CN113453096B

CN113453096B - Method and device for predicting PON port flow of passive optical network

Info

Publication number: CN113453096B
Application number: CN202110626382.9A
Authority: CN
Inventors: 李奥; 苏雨聃; 韩赛; 邵岩; 王光全
Original assignee: China United Network Communications Group Co Ltd
Current assignee: China United Network Communications Group Co Ltd
Priority date: 2021-06-04
Filing date: 2021-06-04
Publication date: 2022-12-13
Anticipated expiration: 2041-06-04
Also published as: CN113453096A

Abstract

The application provides a method and a device for predicting PON port flow, relates to the field of communication, and can predict the PON port flow, so that the capacity expansion of the PON port is guided according to the predicted flow, and when the flow is predicted, the error between the predicted flow and the actual flow of the PON port can be reduced, so that the capacity expansion of the PON port can be guided more accurately. The method comprises the following steps: and acquiring first current network data, and inputting the first current network data into the flow prediction model to obtain the flow of the first PON port. The first current network data comprises data on a first PON port, data corresponding to the first PON port in the subsystem, data corresponding to the first PON port in the authentication, authorization and accounting AAA system, and data corresponding to the first PON port in the number line system.

Description

Method and device for predicting PON port flow of passive optical network

Technical Field

The present application relates to the field of communications, and in particular, to a method and an apparatus for predicting traffic of a passive optical network PON interface.

Background

In network communication, with the increasing popularity of broadband access networks, on one hand, the quality requirements of users for broadband access networks are increasing, and on the other hand, the competition of operators in the field of broadband access networks is also increasing. Based on the above two aspects, higher requirements are put forward for the operator in the aspects of planning construction, operation maintenance and the like of the broadband access network.

For example, in a Passive Optical Network (PON) system, an urgent requirement is to accurately analyze key factors affecting the PON port traffic and further predict the PON port traffic. In the prior art, it is common to analyze key factors affecting PON port traffic and predict PON port traffic based on a front-end person's experience.

However, because the subjectivity of a front-end crew is large, the PON port traffic predicted empirically usually has a large error.

Disclosure of Invention

The application provides a method and a device for predicting PON port flow of a passive optical network, which can reduce the error between the predicted flow and the actual flow of the PON port, thereby accurately guiding the expansion of the PON port according to the predicted flow.

In order to achieve the purpose, the following technical scheme is adopted in the application:

in a first aspect, a method for predicting PON port traffic is provided, where the method may be executed by a traffic prediction apparatus, or may be executed by a component of the traffic prediction apparatus, such as a processor, a chip, or a chip system of the traffic prediction apparatus, or may be implemented by a logic module or software that can implement all or part of the functions of the traffic prediction apparatus, and the method performed by the traffic prediction apparatus is described as an example in the present application. The method comprises the following steps: the flow prediction device acquires first current network data, inputs the first current network data into the flow prediction model, and obtains the flow of the first PON port. The first current network data comprises data on a first PON port, data corresponding to the first PON port in the subsystem, data corresponding to the first PON port in the authentication, authorization and accounting AAA system, and data corresponding to the first PON port in the number line system.

Based on the scheme, the predicted traffic of the PON is obtained by inputting the data related to the PON port in the current network into a traffic prediction model. When the flow of the PON port is predicted, the data related to the PON port in the existing network is used to the maximum extent, compared with the prior art, the flow of the PON port is not predicted according to the experience of a front-line worker any more, the influence of artificial subjective factors on the predicted flow is reduced, the error between the predicted flow and the actual flow of the PON port is reduced, and therefore the expansion of the PON port can be guided more accurately.

In a possible implementation manner of the first aspect, the method further includes: the flow prediction device constructs a flow prediction model according to second current network data, the second current network data comprises data on the N PON ports, data corresponding to the N PON ports in the subsystem respectively, data corresponding to the N PON ports in the AAA system respectively and data corresponding to the N PON ports in the wire system respectively, and N is a positive integer.

In a possible implementation manner of the first aspect, the constructing, by the traffic prediction apparatus, a traffic prediction model according to the second current network data includes: the flow prediction device preprocesses the second current network data to obtain K important characteristic fields; dividing L flow intervals according to the number of users, and determining values of K important characteristic fields corresponding to the L flow intervals respectively; constructing a decision tree according to the values of the important characteristic fields corresponding to the L flow intervals respectively to obtain the weights of the K important characteristic fields; and determining a flow prediction model according to the weights of the K important characteristic fields, wherein K and L are positive integers.

In a possible implementation manner of the first aspect, the preprocessing the second current network data by the traffic prediction device includes: the flow prediction device merges the second current network data to obtain N pieces of data; k significant feature fields of the M feature fields are determined. The N pieces of data comprise M characteristic fields, the N pieces of data correspond to the N PON ports one by one, M is a positive integer larger than or equal to K, the support degree corresponding to the important characteristic fields is larger than or equal to a first threshold, the confidence degree corresponding to the important characteristic fields is larger than or equal to a second threshold, the support degree is used for indicating the frequency of the characteristic fields, and the confidence degree is used for indicating association rules among the characteristic fields.

In a possible implementation manner of the first aspect, the M feature fields include a first feature field, and a support degree of the first feature field is determined by a number of data pieces including the first feature field in the N pieces of data, and a total number N of the data pieces; the confidence of the first feature field is determined by the number of pieces of data including the first feature field and the second feature field, and the number of pieces of data including the first feature field, in the N pieces of data.

In a possible implementation manner of the first aspect, in the L traffic intervals, a difference between a number of users corresponding to the first traffic interval and a number of users corresponding to the second traffic interval is smaller than or equal to a third threshold; the first flow rate interval is a flow rate interval in which the number of corresponding users is the largest, and the second flow rate interval is a flow rate interval in which the number of corresponding users is the smallest.

In a possible implementation manner of the first aspect, the L traffic intervals include a first traffic interval, a value of the important characteristic field corresponding to the first traffic interval includes a value of the important characteristic field corresponding to the second PON port, and a traffic of the second PON port is located in the first traffic interval.

In a possible implementation manner of the first aspect, the method further includes: and the flow prediction device optimizes the flow prediction model according to the complaint information and the energy consumption information corresponding to the PON port.

In a possible implementation manner of the first aspect, the method further includes: the flow prediction device determines to expand the capacity under the condition that the flow of the first PON port is larger than a fourth threshold value; and under the condition that the flow of the first PON port is smaller than the fourth threshold value, determining not to expand the capacity.

