminal device in the communication network at a first moment, first location information of an emergency event, and a time-varying parameter of the emergency event, wherein the first location information is configured to identify a location of the emergency event at the first moment; Determine second location information according to the first location information and the time-varying parameter, wherein the second location information is configured to identify a location of the emergency event at a second moment; Determine second state information of the terminal device at the second moment according to the second location information and the first state information; A second prediction value is determined according to the second state information to determine a network traffic prediction value of the communication network at the second moment.

2. The prediction method according to claim 1, characterized in that: The determining, according to the second location information and the first status information, the second status information of the terminal device at the second moment includes: Obtaining location information of each of the terminal devices; Determining distance information of each terminal device according to the location information of each terminal device and the second location information, wherein the distance information is configured to identify the distance between the terminal device and the emergency event; The second status information of each of the terminal devices is determined according to the distance information of each of the terminal devices and the first status information of each of the terminal devices.

3. The prediction method according to claim 2, characterized in that: The determining the second status information of each of the terminal devices according to the distance information of each of the terminal devices and the first status information of each of the terminal devices includes: When the distance between the terminal device and the emergency event is less than or equal to a specific distance, the first state information of the terminal device is consistent with the second state information.

4. The prediction method according to claim 2, characterized in that: The determining the second status information of each of the terminal devices according to the distance information of each of the terminal devices and the first status information of each of the terminal devices includes: When the distance between the terminal device and the emergency event is greater than a specific distance, obtaining a first space-related parameter of each terminal device, where the first space-related parameter is a space-related parameter of the emergency event to the terminal device at the first moment; Determine a second space-related parameter of each terminal device according to the first space-related parameter of each terminal device, a normal distribution model and the distance information of each terminal device, wherein the second space-related parameter is a space-related parameter of the emergency event on the terminal device at the second moment; The second status information of each of the terminal devices is determined according to the second space-related parameters of each of the terminal devices and the first status information of each of the terminal devices.

5. The prediction method according to claim 4, characterized in that: The first related parameters of each terminal device are the same.

6. The prediction method according to claim 4, characterized in that: The specific distance is determined according to a standard deviation parameter of the normal distribution model.

7. The prediction method according to claim 6, characterized in that: The standard deviation parameter is determined based on the first spatial correlation parameter.

8. The prediction method according to claim 4, characterized in that: After determining the second space-related parameter corresponding to the terminal device, the method includes: Acquire a second time-related parameter, where the second time-related parameter is a time-related parameter of the emergency event on the terminal device at the second moment; The second status information of each of the terminal devices is determined according to the second time-related parameter, the second space-related parameter of each of the terminal devices, and the first status information of each of the terminal devices.

9. The prediction method according to claim 8, characterized in that: The acquiring the second time-related parameter includes: Acquire quantity information and cycle information, wherein the quantity information is configured to identify the quantity of the terminal devices in the communication network, and the cycle information is configured to identify a sampling cycle of the communication network, and within one sampling cycle, each of the terminal devices in the communication network is sampled; A second time-related parameter is determined according to the quantity information, the period information and the Beta distribution model.

10. The prediction method according to claim 1, characterized in that: The time-varying parameter includes preset speed information and / or acceleration information, the speed information is configured to identify the speed of the emergency event, and the acceleration information is configured to identify the acceleration of the emergency event.

11. The prediction method according to claim 1, characterized in that: The second moment is determined according to the first moment and a sampling interval, and the sampling interval is a preset time interval.

12. The prediction method according to claim 11, characterized in that: The determining the second position information according to the first position information and the time-varying parameter includes: Determining the speed and / or acceleration of the emergency event according to the time-varying parameter, and obtaining the sampling interval; Determine the displacement of the sudden event according to the sudden event and the sampling interval; The second position is determined according to the first position and the displacement of the emergency event.

13. The prediction method according to claim 1, characterized in that: The emergency event is an event that affects the communication device to switch from a normal state to an alarm state.

14. The prediction method according to claim 13, characterized in that: The first state information is configured to determine a first state matrix of the terminal device at the first moment, and whether the terminal device is in a normal state or an alarm state at the first moment is determined according to the first state matrix; The second state information is configured to determine a second state matrix of the terminal device at the second moment, and whether the terminal device is in a normal state or an alarm state at the second moment is determined based on the second state matrix.

15. The prediction method according to claim 13, characterized in that: The determining, according to the second location information and the first status information, the second status information of the terminal device at the second moment includes: determining a conversion matrix according to the second position information; The second state matrix is ​​determined according to the conversion matrix and the first state matrix to determine the second state information.

16. The prediction method according to claim 15, characterized in that: The determining a conversion matrix according to the second position information includes: Determine an impact factor according to the second location information, where the impact factor is an impact factor of the emergency event on the terminal device at the second moment; Acquire a first standard matrix and a second standard matrix, wherein the first standard matrix is ​​a completely correlated state transfer matrix, and the second standard matrix is ​​a completely uncorrelated state transfer matrix; The conversion matrix is ​​determined according to the first standard matrix, the second standard matrix and the influencing factor.

17. The prediction method according to claim 16, characterized in that: The determining the impact factor according to the second position information includes: Obtaining location information of the terminal device; Determining distance information of the terminal device according to the location information of the terminal device and the second location information, wherein the distance information is configured to identify a distance between the terminal device and the emergency event; When the distance between the terminal device and the emergency event is less than or equal to a specific distance, the impact factor is zero, so that the conversion matrix is ​​the second standard matrix.

