Dynamic bandwidth allocation method and device based on FTTR-B architecture, medium and equipment

Abstract

The invention discloses a dynamic bandwidth allocation method and device based on an FTTR-B framework, a medium and equipment, and the method comprises the steps: uploading local traffic characteristics of slave gateways to a main gateway in real time, and generating a global traffic prediction result through a global traffic prediction model; based on the global traffic prediction result, the master gateway performs primary bandwidth allocation on each slave gateway through a first bandwidth allocation model; the link quality of each slave gateway is monitored in real time, a link state evaluation result is generated, and the master gateway performs secondary bandwidth allocation on each slave gateway through a second bandwidth allocation model based on the link state evaluation result; and based on the dynamic secondary bandwidth allocation result, each slave gateway calculates and adjusts the bandwidth reservation proportion of the local service. According to the invention, the bandwidth allocation precision can be improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of optical fiber communication network, and particularly relates to a dynamic bandwidth allocation method and device based on an FTTR-B architecture, a medium and equipment. BACKGROUND

[0002] The existing FTTR (fiber to the room) dynamic bandwidth allocation method is mainly based on a static priority or a fixed cycle polling mechanism, and has significant limitations. First, in the case of a bursty traffic scenario (such as VR / AR high bandwidth, low latency service), the existing method lacks the ability to predict future traffic, and cannot effectively predict and adapt to the instantaneous traffic peak, resulting in increased network latency jitter, which seriously affects the user experience. Secondly, the traditional scheme adopts a fixed optical power allocation strategy, which causes energy waste at low load and easy signal interference at high load, making it difficult to balance energy efficiency and interference suppression; in addition, the existing technology lacks a cross-layer coordination mechanism, and the MAC layer bandwidth allocation and the physical layer optical parameter optimization (such as wavelength tuning and power control) are independent of each other, resulting in low resource utilization and failing to fully exploit the performance potential of the FTTR architecture. These problems jointly restrict the network service quality and energy efficiency performance in high dynamic and high concurrency scenarios. SUMMARY

[0003] In view of the deficiencies in the prior art, the purpose of the present application is to provide a dynamic bandwidth allocation method and device based on an FTTR-B architecture, which can improve the accuracy of bandwidth allocation.

[0004] To achieve the above-mentioned purpose, the present application provides the following technical solutions: A dynamic bandwidth allocation method based on an FTTR-B architecture, the method comprising: uploading local traffic characteristics of each slave gateway to a master gateway in real time, and generating a global traffic prediction result through a global traffic prediction model; based on the global traffic prediction result, the master gateway performs a first bandwidth allocation to each slave gateway through a first bandwidth allocation model; monitoring the link quality of each slave gateway in real time to generate a link state evaluation result, and the master gateway performs a second bandwidth allocation to each slave gateway based on the link state evaluation result and through a second bandwidth allocation model; and based on the second bandwidth allocation result, each slave gateway calculates an adjustment of the bandwidth reservation ratio of the local service.

[0005] Optionally, the global traffic prediction model comprises a local LSTM module, a federated aggregation module and a global prediction module, wherein the LSTM module is used to upload the local traffic characteristics of each slave gateway to the master gateway; the federated aggregation module is used to weight and aggregate the local traffic characteristics of each slave gateway; and the global prediction module is used to predict the global traffic based on the weighted and aggregated local traffic characteristics.

[0006] Optionally, the second bandwidth allocation model comprises a chaotic disturbance generation module, a dynamic fitness module, a bandwidth allocation rule module and a constraint condition module, wherein the chaotic disturbance generation module is configured to generate unpredictable chaotic disturbance factors; the dynamic fitness module is configured to calculate the fitness value of each node based on the chaotic disturbance factors; the bandwidth allocation rule module is configured to allocate the total bandwidth in proportion according to the fitness value of each node; and the constraint condition module is configured to force the bandwidth allocated by the bandwidth allocation rule module to meet the minimum bandwidth requirement.

[0007] Optionally, the bandwidth reservation proportion of the local services of each slave gateway is dynamically calculated based on the secondary bandwidth allocation result, comprising: receiving the secondary bandwidth allocation value of the master gateway; identifying the types of the local services and recording the priority and delay sensitivity of each service through a traffic probe; dynamically calculating the bandwidth reservation weight of each service based on the priority and delay sensitivity of each service; and calculating the reservation bandwidth proportion of each service according to the bandwidth reservation weight of each service.