In a second aspect, a communications device is provided for implementing the various methods described above. The communication device may be the flow rate prediction device in the first aspect, or a device including the flow rate prediction device, or a device included in the flow rate prediction device, such as a chip. The communication device includes corresponding modules, units, or means (means) for implementing the above methods, and the modules, units, or means may be implemented by hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the above functions.

In some possible designs, the communication device may include: the device comprises an acquisition module and a processing module. The acquisition module is used for acquiring first current network data; and the processing module is used for inputting the first current network data into the flow prediction model to obtain the flow of the first PON port. The first current network data comprises data on a first PON port, data corresponding to the first PON port in the subsystem, data corresponding to the first PON port in the authentication, authorization and accounting AAA system, and data corresponding to the first PON port in the number line system.

In a possible implementation manner of the second aspect, the processing module is further configured to construct a traffic prediction model according to second existing network data, where the second existing network data includes data on N PON ports, data corresponding to the N PON ports in the subsystem, data corresponding to the N PON ports in the AAA system, and data corresponding to the N PON ports in the number line system, and N is a positive integer.

In a possible implementation manner of the second aspect, the processing module is further configured to construct a traffic prediction model according to the second current network data, and the method includes: the processing module is also used for preprocessing the second current network data to obtain K important characteristic fields; the processing module is also used for dividing L flow intervals according to the number of users and determining the values of K important characteristic fields corresponding to the L flow intervals respectively; the processing module is also used for constructing a decision tree according to the values of the important characteristic fields corresponding to the L flow intervals respectively to obtain the weights of the K important characteristic fields; and the processing module is also used for determining a flow prediction model according to the weights of the K important characteristic fields, wherein K and L are positive integers.

In a possible implementation manner of the second aspect, the processing module is further configured to perform preprocessing on the second current network data, and includes: the processing module is also used for merging the second current network data to obtain N pieces of data; and the processing module is also used for determining K important characteristic fields in the M characteristic fields. The N pieces of data comprise M characteristic fields, the N pieces of data correspond to the N PON ports one by one, M is a positive integer larger than or equal to K, the support degree corresponding to the important characteristic fields is larger than or equal to a first threshold, the confidence degree corresponding to the important characteristic fields is larger than or equal to a second threshold, the support degree is used for indicating the frequency of the characteristic fields, and the confidence degree is used for indicating association rules among the characteristic fields.

In a possible implementation manner of the second aspect, the processing module is further configured to optimize the traffic prediction model according to the complaint information and the energy consumption information corresponding to the PON port.

In a possible implementation manner of the second aspect, the processing module is further configured to determine to perform capacity expansion when a flow rate of the first PON port is greater than a fourth threshold; and under the condition that the flow of the first PON port is smaller than the fourth threshold value, determining not to expand the capacity.

In a third aspect, a communication apparatus is provided, including: at least one processor; the processor is adapted to execute a computer program or instructions to cause the communication device to perform the method of any of the above aspects. The communication device may be the flow rate prediction device in the first aspect, or a device including the flow rate prediction device, or a device included in the flow rate prediction device, such as a chip.

In some possible designs, the communication device further includes a memory for storing necessary program instructions and data. The memory may be coupled to the processor or may be independent of the processor.

In some possible designs, the communication device may be a chip or a system of chips. When the device is a chip system, the device may be composed of a chip, or may include a chip and other discrete devices.

In a fourth aspect, a communication apparatus is provided, including: a processor and a communication interface; the communication interface is used for communicating with a module outside the communication device; the processor is configured to execute a computer program or instructions to cause the communication device to perform the method of any of the above aspects. The communication device may be the flow rate prediction device in the first aspect, or a device including the flow rate prediction device, or a device included in the flow rate prediction device, such as a chip.

In a fifth aspect, a communication apparatus is provided, including: an interface circuit and a processor, the interface circuit is a code/data read/write interface circuit, and the interface circuit is used for receiving computer execution instructions (the computer execution instructions are stored in a memory, may be directly read from the memory, or may pass through other devices) and transmitting the computer execution instructions to the processor; the processor is used for executing computer-executable instructions to enable the communication device to execute the method of any aspect. The communication device may be the flow rate prediction device in the first aspect, or a device including the flow rate prediction device, or a device included in the flow rate prediction device, such as a chip.

In a sixth aspect, there is provided a computer readable storage medium having stored therein instructions, which when run on a communication device, cause the communication device to perform the method of the first aspect described above.

In a seventh aspect, there is provided a computer program product comprising instructions which, when run on a communication device, cause the communication device to perform the method of the first aspect.

It is to be understood that, when the communication apparatus provided in any one of the third to fifth aspects is a chip, the above-mentioned acquiring operation may be understood as inputting information.

For technical effects brought by any one of the design manners in the second aspect to the seventh aspect, reference may be made to the technical effects brought by different design manners in the first aspect, and details are not repeated herein.

Drawings

Fig. 1 is a schematic structural diagram of a PON provided by the present application;

fig. 2 is a schematic structural diagram of a flow rate prediction device provided in the present application;

fig. 3 is a schematic flowchart of a method for predicting PON port traffic according to the present application;

fig. 4 is a schematic flowchart of another PON port traffic prediction method provided in the present application;

FIG. 5 is a schematic flow chart of a method for constructing a flow prediction model according to the present application;

fig. 6 is a schematic structural diagram of another flow rate prediction device provided in the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

In the description of the present application, "plurality" means two or more than two unless otherwise specified. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of the singular or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or multiple.

In addition, in order to facilitate clear description of technical solutions of the embodiments of the present application, in the embodiments of the present application, terms such as "first" and "second" are used to distinguish the same items or similar items having substantially the same functions and actions. Those skilled in the art will appreciate that the terms "first," "second," and the like do not denote any order or importance, but rather the terms "first," "second," and the like do not denote any order or importance. Also, in the embodiments of the present application, the words "exemplary" or "such as" are used herein to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present relevant concepts in a concrete fashion for ease of understanding.

It should be appreciated that reference throughout this specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the various embodiments are not necessarily referring to the same embodiment throughout the specification. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in the various embodiments of the present application, the sequence numbers of the processes do not mean the execution sequence, and the execution sequence of the processes should be determined by the functions and the inherent logic of the processes, and should not constitute any limitation to the implementation process of the embodiments of the present application.

It should be understood that, in the present application, "when" \8230am "and" if "both refer to the corresponding processing under certain objective conditions, and do not limit the time, and do not require an action that must be determined when implemented, nor do they mean that there are other limitations.

The values shown in the tables in the present application are only examples, and may be other values, and the present application is not limited thereto. In addition, appropriate modification adjustments can be made based on the above tables, such as splitting, merging, and so forth. The names of the parameters in the tables may be other names understandable by the device, and the values or the expression of the parameters may be other values or expressions understandable by the device. When the above tables are implemented, other data structures may be used, for example, arrays, queues, containers, stacks, linear tables, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables, or hash tables may be used.