18. The prediction method according to claim 17, characterized in that: The determining the impact factor according to the second position information includes: When the distance between the terminal device and the emergency event is greater than the specific distance, obtaining a first space-related parameter of the terminal device, where the first space-related parameter is a space-related parameter of the emergency event to the terminal device at the first moment; Determine a second space-related parameter of the terminal device according to the first space-related parameter of the terminal device, a normal distribution model and the distance information of the terminal device, wherein the second space-related parameter is a space-related parameter of the emergency event on the terminal device at the second moment; The influencing factor is determined according to the second space-related parameter.

19. The prediction method according to claim 17, characterized in that: The determining the impact factor according to the second position information includes: When the distance between the terminal device and the emergency event is greater than the specific distance, obtaining a first space-related parameter of the terminal device, where the first space-related parameter is a space-related parameter of the emergency event to the terminal device at the first moment; Determine a second space-related parameter of the terminal device according to the first space-related parameter of the terminal device, a normal distribution model and the distance information of the terminal device, wherein the second space-related parameter is a space-related parameter of the emergency event on the terminal device at the second moment; Acquire a second time-related parameter, where the second time-related parameter is a time-related parameter of the emergency event on the terminal device at the second moment; The influencing factor is determined according to the second space-related parameter and the second time-related parameter.

20. The prediction method according to claim 1, characterized in that: The second state information is configured to identify a normal state or an alarm state of the terminal device in the second state, and determining the second prediction value according to the second state information includes: The second prediction value is determined based on the number of the terminal devices in a normal state at the second moment and the number of the terminal devices in an alarm state at the second moment.

21. The prediction method according to claim 1, characterized in that: After determining the second prediction value, the method further includes: updating the second moment to the first moment, and repeatedly performing the steps of obtaining the first state information, the first position information, and the time-varying parameter to determining the second prediction value according to the second state information, so as to determine a plurality of the second prediction values; A network traffic prediction value of the communication network within a sampling period is determined according to the plurality of second prediction values.

22. The prediction method according to claim 1, characterized in that: The second moment is determined according to the first moment and a sampling interval, where the sampling interval is a preset time interval; The number of times the steps of obtaining the first state information, the first position information and the time-varying parameter to determining the second prediction value according to the second state information are performed is determined according to the time interval, the sampling period and the number of the terminal devices.

23. A traffic prediction device for a communication network, characterized in that: The device comprises: an acquisition module, configured to acquire first state information of a terminal device in the communication network at a first moment, first location information of an emergency event, and a time-varying parameter of the emergency event, wherein the first location information is configured to identify a location of the emergency event at the first moment; A determination module is configured to determine second location information based on the first location information and the time-varying parameters, the second location information is configured to identify the location of the emergency at a second moment, the determination module is configured to determine second state information of the terminal device at the second moment based on the second location information and the first state information, and the determination module is configured to determine a second prediction value based on the second state information to determine a network traffic prediction value of the communication network at the second moment.

24. The device according to claim 23, characterized in that The acquisition module is configured to acquire the location information of each of the terminal devices, the determination module is configured to determine the distance information of each of the terminal devices based on the location information of each of the terminal devices and the second location information, the distance information is configured to identify the distance between the terminal device and the emergency event, and the determination module is further configured to determine the second status information of each of the terminal devices based on the distance information of each of the terminal devices and the first status information of each of the terminal devices.

25. The device according to claim 24, characterized in that In a case where the distance between the terminal device and the emergency event is less than or equal to a specific distance, the determination module determines that the first state information of the terminal device is consistent with the second state information.

26. The device according to claim 24, characterized in that The acquisition module is configured to acquire a first spatial-related parameter of each terminal device when the distance between the terminal device and the emergency event is higher than a specific distance, the first spatial-related parameter being the spatial-related parameter of the emergency event on the terminal device at the first moment; the determination module is configured to determine a second spatial-related parameter of each terminal device based on the first spatial-related parameter of each terminal device, a normal distribution model and the distance information of each terminal device, the second spatial-related parameter being the spatial-related parameter of the emergency event on the terminal device at the second moment; the determination module is further configured to determine the second status information of each terminal device based on the second spatial-related parameter of each terminal device and the first status information of each terminal device.

27. The device according to claim 26, characterized in that The acquisition module is also configured to acquire a second time-related parameter, which is a time-related parameter of the emergency event on the terminal device at the second moment. The determination module is also configured to determine the second status information of each terminal device based on the second time-related parameter, the second space-related parameter of each terminal device and the first status information of each terminal device.

28. A chip, characterized in that: The chip includes a memory and a processor, the memory is configured to store a computer program, and the processor implements the traffic prediction method according to any one of claims 1 to 22 when executing the computer program.

29. A communication network system, characterized in that: The system comprises: The flow prediction device according to any one of claims 23 to 27, or the chip according to claim 28; Base station; A plurality of terminal devices located within the coverage area of ​​the base station.

30. The communication network system according to claim 29, characterized in that: The terminal device is a machine type communication device.

31. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by one or more processors, the traffic prediction method according to any one of claims 1 to 22 is implemented.

Images