[0008] The application also provides a dynamic bandwidth allocation device based on the FTTR-B architecture, comprising: a prediction module configured to upload the local traffic characteristics of each slave gateway to the master gateway in real time, and generate a global traffic prediction result through a global traffic prediction model; a first allocation module configured to perform primary bandwidth allocation on each slave gateway through a first bandwidth allocation model based on the global traffic prediction result; a second allocation module configured to monitor the link quality of each slave gateway in real time, generate a link state evaluation result, and perform secondary bandwidth allocation on each slave gateway based on the link state evaluation result through a second bandwidth allocation model; and a calculation adjustment module configured to dynamically calculate the bandwidth reservation proportion of the local services of each slave gateway based on the secondary bandwidth allocation result.

[0009] Optionally, the calculation adjustment module comprises: a receiving submodule configured to receive the secondary bandwidth allocation value of the master gateway; an identifying submodule configured to identify the types of the local services and record the priority and delay sensitivity of each service through a traffic probe; a bandwidth reservation weight calculation submodule configured to dynamically calculate the bandwidth reservation weight of each service based on the priority and delay sensitivity of each service; and a reservation bandwidth calculation submodule configured to calculate the reservation bandwidth proportion of each service according to the bandwidth reservation weight of each service.

[0010] The application also provides a storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method of any one of the preceding claims.

[0011] The application also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of the preceding claims when executing the program.

[0012] Compared with the prior art, the application brings the beneficial effects that: The application realizes efficient adaptation to burst traffic by collecting local traffic characteristics of each slave gateway in real time and using a global traffic prediction model to predict global traffic, combining primary bandwidth allocation and secondary dynamic allocation, significantly reduces network delay jitter, and optimizes energy efficiency and interference management through link quality monitoring and dynamic weight adjustment, improves cross-layer resource collaborative utilization, thereby balancing bandwidth allocation accuracy, service quality and energy efficiency in high concurrency and high dynamic scenarios, and improving user experience. BRIEF DESCRIPTION OF DRAWINGS

[0013] Figure 1 is a flow diagram of a dynamic bandwidth allocation method based on the FTTR-B architecture provided by an embodiment of the application; Figure 2 is a structural diagram of a dynamic bandwidth allocation device based on the FTTR-B architecture provided by another embodiment of the application; Figure 3 is a structural diagram of a storage medium provided by another embodiment of the application; Figure 4 is a structural diagram of an electronic device provided by another embodiment of the application. DETAILED DESCRIPTION

[0014] The specific embodiments of the application will be described in detail below with reference to the accompanying drawings. Although specific embodiments of the application are shown in the drawings, it should be understood that the application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the application and to fully convey the scope of the application to those skilled in the art.

[0015] It should be noted that some terms are used in the specification and claims to refer to specific components. Those skilled in the art should understand that the same component can be referred to by different terms. The specification and claims of this specification do not distinguish components based on differences in terms, but rather on differences in function. As mentioned throughout the specification and claims, "including" or "including" is an open term, which should be interpreted as "including but not limited to". The subsequent description of the specification is a preferred embodiment of the application, which is for the purpose of the general principles of the specification, and is not intended to limit the scope of the application. The scope of protection of the application is defined by the appended claims.

[0016] For the convenience of understanding the embodiments of the present application, the following will be further explained and described with specific embodiments as examples in conjunction with the accompanying drawings, and each drawing does not constitute a limitation to the embodiments of the present application.

[0017] Figure 1 is a dynamic bandwidth allocation method based on FTTR-B architecture provided by an exemplary embodiment of the present application, as shown in the figure, the method comprises the following steps: Figure 1 S100: uploading local traffic characteristics (such as mean, variance and peak period) of each slave gateway to the master gateway in real time, and generating global traffic prediction results through a global traffic prediction model; S200: based on the global traffic prediction results, the master gateway performs primary bandwidth allocation to each slave gateway through a first bandwidth allocation model; S300: real-time monitoring of link quality (including bit error rate, signal-to-noise ratio and interference strength) of each slave gateway, generating link state evaluation results (including current available bandwidth, stability level, interference frequency band and fault alarm), and the master gateway performs secondary bandwidth allocation to each slave gateway based on the link state evaluation results and through a second bandwidth allocation model; S400: based on the secondary bandwidth allocation results, each slave gateway dynamically adjusts the bandwidth reservation ratio of local services.