It can be understood that some optional features in the embodiments of the present application may be implemented independently without depending on other features in some scenarios, for example, a scheme based on which the optional features are currently implemented, so as to solve corresponding technical problems and achieve corresponding effects, or may be combined with other features according to requirements in some scenarios. Correspondingly, the devices provided in the embodiments of the present application may also implement these features or functions accordingly, which are not described herein again.

In this application, the same or similar parts between the respective embodiments may be referred to each other unless otherwise specified. In the embodiments and the implementation methods/implementation methods in the embodiments in the present application, unless otherwise specified or conflicting in logic, terms and/or descriptions between different embodiments and between various implementation methods/implementation methods in various embodiments have consistency and can be mutually cited, and technical features in different embodiments and various implementation methods/implementation methods in various embodiments can be combined to form new embodiments, implementation methods, or implementation methods according to the inherent logic relationships thereof. The embodiments of the present application described below do not limit the scope of the present application.

The technical scheme of the embodiment of the application can be used for various communication systems, such as a Passive Optical Network (PON).

Referring to fig. 1, a schematic structural diagram of a PON provided in an embodiment of the present application is shown. The PON includes an Optical Line Terminal (OLT), an Optical Distribution Network (ODN), and an Optical Network Terminal (ONT).

The OLT is a core component of the PON network, is used to provide an optical fiber interface of the PON network facing a user, is equivalent to a switch and a router in a conventional communication network, and is generally placed at a central office. The ONT is a customer premise equipment in the PON for providing services such as voice, data, and multimedia for a user, and may be, for example, a fiber modem. The OND is used to provide an optical transmission channel between the OLT and the ONT.

The passive Optical Distribution Network (ODN) in the PON does not contain any electronic device and electronic power supply, and is composed of passive devices such as optical splitters and the like, so that electromagnetic interference and lightning influence of external equipment are avoided, the fault rate of lines and the external equipment is reduced, the network reliability is improved, and meanwhile, the maintenance cost is saved.

The downstream port of the OLT is referred to as a PON port. The PON port is typically connected to an optical splitter in the ODN. One PON port corresponds to one optical splitter, and one optical splitter corresponds to a plurality of ONTs.

In some embodiments, the present application further provides a traffic prediction apparatus, which can be used to predict PON port traffic in the PON shown in fig. 1. It may be a general-purpose device or a special-purpose device, and the embodiment of the present application is not limited thereto.

Fig. 2 is a schematic structural diagram of a flow rate prediction apparatus 20 according to an embodiment of the present application.

The flow prediction apparatus 20 includes one or more processors 201, a communication bus 202, and at least one communication interface (which is illustrated in fig. 2 by way of example only to include a communication interface 204 and one processor 201), and optionally, may further include a memory 203.

The processor 201 may be a general-purpose Central Processing Unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more ics for controlling the execution of programs according to the present disclosure. For example, a baseband processor or a central processor. The baseband processor may be configured to process communication protocols and communication data, and the central processor may be configured to control a communication apparatus (e.g., a network device, a terminal device, a chip of the terminal device and the network device, etc.), execute a software program, and process data of the software program. In one embodiment, the processor 201 may also include a plurality of CPUs, such as CPU0 and CPU1 in fig. 2. And the processor 201 may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, or processing cores that process data, such as computer program instructions.

The communication bus 202 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 2, but that does not indicate only one bus or one type of bus. The communication bus 202 is used to connect the different components in the communication device 20 so that the different components can communicate.

The communication interface 204 is used for communicating with other devices or a communication network, such as a Radio Access Network (RAN), a Wireless Local Area Network (WLAN), and the like. Alternatively, the communication interface 204 may be a transceiver, or the like. Optionally, the communication interface 204 may also be a transceiver circuit located in the processor 201, so as to implement signal input and signal output of the processor.

The memory 203 may be a device having a storage function. Such as, but not limited to, read-only memory (ROM) or other types of static storage devices that may store static information and instructions, random Access Memory (RAM) or other types of dynamic storage devices that may store information and instructions, electrically erasable programmable read-only memory (EEPROM), compact disk read-only memory (CD-ROM) or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory may be self-contained and coupled to the processor via a communication bus 202. The memory may also be integral to the processor.

The memory 203 is used for storing computer execution instructions for executing the scheme of the application, and is controlled by the processor 201 to execute. The processor 201 is configured to execute computer-executable instructions stored in the memory 203, so as to implement the method for predicting PON port traffic provided in the embodiment of the present application.

Optionally, the computer-executable instructions in the embodiments of the present application may also be referred to as application program codes, which are not specifically limited in the embodiments of the present application.

Further, the constituent structures shown in fig. 2 do not constitute limitations on the flow rate prediction apparatus, and the flow rate prediction apparatus may include more or less components than those shown in fig. 2, or a combination of some components, or a different arrangement of components, in addition to the components shown in fig. 2.

The method provided by the embodiment of the present application will be explained below from the perspective of the flow rate prediction device 20 shown in fig. 2 with reference to the drawings.

It is to be understood that, in the embodiments of the present application, the executing subject may perform some or all of the steps in the embodiments of the present application, and these steps or operations are merely examples, and the embodiments of the present application may also perform other operations or variations of various operations. Further, the various steps may be performed in a different order presented in the embodiments of the application, and not all operations in the embodiments of the application may be performed.

As shown in fig. 3, a method for predicting PON port traffic provided in an embodiment of the present application includes the following steps:

s301, the flow prediction device acquires first current network data corresponding to the first PON port.

The first current network data includes data on the first PON port, data corresponding to the first PON port in the subsystem, data corresponding to the first PON port in an Authentication Authorization Accounting (AAA) system, and data corresponding to the first PON port in the number line system. That is, the first current network data includes data on the first PON port and data corresponding to the first PON port in the other system.

Wherein the sub-system, i.e. the operation analysis system, is used for analyzing the operation condition based on the operation data of the operator. AAA system, which is used to verify the user's identity and the network service that can be used, opens the network service to the user according to the verification result, records the user's usage of various network services, and provides them to the charging system. And the number line system is used for managing information such as a central office station, a machine room, a switch, an access network, a data network, an optical splitter, a handover device, a fixed network number resource, local network address information and the like of the communication network.

S302, the flow prediction device inputs the first current network data into the flow prediction model to obtain the predicted flow of the first PON port.

Optionally, the flow prediction model may be used to predict one or more of: the incoming peak value, the incoming average value, the outgoing peak value, or the outgoing average value, that is, the obtained predicted traffic of the first PON port may be one or more of the incoming peak value, the incoming average value, the outgoing peak value, or the outgoing average value.

Based on the scheme, the data on the PON port and the data corresponding to the PON port in the branch system, the AAA system and the wire system are input into a flow prediction model to obtain the predicted flow of the PON. When the PON port flow prediction is carried out, actual data in the existing network are used comprehensively, compared with the prior art, the PON port flow is not predicted according to experience of front-line personnel any more, the influence of human subjective factors on the predicted flow is reduced, and the error between the predicted flow and the actual flow of the PON port is reduced, so that the capacity expansion of the PON port has data basis, and the capacity expansion of the PON port can be guided more accurately and scientifically.

Further, after obtaining the predicted flow rate of the PON port, the flow rate prediction apparatus may further determine whether to perform capacity expansion according to the predicted flow rate and a fourth threshold. The following are exemplary: under the condition that the flow of the first PON port is larger than a fourth threshold value, capacity expansion is determined; determining that capacity expansion is not performed under the condition that the flow of the first PON port is smaller than a fourth threshold value; when the flow rate of the first PON port is equal to the fourth threshold, it may be determined to perform capacity expansion, or may not perform capacity expansion, or perform any operation, which is not specifically limited in this application.

As a possible implementation, the capacity expansion may be to increase the device, or may be to increase the capacity of the PON port by other means, which is not limited herein.

It should be noted that, in addition to the fourth threshold, the present application also relates to a first threshold, a second threshold, and a third threshold, which will be described in the following embodiments and will not be described herein again.

Based on the scheme, after the predicted flow of the PON port is obtained, the flow prediction apparatus may determine whether capacity expansion needs to be performed on the PON port according to the predicted flow and the fourth threshold, and when the predicted flow exceeds the threshold, it indicates that the PON port may not bear the upcoming flow, and capacity expansion needs to be performed in time, so that the PON port can bear the upcoming flow, and the influence on user experience is reduced.

Optionally, the fourth threshold may be optimized through complaint information and energy consumption information corresponding to the PON port.

For example, when complaint information of the PON port exists, it indicates that capacity expansion may not be performed on the PON port in time, which results in poor network quality and causes customer complaints. The reason why the capacity is not expanded in time may be that the fourth threshold is set too high, and the fourth threshold is not exceeded even when the predicted flow is large, so that it is determined that the capacity is not to be expanded. At this time, the fourth threshold may be lowered.

Or, when the energy consumption of the PON port is larger than the normal energy consumption, it indicates that unnecessary capacity expansion is performed on the PON port, thereby increasing the energy consumption. The reason why unnecessary expansion is performed may be that the fourth threshold value is set too low and exceeds the fourth threshold value even when the predicted flow rate is small, so that unnecessary expansion is performed. At this time, the fourth threshold may be raised.

Based on the scheme, the complaint information and the energy consumption information corresponding to the PON port are introduced to flexibly adjust the fourth threshold value, so that misjudgment is reduced.

The overall flow of the PON port traffic prediction method provided by the present application is introduced above, and the method is further described below.

Optionally, as shown in fig. 4, before step S301, the method provided by the present application further includes:

s300, the flow prediction device constructs the flow prediction model according to the second current network data. The second current network data includes data on the N PON ports, data corresponding to the N PON ports in the subsystem, data corresponding to the N PON ports in the AAA system, and data corresponding to the N PON ports in the line number system, where N is a positive integer.

As a possible implementation manner, as shown in fig. 5, the traffic prediction apparatus constructs a traffic prediction model according to the second current network data, and specifically includes the following steps:

s3001, the traffic prediction device preprocesses the second current network data to obtain K important characteristic fields, wherein K is a positive integer.

Optionally, the preprocessing the second current network data includes: merging the second current network data to obtain N pieces of data, wherein the N pieces of data comprise M characteristic fields, the N pieces of data correspond to the N PON ports one by one, and M is a positive integer greater than or equal to K; k important characteristic fields in the M characteristic fields are determined, the support degree corresponding to the important characteristic fields is larger than or equal to a first threshold, and the corresponding confidence degree is larger than or equal to a second threshold. The support degree is used for indicating the frequency of the feature fields, that is, high-frequency feature fields can be found based on the support degree of the feature fields, the frequent occurrence of the feature fields indicates that the feature fields have a large influence on the traffic, and the confidence degree is used for indicating the association rules between the feature fields.

For example, the characteristic fields referred to in this application may include a large public supplier type, an Asymmetric Digital Subscriber Line (ADSL) rate, a subscriber package, and the like, and the specific characteristic fields are not limited in this application.

Optionally, the data on the PON port and the data corresponding to the PON port in different systems may not be completely the same, or may be completely the same. The values of the same feature field are the same. For example, the data corresponding to N PON ports in a subsystem may be represented in the form shown in table 1:

TABLE 1

PON port	Characteristic field A	Characteristic field B	Characteristic field C
				PON port 1	A1	B1	C1
PON port 2	A2	B2	C2
				PON port 3	A3	B3	C3
PON port 4	A4	B4	C4
				PON port 5	A5	B5	C5

Table 1 shows data of a PON port for each row, and each column is a value of a feature field corresponding to a different PON port in the subsystem, for example, JA1 is a value of a feature field a corresponding to PON port 1.

Similarly, the data corresponding to N PON ports in the line system may be represented in the form shown in table 2:

TABLE 2

PON port	Characteristic field A	Characteristic field B	Characteristic field D
				PON port 1	A1	B1	D1
PON port 2	A2	B2	D2
				PON port 3	A3	B3	D3
PON port 4	A4	B4	D4
				PON port 5	A5	B5	D5

Table 2 shows data of one PON port per row, and each column is a value of a characteristic field corresponding to a different PON port in the number line system, for example, HA1 is a value of a characteristic field a corresponding to PON port 1.

As can be seen from tables 1 and 2, the data corresponding to N PON ports in the tributary system and the number line system respectively includes the same characteristic field a and characteristic field B, and also includes different characteristic fields C and D.

When data corresponding to a certain PON port does not include a certain characteristic field, the value of the characteristic field corresponding to the PON port is null. That is, JA1-JC5 and HA1-HD5 shown in table 1 above may have a null value, and for example, when J A2 is a null value, it indicates that the data corresponding to PON port 2 in the distributed system does not include the characteristic field a.

It can be understood that the forms of the data on the N PON ports and the data corresponding to the N PON ports in the AAA system are similar to those shown in tables 1 and 2, and are not described herein again.