[0018] The present application can improve the bandwidth allocation accuracy in high concurrency and high dynamic scenarios by performing global traffic prediction and combining primary bandwidth allocation and secondary bandwidth allocation, thereby improving user experience.

[0019] In another exemplary embodiment, in step S100, the global prediction model comprises: a local LSTM module, a federal aggregation module and a global prediction module. The local LSTM module is used to upload local traffic characteristics of each slave gateway to the master gateway, and the local LSTM module is specifically represented as:

[0020]

[0021]

[0022]

[0023]

[0024]

[0025] wherein, , , ​respectively represent the activation values of the forget gate, the input gate and the output gate; represents a candidate memory cell, and represents new information at the current time step; represents a memory cell at the current time step, updated by the forget gate and the input gate; represents a hidden state at the previous time step; represents a hidden state at the current time step; all represent bias terms, used to adjust the activation threshold of each gate; all represent weight matrices, corresponding to the phenomenological transformation parameters of each gate, respectively; represents the spatio-temporal attention weight.

[0026] The federated aggregation module is configured to aggregate the local traffic features of each slave gateway by weighting, and the federated aggregation module is specifically represented as:

[0027] wherein, represents the global model parameter after aggregation, used for global prediction of the master gateway; represents the local model parameter of the th slave gateway; represents the bit error rate of the th slave gateway; represents the total number of slave gateways participating in federated learning; represents the bit error rate of the th slave gateway.

[0028] The global prediction module is configured to predict the global traffic based on the local traffic features after weighting aggregation, and the global prediction module is specifically represented as:

[0029]

[0030] wherein, is a time series attention weight, calculated by a function, representing the importance of different time points to prediction; represents a global hidden state sequence after federated aggregation, covering historical states within a time window ; and represents an attention weight matrix, used to map the hidden state to a weight score; ​​​​​​​MLP, multi-layer perceptron ; denotes the predicted time step.

[0031] That is, the formula represents the prediction at time point , by weighting and summing the global hidden states of the previous time steps, and inputting them into a multi-layer perceptron , to obtain the prediction result at a future time point .

[0032] In the global prediction model, the federal aggregation module can realize the differential fusion of the local model parameters of each slave gateway by introducing the bit error rate weighting mechanism. The aggregation expression can effectively suppress the interference of high bit error rate nodes on the global model performance, and enhance the robustness and generalization ability of the system. This mechanism ensures that even in a distributed environment with uneven link quality, the global representation aggregated can still reflect the main real traffic trend.

[0033] The global prediction module takes the aggregated global hidden state sequence as input, combines the time attention mechanism, dynamically evaluates the influence degree of each state in the historical time sequence on the future traffic, and performs nonlinear mapping on the weighted result through a multi-layer perceptron (MLP) to output the prediction value. This module combines the advantages of time importance modeling and nonlinear feature extraction, and can significantly improve the response ability and prediction accuracy of sudden traffic changes, ensuring that the bandwidth allocation decision is more forward-looking and adaptive. In summary, the two modules cooperate with the local LSTM module to make the global prediction model balance data heterogeneity and prediction accuracy while ensuring privacy.

[0034] In another exemplary embodiment, in step S300, the first bandwidth allocation model is represented as follows:

[0035] wherein, denotes the need to adjust the decision variable to maximize the value of the objective function; denotes the service priority of the th slave gateway at time ; denotes the throughput obtained by the th slave gateway; denotes the penalty for the actual bandwidth deviating from the predicted demand of the th slave gateway, to ensure that the allocation is close to the demand; denotes the suppression of low-quality links (low The bandwidth to be occupied; Indicates the total number of gateways; Indicates assignment to the first The bandwidth value from the gateway; This represents the penalty factor, used to control the weight of the demand penalty item; This represents the energy efficiency cost factor, used to control the impact of link quality on resource allocation.

[0036] The first bandwidth allocation model shown above must comply with the following constraints: Total bandwidth limit:

[0037] Fractal burst adaptation: (like If the value is greater than 0.7, then additional bandwidth is reserved. Minimum bandwidth guarantee:

[0038] in, Represents the fractal burst adaptability coefficient; Indicates the minimum bandwidth percentage. This is used to prevent bandwidth from being completely stripped from the gateway; Indicates from the gateway Forecasted traffic demand; This represents the Hurst index of traffic from the gateway, and ; This represents a comprehensive indicator of link quality. Indicates dynamic priority weight (updated in real time, such as in VR services). Video stream ); This represents the total available bandwidth, used to constrain the upper limit of the total allocated bandwidth to ensure that it does not exceed existing resources.

[0039] The dynamic priority update rule is as follows:

[0040] in, This indicates the basic priority, such as VR=1.5, video=1.0; Indicates the sensitivity coefficient of emergency business. .

[0041] The first bandwidth allocation model proposed in this application adopts a weighted utility maximization structure, unifying priority-weighted throughput, bandwidth demand deviation penalty term, and energy efficiency cost term into the objective function, thus forming a multi-objective optimization framework. The model's characteristic lies in... Strengthen resource allocation to high-priority business, through Precisely control the deviation between bandwidth allocation and actual demand, improve resource matching, and introduce... This model suppresses resource consumption by low-quality links, thus achieving a trade-off between energy efficiency and performance. It balances service quality, bandwidth utilization, and system energy efficiency, and maintains strong adaptability and scheduling robustness even under bursty traffic and complex network environments. In another exemplary embodiment, in step S300, the second bandwidth allocation model includes a chaotic perturbation generation module, a dynamic fitness module, a bandwidth allocation rule module, and a condition constraint module. The chaotic perturbation generation module is used to generate unpredictable chaotic perturbation factors to disrupt the static allocation equilibrium. Specifically, the chaotic perturbation generation module is represented as follows:

[0042] in, This represents the chaos perturbation factor at the current moment, with a value range of (0,1). This represents the chaotic perturbation factor at the next moment, used as a fairness compensation term in the dynamic fitness function to break the static allocation pattern. This represents the initial chaotic perturbation factor, which is randomly selected. For example, .

[0043] The dynamic fitness module is used to calculate the fitness value of each node based on the chaotic perturbation factor generated by the chaotic perturbation generation module. The dynamic fitness module is represented as follows:

[0044] in, Represents a node The fitness value indicates that the higher the value, the stronger the competitiveness. Represents a node The urgency of the business ; Represents a node Real-time channel capacity; Indicates the chaotic perturbation factor; Represents a node exist The time frame refers to the allocated bandwidth of the previous time frame; This represents the total available bandwidth.

[0045] The bandwidth allocation rule module is used to allocate the total bandwidth proportionally according to the fitness value of each node in order to achieve equilibrium in the bee colony game. The bandwidth allocation rule module is represented as follows:

[0046] in, This is an intermediate variable representing the sum of the fitness values ​​of all nodes.

[0047] The constraint module is used to force the bandwidth allocated by the bandwidth allocation rule module to meet the minimum bandwidth requirement. The constraint module is specifically represented as follows: 1. Minimum bandwidth guarantee:

[0048] 2. Burst Traffic Response Rules: like but

[0049] in, This represents the minimum bandwidth percentage coefficient, with a default value of 0.05. This indicates the weighting increase used to dynamically adjust sudden business events.

[0050] The first constraint ensures that the final allocated bandwidth remains constant regardless of the node's fitness calculation results. At least of the total bandwidth The multiplier is 5%, which defaults to 5%. For example, assuming a node... Its adaptability is extremely low; proportionally, it should only be allocated 2%, but it is forcibly increased to 5%. .

[0051] The second constraint ensures that even if a sudden surge in traffic causes a significant increase in bandwidth allocation, the base bandwidth of all nodes will still not be less than [a certain value]. .

[0052] In summary, the second bandwidth allocation model can be represented as follows: in, Indicates at time , for the first The bandwidth allocated from the gateway; This represents the minimum bandwidth percentage coefficient, ensuring that each gateway receives the minimum guaranteed bandwidth. Indicates the total available bandwidth; Indicates the first Each gateway at time The business urgency index ranges from [0,1]. Indicates the first The current channel capacity of the gateway; This represents a chaos fairness compensation factor, used to introduce perturbations to avoid resource allocation rigidity. Indicates that the previous time was from the gateway. The allocated bandwidth value; Indicates an indicator function, if If the value is greater than 0.8, the value is 1; otherwise, it is 0. Indicates the first fitness function value of the node, for bandwidth proportional distribution; denotes the sum of fitness of all slaves from the gateway; denotes the total number of slaves from the gateway.