As a possible implementation, merging the second current network data may specifically include: and determining all the characteristic fields corresponding to each PON port and the values of the characteristic fields. Exemplarily, based on the examples shown in table 1 and table 2, as shown in table 3, the data corresponding to the N PON ports in the combined sub-system and number line system are:

TABLE 3

For example, the feature field corresponding to PON port 1 in the data of the subsystem includes feature field a, feature field B, and feature field C, the feature field corresponding to PON port 1 in the data of the wire system includes feature field a, feature field B, and feature field D, and the feature field corresponding to PON port 1 after combination includes feature field a, feature field B, feature field C, and feature field D.

The above is only described by taking data merging of two systems as an example, and in the actual merging, the feature fields corresponding to the PON port on one PON port and in different systems are merged, which is not described herein again.

As a possible implementation, determining K important feature fields in the M feature fields may specifically include: and calculating the support degree and the confidence degree of each characteristic field in the M characteristic fields, and determining that a certain characteristic field is an important characteristic field when the support degree of the certain characteristic field is greater than or equal to a first threshold and the confidence degree is greater than or equal to a second threshold. The support degree is used for indicating the frequency of the appearance of the characteristic field, and when the support degree of the characteristic field is greater than or equal to a first threshold value, the support degree indicates that the frequency of the appearance of the characteristic field is higher; the confidence level is used for indicating the association rule between the characteristic fields, and when the confidence level of a characteristic field is greater than or equal to a second threshold value, the characteristic field is indicated to have closer relation with other characteristic fields.

Optionally, taking the example that the M characteristic fields include the first characteristic field, the support degree of the first characteristic field may be determined by the number of data pieces including the first characteristic field in the N pieces of data, and the total number N of data pieces.

Illustratively, the support degree of the first characteristic field, the number of data pieces including the first characteristic field in the N pieces of data, and the total number of data pieces N may satisfy:

the support of the first feature field = number of pieces of data including the first feature field/total number of pieces of data N.

Based on the example shown in table 3, if (A1), (A2), and (A5) are not null values, and (A3) and (A4) are null values, the number of pieces of data including the feature field a is 3, the total number of pieces of data is 5, and the support degree of the feature field a =3/5.

Optionally, the confidence of the first feature field is determined by the number of pieces of data including the first feature field and the second feature field, and the number of pieces of data including the first feature field, and the second feature field includes at least one feature field.

Illustratively, the confidence of the first feature field, the number of pieces of data comprising the first feature field and the second feature field, and the number of pieces of data comprising the first feature field may satisfy:

confidence of the first feature field = number of pieces of data including the first feature field and the second feature field/number of pieces including the first feature field

The second characteristic field may include one characteristic field or a plurality of characteristic fields. Based on the example shown in table 3, if the second feature field includes the feature field B, if (A1), (A2), (A5), (B1), (B5) are not null values, and (A3), (A4), (B2), (B3), (B4) are null values, the number of pieces of data including the feature field a and including the feature field B is 2, the number of pieces including the first feature field is 3, and the confidence of the feature field a =2/3. When the second feature field includes a plurality of feature fields, the confidence level calculation method of the feature field a is similar to the method, and is not described herein again.

Optionally, in step S3001, the important feature field may also be mined by using an association rule algorithm (apriori), a frequent pattern-growth algorithm (FP-growth), and the like, which is not limited in this application.

S3002, the flow prediction device divides L flow intervals according to the number of users, and determines important characteristic fields corresponding to the L flow intervals respectively, wherein L is a positive integer.

Optionally, in the L flow intervals, a difference between the number of users corresponding to the first flow interval and the number of users corresponding to the second flow interval is less than or equal to a third threshold; the first flow rate section is a flow rate section in which the number of corresponding users is the largest, and the second flow rate section is a flow rate section in which the number of corresponding users is the smallest. That is, the number of users corresponding to the L traffic intervals is almost the same.

For example, the flow intervals may be divided for different flow types, for example, L flow intervals may be divided for an outflow mean, an outflow peak, an inflow mean, and an inflow peak. The flow rate interval is divided by taking the outflow average value as an example, and the method for dividing the flow rate interval by the outflow peak value, the inflow average value and the inflow peak value is similar to the above, and is not described herein again.

First, an initial outflow mean interval may be determined, and the number of users in each initial outflow mean interval may be counted. For example, taking the unit of traffic as megabits per second (Mb/s) as an example, the initial outgoing mean interval may include: 0 to 100Mb/s, 100 to 200Mb/s, 200 to 300Mb/s, and the like. Then, each initial outflow average value interval is subdivided into L flow rate intervals, so that the number of users corresponding to each flow rate interval is basically the same. In this way, the data volume of each interval for training can be ensured to be basically the same, and the data balance is ensured.

Optionally, taking that the L traffic intervals include the first traffic interval as an example, the value of the important characteristic field corresponding to the first traffic interval includes the value of the important characteristic field corresponding to the second PON port, and the traffic of the second PON port is located in the first traffic interval. That is, the value of the important characteristic field corresponding to each traffic interval is the value of the important characteristic field corresponding to the PON port whose traffic is located in the traffic interval. There may be one or more PON ports located in the traffic interval.

For example, based on the example shown in table 3, if the outgoing mean values corresponding to PON port 1 and PON port 2 are within the outgoing mean value interval 1, the outgoing mean value corresponding to PON port 3 is within the outgoing mean value interval 2, the outgoing mean values corresponding to PON port 4 and PON port 5 are within the outgoing mean value interval 3, and the form of the important feature field corresponding to L traffic intervals refers to table 4:

TABLE 4

Optionally, in step S3002, the L traffic intervals may be divided according to the number of samples by using a synthesis timing over sampling technique (SMOTE) algorithm, a median method, and an average method, which are not limited in this application.

S3003, the flow prediction device constructs a decision tree according to the values of the important characteristic fields corresponding to the L flow intervals respectively, and obtains the weight of the K important characteristic fields.

For example, the information entropy and the information gain of each important feature field can be calculated, and the important feature field with the largest information gain is selected as the root node of the decision tree. And then, in other important characteristic fields except the important characteristic field serving as the root node, the important characteristic field with the largest information gain is used as a child node of the root node, and so on until the construction of the decision tree is completed, so that the leaf node outputs the weight of the important characteristic field.

Based on the scheme, as the information gain is larger and the distinguishing capability is stronger, all important data features can be distinguished through fewer decision tree levels. Therefore, by selecting the important feature field with the largest information gain as the root node, the hierarchy of the decision tree can be reduced, the capability of the decision tree for distinguishing the important feature fields is enhanced, and the efficiency of the decision tree for classifying the important feature fields is improved.

The calculation formula of the information entropy is as follows:

x is the value of the important characteristic field X, and pi is the probability of each value in the important characteristic field being taken. H (X) is the information entropy of the significant features field X.

The calculation formula of the information gain is as follows:

s is a set of values of all important characteristic fields, T is a set of all values of the important characteristic fields T in the set S, IG (S | T) is information gain of the important characteristic fields T in the set S, sv is a set of values v in the important characteristic fields T, and the absolute value of the Sv is the number of values v in the important characteristic fields T.

Optionally, the weight of the important feature field may also be obtained by using a random forest, a Gradient Boosting Decision Tree (GBDT), and a classification and regression tree (CART), which is not limited in the present application.

And S3004, the flow prediction device determines a flow prediction model according to the weight of the K important characteristic fields.

Illustratively, the traffic prediction model may be a function of the weights of the K significant features fields.

Based on the scheme, the influence degree of the K important characteristic fields on the flow can be determined, and then a flow prediction model is constructed to predict the flow of the PON port.

In some embodiments, in step S3002, it may further add, as a new important characteristic field, whether the PON port located in the traffic interval is a high-traffic PON port, to the important characteristic field corresponding to the traffic interval.

Optionally, the flows corresponding to all PON ports may be sequenced from high to low, and the PON port with the flow located in the first 10% is determined as a high-flow PON port. For example, the outflow averages corresponding to all PON ports are sorted from high to low, and the PON ports with the outflow average in the first 10% are high-flow PON ports. In addition, the high-flow PON port may also be determined according to the outflow peak value, the inflow average value, and the inflow peak value, and reference may be made to a manner of determining the high-flow PON port according to the outflow average value, which is not described herein again.

For example, based on the example shown in table 3, taking as an example that it is determined according to the outflow average value whether the high-flow PON port, the high-flow PON port correspond to the high-flow PON port with the value of 1, and whether the other PON ports correspond to the high-flow PON ports with the value of 0, if the outflow average values corresponding to PON ports 1 and 2 are within the outflow average value interval 1, the outflow average value corresponding to PON port 3 is within the outflow average value interval 2, the outflow average values corresponding to PON ports 4 and 5 are within the outflow average value interval 3, and the form of the important feature fields corresponding to L flow intervals refers to table 5:

TABLE 5

In this scenario, in S3003, the traffic prediction apparatus constructs a decision tree according to the values of the important characteristic fields corresponding to the L traffic intervals, and obtains the weights of the K important characteristic fields and the weight of whether the K important characteristic fields are the weights of the high-traffic PON port.

In S3004, the traffic prediction apparatus determines a traffic prediction model based on the weight of the K significant feature fields and the weight of whether or not the K significant feature fields are high-traffic PON ports.

Under the scene, K important characteristic fields and whether the K important characteristic fields are different influence degrees of the high-flow PON port on the flow can be determined, and whether the PON port is the high-flow PON port or not is further considered during flow prediction, so that the error of flow prediction is further reduced.

It can be understood that, in step S3003, when the flow type of the flow interval is the outflow average value, the flow prediction model may be used to predict the outflow average value of the PON port. Similarly, when the flow type of the flow interval is an outflow peak value, an inflow average value, or an inflow peak value, the flow prediction model may be used to predict the outflow peak value, the inflow average value, or the inflow peak value of the PON port, respectively.

Optionally, after the flow prediction model is determined, complaint information and energy consumption information corresponding to the PON port may also be introduced to optimize the flow prediction model. The complaint information is used for indicating complaints of network quality of the PON port by users, and the energy consumption information is used for indicating energy consumed by the PON port.

For example, the optimizing the traffic prediction model may specifically include: and acquiring third current network data, executing the steps similar to the steps S3001-S3004, and constructing an optimized flow prediction model. The third current network data includes: complaint information and energy consumption information corresponding to the N PON ports respectively, data on the N PON ports, data corresponding to the N PON ports in the subsystem system respectively, data corresponding to the N PON ports in the AAA system and data corresponding to the N PON ports in the wire system are determined, and an optimized flow prediction model containing the complaint information and the energy consumption information weight is determined.

Based on the scheme, the weights of all important characteristic fields are flexibly adjusted by introducing complaint information and energy consumption information corresponding to the PON port, and the error between the predicted flow and the actual flow of the PON port is further reduced.

The actions implemented by the flow prediction apparatus in the above embodiment may be executed by the processor 201 in the flow prediction apparatus 20 shown in fig. 2 calling an application program code stored in the memory 203 to instruct the flow prediction apparatus to perform, which is not limited in this embodiment.

It is to be understood that, in the above embodiments, the method and/or the steps implemented by the flow prediction apparatus may also be implemented by a component (e.g., a chip or a circuit) that can be used for the flow prediction apparatus.

The above description mainly introduces the solution provided in the present application from the perspective of a flow prediction device. Correspondingly, the application also provides a communication device which is used for realizing the various methods. The communication device may be the flow prediction device in the above method embodiment, or a device including the above flow prediction device, or a component that can be used in the flow prediction device.

It is understood that the flow prediction device includes hardware structures and/or software modules for performing the above functions. Those of skill in the art will readily appreciate that the various illustrative elements and steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiment of the present application, the flow prediction apparatus may be divided into functional modules according to the method embodiment, for example, each functional module may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. It should be noted that, in the embodiment of the present application, the division of the module is schematic, and is only one logic function division, and there may be another division manner in actual implementation.

In an implementation scenario, taking the flow prediction apparatus in the above method embodiment as an example, fig. 6 shows a schematic structural diagram of a flow prediction apparatus 60. The flow prediction apparatus 60 includes a processing module 601 and an obtaining module 602.

In some embodiments, the flow prediction device 60 may also include a memory module (not shown in fig. 6) for storing program instructions and data.

As an example:

an obtaining module 602, configured to obtain first current network data; the processing module 601 is configured to input the first current network data into the traffic prediction model to obtain the traffic of the first PON port. The first current network data comprises data on a first PON port, data corresponding to the first PON port in the subsystem, data corresponding to the first PON port in the authentication, authorization and accounting AAA system, and data corresponding to the first PON port in the number line system.

Optionally, the processing module 601 is further configured to construct a traffic prediction model according to second current network data, where the second current network data includes data on N PON ports, data corresponding to the N PON ports in the subsystem, data corresponding to the N PON ports in the AAA system, and data corresponding to the N PON ports in the number line system, and N is a positive integer.