[0053] The second bandwidth allocation model proposed in the present application adopts a proportional distribution structure based on chaotic disturbance and dynamic fitness driving, fuses a disturbance factor, service urgency, channel capacity and historical allocation results to construct a multi-dimensional fitness function, and realizes dynamic proportional distribution of the total bandwidth through fitness normalization. The model is characterized in that chaotic disturbance is introduced to break static balance and improve the diversity and fairness of resource scheduling, and at the same time, a burst service identification mechanism (such as an urgency threshold judgment) is used to realize bandwidth increase compensation for high-priority burst services.

[0054] In summary, the model can flexibly respond to changes in service load and link state while meeting the minimum bandwidth guarantee, improve the scheduling accuracy and bandwidth utilization efficiency of the system in high-dynamic and high-concurrent scenarios, and effectively alleviate the allocation bottleneck of traditional static strategies in complex network environments.

[0055] In another exemplary embodiment, in step S400, the slave gateway dynamically adjusts the bandwidth reservation proportion of the local service based on the secondary bandwidth allocation result, including the following steps: S401: receiving the secondary bandwidth allocation value of the master gateway; S402: identifying the local service type (such as VR, video stream, IoT data, etc.), and recording the priority and delay sensitivity of each service through a flow probe; S403: dynamically calculating the bandwidth reservation weight of each service based on the priority and delay sensitivity of each service, specifically through the following formula:

[0056] wherein, denotes the bandwidth reservation weight of the service ; , , and all denote weight coefficients, and by default , , , ; denotes the priority of the service ; ; denotes the delay sensitivity of the service , , and the larger the value, the more sensitive the service to delay.

[0057] S404: Calculate the reserved bandwidth proportion of each service according to the bandwidth reservation weight of each service, specifically according to the following formula:

[0058] wherein, represents the bandwidth value allocated to the first service or from the gateway; represents the weight value of the first object; represents the weight sum of all objects as the normalization denominator; represents the total bandwidth that can be allocated.

[0059] The constraint condition is:

[0060] Dynamic adjustment strategy: If the instantaneous flow of a certain service is large, temporarily increase its weight, that is:

[0061] If the bit error rate (BER) increases, reduce the bandwidth of low-priority services (such as ), that is: .

[0062] In another exemplary embodiment, the present application also provides a dynamic bandwidth allocation device based on FTTR-B architecture, as shown in Figure 2 , the device comprises: a prediction module 100 for uploading the local traffic characteristics of each slave gateway to the master gateway in real time, and generating a global traffic prediction result through a global traffic prediction model; a first allocation module 200 for performing initial bandwidth allocation to each slave gateway through a first bandwidth allocation model based on the global traffic prediction result; a second allocation module 300 for monitoring the link quality of each slave gateway in real time, generating a link state evaluation result, and performing secondary bandwidth allocation to each slave gateway based on the link state evaluation result through a second bandwidth allocation model; a calculation adjustment module 400 for dynamically calculating and adjusting the bandwidth reservation proportion of local services of each slave gateway based on the secondary bandwidth allocation result.

[0063] Optionally, the computing adjustment module 400 comprises: a receiving submodule for receiving the secondary bandwidth allocation value of the master gateway; an identifying submodule for identifying the local service type and recording the priority and delay sensitivity of each service through a traffic probe; a bandwidth reservation weight calculation submodule for dynamically calculating the bandwidth reservation weight of each service based on the priority and delay sensitivity of each service; and a reserved bandwidth calculation submodule for calculating the reserved bandwidth proportion of each service according to the bandwidth reservation weight of each service.

[0064] On the basis of the above-mentioned embodiments, with reference to Figure 3 The computer readable storage medium of the exemplary embodiments of the present application is described as follows. Figure 3 The computer readable storage medium shown is an optical disc 40, and a computer program (i.e., a program product) is stored on the optical disc 40. When the computer program is run by a processor, each step described in the above-mentioned method embodiments is implemented, for example, the local traffic characteristics of each slave gateway are uploaded to the master gateway in real time, and a global traffic prediction result is generated through a global traffic prediction model; based on the global traffic prediction result, the master gateway performs primary bandwidth allocation on each slave gateway through a first bandwidth allocation model; the link quality of each slave gateway is monitored in real time to generate a link state evaluation result, and the master gateway performs secondary bandwidth allocation on each slave gateway based on the link state evaluation result and through a second bandwidth allocation model; and each slave gateway dynamically adjusts the bandwidth reservation proportion of the local service based on the secondary bandwidth allocation result. The specific implementation method of each step is not repeated here.

[0065] It should be noted that the computer readable storage medium includes but is not limited to a phase change memory (PRAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), other types of random access memory (RAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, or other optical or magnetic storage medium, which will not be repeated here.

[0066] On the basis of the above-mentioned embodiments, the present application further provides an electronic device, which is described below with reference to Figure 4 The electronic device for file downloading of the exemplary embodiments of the present application is described.

[0067] Figure 4 A block diagram of an exemplary electronic device 50 suitable for implementing the embodiments of the present application is shown, which can be a computer system or a cloud server. Figure 4 The electronic device 50 shown is only an example, and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0068] As Figure 4As shown, the electronic device 50 includes, inter alia, one or more processors or processing units 501, a system memory 502, and a bus 503 that couples various system components including the system memory 502 to the processing unit 501.

[0069] The electronic device 50 typically includes a variety of computer system readable media. Such media can be any available media that is located either internally or externally to the electronic device 50, including both volatile and nonvolatile media, removable and non-removable media.

[0070] The system memory 502 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 5021 and / or cache memory 5022. The electronic device 50 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, ROM 5023 can be used to read-only memory, such as a magnetic disk drive (not shown) that reads from or writes to a nonremovable, nonvolatile magnetic media (not shown). Figure 4 Although not specifically shown, the ROM 5023 can also be used to read-only memory, such as a magnetic disk drive (not shown) that reads from or writes to a nonremovable, nonvolatile magnetic media (not shown). Figure 4 Although not specifically shown, the ROM 5023 can also be used to read-only memory, such as a magnetic disk drive (not shown) that reads from or writes to a nonremovable, nonvolatile magnetic media (not shown).

[0071] Program / utility 5025 having a set (at least one) of program modules 5024 can be stored in, for example, system memory 502 and implemented or accessed by such program modules 5024 can include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or a combination can include implementation of a network environment. Program modules 5024 generally carry out the functions and / or methodologies of embodiments described herein.

[0072] The electronic device 50 can also communicate with one or more external devices 504 such as a keyboard or pointing device, a display 505, etc. through an input / output (I / O) interface 505. Further, the electronic device 50 can communicate with one or more networks such as a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet, through a network adapter 506. As Figure 4 illustrated, the network adapter 506 communicates with the other system components, such as the processing unit 501, via the bus 503. It should be appreciated that the network adapter 506 and / or the bus 503 can be implemented using one or more busses, such as a Peripheral Component Interconnect (PCI) bus, a Micro-Channel Architecture (MCA) bus, etc. Figure 4Other hardware and / or software modules can be used in conjunction with the electronic device 50, as shown.

[0073] The processing unit 501 performs various function applications and data processing by running programs stored in the system memory 502, such as uploading local traffic characteristics of each slave gateway to the master gateway in real time, generating a global traffic prediction result by a global traffic prediction model, performing primary bandwidth allocation for each slave gateway by the first bandwidth allocation model based on the global traffic prediction result, monitoring link quality of each slave gateway in real time to generate a link state evaluation result, performing secondary bandwidth allocation for each slave gateway by the second bandwidth allocation model based on the link state evaluation result, and dynamically calculating a bandwidth reservation ratio of local services by each slave gateway based on the secondary bandwidth allocation result.

[0074] The specific implementation of each step will not be repeated here. It should be noted that although several units / modules or sub-units / sub-modules of the file concurrent downloading apparatus are mentioned in the foregoing detailed description, such division is only exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into a plurality of units / modules.

[0075] In the description of the present application, it should be noted that the terms "first", "second", "third" are only for the purpose of description and cannot be understood as indicating or implying relative importance.

[0076] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, apparatus and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0077] In several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method can be implemented by other ways. The apparatus embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interface, device or unit, which can be electrical, mechanical or other forms.