Optionally, the processing module 601 is further configured to construct a traffic prediction model according to the second current network data, where the traffic prediction model includes: the processing module 601 is further configured to pre-process the second current network data to obtain K important feature fields; the processing module 601 is further configured to divide L traffic intervals according to the number of users, and determine important feature fields corresponding to the L traffic intervals respectively; the processing module 601 is further configured to construct a decision tree according to the important feature fields corresponding to the L traffic intervals, respectively, and obtain weights of the K important feature fields; the processing module 601 is further configured to determine a flow prediction model according to the weights of the K important feature fields, where K and L are positive integers.

Optionally, the processing module 601 is further configured to perform preprocessing on the second current network data, including: the processing module 601 is further configured to merge the second current network data to obtain N pieces of data; the processing module 601 is further configured to determine K important feature fields in the M feature fields. The N pieces of data comprise M characteristic fields, the N pieces of data correspond to the N PON ports one by one, M is a positive integer larger than or equal to K, the support degree corresponding to the important characteristic fields is larger than or equal to a first threshold value, the confidence degree corresponding to the important characteristic fields is larger than or equal to a second threshold value, the support degree is used for indicating the frequency of the characteristic fields, and the confidence degree is used for indicating association rules among the characteristic fields.

Optionally, the M characteristic fields include a first characteristic field, and the support degree of the first characteristic field is determined by the number of data pieces including the first characteristic field in the N pieces of data, and the total number of data pieces N; the confidence of the first feature field is determined by the number of pieces of data including the first feature field and the second feature field, and the number of pieces of data including the first feature field, in the N pieces of data, and the second feature field includes at least one feature field.

Optionally, in the L traffic intervals, a difference between the number of users corresponding to the first traffic interval and the number of users corresponding to the second traffic interval is smaller than or equal to a third threshold; the first flow rate section is a flow rate section in which the number of corresponding users is the largest, and the second flow rate section is a flow rate section in which the number of corresponding users is the smallest.

Optionally, the L traffic intervals include a first traffic interval, the important feature field corresponding to the first traffic interval includes an important feature field corresponding to the second PON port, and the traffic of the second PON port is located in the first traffic interval.

Optionally, the processing module 601 is further configured to optimize the flow prediction model according to the complaint information and the energy consumption information corresponding to the PON port.

Optionally, the processing module 601 is further configured to determine to perform capacity expansion when the flow rate of the first PON port is greater than a fourth threshold; the processing module is further configured to determine that capacity expansion is not performed when the flow rate of the first PON port is smaller than a fourth threshold.

All relevant contents of each step related to the above method embodiment may be referred to the functional description of the corresponding functional module, and are not described herein again.

In the present application, the flow prediction apparatus 60 is presented in the form of dividing each functional module in an integrated manner. A "module" herein may refer to a specific application-specific integrated circuit (ASIC), an electronic circuit, a processor and memory that execute one or more software or firmware programs, an integrated logic circuit, and/or other devices that may provide the described functionality.

As an example, the functions/implementation processes of the processing module 601 in fig. 6 may be implemented by the processor 201 in the flow prediction apparatus 20 shown in fig. 2 calling a computer executing instructions stored in the memory 203. The function/implementation of the obtaining module 602 may be implemented by the communication interface 204 in the flow prediction apparatus 20 shown in fig. 2.

In some embodiments, when the flow prediction apparatus 60 in fig. 6 is a chip or a chip system, the function/implementation process of the obtaining module 602 may be implemented by an input/output interface (or a communication interface) of the chip or the chip system, and the function/implementation process of the processing module 601 may be implemented by a processor (or a processing circuit) of the chip or the chip system.

Since the flow prediction apparatus 60 provided in this embodiment can execute the above method, the technical effects obtained by the flow prediction apparatus can refer to the above method embodiment, and are not described herein again.

As one possible product form, the flow rate prediction device according to the embodiment of the present application may be realized by using: one or more Field Programmable Gate Arrays (FPGAs), programmable Logic Devices (PLDs), controllers, state machines, gate logic, discrete hardware components, any other suitable circuitry, or any combination of circuitry capable of performing the various functions described throughout this application.

In some embodiments, an embodiment of the present application further provides a communication device, which includes a processor and is configured to implement the method in any of the method embodiments described above.

As a possible implementation, the communication device further comprises a memory. The memory for storing the necessary program instructions and data, the processor may call the program code stored in the memory to instruct the communication device to perform the method of any of the method embodiments described above. Of course, the memory may not be in the communication device.

As another possible implementation, the communication device further includes an interface circuit, which is a code/data read/write interface circuit, and the interface circuit is used to receive computer execution instructions (the computer execution instructions are stored in the memory, may be directly read from the memory, or may pass through other devices) and transmit the computer execution instructions to the processor.

As yet another possible implementation, the communication device further includes a communication interface for communicating with a module external to the communication device.

It is to be understood that the communication device may be a chip or a chip system, and when the communication device is a chip system, the communication device may be formed by a chip, or may include a chip and other discrete devices, which is not specifically limited in this embodiment of the present application.

The present application also provides a computer-readable storage medium having stored thereon a computer program or instructions which, when executed by a computer, implement the functionality of any of the above-described method embodiments.

The present application also provides a computer program product which, when executed by a computer, implements the functionality of any of the method embodiments described above.

For convenience and simplicity of description, a person of ordinary skill in the art may refer to corresponding processes in the foregoing method embodiments for specific working processes of the above-described systems, apparatuses, and units, which are not described herein again.

It will be appreciated that the systems, apparatus and methods described herein may be implemented in other ways. For example, the above described embodiments of the flow prediction apparatus are merely illustrative, and for example, the division of the units is only one logical functional division, and the actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, may be located in one place, or may be distributed over a plurality of network units. The components displayed as a unit may or may not be a physical unit. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

In the above embodiments, all or part of the implementation may be realized by software, hardware, firmware, or any combination thereof. When implemented using a software program, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions described in accordance with the embodiments of the present application are all or partially generated upon loading and execution of computer program instructions on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or can comprise one or more data storage devices, such as a server, a data center, etc., that can be integrated with the medium. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), among others. In the embodiment of the present application, the computer may include the foregoing apparatus.