[0078] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0079] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit.

[0080] If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for executing all or part of the steps of the method described in each embodiment of the present application by a computer device (which can be a personal computer, a cloud server, or a network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and various program code storage media.

[0081] The above embodiments are only for illustrating the technical concept and characteristics of the present application, and the purpose is to enable those skilled in the art to understand the content of the present application and to implement it, and cannot limit the protection scope of the present application. Any equivalent changes or modifications made according to the spirit and essence of the present application should be covered within the protection scope of the present application.

Claims

1. A dynamic bandwidth allocation method based on FTTR-B architecture, characterized in that, The method comprises: uploading local traffic features of each slave gateway to a master gateway in real time, and generating a global traffic prediction result through a global traffic prediction model; based on the global traffic prediction result, the master gateway performs initial bandwidth allocation to each slave gateway through a first bandwidth allocation model; real-time monitoring of the link quality of each slave gateway generates a link state evaluation result, and the master gateway performs secondary bandwidth allocation to each slave gateway based on the link state evaluation result and through a second bandwidth allocation model; based on the secondary bandwidth allocation result, each slave gateway dynamically calculates the bandwidth reservation ratio of local services.

2. The method of claim 1, wherein, The global traffic prediction model comprises: a local LSTM module, a federal aggregation module and a global prediction module, wherein the LSTM module is used to upload the local traffic features of each slave gateway to the master gateway; the federal aggregation module is used to weight and aggregate the local traffic features of each slave gateway; the global prediction module is used to predict the global traffic based on the weighted and aggregated local traffic features.

3. The method of claim 1, wherein, The second bandwidth allocation model comprises: a chaotic disturbance generation module, a dynamic fitness module, a bandwidth allocation rule module and a constraint condition module, wherein the chaotic disturbance generation module is used to generate unpredictable chaotic disturbance factors; the dynamic fitness module is used to calculate the fitness value of each node based on the chaotic disturbance factors; the bandwidth allocation rule module is used to allocate the total bandwidth in proportion according to the fitness value of each node; the constraint condition module is used to force the bandwidth allocated by the bandwidth allocation rule module to meet the minimum bandwidth requirement.

4. The method of claim 1, wherein, Based on the secondary bandwidth allocation result, each slave gateway dynamically calculates the bandwidth reservation ratio of local services, which comprises: receiving the secondary bandwidth allocation value of the master gateway; identifying the type of local services and recording the priority and delay sensitivity of each service through a traffic probe; based on the priority and delay sensitivity of each service, dynamically calculating the bandwidth reservation weight of each service; calculating the reserved bandwidth ratio of each service according to the bandwidth reservation weight of each service.

5. A dynamic bandwidth allocation apparatus based on FTTR-B architecture, characterized in that, The device comprises: a prediction module for uploading local traffic features of each slave gateway to a master gateway in real time, and generating a global traffic prediction result through a global traffic prediction model; a first allocation module for performing initial bandwidth allocation to each slave gateway through a first bandwidth allocation model based on the global traffic prediction result; a second allocation module for real-time monitoring of the link quality of each slave gateway, generating a link state evaluation result, and performing secondary bandwidth allocation to each slave gateway based on the link state evaluation result and through a second bandwidth allocation model; a calculation and adjustment module for dynamically calculating the bandwidth reservation ratio of local services by each slave gateway based on the secondary bandwidth allocation result.

6. The dynamic bandwidth allocation apparatus based on FTTR-B architecture according to claim 5, wherein, The calculation and adjustment module comprises: a receiving submodule for receiving the secondary bandwidth allocation value of the master gateway; an identification submodule for identifying the type of local services and recording the priority and delay sensitivity of each service through a traffic probe; a bandwidth reservation weight calculation submodule for dynamically calculating the bandwidth reservation weight of each service based on the priority and delay sensitivity of each service; The reserved bandwidth calculation sub-module is configured to calculate a reserved bandwidth ratio of each service according to a bandwidth reserved weight of the service.

7. A storage medium, characterized by The computer program comprises instructions which, when the program is executed by a computer, cause the computer to carry out the method of any one of claims 1-4.

8. An electronic device, comprising: The electronic device comprises: A memory, a processor and a computer program stored in the memory and executable on the processor, wherein, The processor implements the method of any one of claims 1-4 when executing the program.

Images