While the present application has been described in connection with various embodiments, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from a review of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

Although the present application has been described in conjunction with specific features and embodiments thereof, it will be evident that various modifications and combinations can be made thereto without departing from the spirit and scope of the application. Accordingly, the specification and figures are merely exemplary of the present application as defined in the appended claims and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. A method for predicting the PON port flow of a Passive Optical Network (PON), which is characterized by comprising the following steps:

acquiring first current network data, wherein the first current network data comprises data on a first PON port, data corresponding to the first PON port in a subsystem, data corresponding to the first PON port in an authentication, authorization and accounting (AAA) system and data corresponding to the first PON port in a line number system;

inputting the first current network data into a flow prediction model to obtain the flow of the first PON port;

constructing the flow prediction model according to second existing network data, wherein the second existing network data comprises data on N PON ports, data corresponding to the N PON ports in the branching system respectively, data corresponding to the N PON ports in the AAA system respectively and data corresponding to the N PON ports in the number line system respectively, and N is a positive integer;

according to the second current network data, constructing the flow prediction model, which comprises the following steps:

preprocessing the second current network data to obtain K important characteristic fields, wherein K is a positive integer;

dividing L flow intervals according to the number of users, and determining the values of the K important characteristic fields corresponding to the L flow intervals respectively, wherein L is a positive integer;

constructing a decision tree according to the values of the important characteristic fields corresponding to the L flow intervals respectively to obtain the weights of the K important characteristic fields;

and determining the flow prediction model according to the weights of the K important characteristic fields.

2. The method of claim 1, wherein pre-processing the second live data comprises:

merging the second current network data to obtain N pieces of data, wherein the N pieces of data comprise M characteristic fields, the N pieces of data correspond to the N PON ports one by one, and M is a positive integer greater than or equal to K;

determining the K important characteristic fields in the M characteristic fields, wherein the support degree corresponding to the important characteristic fields is greater than or equal to a first threshold value, and the confidence degree corresponding to the important characteristic fields is greater than or equal to a second threshold value, the support degree is used for indicating the frequency of the appearance of the characteristic fields, and the confidence degree is used for indicating the association rule between the characteristic fields.

3. The method according to claim 2, wherein the M feature fields include a first feature field, and wherein a degree of support of the first feature field is determined by a number of pieces of data including the first feature field in the N pieces of data, and a total number N of pieces of data;

the confidence of the first feature field is determined by the number of pieces of data including the first feature field and a second feature field, which includes at least one feature field, in the N pieces of data and the number of pieces of data including the first feature field.

4. The method according to any one of claims 1 to 3, wherein in the L traffic intervals, the difference between the number of users corresponding to the first traffic interval and the number of users corresponding to the second traffic interval is less than or equal to a third threshold; the first flow rate interval is a flow rate interval in which the number of corresponding users is the largest, and the second flow rate interval is a flow rate interval in which the number of corresponding users is the smallest.

5. The method according to any of claims 1-3, wherein the L traffic intervals comprise a first traffic interval, wherein the value of the importance characteristic field corresponding to the first traffic interval comprises the value of the importance characteristic field corresponding to a second PON port, and wherein the traffic of the second PON port is located in the first traffic interval.

6. The method according to any one of claims 1-3, further comprising:

and optimizing the flow prediction model according to the complaint information and the energy consumption information corresponding to the PON port.

7. The method according to any one of claims 1-3, further comprising:

when the flow of the first PON port is larger than a fourth threshold value, capacity expansion is determined;

and under the condition that the flow of the first PON port is smaller than a fourth threshold value, determining not to expand the capacity.

8. A flow rate prediction apparatus, characterized by comprising: the device comprises an acquisition module and a processing module;

the acquisition module is used for acquiring first current network data, wherein the first current network data comprises data on a first PON port, data corresponding to the first PON port in a subsystem, data corresponding to the first PON port in an authentication, authorization and accounting (AAA) system and data corresponding to the first PON port in a line number system;

the processing module is configured to input the first current network data into a traffic prediction model to obtain a traffic of the first PON port;

the processing module is further configured to construct the traffic prediction model according to second existing network data, where the second existing network data includes data on N PON ports, data corresponding to the N PON ports in the transit subsystem, data corresponding to the N PON ports in the AAA system, and data corresponding to the N PON ports in the number line system, and N is a positive integer;

the processing module is further configured to construct the traffic prediction model according to the second current network data, and includes:

the processing module is further configured to pre-process the second current network data to obtain K important feature fields, where K is a positive integer;

the processing module is further configured to divide L traffic intervals according to the number of users, and determine values of K important feature fields corresponding to the L traffic intervals, where L is a positive integer;

the processing module is further configured to construct a decision tree according to the values of the important feature fields corresponding to the L traffic intervals, respectively, to obtain weights of the K important feature fields;

the processing module is further configured to determine the flow prediction model according to the weights of the K important feature fields.

9. The apparatus of claim 8, wherein the processing module is further configured to pre-process the second existing network data, and comprises:

the processing module is further configured to merge the second current network data to obtain N pieces of data, where the N pieces of data include M feature fields, the N pieces of data correspond to the N PON ports one to one, and M is a positive integer greater than or equal to K;

the processing module is further configured to determine the K important feature fields in the M feature fields, where a support degree corresponding to the important feature fields is greater than or equal to a first threshold, and a confidence degree corresponding to the important feature fields is greater than or equal to a second threshold, where the support degree is used to indicate a frequency of occurrence of the feature fields, and the confidence degree is used to indicate an association rule between the feature fields.

10. The apparatus according to claim 9, wherein the M feature fields include a first feature field, and wherein a support degree of the first feature field is determined by a number of pieces of data including the first feature field in the N pieces of data, and a total number of pieces of data N;

11. The apparatus according to any one of claims 8 to 10, wherein, in the L traffic intervals, a difference between the number of users corresponding to a first traffic interval and the number of users corresponding to a second traffic interval is less than or equal to a third threshold; the first flow rate interval is a flow rate interval in which the number of corresponding users is the largest, and the second flow rate interval is a flow rate interval in which the number of corresponding users is the smallest.

12. The apparatus according to any of claims 8-10, wherein the L traffic intervals comprise a first traffic interval, and wherein the value of the significance signature field corresponding to the first traffic interval comprises the value of the significance signature field corresponding to a second PON port, and wherein the traffic of the second PON port is located in the first traffic interval.

13. The apparatus according to any one of claims 8 to 10,

and the processing module is further used for optimizing the flow prediction model according to the complaint information and the energy consumption information corresponding to the PON port.

14. The apparatus according to any one of claims 8 to 10,

the processing module is further configured to determine to perform capacity expansion when the flow rate of the first PON port is greater than a fourth threshold;

the processing module is further configured to determine not to perform capacity expansion when the flow rate of the first PON port is smaller than a fourth threshold.

15. A communication apparatus, characterized in that the communication apparatus comprises: at least one processor;

the processor for executing a computer program or instructions to cause the communication device to perform the method of any of claims 1-7.

16. A computer-readable storage medium, in which a computer program or instructions are stored which, when executed by a communication apparatus, carry out the method of any one of claims 1-7.